// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_dir2.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_trans.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_bmap_btree.h"
#include "xfs_rtalloc.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_trans_space.h"
#include "xfs_buf_item.h"
#include "xfs_trace.h"
#include "xfs_attr_leaf.h"
#include "xfs_filestream.h"
#include "xfs_rmap.h"
#include "xfs_ag_resv.h"
#include "xfs_refcount.h"
#include "xfs_icache.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(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;
}

STATIC int                              /* error */
xfs_bmbt_lookup_eq(
        struct xfs_btree_cur    *cur,
        struct xfs_bmbt_irec    *irec,
        int                     *stat)  /* success/failure */
{
        cur->bc_rec.b = *irec;
        return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
}

STATIC int                              /* error */
xfs_bmbt_lookup_first(
        struct xfs_btree_cur    *cur,
        int                     *stat)  /* success/failure */
{
        cur->bc_rec.b.br_startoff = 0;
        cur->bc_rec.b.br_startblock = 0;
        cur->bc_rec.b.br_blockcount = 0;
        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 whichfork != XFS_COW_FORK &&
                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 whichfork != XFS_COW_FORK &&
                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 irec
 * This either works (return 0) or gets an EFSCORRUPTED error.
 */
STATIC int
xfs_bmbt_update(
        struct xfs_btree_cur    *cur,
        struct xfs_bmbt_irec    *irec)
{
        union xfs_btree_rec     rec;

        xfs_bmbt_disk_set_all(&rec.bmbt, irec);
        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_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_BTREE) {
                uint    dfl_forkoff = xfs_default_attroffset(ip) >> 3;

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

#ifdef DEBUG
STATIC struct xfs_buf *
xfs_bmap_get_bp(
        struct xfs_btree_cur    *cur,
        xfs_fsblock_t           bno)
{
        struct xfs_log_item     *lip;
        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(lip, &cur->bc_tp->t_items, li_trans) {
                struct xfs_buf_log_item *bip = (struct xfs_buf_log_item *)lip;

                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));
                                xfs_err(mp, "%s: ptrs are equal in node\n",
                                        __func__);
                                xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
                        }
                }
        }
}

/*
 * Check that the extents for the inode ip are in the right order in all
 * btree leaves. THis becomes prohibitively expensive for large extent count
 * files, so don't bother with inodes that have more than 10,000 extents in
 * them. The btree record ordering checks will still be done, so for such large
 * bmapbt constructs that is going to catch most corruptions.
 */
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 */
        struct xfs_ifork        *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;
        }

        /* skip large extent count inodes */
        if (ip->i_d.di_nextents > 10000)
                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 != NULLFSBLOCK);
        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, &bp,
                                                XFS_BMAP_BTREE_REF,
                                                &xfs_bmbt_buf_ops);
                        if (error)
                                goto error_norelse;
                }
                block = XFS_BUF_TO_BLOCK(bp);
                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(mp,
                                        xfs_verify_fsbno(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, &bp,
                                                XFS_BMAP_BTREE_REF,
                                                &xfs_bmbt_buf_ops);
                        if (error)
                                goto error_norelse;
                }
                block = XFS_BUF_TO_BLOCK(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);
        xfs_err(mp, "%s: CORRUPTED BTREE OR SOMETHING", __func__);
        xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
        return;
}

/*
 * Validate that the bmbt_irecs being returned from bmapi are valid
 * given the caller's original parameters.  Specifically check the
 * ranges of the returned irecs to ensure that they only extend 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)    do { } while (0)
#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(
        struct xfs_trans                *tp,
        xfs_fsblock_t                   bno,
        xfs_filblks_t                   len,
        const struct xfs_owner_info     *oinfo,
        bool                            skip_discard)
{
        struct xfs_extent_free_item     *new;           /* new element */
#ifdef DEBUG
        struct xfs_mount                *mp = tp->t_mountp;
        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, 0);
        new->xefi_startblock = bno;
        new->xefi_blockcount = (xfs_extlen_t)len;
        if (oinfo)
                new->xefi_oinfo = *oinfo;
        else
                new->xefi_oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
        new->xefi_skip_discard = skip_discard;
        trace_xfs_bmap_free_defer(tp->t_mountp,
                        XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
                        XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
        xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
}

/*
 * Inode fork format manipulation functions
 */

/*
 * Convert the inode format to extent format if it currently is in btree format,
 * but the extent list is small enough that it fits into the extent format.
 *
 * Since the 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(
        struct xfs_trans        *tp,    /* transaction pointer */
        struct xfs_inode        *ip,    /* incore inode pointer */
        struct xfs_btree_cur    *cur,   /* btree cursor */
        int                     *logflagsp, /* inode logging flags */
        int                     whichfork)  /* data or attr fork */
{
        struct xfs_ifork        *ifp = XFS_IFORK_PTR(ip, whichfork);
        struct xfs_mount        *mp = ip->i_mount;
        struct xfs_btree_block  *rblock = ifp->if_broot;
        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 */
        __be64                  *pp;    /* ptr to block address */
        struct xfs_owner_info   oinfo;

