fs/xfs/xfs_bmap.c

/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_mount.h"
#include "xfs_da_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_mount.h"
#include "xfs_itable.h"
#include "xfs_inode_item.h"
#include "xfs_extfree_item.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_attr_leaf.h"
#include "xfs_quota.h"
#include "xfs_trans_space.h"
#include "xfs_buf_item.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"
#include "xfs_trace.h"
#include "xfs_symlink.h"


kmem_zone_t		*xfs_bmap_free_item_zone;

/*
 * Miscellaneous helper functions
 */

/*
 * Compute and fill in the value of the maximum depth of a bmap btree
 * in this filesystem.  Done once, during mount.
 */
void
xfs_bmap_compute_maxlevels(
	xfs_mount_t	*mp,		/* file system mount structure */
	int		whichfork)	/* data or attr fork */
{
	int		level;		/* btree level */
	uint		maxblocks;	/* max blocks at this level */
	uint		maxleafents;	/* max leaf entries possible */
	int		maxrootrecs;	/* max records in root block */
	int		minleafrecs;	/* min records in leaf block */
	int		minnoderecs;	/* min records in node block */
	int		sz;		/* root block size */

	/*
	 * The maximum number of extents in a file, hence the maximum
	 * number of leaf entries, is controlled by the type of di_nextents
	 * (a signed 32-bit number, xfs_extnum_t), or by di_anextents
	 * (a signed 16-bit number, xfs_aextnum_t).
	 *
	 * Note that we can no longer assume that if we are in ATTR1 that
	 * the fork offset of all the inodes will be
	 * (xfs_default_attroffset(ip) >> 3) because we could have mounted
	 * with ATTR2 and then mounted back with ATTR1, keeping the
	 * di_forkoff's fixed but probably at various positions. Therefore,
	 * for both ATTR1 and ATTR2 we have to assume the worst case scenario
	 * of a minimum size available.
	 */
	if (whichfork == XFS_DATA_FORK) {
		maxleafents = MAXEXTNUM;
		sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
	} else {
		maxleafents = MAXAEXTNUM;
		sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
	}
	maxrootrecs = xfs_bmdr_maxrecs(mp, sz, 0);
	minleafrecs = mp->m_bmap_dmnr[0];
	minnoderecs = mp->m_bmap_dmnr[1];
	maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
	for (level = 1; maxblocks > 1; level++) {
		if (maxblocks <= maxrootrecs)
			maxblocks = 1;
		else
			maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
	}
	mp->m_bm_maxlevels[whichfork] = level;
}

/*
 * Convert the given file system block to a disk block.  We have to treat it
 * differently based on whether the file is a real time file or not, because the
 * bmap code does.
 */
xfs_daddr_t
xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
{
	return (XFS_IS_REALTIME_INODE(ip) ? \
		 (xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \
		 XFS_FSB_TO_DADDR((ip)->i_mount, (fsb)));
}

STATIC int				/* error */
xfs_bmbt_lookup_eq(
	struct xfs_btree_cur	*cur,
	xfs_fileoff_t		off,
	xfs_fsblock_t		bno,
	xfs_filblks_t		len,
	int			*stat)	/* success/failure */
{
	cur->bc_rec.b.br_startoff = off;
	cur->bc_rec.b.br_startblock = bno;
	cur->bc_rec.b.br_blockcount = len;
	return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
}

STATIC int				/* error */
xfs_bmbt_lookup_ge(
	struct xfs_btree_cur	*cur,
	xfs_fileoff_t		off,
	xfs_fsblock_t		bno,
	xfs_filblks_t		len,
	int			*stat)	/* success/failure */
{
	cur->bc_rec.b.br_startoff = off;
	cur->bc_rec.b.br_startblock = bno;
	cur->bc_rec.b.br_blockcount = len;
	return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
}

/*
 * Check if the inode needs to be converted to btree format.
 */
static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork)
{
	return XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
		XFS_IFORK_NEXTENTS(ip, whichfork) >
			XFS_IFORK_MAXEXT(ip, whichfork);
}

/*
 * Check if the inode should be converted to extent format.
 */
static inline bool xfs_bmap_wants_extents(struct xfs_inode *ip, int whichfork)
{
	return XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE &&
		XFS_IFORK_NEXTENTS(ip, whichfork) <=
			XFS_IFORK_MAXEXT(ip, whichfork);
}

/*
 * Update the record referred to by cur to the value given
 * by [off, bno, len, state].
 * This either works (return 0) or gets an EFSCORRUPTED error.
 */
STATIC int
xfs_bmbt_update(
	struct xfs_btree_cur	*cur,
	xfs_fileoff_t		off,
	xfs_fsblock_t		bno,
	xfs_filblks_t		len,
	xfs_exntst_t		state)
{
	union xfs_btree_rec	rec;

	xfs_bmbt_disk_set_allf(&rec.bmbt, off, bno, len, state);
	return xfs_btree_update(cur, &rec);
}

/*
 * Compute the worst-case number of indirect blocks that will be used
 * for ip's delayed extent of length "len".
 */
STATIC xfs_filblks_t
xfs_bmap_worst_indlen(
	xfs_inode_t	*ip,		/* incore inode pointer */
	xfs_filblks_t	len)		/* delayed extent length */
{
	int		level;		/* btree level number */
	int		maxrecs;	/* maximum record count at this level */
	xfs_mount_t	*mp;		/* mount structure */
	xfs_filblks_t	rval;		/* return value */

	mp = ip->i_mount;
	maxrecs = mp->m_bmap_dmxr[0];
	for (level = 0, rval = 0;
	     level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
	     level++) {
		len += maxrecs - 1;
		do_div(len, maxrecs);
		rval += len;
		if (len == 1)
			return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
				level - 1;
		if (level == 0)
			maxrecs = mp->m_bmap_dmxr[1];
	}
	return rval;
}

/*
 * Calculate the default attribute fork offset for newly created inodes.
 */
uint
xfs_default_attroffset(
	struct xfs_inode	*ip)
{
	struct xfs_mount	*mp = ip->i_mount;
	uint			offset;

	if (mp->m_sb.sb_inodesize == 256) {
		offset = XFS_LITINO(mp, ip->i_d.di_version) -
				XFS_BMDR_SPACE_CALC(MINABTPTRS);
	} else {
		offset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
	}

	ASSERT(offset < XFS_LITINO(mp, ip->i_d.di_version));
	return offset;
}

/*
 * Helper routine to reset inode di_forkoff field when switching
 * attribute fork from local to extent format - we reset it where
 * possible to make space available for inline data fork extents.
 */
STATIC void
xfs_bmap_forkoff_reset(
	xfs_mount_t	*mp,
	xfs_inode_t	*ip,
	int		whichfork)
{
	if (whichfork == XFS_ATTR_FORK &&
	    ip->i_d.di_format != XFS_DINODE_FMT_DEV &&
	    ip->i_d.di_format != XFS_DINODE_FMT_UUID &&
	    ip->i_d.di_format != XFS_DINODE_FMT_BTREE) {
		uint	dfl_forkoff = xfs_default_attroffset(ip) >> 3;

		if (dfl_forkoff > ip->i_d.di_forkoff)
			ip->i_d.di_forkoff = dfl_forkoff;
	}
}

/*
 * Extent tree block counting routines.
 */

/*
 * Count leaf blocks given a range of extent records.
 */
STATIC void
xfs_bmap_count_leaves(
	xfs_ifork_t		*ifp,
	xfs_extnum_t		idx,
	int			numrecs,
	int			*count)
{
	int		b;

	for (b = 0; b < numrecs; b++) {
		xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, idx + b);
		*count += xfs_bmbt_get_blockcount(frp);
	}
}

/*
 * Count leaf blocks given a range of extent records originally
 * in btree format.
 */
STATIC void
xfs_bmap_disk_count_leaves(
	struct xfs_mount	*mp,
	struct xfs_btree_block	*block,
	int			numrecs,
	int			*count)
{
	int		b;
	xfs_bmbt_rec_t	*frp;

	for (b = 1; b <= numrecs; b++) {
		frp = XFS_BMBT_REC_ADDR(mp, block, b);
		*count += xfs_bmbt_disk_get_blockcount(frp);
	}
}

/*
 * Recursively walks each level of a btree
 * to count total fsblocks is use.
 */
STATIC int                                     /* error */
xfs_bmap_count_tree(
	xfs_mount_t     *mp,            /* file system mount point */
	xfs_trans_t     *tp,            /* transaction pointer */
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_fsblock_t   blockno,	/* file system block number */
	int             levelin,	/* level in btree */
	int		*count)		/* Count of blocks */
{
	int			error;
	xfs_buf_t		*bp, *nbp;
	int			level = levelin;
	__be64			*pp;
	xfs_fsblock_t           bno = blockno;
	xfs_fsblock_t		nextbno;
	struct xfs_btree_block	*block, *nextblock;
	int			numrecs;

	error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, XFS_BMAP_BTREE_REF,
						&xfs_bmbt_buf_ops);
	if (error)
		return error;
	*count += 1;
	block = XFS_BUF_TO_BLOCK(bp);

	if (--level) {
		/* Not at node above leaves, count this level of nodes */
		nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
		while (nextbno != NULLFSBLOCK) {
			error = xfs_btree_read_bufl(mp, tp, nextbno, 0, &nbp,
						XFS_BMAP_BTREE_REF,
						&xfs_bmbt_buf_ops);
			if (error)
				return error;
			*count += 1;
			nextblock = XFS_BUF_TO_BLOCK(nbp);
			nextbno = be64_to_cpu(nextblock->bb_u.l.bb_rightsib);
			xfs_trans_brelse(tp, nbp);
		}

		/* Dive to the next level */
		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
		bno = be64_to_cpu(*pp);
		if (unlikely((error =
		     xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
			xfs_trans_brelse(tp, bp);
			XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
					 XFS_ERRLEVEL_LOW, mp);
			return XFS_ERROR(EFSCORRUPTED);
		}
		xfs_trans_brelse(tp, bp);
	} else {
		/* count all level 1 nodes and their leaves */
		for (;;) {
			nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
			numrecs = be16_to_cpu(block->bb_numrecs);
			xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
			xfs_trans_brelse(tp, bp);
			if (nextbno == NULLFSBLOCK)
				break;
			bno = nextbno;
			error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
						XFS_BMAP_BTREE_REF,
						&xfs_bmbt_buf_ops);
			if (error)
				return error;
			*count += 1;
			block = XFS_BUF_TO_BLOCK(bp);
		}
	}
	return 0;
}

/*
 * Count fsblocks of the given fork.
 */
int						/* error */
xfs_bmap_count_blocks(
	xfs_trans_t		*tp,		/* transaction pointer */
	xfs_inode_t		*ip,		/* incore inode */
	int			whichfork,	/* data or attr fork */
	int			*count)		/* out: count of blocks */
{
	struct xfs_btree_block	*block;	/* current btree block */
	xfs_fsblock_t		bno;	/* block # of "block" */
	xfs_ifork_t		*ifp;	/* fork structure */
	int			level;	/* btree level, for checking */
	xfs_mount_t		*mp;	/* file system mount structure */
	__be64			*pp;	/* pointer to block address */

	bno = NULLFSBLOCK;
	mp = ip->i_mount;
	ifp = XFS_IFORK_PTR(ip, whichfork);
	if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
		xfs_bmap_count_leaves(ifp, 0,
			ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t),
			count);
		return 0;
	}

	/*
	 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
	 */
	block = ifp->if_broot;
	level = be16_to_cpu(block->bb_level);
	ASSERT(level > 0);
	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
	bno = be64_to_cpu(*pp);
	ASSERT(bno != NULLDFSBNO);
	ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
	ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);

	if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) {
		XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW,
				 mp);
		return XFS_ERROR(EFSCORRUPTED);
	}

	return 0;
}

/*
 * Debug/sanity checking code
 */

STATIC int
xfs_bmap_sanity_check(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	int			level)
{
	struct xfs_btree_block  *block = XFS_BUF_TO_BLOCK(bp);

	if (block->bb_magic != cpu_to_be32(XFS_BMAP_CRC_MAGIC) &&
	    block->bb_magic != cpu_to_be32(XFS_BMAP_MAGIC))
		return 0;

	if (be16_to_cpu(block->bb_level) != level ||
	    be16_to_cpu(block->bb_numrecs) == 0 ||
	    be16_to_cpu(block->bb_numrecs) > mp->m_bmap_dmxr[level != 0])
		return 0;

	return 1;
}

#ifdef DEBUG
STATIC struct xfs_buf *
xfs_bmap_get_bp(
	struct xfs_btree_cur	*cur,
	xfs_fsblock_t		bno)
{
	struct xfs_log_item_desc *lidp;
	int			i;

	if (!cur)
		return NULL;

	for (i = 0; i < XFS_BTREE_MAXLEVELS; i++) {
		if (!cur->bc_bufs[i])
			break;
		if (XFS_BUF_ADDR(cur->bc_bufs[i]) == bno)
			return cur->bc_bufs[i];
	}

	/* Chase down all the log items to see if the bp is there */
	list_for_each_entry(lidp, &cur->bc_tp->t_items, lid_trans) {
		struct xfs_buf_log_item	*bip;
		bip = (struct xfs_buf_log_item *)lidp->lid_item;
		if (bip->bli_item.li_type == XFS_LI_BUF &&
		    XFS_BUF_ADDR(bip->bli_buf) == bno)
			return bip->bli_buf;
	}

	return NULL;
}

STATIC void
xfs_check_block(
	struct xfs_btree_block	*block,
	xfs_mount_t		*mp,
	int			root,
	short			sz)
{
	int			i, j, dmxr;
	__be64			*pp, *thispa;	/* pointer to block address */
	xfs_bmbt_key_t		*prevp, *keyp;

	ASSERT(be16_to_cpu(block->bb_level) > 0);

	prevp = NULL;
	for( i = 1; i <= xfs_btree_get_numrecs(block); i++) {
		dmxr = mp->m_bmap_dmxr[0];
		keyp = XFS_BMBT_KEY_ADDR(mp, block, i);

		if (prevp) {
			ASSERT(be64_to_cpu(prevp->br_startoff) <
			       be64_to_cpu(keyp->br_startoff));
		}
		prevp = keyp;

		/*
		 * Compare the block numbers to see if there are dups.
		 */
		if (root)
			pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, i, sz);
		else
			pp = XFS_BMBT_PTR_ADDR(mp, block, i, dmxr);

		for (j = i+1; j <= be16_to_cpu(block->bb_numrecs); j++) {
			if (root)
				thispa = XFS_BMAP_BROOT_PTR_ADDR(mp, block, j, sz);
			else
				thispa = XFS_BMBT_PTR_ADDR(mp, block, j, dmxr);
			if (*thispa == *pp) {
				xfs_warn(mp, "%s: thispa(%d) == pp(%d) %Ld",
					__func__, j, i,
					(unsigned long long)be64_to_cpu(*thispa));
				panic("%s: ptrs are equal in node\n",
					__func__);
			}
		}
	}
}

/*
 * Check that the extents for the inode ip are in the right order in all
 * btree leaves.
 */

STATIC void
xfs_bmap_check_leaf_extents(
	xfs_btree_cur_t		*cur,	/* btree cursor or null */
	xfs_inode_t		*ip,		/* incore inode pointer */
	int			whichfork)	/* data or attr fork */
{
	struct xfs_btree_block	*block;	/* current btree block */
	xfs_fsblock_t		bno;	/* block # of "block" */
	xfs_buf_t		*bp;	/* buffer for "block" */
	int			error;	/* error return value */
	xfs_extnum_t		i=0, j;	/* index into the extents list */
	xfs_ifork_t		*ifp;	/* fork structure */
	int			level;	/* btree level, for checking */
	xfs_mount_t		*mp;	/* file system mount structure */
	__be64			*pp;	/* pointer to block address */
	xfs_bmbt_rec_t		*ep;	/* pointer to current extent */
	xfs_bmbt_rec_t		last = {0, 0}; /* last extent in prev block */
	xfs_bmbt_rec_t		*nextp;	/* pointer to next extent */
	int			bp_release = 0;

	if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE) {
		return;
	}

	bno = NULLFSBLOCK;
	mp = ip->i_mount;
	ifp = XFS_IFORK_PTR(ip, whichfork);
	block = ifp->if_broot;
	/*
	 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
	 */
	level = be16_to_cpu(block->bb_level);
	ASSERT(level > 0);
	xfs_check_block(block, mp, 1, ifp->if_broot_bytes);
	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
	bno = be64_to_cpu(*pp);

	ASSERT(bno != NULLDFSBNO);
	ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
	ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);

	/*
	 * Go down the tree until leaf level is reached, following the first
	 * pointer (leftmost) at each level.
	 */
	while (level-- > 0) {
		/* See if buf is in cur first */
		bp_release = 0;
		bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
		if (!bp) {
			bp_release = 1;
			error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp,
						XFS_BMAP_BTREE_REF,
						&xfs_bmbt_buf_ops);
			if (error)
				goto error_norelse;
		}
		block = XFS_BUF_TO_BLOCK(bp);
		XFS_WANT_CORRUPTED_GOTO(
			xfs_bmap_sanity_check(mp, bp, level),
			error0);
		if (level == 0)
			break;

		/*
		 * Check this block for basic sanity (increasing keys and
		 * no duplicate blocks).
		 */

		xfs_check_block(block, mp, 0, 0);
		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
		bno = be64_to_cpu(*pp);
		XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
		if (bp_release) {
			bp_release = 0;
			xfs_trans_brelse(NULL, bp);
		}
	}

	/*
	 * Here with bp and block set to the leftmost leaf node in the tree.
	 */
	i = 0;

	/*
	 * Loop over all leaf nodes checking that all extents are in the right order.
	 */
	for (;;) {
		xfs_fsblock_t	nextbno;
		xfs_extnum_t	num_recs;


		num_recs = xfs_btree_get_numrecs(block);

		/*
		 * Read-ahead the next leaf block, if any.
		 */

		nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);

		/*
		 * Check all the extents to make sure they are OK.
		 * If we had a previous block, the last entry should
		 * conform with the first entry in this one.
		 */

		ep = XFS_BMBT_REC_ADDR(mp, block, 1);
		if (i) {
			ASSERT(xfs_bmbt_disk_get_startoff(&last) +
			       xfs_bmbt_disk_get_blockcount(&last) <=
			       xfs_bmbt_disk_get_startoff(ep));
		}
		for (j = 1; j < num_recs; j++) {
			nextp = XFS_BMBT_REC_ADDR(mp, block, j + 1);
			ASSERT(xfs_bmbt_disk_get_startoff(ep) +
			       xfs_bmbt_disk_get_blockcount(ep) <=
			       xfs_bmbt_disk_get_startoff(nextp));
			ep = nextp;
		}

		last = *ep;
		i += num_recs;
		if (bp_release) {
			bp_release = 0;
			xfs_trans_brelse(NULL, bp);
		}
		bno = nextbno;
		/*
		 * If we've reached the end, stop.
		 */
		if (bno == NULLFSBLOCK)
			break;

		bp_release = 0;
		bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
		if (!bp) {
			bp_release = 1;
			error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp,
						XFS_BMAP_BTREE_REF,
						&xfs_bmbt_buf_ops);
			if (error)
				goto error_norelse;
		}
		block = XFS_BUF_TO_BLOCK(bp);
	}
	if (bp_release) {
		bp_release = 0;
		xfs_trans_brelse(NULL, bp);
	}
	return;

error0:
	xfs_warn(mp, "%s: at error0", __func__);
	if (bp_release)
		xfs_trans_brelse(NULL, bp);
error_norelse:
	xfs_warn(mp, "%s: BAD after btree leaves for %d extents",
		__func__, i);
	panic("%s: CORRUPTED BTREE OR SOMETHING", __func__);
	return;
}

/*
 * Add bmap trace insert entries for all the contents of the extent records.
 */
void
xfs_bmap_trace_exlist(
	xfs_inode_t	*ip,		/* incore inode pointer */
	xfs_extnum_t	cnt,		/* count of entries in the list */
	int		whichfork,	/* data or attr fork */
	unsigned long	caller_ip)
{
	xfs_extnum_t	idx;		/* extent record index */
	xfs_ifork_t	*ifp;		/* inode fork pointer */
	int		state = 0;

	if (whichfork == XFS_ATTR_FORK)
		state |= BMAP_ATTRFORK;

	ifp = XFS_IFORK_PTR(ip, whichfork);
	ASSERT(cnt == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));
	for (idx = 0; idx < cnt; idx++)
		trace_xfs_extlist(ip, idx, whichfork, caller_ip);
}

/*
 * Validate that the bmbt_irecs being returned from bmapi are valid
 * given the callers original parameters.  Specifically check the
 * ranges of the returned irecs to ensure that they only extent beyond
 * the given parameters if the XFS_BMAPI_ENTIRE flag was set.
 */
STATIC void
xfs_bmap_validate_ret(
	xfs_fileoff_t		bno,
	xfs_filblks_t		len,
	int			flags,
	xfs_bmbt_irec_t		*mval,
	int			nmap,
	int			ret_nmap)
{
	int			i;		/* index to map values */

	ASSERT(ret_nmap <= nmap);

	for (i = 0; i < ret_nmap; i++) {
		ASSERT(mval[i].br_blockcount > 0);
		if (!(flags & XFS_BMAPI_ENTIRE)) {
			ASSERT(mval[i].br_startoff >= bno);
			ASSERT(mval[i].br_blockcount <= len);
			ASSERT(mval[i].br_startoff + mval[i].br_blockcount <=
			       bno + len);
		} else {
			ASSERT(mval[i].br_startoff < bno + len);
			ASSERT(mval[i].br_startoff + mval[i].br_blockcount >
			       bno);
		}
		ASSERT(i == 0 ||
		       mval[i - 1].br_startoff + mval[i - 1].br_blockcount ==
		       mval[i].br_startoff);
		ASSERT(mval[i].br_startblock != DELAYSTARTBLOCK &&
		       mval[i].br_startblock != HOLESTARTBLOCK);
		ASSERT(mval[i].br_state == XFS_EXT_NORM ||
		       mval[i].br_state == XFS_EXT_UNWRITTEN);
	}
}

#else
#define xfs_bmap_check_leaf_extents(cur, ip, whichfork)		do { } while (0)
#define	xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap)
#endif /* DEBUG */

/*
 * bmap free list manipulation functions
 */

/*
 * Add the extent to the list of extents to be free at transaction end.
 * The list is maintained sorted (by block number).
 */
void
xfs_bmap_add_free(
	xfs_fsblock_t		bno,		/* fs block number of extent */
	xfs_filblks_t		len,		/* length of extent */
	xfs_bmap_free_t		*flist,		/* list of extents */
	xfs_mount_t		*mp)		/* mount point structure */
{
	xfs_bmap_free_item_t	*cur;		/* current (next) element */
	xfs_bmap_free_item_t	*new;		/* new element */
	xfs_bmap_free_item_t	*prev;		/* previous element */
#ifdef DEBUG
	xfs_agnumber_t		agno;
	xfs_agblock_t		agbno;