        /* check if we actually need the extent format first: */
        if (!xfs_bmap_wants_extents(ip, whichfork))
                return 0;

        ASSERT(cur);
        ASSERT(whichfork != XFS_COW_FORK);
        ASSERT(ifp->if_flags & XFS_IFEXTENTS);
        ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
        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);
#ifdef DEBUG
        XFS_WANT_CORRUPTED_RETURN(cur->bc_mp,
                        xfs_btree_check_lptr(cur, cbno, 1));
#endif
        error = xfs_btree_read_bufl(mp, tp, cbno, &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_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
        xfs_bmap_add_free(cur->bc_tp, cbno, 1, &oinfo);
        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(
        struct xfs_trans        *tp,            /* transaction pointer */
        struct xfs_inode        *ip,            /* incore inode pointer */
        struct xfs_btree_cur    **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 */
        struct xfs_buf          *abp;           /* buffer for ablock */
        struct xfs_alloc_arg    args;           /* allocation arguments */
        struct xfs_bmbt_rec     *arp;           /* child record pointer */
        struct xfs_btree_block  *block;         /* btree root block */
        struct xfs_btree_cur    *cur;           /* bmap btree cursor */
        int                     error;          /* error return value */
        struct xfs_ifork        *ifp;           /* inode fork pointer */
        struct xfs_bmbt_key     *kp;            /* root block key pointer */
        struct xfs_mount        *mp;            /* mount structure */
        xfs_bmbt_ptr_t          *pp;            /* root block address pointer */
        struct xfs_iext_cursor  icur;
        struct xfs_bmbt_irec    rec;
        xfs_extnum_t            cnt = 0;

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

        /*
         * Make space in the inode incore. This needs to be undone if we fail
         * to expand the root.
         */
        xfs_iroot_realloc(ip, 1, whichfork);
        ifp->if_flags |= XFS_IFBROOT;

        /*
         * Fill in the root.
         */
        block = ifp->if_broot;
        xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
                                 XFS_BTNUM_BMAP, 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.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;
        xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);
        if (tp->t_firstblock == NULLFSBLOCK) {
                args.type = XFS_ALLOCTYPE_START_BNO;
                args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
        } else if (tp->t_flags & XFS_TRANS_LOWMODE) {
                args.type = XFS_ALLOCTYPE_START_BNO;
                args.fsbno = tp->t_firstblock;
        } else {
                args.type = XFS_ALLOCTYPE_NEAR_BNO;
                args.fsbno = tp->t_firstblock;
        }
        args.minlen = args.maxlen = args.prod = 1;
        args.wasdel = wasdel;
        *logflagsp = 0;
        error = xfs_alloc_vextent(&args);
        if (error)
                goto out_root_realloc;

        if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
                error = -ENOSPC;
                goto out_root_realloc;
        }

        /*
         * Allocation can't fail, the space was reserved.
         */
        ASSERT(tp->t_firstblock == NULLFSBLOCK ||
               args.agno >= XFS_FSB_TO_AGNO(mp, tp->t_firstblock));
        tp->t_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);
        if (!abp) {
                error = -EFSCORRUPTED;
                goto out_unreserve_dquot;
        }

        /*
         * Fill in the child block.
         */
        abp->b_ops = &xfs_bmbt_buf_ops;
        ablock = XFS_BUF_TO_BLOCK(abp);
        xfs_btree_init_block_int(mp, ablock, abp->b_bn,
                                XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
                                XFS_BTREE_LONG_PTRS);

        for_each_xfs_iext(ifp, &icur, &rec) {
                if (isnullstartblock(rec.br_startblock))
                        continue;
                arp = XFS_BMBT_REC_ADDR(mp, ablock, 1 + cnt);
                xfs_bmbt_disk_set_all(arp, &rec);
                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;

out_unreserve_dquot:
        xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
out_root_realloc:
        xfs_iroot_realloc(ip, -1, whichfork);
        XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
        ASSERT(ifp->if_broot == NULL);
        xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);

        return error;
}

/*
 * 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).
 */
void
xfs_bmap_local_to_extents_empty(
        struct xfs_trans        *tp,
        struct xfs_inode        *ip,
        int                     whichfork)
{
        struct xfs_ifork        *ifp = XFS_IFORK_PTR(ip, whichfork);

        ASSERT(whichfork != XFS_COW_FORK);
        ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
        ASSERT(ifp->if_bytes == 0);
        ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0);

        xfs_bmap_forkoff_reset(ip, whichfork);
        ifp->if_flags &= ~XFS_IFINLINE;
        ifp->if_flags |= XFS_IFEXTENTS;
        ifp->if_u1.if_root = NULL;
        ifp->if_height = 0;
        XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
        xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}