	ASSERT(bno != NULLFSBLOCK);
	ASSERT(len > 0);
	ASSERT(len <= MAXEXTLEN);
	ASSERT(!isnullstartblock(bno));
	agno = XFS_FSB_TO_AGNO(mp, bno);
	agbno = XFS_FSB_TO_AGBNO(mp, bno);
	ASSERT(agno < mp->m_sb.sb_agcount);
	ASSERT(agbno < mp->m_sb.sb_agblocks);
	ASSERT(len < mp->m_sb.sb_agblocks);
	ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
#endif
	ASSERT(xfs_bmap_free_item_zone != NULL);
	new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
	new->xbfi_startblock = bno;
	new->xbfi_blockcount = (xfs_extlen_t)len;
	for (prev = NULL, cur = flist->xbf_first;
	     cur != NULL;
	     prev = cur, cur = cur->xbfi_next) {
		if (cur->xbfi_startblock >= bno)
			break;
	}
	if (prev)
		prev->xbfi_next = new;
	else
		flist->xbf_first = new;
	new->xbfi_next = cur;
	flist->xbf_count++;
}

/*
 * Remove the entry "free" from the free item list.  Prev points to the
 * previous entry, unless "free" is the head of the list.
 */
STATIC void
xfs_bmap_del_free(
	xfs_bmap_free_t		*flist,	/* free item list header */
	xfs_bmap_free_item_t	*prev,	/* previous item on list, if any */
	xfs_bmap_free_item_t	*free)	/* list item to be freed */
{
	if (prev)
		prev->xbfi_next = free->xbfi_next;
	else
		flist->xbf_first = free->xbfi_next;
	flist->xbf_count--;
	kmem_zone_free(xfs_bmap_free_item_zone, free);
}


/*
 * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
 * caller.  Frees all the extents that need freeing, which must be done
 * last due to locking considerations.  We never free any extents in
 * the first transaction.
 *
 * Return 1 if the given transaction was committed and a new one
 * started, and 0 otherwise in the committed parameter.
 */
int						/* error */
xfs_bmap_finish(
	xfs_trans_t		**tp,		/* transaction pointer addr */
	xfs_bmap_free_t		*flist,		/* i/o: list extents to free */
	int			*committed)	/* xact committed or not */
{
	xfs_efd_log_item_t	*efd;		/* extent free data */
	xfs_efi_log_item_t	*efi;		/* extent free intention */
	int			error;		/* error return value */
	xfs_bmap_free_item_t	*free;		/* free extent item */
	unsigned int		logres;		/* new log reservation */
	unsigned int		logcount;	/* new log count */
	xfs_mount_t		*mp;		/* filesystem mount structure */
	xfs_bmap_free_item_t	*next;		/* next item on free list */
	xfs_trans_t		*ntp;		/* new transaction pointer */

	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
	if (flist->xbf_count == 0) {
		*committed = 0;
		return 0;
	}
	ntp = *tp;
	efi = xfs_trans_get_efi(ntp, flist->xbf_count);
	for (free = flist->xbf_first; free; free = free->xbfi_next)
		xfs_trans_log_efi_extent(ntp, efi, free->xbfi_startblock,
			free->xbfi_blockcount);
	logres = ntp->t_log_res;
	logcount = ntp->t_log_count;
	ntp = xfs_trans_dup(*tp);
	error = xfs_trans_commit(*tp, 0);
	*tp = ntp;
	*committed = 1;
	/*
	 * We have a new transaction, so we should return committed=1,
	 * even though we're returning an error.
	 */
	if (error)
		return error;

	/*
	 * transaction commit worked ok so we can drop the extra ticket
	 * reference that we gained in xfs_trans_dup()
	 */
	xfs_log_ticket_put(ntp->t_ticket);

	if ((error = xfs_trans_reserve(ntp, 0, logres, 0, XFS_TRANS_PERM_LOG_RES,
			logcount)))
		return error;
	efd = xfs_trans_get_efd(ntp, efi, flist->xbf_count);
	for (free = flist->xbf_first; free != NULL; free = next) {
		next = free->xbfi_next;
		if ((error = xfs_free_extent(ntp, free->xbfi_startblock,
				free->xbfi_blockcount))) {
			/*
			 * The bmap free list will be cleaned up at a
			 * higher level.  The EFI will be canceled when
			 * this transaction is aborted.
			 * Need to force shutdown here to make sure it
			 * happens, since this transaction may not be
			 * dirty yet.
			 */
			mp = ntp->t_mountp;
			if (!XFS_FORCED_SHUTDOWN(mp))
				xfs_force_shutdown(mp,
						   (error == EFSCORRUPTED) ?
						   SHUTDOWN_CORRUPT_INCORE :
						   SHUTDOWN_META_IO_ERROR);
			return error;
		}
		xfs_trans_log_efd_extent(ntp, efd, free->xbfi_startblock,
			free->xbfi_blockcount);
		xfs_bmap_del_free(flist, NULL, free);
	}
	return 0;
}

/*
 * Free up any items left in the list.
 */
void
xfs_bmap_cancel(
	xfs_bmap_free_t		*flist)	/* list of bmap_free_items */
{
	xfs_bmap_free_item_t	*free;	/* free list item */
	xfs_bmap_free_item_t	*next;

	if (flist->xbf_count == 0)
		return;
	ASSERT(flist->xbf_first != NULL);
	for (free = flist->xbf_first; free; free = next) {
		next = free->xbfi_next;
		xfs_bmap_del_free(flist, NULL, free);
	}
	ASSERT(flist->xbf_count == 0);
}

/*
 * Inode fork format manipulation functions
 */

/*
 * Transform a btree format file with only one leaf node, where the
 * extents list will fit in the inode, into an extents format file.
 * Since the file extents are already in-core, all we have to do is
 * give up the space for the btree root and pitch the leaf block.
 */
STATIC int				/* error */
xfs_bmap_btree_to_extents(
	xfs_trans_t		*tp,	/* transaction pointer */
	xfs_inode_t		*ip,	/* incore inode pointer */
	xfs_btree_cur_t		*cur,	/* btree cursor */
	int			*logflagsp, /* inode logging flags */
	int			whichfork)  /* data or attr fork */
{
	/* REFERENCED */
	struct xfs_btree_block	*cblock;/* child btree block */
	xfs_fsblock_t		cbno;	/* child block number */
	xfs_buf_t		*cbp;	/* child block's buffer */
	int			error;	/* error return value */
	xfs_ifork_t		*ifp;	/* inode fork data */
	xfs_mount_t		*mp;	/* mount point structure */
	__be64			*pp;	/* ptr to block address */
	struct xfs_btree_block	*rblock;/* root btree block */

	mp = ip->i_mount;
	ifp = XFS_IFORK_PTR(ip, whichfork);
	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
	rblock = ifp->if_broot;
	ASSERT(be16_to_cpu(rblock->bb_level) == 1);
	ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1);
	ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0) == 1);
	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes);
	cbno = be64_to_cpu(*pp);
	*logflagsp = 0;
#ifdef DEBUG
	if ((error = xfs_btree_check_lptr(cur, cbno, 1)))
		return error;
#endif
	error = xfs_btree_read_bufl(mp, tp, cbno, 0, &cbp, XFS_BMAP_BTREE_REF,
				&xfs_bmbt_buf_ops);
	if (error)
		return error;
	cblock = XFS_BUF_TO_BLOCK(cbp);
	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
		return error;
	xfs_bmap_add_free(cbno, 1, cur->bc_private.b.flist, mp);
	ip->i_d.di_nblocks--;
	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
	xfs_trans_binval(tp, cbp);
	if (cur->bc_bufs[0] == cbp)
		cur->bc_bufs[0] = NULL;
	xfs_iroot_realloc(ip, -1, whichfork);
	ASSERT(ifp->if_broot == NULL);
	ASSERT((ifp->if_flags & XFS_IFBROOT) == 0);
	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
	*logflagsp = XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
	return 0;
}

/*
 * Convert an extents-format file into a btree-format file.
 * The new file will have a root block (in the inode) and a single child block.
 */
STATIC int					/* error */
xfs_bmap_extents_to_btree(
	xfs_trans_t		*tp,		/* transaction pointer */
	xfs_inode_t		*ip,		/* incore inode pointer */
	xfs_fsblock_t		*firstblock,	/* first-block-allocated */
	xfs_bmap_free_t		*flist,		/* blocks freed in xaction */
	xfs_btree_cur_t		**curp,		/* cursor returned to caller */
	int			wasdel,		/* converting a delayed alloc */
	int			*logflagsp,	/* inode logging flags */
	int			whichfork)	/* data or attr fork */
{
	struct xfs_btree_block	*ablock;	/* allocated (child) bt block */
	xfs_buf_t		*abp;		/* buffer for ablock */
	xfs_alloc_arg_t		args;		/* allocation arguments */
	xfs_bmbt_rec_t		*arp;		/* child record pointer */
	struct xfs_btree_block	*block;		/* btree root block */
	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
	xfs_bmbt_rec_host_t	*ep;		/* extent record pointer */
	int			error;		/* error return value */
	xfs_extnum_t		i, cnt;		/* extent record index */
	xfs_ifork_t		*ifp;		/* inode fork pointer */
	xfs_bmbt_key_t		*kp;		/* root block key pointer */
	xfs_mount_t		*mp;		/* mount structure */
	xfs_extnum_t		nextents;	/* number of file extents */
	xfs_bmbt_ptr_t		*pp;		/* root block address pointer */

	mp = ip->i_mount;
	ifp = XFS_IFORK_PTR(ip, whichfork);
	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS);

	/*
	 * Make space in the inode incore.
	 */
	xfs_iroot_realloc(ip, 1, whichfork);
	ifp->if_flags |= XFS_IFBROOT;

	/*
	 * Fill in the root.
	 */
	block = ifp->if_broot;
	if (xfs_sb_version_hascrc(&mp->m_sb))
		xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
				 XFS_BMAP_CRC_MAGIC, 1, 1, ip->i_ino,
				 XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS);
	else
		xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
				 XFS_BMAP_MAGIC, 1, 1, ip->i_ino,
				 XFS_BTREE_LONG_PTRS);

	/*
	 * Need a cursor.  Can't allocate until bb_level is filled in.
	 */
	cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
	cur->bc_private.b.firstblock = *firstblock;
	cur->bc_private.b.flist = flist;
	cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
	/*
	 * Convert to a btree with two levels, one record in root.
	 */
	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE);
	memset(&args, 0, sizeof(args));
	args.tp = tp;
	args.mp = mp;
	args.firstblock = *firstblock;
	if (*firstblock == NULLFSBLOCK) {
		args.type = XFS_ALLOCTYPE_START_BNO;
		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
	} else if (flist->xbf_low) {
		args.type = XFS_ALLOCTYPE_START_BNO;
		args.fsbno = *firstblock;
	} else {
		args.type = XFS_ALLOCTYPE_NEAR_BNO;
		args.fsbno = *firstblock;
	}
	args.minlen = args.maxlen = args.prod = 1;
	args.wasdel = wasdel;
	*logflagsp = 0;
	if ((error = xfs_alloc_vextent(&args))) {
		xfs_iroot_realloc(ip, -1, whichfork);
		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
		return error;
	}
	/*
	 * Allocation can't fail, the space was reserved.
	 */
	ASSERT(args.fsbno != NULLFSBLOCK);
	ASSERT(*firstblock == NULLFSBLOCK ||
	       args.agno == XFS_FSB_TO_AGNO(mp, *firstblock) ||
	       (flist->xbf_low &&
		args.agno > XFS_FSB_TO_AGNO(mp, *firstblock)));
	*firstblock = cur->bc_private.b.firstblock = args.fsbno;
	cur->bc_private.b.allocated++;
	ip->i_d.di_nblocks++;
	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
	abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0);
	/*
	 * Fill in the child block.
	 */
	abp->b_ops = &xfs_bmbt_buf_ops;
	ablock = XFS_BUF_TO_BLOCK(abp);
	if (xfs_sb_version_hascrc(&mp->m_sb))
		xfs_btree_init_block_int(mp, ablock, abp->b_bn,
				XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino,
				XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS);
	else
		xfs_btree_init_block_int(mp, ablock, abp->b_bn,
				XFS_BMAP_MAGIC, 0, 0, ip->i_ino,
				XFS_BTREE_LONG_PTRS);

	arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	for (cnt = i = 0; i < nextents; i++) {
		ep = xfs_iext_get_ext(ifp, i);
		if (!isnullstartblock(xfs_bmbt_get_startblock(ep))) {
			arp->l0 = cpu_to_be64(ep->l0);
			arp->l1 = cpu_to_be64(ep->l1);
			arp++; cnt++;
		}
	}
	ASSERT(cnt == XFS_IFORK_NEXTENTS(ip, whichfork));
	xfs_btree_set_numrecs(ablock, cnt);

	/*
	 * Fill in the root key and pointer.
	 */
	kp = XFS_BMBT_KEY_ADDR(mp, block, 1);
	arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
	kp->br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(arp));
	pp = XFS_BMBT_PTR_ADDR(mp, block, 1, xfs_bmbt_get_maxrecs(cur,
						be16_to_cpu(block->bb_level)));
	*pp = cpu_to_be64(args.fsbno);

	/*
	 * Do all this logging at the end so that
	 * the root is at the right level.
	 */
	xfs_btree_log_block(cur, abp, XFS_BB_ALL_BITS);
	xfs_btree_log_recs(cur, abp, 1, be16_to_cpu(ablock->bb_numrecs));
	ASSERT(*curp == NULL);
	*curp = cur;
	*logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork);
	return 0;
}

/*
 * Convert a local file to an extents file.
 * This code is out of bounds for data forks of regular files,
 * since the file data needs to get logged so things will stay consistent.
 * (The bmap-level manipulations are ok, though).
 */
STATIC int				/* error */
xfs_bmap_local_to_extents(
	xfs_trans_t	*tp,		/* transaction pointer */
	xfs_inode_t	*ip,		/* incore inode pointer */
	xfs_fsblock_t	*firstblock,	/* first block allocated in xaction */
	xfs_extlen_t	total,		/* total blocks needed by transaction */
	int		*logflagsp,	/* inode logging flags */
	int		whichfork,
	void		(*init_fn)(struct xfs_trans *tp,
				   struct xfs_buf *bp,
				   struct xfs_inode *ip,
				   struct xfs_ifork *ifp))
{
	int		error;		/* error return value */
	int		flags;		/* logging flags returned */
	xfs_ifork_t	*ifp;		/* inode fork pointer */

	/*
	 * We don't want to deal with the case of keeping inode data inline yet.
	 * So sending the data fork of a regular inode is invalid.
	 */
	ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK));
	ifp = XFS_IFORK_PTR(ip, whichfork);
	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
	flags = 0;
	error = 0;
	if (ifp->if_bytes) {
		xfs_alloc_arg_t	args;	/* allocation arguments */
		xfs_buf_t	*bp;	/* buffer for extent block */
		xfs_bmbt_rec_host_t *ep;/* extent record pointer */

		ASSERT((ifp->if_flags &
			(XFS_IFINLINE|XFS_IFEXTENTS|XFS_IFEXTIREC)) == XFS_IFINLINE);
		memset(&args, 0, sizeof(args));
		args.tp = tp;
		args.mp = ip->i_mount;
		args.firstblock = *firstblock;
		/*
		 * Allocate a block.  We know we need only one, since the
		 * file currently fits in an inode.
		 */
		if (*firstblock == NULLFSBLOCK) {
			args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
			args.type = XFS_ALLOCTYPE_START_BNO;
		} else {
			args.fsbno = *firstblock;
			args.type = XFS_ALLOCTYPE_NEAR_BNO;
		}
		args.total = total;
		args.minlen = args.maxlen = args.prod = 1;
		error = xfs_alloc_vextent(&args);
		if (error)
			goto done;

		/* Can't fail, the space was reserved. */
		ASSERT(args.fsbno != NULLFSBLOCK);
		ASSERT(args.len == 1);
		*firstblock = args.fsbno;
		bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);

		/* initialise the block and copy the data */
		init_fn(tp, bp, ip, ifp);

		/* account for the change in fork size and log everything */
		xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
		xfs_bmap_forkoff_reset(args.mp, ip, whichfork);
		xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
		xfs_iext_add(ifp, 0, 1);
		ep = xfs_iext_get_ext(ifp, 0);
		xfs_bmbt_set_allf(ep, 0, args.fsbno, 1, XFS_EXT_NORM);
		trace_xfs_bmap_post_update(ip, 0,
				whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0,
				_THIS_IP_);
		XFS_IFORK_NEXT_SET(ip, whichfork, 1);
		ip->i_d.di_nblocks = 1;
		xfs_trans_mod_dquot_byino(tp, ip,
			XFS_TRANS_DQ_BCOUNT, 1L);
		flags |= xfs_ilog_fext(whichfork);
	} else {
		ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0);
		xfs_bmap_forkoff_reset(ip->i_mount, ip, whichfork);
	}
	ifp->if_flags &= ~XFS_IFINLINE;
	ifp->if_flags |= XFS_IFEXTENTS;
	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
	flags |= XFS_ILOG_CORE;
done:
	*logflagsp = flags;
	return error;
}

/*
 * Called from xfs_bmap_add_attrfork to handle btree format files.
 */
STATIC int					/* error */
xfs_bmap_add_attrfork_btree(
	xfs_trans_t		*tp,		/* transaction pointer */
	xfs_inode_t		*ip,		/* incore inode pointer */
	xfs_fsblock_t		*firstblock,	/* first block allocated */
	xfs_bmap_free_t		*flist,		/* blocks to free at commit */
	int			*flags)		/* inode logging flags */
{
	xfs_btree_cur_t		*cur;		/* btree cursor */
	int			error;		/* error return value */
	xfs_mount_t		*mp;		/* file system mount struct */
	int			stat;		/* newroot status */

	mp = ip->i_mount;
	if (ip->i_df.if_broot_bytes <= XFS_IFORK_DSIZE(ip))
		*flags |= XFS_ILOG_DBROOT;
	else {
		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
		cur->bc_private.b.flist = flist;
		cur->bc_private.b.firstblock = *firstblock;
		if ((error = xfs_bmbt_lookup_ge(cur, 0, 0, 0, &stat)))
			goto error0;
		/* must be at least one entry */
		XFS_WANT_CORRUPTED_GOTO(stat == 1, error0);
		if ((error = xfs_btree_new_iroot(cur, flags, &stat)))
			goto error0;
		if (stat == 0) {
			xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
			return XFS_ERROR(ENOSPC);
		}
		*firstblock = cur->bc_private.b.firstblock;
		cur->bc_private.b.allocated = 0;
		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	}
	return 0;
error0:
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
	return error;
}

/*
 * Called from xfs_bmap_add_attrfork to handle extents format files.
 */
STATIC int					/* error */
xfs_bmap_add_attrfork_extents(
	xfs_trans_t		*tp,		/* transaction pointer */
	xfs_inode_t		*ip,		/* incore inode pointer */
	xfs_fsblock_t		*firstblock,	/* first block allocated */
	xfs_bmap_free_t		*flist,		/* blocks to free at commit */
	int			*flags)		/* inode logging flags */
{
	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
	int			error;		/* error return value */

	if (ip->i_d.di_nextents * sizeof(xfs_bmbt_rec_t) <= XFS_IFORK_DSIZE(ip))
		return 0;
	cur = NULL;
	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, flist, &cur, 0,
		flags, XFS_DATA_FORK);
	if (cur) {
		cur->bc_private.b.allocated = 0;
		xfs_btree_del_cursor(cur,
			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
	}
	return error;
}

/*
 * Block initialisation function for local to extent format conversion.
 *
 * This shouldn't actually be called by anyone, so make sure debug kernels cause
 * a noticable failure.
 */
STATIC void
xfs_bmap_local_to_extents_init_fn(
	struct xfs_trans	*tp,
	struct xfs_buf		*bp,
	struct xfs_inode	*ip,
	struct xfs_ifork	*ifp)
{
	ASSERT(0);
	bp->b_ops = &xfs_bmbt_buf_ops;
	memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_BTREE_BUF);
}

/*
 * Called from xfs_bmap_add_attrfork to handle local format files. Each
 * different data fork content type needs a different callout to do the
 * conversion. Some are basic and only require special block initialisation
 * callouts for the data formating, others (directories) are so specialised they
 * handle everything themselves.
 *
 * XXX (dgc): investigate whether directory conversion can use the generic
 * formatting callout. It should be possible - it's just a very complex
 * formatter.
 */
STATIC int					/* error */
xfs_bmap_add_attrfork_local(
	xfs_trans_t		*tp,		/* transaction pointer */
	xfs_inode_t		*ip,		/* incore inode pointer */
	xfs_fsblock_t		*firstblock,	/* first block allocated */
	xfs_bmap_free_t		*flist,		/* blocks to free at commit */
	int			*flags)		/* inode logging flags */
{
	xfs_da_args_t		dargs;		/* args for dir/attr code */

	if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
		return 0;

	if (S_ISDIR(ip->i_d.di_mode)) {
		memset(&dargs, 0, sizeof(dargs));
		dargs.dp = ip;
		dargs.firstblock = firstblock;
		dargs.flist = flist;
		dargs.total = ip->i_mount->m_dirblkfsbs;
		dargs.whichfork = XFS_DATA_FORK;
		dargs.trans = tp;
		return xfs_dir2_sf_to_block(&dargs);
	}

	if (S_ISLNK(ip->i_d.di_mode))
		return xfs_bmap_local_to_extents(tp, ip, firstblock, 1,
						 flags, XFS_DATA_FORK,
						 xfs_symlink_local_to_remote);

	return xfs_bmap_local_to_extents(tp, ip, firstblock, 1, flags,
					 XFS_DATA_FORK,
					 xfs_bmap_local_to_extents_init_fn);
}

/*
 * Convert inode from non-attributed to attributed.
 * Must not be in a transaction, ip must not be locked.
 */
int						/* error code */
xfs_bmap_add_attrfork(
	xfs_inode_t		*ip,		/* incore inode pointer */
	int			size,		/* space new attribute needs */
	int			rsvd)		/* xact may use reserved blks */
{
	xfs_fsblock_t		firstblock;	/* 1st block/ag allocated */
	xfs_bmap_free_t		flist;		/* freed extent records */
	xfs_mount_t		*mp;		/* mount structure */
	xfs_trans_t		*tp;		/* transaction pointer */
	int			blks;		/* space reservation */
	int			version = 1;	/* superblock attr version */
	int			committed;	/* xaction was committed */
	int			logflags;	/* logging flags */
	int			error;		/* error return value */

	ASSERT(XFS_IFORK_Q(ip) == 0);

	mp = ip->i_mount;
	ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
	tp = xfs_trans_alloc(mp, XFS_TRANS_ADDAFORK);
	blks = XFS_ADDAFORK_SPACE_RES(mp);
	if (rsvd)
		tp->t_flags |= XFS_TRANS_RESERVE;
	if ((error = xfs_trans_reserve(tp, blks, XFS_ADDAFORK_LOG_RES(mp), 0,
			XFS_TRANS_PERM_LOG_RES, XFS_ADDAFORK_LOG_COUNT)))
		goto error0;
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
			XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
			XFS_QMOPT_RES_REGBLKS);
	if (error) {
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES);
		return error;
	}
	if (XFS_IFORK_Q(ip))
		goto error1;
	if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS) {
		/*
		 * For inodes coming from pre-6.2 filesystems.
		 */
		ASSERT(ip->i_d.di_aformat == 0);
		ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
	}
	ASSERT(ip->i_d.di_anextents == 0);

	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	switch (ip->i_d.di_format) {
	case XFS_DINODE_FMT_DEV:
		ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3;
		break;
	case XFS_DINODE_FMT_UUID:
		ip->i_d.di_forkoff = roundup(sizeof(uuid_t), 8) >> 3;
		break;
	case XFS_DINODE_FMT_LOCAL:
	case XFS_DINODE_FMT_EXTENTS:
	case XFS_DINODE_FMT_BTREE:
		ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size);
		if (!ip->i_d.di_forkoff)
			ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3;
		else if (mp->m_flags & XFS_MOUNT_ATTR2)
			version = 2;
		break;
	default:
		ASSERT(0);
		error = XFS_ERROR(EINVAL);
		goto error1;
	}

	ASSERT(ip->i_afp == NULL);
	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
	ip->i_afp->if_flags = XFS_IFEXTENTS;
	logflags = 0;
	xfs_bmap_init(&flist, &firstblock);
	switch (ip->i_d.di_format) {
	case XFS_DINODE_FMT_LOCAL:
		error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &flist,
			&logflags);
		break;
	case XFS_DINODE_FMT_EXTENTS:
		error = xfs_bmap_add_attrfork_extents(tp, ip, &firstblock,
			&flist, &logflags);
		break;
	case XFS_DINODE_FMT_BTREE:
		error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock, &flist,
			&logflags);
		break;
	default:
		error = 0;
		break;
	}
	if (logflags)
		xfs_trans_log_inode(tp, ip, logflags);
	if (error)
		goto error2;
	if (!xfs_sb_version_hasattr(&mp->m_sb) ||
	   (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
		__int64_t sbfields = 0;

		spin_lock(&mp->m_sb_lock);
		if (!xfs_sb_version_hasattr(&mp->m_sb)) {
			xfs_sb_version_addattr(&mp->m_sb);
			sbfields |= XFS_SB_VERSIONNUM;
		}
		if (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2) {
			xfs_sb_version_addattr2(&mp->m_sb);
			sbfields |= (XFS_SB_VERSIONNUM | XFS_SB_FEATURES2);
		}
		if (sbfields) {
			spin_unlock(&mp->m_sb_lock);
			xfs_mod_sb(tp, sbfields);
		} else
			spin_unlock(&mp->m_sb_lock);
	}

	error = xfs_bmap_finish(&tp, &flist, &committed);
	if (error)
		goto error2;
	return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
error2:
	xfs_bmap_cancel(&flist);
error1:
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
error0:
	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
	return error;
}

/*
 * Internal and external extent tree search functions.
 */

/*
 * Read in the extents to if_extents.
 * All inode fields are set up by caller, we just traverse the btree
 * and copy the records in. If the file system cannot contain unwritten
 * extents, the records are checked for no "state" flags.
 */
int					/* error */
xfs_bmap_read_extents(
	xfs_trans_t		*tp,	/* transaction pointer */
	xfs_inode_t		*ip,	/* incore inode */
	int			whichfork) /* data or attr fork */
{
	struct xfs_btree_block	*block;	/* current btree block */
	xfs_fsblock_t		bno;	/* block # of "block" */
	xfs_buf_t		*bp;	/* buffer for "block" */
	int			error;	/* error return value */
	xfs_exntfmt_t		exntf;	/* XFS_EXTFMT_NOSTATE, if checking */
	xfs_extnum_t		i, j;	/* index into the extents list */
	xfs_ifork_t		*ifp;	/* fork structure */
	int			level;	/* btree level, for checking */
	xfs_mount_t		*mp;	/* file system mount structure */
	__be64			*pp;	/* pointer to block address */
	/* REFERENCED */
	xfs_extnum_t		room;	/* number of entries there's room for */

	bno = NULLFSBLOCK;
	mp = ip->i_mount;
	ifp = XFS_IFORK_PTR(ip, whichfork);
	exntf = (whichfork != XFS_DATA_FORK) ? XFS_EXTFMT_NOSTATE :
					XFS_EXTFMT_INODE(ip);
	block = ifp->if_broot;
	/*
	 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
	 */
	level = be16_to_cpu(block->bb_level);
	ASSERT(level > 0);
	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
	bno = be64_to_cpu(*pp);
	ASSERT(bno != NULLDFSBNO);
	ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
	ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
	/*
	 * Go down the tree until leaf level is reached, following the first
	 * pointer (leftmost) at each level.
	 */
	while (level-- > 0) {
		error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
				XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops);
		if (error)
			return error;
		block = XFS_BUF_TO_BLOCK(bp);
		XFS_WANT_CORRUPTED_GOTO(
			xfs_bmap_sanity_check(mp, bp, level),
			error0);
		if (level == 0)
			break;
		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
		bno = be64_to_cpu(*pp);
		XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
		xfs_trans_brelse(tp, bp);
	}
	/*
	 * Here with bp and block set to the leftmost leaf node in the tree.
	 */
	room = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	i = 0;
	/*
	 * Loop over all leaf nodes.  Copy information to the extent records.
	 */
	for (;;) {
		xfs_bmbt_rec_t	*frp;
		xfs_fsblock_t	nextbno;
		xfs_extnum_t	num_recs;
		xfs_extnum_t	start;

		num_recs = xfs_btree_get_numrecs(block);
		if (unlikely(i + num_recs > room)) {
			ASSERT(i + num_recs <= room);
			xfs_warn(ip->i_mount,
				"corrupt dinode %Lu, (btree extents).",
				(unsigned long long) ip->i_ino);
			XFS_CORRUPTION_ERROR("xfs_bmap_read_extents(1)",
				XFS_ERRLEVEL_LOW, ip->i_mount, block);
			goto error0;
		}
		XFS_WANT_CORRUPTED_GOTO(
			xfs_bmap_sanity_check(mp, bp, 0),
			error0);
		/*
		 * Read-ahead the next leaf block, if any.
		 */
		nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
		if (nextbno != NULLFSBLOCK)
			xfs_btree_reada_bufl(mp, nextbno, 1,
					     &xfs_bmbt_buf_ops);
		/*
		 * Copy records into the extent records.
		 */
		frp = XFS_BMBT_REC_ADDR(mp, block, 1);
		start = i;
		for (j = 0; j < num_recs; j++, i++, frp++) {
			xfs_bmbt_rec_host_t *trp = xfs_iext_get_ext(ifp, i);
			trp->l0 = be64_to_cpu(frp->l0);
			trp->l1 = be64_to_cpu(frp->l1);
		}
		if (exntf == XFS_EXTFMT_NOSTATE) {
			/*
			 * Check all attribute bmap btree records and
			 * any "older" data bmap btree records for a
			 * set bit in the "extent flag" position.
			 */
			if (unlikely(xfs_check_nostate_extents(ifp,
					start, num_recs))) {
				XFS_ERROR_REPORT("xfs_bmap_read_extents(2)",
						 XFS_ERRLEVEL_LOW,
						 ip->i_mount);
				goto error0;
			}
		}
		xfs_trans_brelse(tp, bp);
		bno = nextbno;
		/*
		 * If we've reached the end, stop.
		 */
		if (bno == NULLFSBLOCK)
			break;
		error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
				XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops);
		if (error)
			return error;
		block = XFS_BUF_TO_BLOCK(bp);
	}
	ASSERT(i == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));
	ASSERT(i == XFS_IFORK_NEXTENTS(ip, whichfork));
	XFS_BMAP_TRACE_EXLIST(ip, i, whichfork);
	return 0;
error0:
	xfs_trans_brelse(tp, bp);
	return XFS_ERROR(EFSCORRUPTED);
}


/*
 * Search the extent records for the entry containing block bno.
 * If bno lies in a hole, point to the next entry.  If bno lies
 * past eof, *eofp will be set, and *prevp will contain the last
 * entry (null if none).  Else, *lastxp will be set to the index
 * of the found entry; *gotp will contain the entry.
 */
STATIC xfs_bmbt_rec_host_t *		/* pointer to found extent entry */
xfs_bmap_search_multi_extents(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_fileoff_t	bno,		/* block number searched for */
	int		*eofp,		/* out: end of file found */
	xfs_extnum_t	*lastxp,	/* out: last extent index */
	xfs_bmbt_irec_t	*gotp,		/* out: extent entry found */
	xfs_bmbt_irec_t	*prevp)		/* out: previous extent entry found */
{
	xfs_bmbt_rec_host_t *ep;		/* extent record pointer */
	xfs_extnum_t	lastx;		/* last extent index */

	/*
	 * Initialize the extent entry structure to catch access to
	 * uninitialized br_startblock field.
	 */
	gotp->br_startoff = 0xffa5a5a5a5a5a5a5LL;
	gotp->br_blockcount = 0xa55a5a5a5a5a5a5aLL;
	gotp->br_state = XFS_EXT_INVALID;
#if XFS_BIG_BLKNOS
	gotp->br_startblock = 0xffffa5a5a5a5a5a5LL;
#else
	gotp->br_startblock = 0xffffa5a5;
#endif
	prevp->br_startoff = NULLFILEOFF;

	ep = xfs_iext_bno_to_ext(ifp, bno, &lastx);
	if (lastx > 0) {
		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx - 1), prevp);
	}
	if (lastx < (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))) {
		xfs_bmbt_get_all(ep, gotp);
		*eofp = 0;
	} else {
		if (lastx > 0) {
			*gotp = *prevp;
		}
		*eofp = 1;
		ep = NULL;
	}
	*lastxp = lastx;
	return ep;
}

/*
 * Search the extents list for the inode, for the extent containing bno.
 * If bno lies in a hole, point to the next entry.  If bno lies past eof,
 * *eofp will be set, and *prevp will contain the last entry (null if none).
 * Else, *lastxp will be set to the index of the found
 * entry; *gotp will contain the entry.
 */
STATIC xfs_bmbt_rec_host_t *                 /* pointer to found extent entry */
xfs_bmap_search_extents(
	xfs_inode_t     *ip,            /* incore inode pointer */
	xfs_fileoff_t   bno,            /* block number searched for */
	int             fork,      	/* data or attr fork */
	int             *eofp,          /* out: end of file found */
	xfs_extnum_t    *lastxp,        /* out: last extent index */
	xfs_bmbt_irec_t *gotp,          /* out: extent entry found */
	xfs_bmbt_irec_t *prevp)         /* out: previous extent entry found */
{
	xfs_ifork_t	*ifp;		/* inode fork pointer */
	xfs_bmbt_rec_host_t  *ep;            /* extent record pointer */

	XFS_STATS_INC(xs_look_exlist);
	ifp = XFS_IFORK_PTR(ip, fork);

	ep = xfs_bmap_search_multi_extents(ifp, bno, eofp, lastxp, gotp, prevp);

	if (unlikely(!(gotp->br_startblock) && (*lastxp != NULLEXTNUM) &&
		     !(XFS_IS_REALTIME_INODE(ip) && fork == XFS_DATA_FORK))) {
		xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
				"Access to block zero in inode %llu "
				"start_block: %llx start_off: %llx "
				"blkcnt: %llx extent-state: %x lastx: %x\n",
			(unsigned long long)ip->i_ino,
			(unsigned long long)gotp->br_startblock,
			(unsigned long long)gotp->br_startoff,
			(unsigned long long)gotp->br_blockcount,
			gotp->br_state, *lastxp);
		*lastxp = NULLEXTNUM;
		*eofp = 1;
		return NULL;
	}
	return ep;
}

/*
 * Returns the file-relative block number of the first unused block(s)
 * in the file with at least "len" logically contiguous blocks free.
 * This is the lowest-address hole if the file has holes, else the first block
 * past the end of file.
 * Return 0 if the file is currently local (in-inode).
 */
int						/* error */
xfs_bmap_first_unused(
	xfs_trans_t	*tp,			/* transaction pointer */
	xfs_inode_t	*ip,			/* incore inode */
	xfs_extlen_t	len,			/* size of hole to find */
	xfs_fileoff_t	*first_unused,		/* unused block */
	int		whichfork)		/* data or attr fork */
{
	int		error;			/* error return value */
	int		idx;			/* extent record index */
	xfs_ifork_t	*ifp;			/* inode fork pointer */
	xfs_fileoff_t	lastaddr;		/* last block number seen */
	xfs_fileoff_t	lowest;			/* lowest useful block */
	xfs_fileoff_t	max;			/* starting useful block */
	xfs_fileoff_t	off;			/* offset for this block */
	xfs_extnum_t	nextents;		/* number of extent entries */

	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE ||
	       XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ||
	       XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
		*first_unused = 0;
		return 0;
	}
	ifp = XFS_IFORK_PTR(ip, whichfork);
	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
	    (error = xfs_iread_extents(tp, ip, whichfork)))
		return error;
	lowest = *first_unused;
	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	for (idx = 0, lastaddr = 0, max = lowest; idx < nextents; idx++) {
		xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, idx);
		off = xfs_bmbt_get_startoff(ep);
		/*
		 * See if the hole before this extent will work.
		 */
		if (off >= lowest + len && off - max >= len) {
			*first_unused = max;
			return 0;
		}
		lastaddr = off + xfs_bmbt_get_blockcount(ep);
		max = XFS_FILEOFF_MAX(lastaddr, lowest);
	}
	*first_unused = max;
	return 0;
}

/*
 * Returns the file-relative block number of the last block + 1 before
 * last_block (input value) in the file.
 * This is not based on i_size, it is based on the extent records.
 * Returns 0 for local files, as they do not have extent records.
 */
int						/* error */
xfs_bmap_last_before(
	xfs_trans_t	*tp,			/* transaction pointer */
	xfs_inode_t	*ip,			/* incore inode */
	xfs_fileoff_t	*last_block,		/* last block */
	int		whichfork)		/* data or attr fork */
{
	xfs_fileoff_t	bno;			/* input file offset */
	int		eof;			/* hit end of file */
	xfs_bmbt_rec_host_t *ep;		/* pointer to last extent */
	int		error;			/* error return value */
	xfs_bmbt_irec_t	got;			/* current extent value */
	xfs_ifork_t	*ifp;			/* inode fork pointer */
	xfs_extnum_t	lastx;			/* last extent used */
	xfs_bmbt_irec_t	prev;			/* previous extent value */

	if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE &&
	    XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
	    XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL)
	       return XFS_ERROR(EIO);
	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
		*last_block = 0;
		return 0;
	}
	ifp = XFS_IFORK_PTR(ip, whichfork);
	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
	    (error = xfs_iread_extents(tp, ip, whichfork)))
		return error;
	bno = *last_block - 1;
	ep = xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got,
		&prev);
	if (eof || xfs_bmbt_get_startoff(ep) > bno) {
		if (prev.br_startoff == NULLFILEOFF)
			*last_block = 0;
		else
			*last_block = prev.br_startoff + prev.br_blockcount;
	}
	/*
	 * Otherwise *last_block is already the right answer.
	 */
	return 0;
}

STATIC int
xfs_bmap_last_extent(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip,
	int			whichfork,
	struct xfs_bmbt_irec	*rec,
	int			*is_empty)
{
	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
	int			error;
	int			nextents;

	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
		error = xfs_iread_extents(tp, ip, whichfork);
		if (error)
			return error;
	}

	nextents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
	if (nextents == 0) {
		*is_empty = 1;
		return 0;
	}

	xfs_bmbt_get_all(xfs_iext_get_ext(ifp, nextents - 1), rec);
	*is_empty = 0;
	return 0;
}

/*
 * Check the last inode extent to determine whether this allocation will result
 * in blocks being allocated at the end of the file. When we allocate new data
 * blocks at the end of the file which do not start at the previous data block,
 * we will try to align the new blocks at stripe unit boundaries.
 *
 * Returns 0 in bma->aeof if the file (fork) is empty as any new write will be
 * at, or past the EOF.
 */
STATIC int
xfs_bmap_isaeof(
	struct xfs_bmalloca	*bma,
	int			whichfork)
{
	struct xfs_bmbt_irec	rec;
	int			is_empty;
	int			error;

	bma->aeof = 0;
	error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec,
				     &is_empty);
	if (error || is_empty)
		return error;

	/*
	 * Check if we are allocation or past the last extent, or at least into
	 * the last delayed allocated extent.
	 */
	bma->aeof = bma->offset >= rec.br_startoff + rec.br_blockcount ||
		(bma->offset >= rec.br_startoff &&
		 isnullstartblock(rec.br_startblock));
	return 0;
}

/*
 * Check if the endoff is outside the last extent. If so the caller will grow
 * the allocation to a stripe unit boundary.  All offsets are considered outside
 * the end of file for an empty fork, so 1 is returned in *eof in that case.
 */
int
xfs_bmap_eof(
	struct xfs_inode	*ip,
	xfs_fileoff_t		endoff,
	int			whichfork,
	int			*eof)
{
	struct xfs_bmbt_irec	rec;
	int			error;

	error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, eof);
	if (error || *eof)
		return error;

	*eof = endoff >= rec.br_startoff + rec.br_blockcount;
	return 0;
}

/*
 * Returns the file-relative block number of the first block past eof in
 * the file.  This is not based on i_size, it is based on the extent records.
 * Returns 0 for local files, as they do not have extent records.
 */
int
xfs_bmap_last_offset(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip,
	xfs_fileoff_t		*last_block,
	int			whichfork)
{
	struct xfs_bmbt_irec	rec;
	int			is_empty;
	int			error;

	*last_block = 0;

	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL)
		return 0;

	if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE &&
	    XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS)
	       return XFS_ERROR(EIO);

	error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, &is_empty);
	if (error || is_empty)
		return error;

	*last_block = rec.br_startoff + rec.br_blockcount;
	return 0;
}

/*
 * Returns whether the selected fork of the inode has exactly one
 * block or not.  For the data fork we check this matches di_size,
 * implying the file's range is 0..bsize-1.
 */
int					/* 1=>1 block, 0=>otherwise */
xfs_bmap_one_block(
	xfs_inode_t	*ip,		/* incore inode */
	int		whichfork)	/* data or attr fork */
{
	xfs_bmbt_rec_host_t *ep;	/* ptr to fork's extent */
	xfs_ifork_t	*ifp;		/* inode fork pointer */
	int		rval;		/* return value */
	xfs_bmbt_irec_t	s;		/* internal version of extent */

#ifndef DEBUG
	if (whichfork == XFS_DATA_FORK)
		return XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize;
#endif	/* !DEBUG */
	if (XFS_IFORK_NEXTENTS(ip, whichfork) != 1)
		return 0;
	if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS)
		return 0;
	ifp = XFS_IFORK_PTR(ip, whichfork);
	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
	ep = xfs_iext_get_ext(ifp, 0);
	xfs_bmbt_get_all(ep, &s);
	rval = s.br_startoff == 0 && s.br_blockcount == 1;
	if (rval && whichfork == XFS_DATA_FORK)
		ASSERT(XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize);
	return rval;
}

/*
 * Extent tree manipulation functions used during allocation.
 */

/*
 * Convert a delayed allocation to a real allocation.
 */
STATIC int				/* error */
xfs_bmap_add_extent_delay_real(
	struct xfs_bmalloca	*bma)
{
	struct xfs_bmbt_irec	*new = &bma->got;
	int			diff;	/* temp value */
	xfs_bmbt_rec_host_t	*ep;	/* extent entry for idx */
	int			error;	/* error return value */
	int			i;	/* temp state */
	xfs_ifork_t		*ifp;	/* inode fork pointer */
	xfs_fileoff_t		new_endoff;	/* end offset of new entry */
	xfs_bmbt_irec_t		r[3];	/* neighbor extent entries */
					/* left is 0, right is 1, prev is 2 */
	int			rval=0;	/* return value (logging flags) */
	int			state = 0;/* state bits, accessed thru macros */
	xfs_filblks_t		da_new; /* new count del alloc blocks used */
	xfs_filblks_t		da_old; /* old count del alloc blocks used */
	xfs_filblks_t		temp=0;	/* value for da_new calculations */
	xfs_filblks_t		temp2=0;/* value for da_new calculations */
	int			tmp_rval;	/* partial logging flags */

	ifp = XFS_IFORK_PTR(bma->ip, XFS_DATA_FORK);

	ASSERT(bma->idx >= 0);
	ASSERT(bma->idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
	ASSERT(!isnullstartblock(new->br_startblock));
	ASSERT(!bma->cur ||
	       (bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));

	XFS_STATS_INC(xs_add_exlist);

#define	LEFT		r[0]
#define	RIGHT		r[1]
#define	PREV		r[2]

	/*
	 * Set up a bunch of variables to make the tests simpler.
	 */
	ep = xfs_iext_get_ext(ifp, bma->idx);
	xfs_bmbt_get_all(ep, &PREV);
	new_endoff = new->br_startoff + new->br_blockcount;
	ASSERT(PREV.br_startoff <= new->br_startoff);
	ASSERT(PREV.br_startoff + PREV.br_blockcount >= new_endoff);

	da_old = startblockval(PREV.br_startblock);
	da_new = 0;

	/*
	 * Set flags determining what part of the previous delayed allocation
	 * extent is being replaced by a real allocation.
	 */
	if (PREV.br_startoff == new->br_startoff)
		state |= BMAP_LEFT_FILLING;
	if (PREV.br_startoff + PREV.br_blockcount == new_endoff)
		state |= BMAP_RIGHT_FILLING;

	/*
	 * Check and set flags if this segment has a left neighbor.
	 * Don't set contiguous if the combined extent would be too large.
	 */
	if (bma->idx > 0) {
		state |= BMAP_LEFT_VALID;
		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx - 1), &LEFT);

		if (isnullstartblock(LEFT.br_startblock))
			state |= BMAP_LEFT_DELAY;
	}

	if ((state & BMAP_LEFT_VALID) && !(state & BMAP_LEFT_DELAY) &&
	    LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
	    LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
	    LEFT.br_state == new->br_state &&
	    LEFT.br_blockcount + new->br_blockcount <= MAXEXTLEN)
		state |= BMAP_LEFT_CONTIG;

	/*
	 * Check and set flags if this segment has a right neighbor.
	 * Don't set contiguous if the combined extent would be too large.
	 * Also check for all-three-contiguous being too large.
	 */
	if (bma->idx < bma->ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
		state |= BMAP_RIGHT_VALID;
		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx + 1), &RIGHT);

		if (isnullstartblock(RIGHT.br_startblock))
			state |= BMAP_RIGHT_DELAY;
	}

	if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) &&
	    new_endoff == RIGHT.br_startoff &&
	    new->br_startblock + new->br_blockcount == RIGHT.br_startblock &&
	    new->br_state == RIGHT.br_state &&
	    new->br_blockcount + RIGHT.br_blockcount <= MAXEXTLEN &&
	    ((state & (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
		       BMAP_RIGHT_FILLING)) !=
		      (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
		       BMAP_RIGHT_FILLING) ||
	     LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
			<= MAXEXTLEN))
		state |= BMAP_RIGHT_CONTIG;

	error = 0;
	/*
	 * Switch out based on the FILLING and CONTIG state bits.
	 */
	switch (state & (BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG |
			 BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG)) {
	case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG |
	     BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG:
		/*
		 * Filling in all of a previously delayed allocation extent.
		 * The left and right neighbors are both contiguous with new.
		 */
		bma->idx--;
		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, bma->idx),
			LEFT.br_blockcount + PREV.br_blockcount +
			RIGHT.br_blockcount);
		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);

		xfs_iext_remove(bma->ip, bma->idx + 1, 2, state);
		bma->ip->i_d.di_nextents--;
		if (bma->cur == NULL)
			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
		else {
			rval = XFS_ILOG_CORE;
			error = xfs_bmbt_lookup_eq(bma->cur, RIGHT.br_startoff,
					RIGHT.br_startblock,
					RIGHT.br_blockcount, &i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			error = xfs_btree_delete(bma->cur, &i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			error = xfs_btree_decrement(bma->cur, 0, &i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			error = xfs_bmbt_update(bma->cur, LEFT.br_startoff,
					LEFT.br_startblock,
					LEFT.br_blockcount +
					PREV.br_blockcount +
					RIGHT.br_blockcount, LEFT.br_state);
			if (error)
				goto done;
		}
		break;

	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_LEFT_CONTIG:
		/*
		 * Filling in all of a previously delayed allocation extent.
		 * The left neighbor is contiguous, the right is not.
		 */
		bma->idx--;

		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, bma->idx),
			LEFT.br_blockcount + PREV.br_blockcount);
		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);

		xfs_iext_remove(bma->ip, bma->idx + 1, 1, state);
		if (bma->cur == NULL)
			rval = XFS_ILOG_DEXT;
		else {
			rval = 0;
			error = xfs_bmbt_lookup_eq(bma->cur, LEFT.br_startoff,
					LEFT.br_startblock, LEFT.br_blockcount,
					&i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			error = xfs_bmbt_update(bma->cur, LEFT.br_startoff,
					LEFT.br_startblock,
					LEFT.br_blockcount +
					PREV.br_blockcount, LEFT.br_state);
			if (error)
				goto done;
		}
		break;

	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG:
		/*
		 * Filling in all of a previously delayed allocation extent.
		 * The right neighbor is contiguous, the left is not.
		 */
		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
		xfs_bmbt_set_startblock(ep, new->br_startblock);
		xfs_bmbt_set_blockcount(ep,
			PREV.br_blockcount + RIGHT.br_blockcount);
		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);

		xfs_iext_remove(bma->ip, bma->idx + 1, 1, state);
		if (bma->cur == NULL)
			rval = XFS_ILOG_DEXT;
		else {
			rval = 0;
			error = xfs_bmbt_lookup_eq(bma->cur, RIGHT.br_startoff,
					RIGHT.br_startblock,
					RIGHT.br_blockcount, &i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			error = xfs_bmbt_update(bma->cur, PREV.br_startoff,
					new->br_startblock,
					PREV.br_blockcount +
					RIGHT.br_blockcount, PREV.br_state);
			if (error)
				goto done;
		}
		break;

	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING:
		/*
		 * Filling in all of a previously delayed allocation extent.
		 * Neither the left nor right neighbors are contiguous with
		 * the new one.
		 */
		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
		xfs_bmbt_set_startblock(ep, new->br_startblock);
		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);

		bma->ip->i_d.di_nextents++;
		if (bma->cur == NULL)
			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
		else {
			rval = XFS_ILOG_CORE;
			error = xfs_bmbt_lookup_eq(bma->cur, new->br_startoff,
					new->br_startblock, new->br_blockcount,
					&i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
			bma->cur->bc_rec.b.br_state = XFS_EXT_NORM;
			error = xfs_btree_insert(bma->cur, &i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
		}
		break;

	case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG:
		/*
		 * Filling in the first part of a previous delayed allocation.
		 * The left neighbor is contiguous.
		 */
		trace_xfs_bmap_pre_update(bma->ip, bma->idx - 1, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, bma->idx - 1),
			LEFT.br_blockcount + new->br_blockcount);
		xfs_bmbt_set_startoff(ep,
			PREV.br_startoff + new->br_blockcount);
		trace_xfs_bmap_post_update(bma->ip, bma->idx - 1, state, _THIS_IP_);

		temp = PREV.br_blockcount - new->br_blockcount;
		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(ep, temp);
		if (bma->cur == NULL)
			rval = XFS_ILOG_DEXT;
		else {
			rval = 0;
			error = xfs_bmbt_lookup_eq(bma->cur, LEFT.br_startoff,
					LEFT.br_startblock, LEFT.br_blockcount,
					&i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			error = xfs_bmbt_update(bma->cur, LEFT.br_startoff,
					LEFT.br_startblock,
					LEFT.br_blockcount +
					new->br_blockcount,
					LEFT.br_state);
			if (error)
				goto done;
		}
		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp),
			startblockval(PREV.br_startblock));
		xfs_bmbt_set_startblock(ep, nullstartblock(da_new));
		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);

		bma->idx--;
		break;

	case BMAP_LEFT_FILLING:
		/*
		 * Filling in the first part of a previous delayed allocation.
		 * The left neighbor is not contiguous.
		 */
		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
		xfs_bmbt_set_startoff(ep, new_endoff);
		temp = PREV.br_blockcount - new->br_blockcount;
		xfs_bmbt_set_blockcount(ep, temp);
		xfs_iext_insert(bma->ip, bma->idx, 1, new, state);
		bma->ip->i_d.di_nextents++;
		if (bma->cur == NULL)
			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
		else {
			rval = XFS_ILOG_CORE;
			error = xfs_bmbt_lookup_eq(bma->cur, new->br_startoff,
					new->br_startblock, new->br_blockcount,
					&i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
			bma->cur->bc_rec.b.br_state = XFS_EXT_NORM;
			error = xfs_btree_insert(bma->cur, &i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
		}

		if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
					bma->firstblock, bma->flist,
					&bma->cur, 1, &tmp_rval, XFS_DATA_FORK);
			rval |= tmp_rval;
			if (error)
				goto done;
		}
		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp),
			startblockval(PREV.br_startblock) -
			(bma->cur ? bma->cur->bc_private.b.allocated : 0));
		ep = xfs_iext_get_ext(ifp, bma->idx + 1);
		xfs_bmbt_set_startblock(ep, nullstartblock(da_new));
		trace_xfs_bmap_post_update(bma->ip, bma->idx + 1, state, _THIS_IP_);
		break;

	case BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG:
		/*
		 * Filling in the last part of a previous delayed allocation.
		 * The right neighbor is contiguous with the new allocation.
		 */
		temp = PREV.br_blockcount - new->br_blockcount;
		trace_xfs_bmap_pre_update(bma->ip, bma->idx + 1, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(ep, temp);
		xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, bma->idx + 1),
			new->br_startoff, new->br_startblock,
			new->br_blockcount + RIGHT.br_blockcount,
			RIGHT.br_state);
		trace_xfs_bmap_post_update(bma->ip, bma->idx + 1, state, _THIS_IP_);
		if (bma->cur == NULL)
			rval = XFS_ILOG_DEXT;
		else {
			rval = 0;
			error = xfs_bmbt_lookup_eq(bma->cur, RIGHT.br_startoff,
					RIGHT.br_startblock,
					RIGHT.br_blockcount, &i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			error = xfs_bmbt_update(bma->cur, new->br_startoff,
					new->br_startblock,
					new->br_blockcount +
					RIGHT.br_blockcount,
					RIGHT.br_state);
			if (error)
				goto done;
		}

		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp),
			startblockval(PREV.br_startblock));
		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
		xfs_bmbt_set_startblock(ep, nullstartblock(da_new));
		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);

		bma->idx++;
		break;

	case BMAP_RIGHT_FILLING:
		/*
		 * Filling in the last part of a previous delayed allocation.
		 * The right neighbor is not contiguous.
		 */
		temp = PREV.br_blockcount - new->br_blockcount;
		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(ep, temp);
		xfs_iext_insert(bma->ip, bma->idx + 1, 1, new, state);
		bma->ip->i_d.di_nextents++;
		if (bma->cur == NULL)
			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
		else {
			rval = XFS_ILOG_CORE;
			error = xfs_bmbt_lookup_eq(bma->cur, new->br_startoff,
					new->br_startblock, new->br_blockcount,
					&i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
			bma->cur->bc_rec.b.br_state = XFS_EXT_NORM;
			error = xfs_btree_insert(bma->cur, &i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
		}

		if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
				bma->firstblock, bma->flist, &bma->cur, 1,
				&tmp_rval, XFS_DATA_FORK);
			rval |= tmp_rval;
			if (error)
				goto done;
		}
		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp),
			startblockval(PREV.br_startblock) -
			(bma->cur ? bma->cur->bc_private.b.allocated : 0));
		ep = xfs_iext_get_ext(ifp, bma->idx);
		xfs_bmbt_set_startblock(ep, nullstartblock(da_new));
		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);

		bma->idx++;
		break;

	case 0:
		/*
		 * Filling in the middle part of a previous delayed allocation.
		 * Contiguity is impossible here.
		 * This case is avoided almost all the time.
		 *
		 * We start with a delayed allocation:
		 *
		 * +ddddddddddddddddddddddddddddddddddddddddddddddddddddddd+
		 *  PREV @ idx
		 *
	         * and we are allocating:
		 *                     +rrrrrrrrrrrrrrrrr+
		 *			      new
		 *
		 * and we set it up for insertion as:
		 * +ddddddddddddddddddd+rrrrrrrrrrrrrrrrr+ddddddddddddddddd+
		 *                            new
		 *  PREV @ idx          LEFT              RIGHT
		 *                      inserted at idx + 1
		 */
		temp = new->br_startoff - PREV.br_startoff;
		temp2 = PREV.br_startoff + PREV.br_blockcount - new_endoff;
		trace_xfs_bmap_pre_update(bma->ip, bma->idx, 0, _THIS_IP_);
		xfs_bmbt_set_blockcount(ep, temp);	/* truncate PREV */
		LEFT = *new;
		RIGHT.br_state = PREV.br_state;
		RIGHT.br_startblock = nullstartblock(
				(int)xfs_bmap_worst_indlen(bma->ip, temp2));
		RIGHT.br_startoff = new_endoff;
		RIGHT.br_blockcount = temp2;
		/* insert LEFT (r[0]) and RIGHT (r[1]) at the same time */
		xfs_iext_insert(bma->ip, bma->idx + 1, 2, &LEFT, state);
		bma->ip->i_d.di_nextents++;
		if (bma->cur == NULL)
			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
		else {
			rval = XFS_ILOG_CORE;
			error = xfs_bmbt_lookup_eq(bma->cur, new->br_startoff,
					new->br_startblock, new->br_blockcount,
					&i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
			bma->cur->bc_rec.b.br_state = XFS_EXT_NORM;
			error = xfs_btree_insert(bma->cur, &i);
			if (error)
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
		}

		if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
					bma->firstblock, bma->flist, &bma->cur,
					1, &tmp_rval, XFS_DATA_FORK);
			rval |= tmp_rval;
			if (error)
				goto done;
		}
		temp = xfs_bmap_worst_indlen(bma->ip, temp);
		temp2 = xfs_bmap_worst_indlen(bma->ip, temp2);
		diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) -
			(bma->cur ? bma->cur->bc_private.b.allocated : 0));
		if (diff > 0) {
			error = xfs_icsb_modify_counters(bma->ip->i_mount,
					XFS_SBS_FDBLOCKS,
					-((int64_t)diff), 0);
			ASSERT(!error);
			if (error)
				goto done;
		}

		ep = xfs_iext_get_ext(ifp, bma->idx);
		xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);
		trace_xfs_bmap_pre_update(bma->ip, bma->idx + 2, state, _THIS_IP_);
		xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, bma->idx + 2),
			nullstartblock((int)temp2));
		trace_xfs_bmap_post_update(bma->ip, bma->idx + 2, state, _THIS_IP_);

		bma->idx++;
		da_new = temp + temp2;
		break;

	case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
	case BMAP_RIGHT_FILLING | BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
	case BMAP_LEFT_FILLING | BMAP_RIGHT_CONTIG:
	case BMAP_RIGHT_FILLING | BMAP_LEFT_CONTIG:
	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
	case BMAP_LEFT_CONTIG:
	case BMAP_RIGHT_CONTIG:
		/*
		 * These cases are all impossible.
		 */
		ASSERT(0);
	}

	/* convert to a btree if necessary */
	if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
		int	tmp_logflags;	/* partial log flag return val */

		ASSERT(bma->cur == NULL);
		error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
				bma->firstblock, bma->flist, &bma->cur,
				da_old > 0, &tmp_logflags, XFS_DATA_FORK);
		bma->logflags |= tmp_logflags;
		if (error)
			goto done;
	}

	/* adjust for changes in reserved delayed indirect blocks */
	if (da_old || da_new) {
		temp = da_new;
		if (bma->cur)
			temp += bma->cur->bc_private.b.allocated;
		ASSERT(temp <= da_old);
		if (temp < da_old)
			xfs_icsb_modify_counters(bma->ip->i_mount,
					XFS_SBS_FDBLOCKS,
					(int64_t)(da_old - temp), 0);
	}

	/* clear out the allocated field, done with it now in any case. */
	if (bma->cur)
		bma->cur->bc_private.b.allocated = 0;

	xfs_bmap_check_leaf_extents(bma->cur, bma->ip, XFS_DATA_FORK);
done:
	bma->logflags |= rval;
	return error;
#undef	LEFT
#undef	RIGHT
#undef	PREV
}

/*
 * Convert an unwritten allocation to a real allocation or vice versa.
 */
STATIC int				/* error */
xfs_bmap_add_extent_unwritten_real(
	struct xfs_trans	*tp,
	xfs_inode_t		*ip,	/* incore inode pointer */
	xfs_extnum_t		*idx,	/* extent number to update/insert */
	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
	xfs_bmap_free_t		*flist,	/* list of extents to be freed */
	int			*logflagsp) /* inode logging flags */
{
	xfs_btree_cur_t		*cur;	/* btree cursor */
	xfs_bmbt_rec_host_t	*ep;	/* extent entry for idx */
	int			error;	/* error return value */
	int			i;	/* temp state */
	xfs_ifork_t		*ifp;	/* inode fork pointer */
	xfs_fileoff_t		new_endoff;	/* end offset of new entry */
	xfs_exntst_t		newext;	/* new extent state */
	xfs_exntst_t		oldext;	/* old extent state */
	xfs_bmbt_irec_t		r[3];	/* neighbor extent entries */
					/* left is 0, right is 1, prev is 2 */
	int			rval=0;	/* return value (logging flags) */
	int			state = 0;/* state bits, accessed thru macros */

	*logflagsp = 0;

	cur = *curp;
	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);

	ASSERT(*idx >= 0);
	ASSERT(*idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
	ASSERT(!isnullstartblock(new->br_startblock));

	XFS_STATS_INC(xs_add_exlist);

#define	LEFT		r[0]
#define	RIGHT		r[1]
#define	PREV		r[2]

	/*
	 * Set up a bunch of variables to make the tests simpler.
	 */
	error = 0;
	ep = xfs_iext_get_ext(ifp, *idx);
	xfs_bmbt_get_all(ep, &PREV);
	newext = new->br_state;
	oldext = (newext == XFS_EXT_UNWRITTEN) ?
		XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
	ASSERT(PREV.br_state == oldext);
	new_endoff = new->br_startoff + new->br_blockcount;
	ASSERT(PREV.br_startoff <= new->br_startoff);
	ASSERT(PREV.br_startoff + PREV.br_blockcount >= new_endoff);

	/*
	 * Set flags determining what part of the previous oldext allocation
	 * extent is being replaced by a newext allocation.
	 */
	if (PREV.br_startoff == new->br_startoff)
		state |= BMAP_LEFT_FILLING;
	if (PREV.br_startoff + PREV.br_blockcount == new_endoff)
		state |= BMAP_RIGHT_FILLING;

	/*
	 * Check and set flags if this segment has a left neighbor.
	 * Don't set contiguous if the combined extent would be too large.
	 */
	if (*idx > 0) {
		state |= BMAP_LEFT_VALID;
		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx - 1), &LEFT);

		if (isnullstartblock(LEFT.br_startblock))
			state |= BMAP_LEFT_DELAY;
	}

	if ((state & BMAP_LEFT_VALID) && !(state & BMAP_LEFT_DELAY) &&
	    LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
	    LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
	    LEFT.br_state == newext &&
	    LEFT.br_blockcount + new->br_blockcount <= MAXEXTLEN)
		state |= BMAP_LEFT_CONTIG;

	/*
	 * Check and set flags if this segment has a right neighbor.
	 * Don't set contiguous if the combined extent would be too large.
	 * Also check for all-three-contiguous being too large.
	 */
	if (*idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
		state |= BMAP_RIGHT_VALID;
		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx + 1), &RIGHT);
		if (isnullstartblock(RIGHT.br_startblock))
			state |= BMAP_RIGHT_DELAY;
	}

	if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) &&
	    new_endoff == RIGHT.br_startoff &&
	    new->br_startblock + new->br_blockcount == RIGHT.br_startblock &&
	    newext == RIGHT.br_state &&
	    new->br_blockcount + RIGHT.br_blockcount <= MAXEXTLEN &&
	    ((state & (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
		       BMAP_RIGHT_FILLING)) !=
		      (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
		       BMAP_RIGHT_FILLING) ||
	     LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
			<= MAXEXTLEN))
		state |= BMAP_RIGHT_CONTIG;

	/*
	 * Switch out based on the FILLING and CONTIG state bits.
	 */
	switch (state & (BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG |
			 BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG)) {
	case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG |
	     BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG:
		/*
		 * Setting all of a previous oldext extent to newext.
		 * The left and right neighbors are both contiguous with new.
		 */
		--*idx;

		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx),
			LEFT.br_blockcount + PREV.br_blockcount +
			RIGHT.br_blockcount);
		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);

		xfs_iext_remove(ip, *idx + 1, 2, state);
		ip->i_d.di_nextents -= 2;
		if (cur == NULL)
			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
		else {
			rval = XFS_ILOG_CORE;
			if ((error = xfs_bmbt_lookup_eq(cur, RIGHT.br_startoff,
					RIGHT.br_startblock,
					RIGHT.br_blockcount, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_btree_delete(cur, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_btree_decrement(cur, 0, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_btree_delete(cur, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_btree_decrement(cur, 0, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
				LEFT.br_startblock,
				LEFT.br_blockcount + PREV.br_blockcount +
				RIGHT.br_blockcount, LEFT.br_state)))
				goto done;
		}
		break;

	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_LEFT_CONTIG:
		/*
		 * Setting all of a previous oldext extent to newext.
		 * The left neighbor is contiguous, the right is not.
		 */
		--*idx;

		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx),
			LEFT.br_blockcount + PREV.br_blockcount);
		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);

		xfs_iext_remove(ip, *idx + 1, 1, state);
		ip->i_d.di_nextents--;
		if (cur == NULL)
			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
		else {
			rval = XFS_ILOG_CORE;
			if ((error = xfs_bmbt_lookup_eq(cur, PREV.br_startoff,
					PREV.br_startblock, PREV.br_blockcount,
					&i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_btree_delete(cur, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_btree_decrement(cur, 0, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
				LEFT.br_startblock,
				LEFT.br_blockcount + PREV.br_blockcount,
				LEFT.br_state)))
				goto done;
		}
		break;

	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG:
		/*
		 * Setting all of a previous oldext extent to newext.
		 * The right neighbor is contiguous, the left is not.
		 */
		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(ep,
			PREV.br_blockcount + RIGHT.br_blockcount);
		xfs_bmbt_set_state(ep, newext);
		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
		xfs_iext_remove(ip, *idx + 1, 1, state);
		ip->i_d.di_nextents--;
		if (cur == NULL)
			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
		else {
			rval = XFS_ILOG_CORE;
			if ((error = xfs_bmbt_lookup_eq(cur, RIGHT.br_startoff,
					RIGHT.br_startblock,
					RIGHT.br_blockcount, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_btree_delete(cur, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_btree_decrement(cur, 0, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_bmbt_update(cur, new->br_startoff,
				new->br_startblock,
				new->br_blockcount + RIGHT.br_blockcount,
				newext)))
				goto done;
		}
		break;

	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING:
		/*
		 * Setting all of a previous oldext extent to newext.
		 * Neither the left nor right neighbors are contiguous with
		 * the new one.
		 */
		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
		xfs_bmbt_set_state(ep, newext);
		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);

		if (cur == NULL)
			rval = XFS_ILOG_DEXT;
		else {
			rval = 0;
			if ((error = xfs_bmbt_lookup_eq(cur, new->br_startoff,
					new->br_startblock, new->br_blockcount,
					&i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_bmbt_update(cur, new->br_startoff,
				new->br_startblock, new->br_blockcount,
				newext)))
				goto done;
		}
		break;

	case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG:
		/*
		 * Setting the first part of a previous oldext extent to newext.
		 * The left neighbor is contiguous.
		 */
		trace_xfs_bmap_pre_update(ip, *idx - 1, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx - 1),
			LEFT.br_blockcount + new->br_blockcount);
		xfs_bmbt_set_startoff(ep,
			PREV.br_startoff + new->br_blockcount);
		trace_xfs_bmap_post_update(ip, *idx - 1, state, _THIS_IP_);

		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
		xfs_bmbt_set_startblock(ep,
			new->br_startblock + new->br_blockcount);
		xfs_bmbt_set_blockcount(ep,
			PREV.br_blockcount - new->br_blockcount);
		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);

		--*idx;

		if (cur == NULL)
			rval = XFS_ILOG_DEXT;
		else {
			rval = 0;
			if ((error = xfs_bmbt_lookup_eq(cur, PREV.br_startoff,
					PREV.br_startblock, PREV.br_blockcount,
					&i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_bmbt_update(cur,
				PREV.br_startoff + new->br_blockcount,
				PREV.br_startblock + new->br_blockcount,
				PREV.br_blockcount - new->br_blockcount,
				oldext)))
				goto done;
			if ((error = xfs_btree_decrement(cur, 0, &i)))
				goto done;
			error = xfs_bmbt_update(cur, LEFT.br_startoff,
				LEFT.br_startblock,
				LEFT.br_blockcount + new->br_blockcount,
				LEFT.br_state);
			if (error)
				goto done;
		}
		break;

	case BMAP_LEFT_FILLING:
		/*
		 * Setting the first part of a previous oldext extent to newext.
		 * The left neighbor is not contiguous.
		 */
		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
		ASSERT(ep && xfs_bmbt_get_state(ep) == oldext);
		xfs_bmbt_set_startoff(ep, new_endoff);
		xfs_bmbt_set_blockcount(ep,
			PREV.br_blockcount - new->br_blockcount);
		xfs_bmbt_set_startblock(ep,
			new->br_startblock + new->br_blockcount);
		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);

		xfs_iext_insert(ip, *idx, 1, new, state);
		ip->i_d.di_nextents++;
		if (cur == NULL)
			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
		else {
			rval = XFS_ILOG_CORE;
			if ((error = xfs_bmbt_lookup_eq(cur, PREV.br_startoff,
					PREV.br_startblock, PREV.br_blockcount,
					&i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
			if ((error = xfs_bmbt_update(cur,
				PREV.br_startoff + new->br_blockcount,
				PREV.br_startblock + new->br_blockcount,
				PREV.br_blockcount - new->br_blockcount,
				oldext)))
				goto done;
			cur->bc_rec.b = *new;
			if ((error = xfs_btree_insert(cur, &i)))
				goto done;
			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
		}
		break;

	case BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG:
		/*
		 * Setting the last part of a previous oldext extent to newext.
		 * The right neighbor is contiguous with the new allocation.
		 */
		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
		xfs_bmbt_set_blockcount(ep,
			PREV.br_blockcount - new->br_blockcount);
		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);

		++*idx;

		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
		xfs_bmbt_set_allf(<