STATIC int                              /* error */
xfs_bmap_local_to_extents(
        xfs_trans_t     *tp,            /* transaction pointer */
        xfs_inode_t     *ip,            /* incore inode pointer */
        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 = 0;
        int             flags;          /* logging flags returned */
        struct xfs_ifork *ifp;          /* inode fork pointer */
        xfs_alloc_arg_t args;           /* allocation arguments */
        xfs_buf_t       *bp;            /* buffer for extent block */
        struct xfs_bmbt_irec rec;
        struct xfs_iext_cursor icur;

        /*
         * 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(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK));
        ifp = XFS_IFORK_PTR(ip, whichfork);
        ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);

        if (!ifp->if_bytes) {
                xfs_bmap_local_to_extents_empty(tp, ip, whichfork);
                flags = XFS_ILOG_CORE;
                goto done;
        }

        flags = 0;
        error = 0;
        ASSERT((ifp->if_flags & (XFS_IFINLINE|XFS_IFEXTENTS)) == XFS_IFINLINE);
        memset(&args, 0, sizeof(args));
        args.tp = tp;
        args.mp = ip->i_mount;
        xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);
        /*
         * Allocate a block.  We know we need only one, since the
         * file currently fits in an inode.
         */
        if (tp->t_firstblock == NULLFSBLOCK) {
                args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
                args.type = XFS_ALLOCTYPE_START_BNO;
        } else {
                args.fsbno = tp->t_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);
        tp->t_firstblock = args.fsbno;
        bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno);

        /*
         * Initialize the block, copy the data and log the remote buffer.
         *
         * The callout is responsible for logging because the remote format
         * might differ from the local format and thus we don't know how much to
         * log here. Note that init_fn must also set the buffer log item type
         * correctly.
         */
        init_fn(tp, bp, ip, ifp);

        /* account for the change in fork size */
        xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
        xfs_bmap_local_to_extents_empty(tp, ip, whichfork);
        flags |= XFS_ILOG_CORE;

        ifp->if_u1.if_root = NULL;
        ifp->if_height = 0;

        rec.br_startoff = 0;
        rec.br_startblock = args.fsbno;
        rec.br_blockcount = 1;
        rec.br_state = XFS_EXT_NORM;
        xfs_iext_first(ifp, &icur);
        xfs_iext_insert(ip, &icur, &rec, 0);

        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);

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 */
        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);
                error = xfs_bmbt_lookup_first(cur, &stat);
                if (error)
                        goto error0;
                /* must be at least one entry */
                XFS_WANT_CORRUPTED_GOTO(mp, 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 -ENOSPC;
                }
                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(
        struct xfs_trans        *tp,            /* transaction pointer */
        struct xfs_inode        *ip,            /* incore inode pointer */
        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, &cur, 0, flags,
                                          XFS_DATA_FORK);
        if (cur) {
                cur->bc_private.b.allocated = 0;
                xfs_btree_del_cursor(cur, error);
        }
        return error;
}

/*
 * 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(
        struct xfs_trans        *tp,            /* transaction pointer */
        struct xfs_inode        *ip,            /* incore inode pointer */
        int                     *flags)         /* inode logging flags */
{
        struct xfs_da_args      dargs;          /* args for dir/attr code */

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

        if (S_ISDIR(VFS_I(ip)->i_mode)) {
                memset(&dargs, 0, sizeof(dargs));
                dargs.geo = ip->i_mount->m_dir_geo;
                dargs.dp = ip;
                dargs.total = dargs.geo->fsbcount;
                dargs.whichfork = XFS_DATA_FORK;
                dargs.trans = tp;
                return xfs_dir2_sf_to_block(&dargs);
        }

        if (S_ISLNK(VFS_I(ip)->i_mode))
                return xfs_bmap_local_to_extents(tp, ip, 1, flags,
                                                 XFS_DATA_FORK,
                                                 xfs_symlink_local_to_remote);

        /* should only be called for types that support local format data */
        ASSERT(0);
        return -EFSCORRUPTED;
}

/* Set an inode attr fork off based on the format */
int
xfs_bmap_set_attrforkoff(
        struct xfs_inode        *ip,
        int                     size,
        int                     *version)
{
        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_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 ((ip->i_mount->m_flags & XFS_MOUNT_ATTR2) && version)
                        *version = 2;
                break;
        default:
                ASSERT(0);
                return -EINVAL;
        }

        return 0;
}

/*
 * 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_mount_t             *mp;            /* mount structure */
        xfs_trans_t             *tp;            /* transaction pointer */
        int                     blks;           /* space reservation */
        int                     version = 1;    /* superblock attr version */
        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));

        blks = XFS_ADDAFORK_SPACE_RES(mp);

        error = xfs_trans_alloc(mp, &M_RES(mp)->tr_addafork, blks, 0,
                        rsvd ? XFS_TRANS_RESERVE : 0, &tp);
        if (error)
                return error;

        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)
                goto trans_cancel;
        if (XFS_IFORK_Q(ip))
                goto trans_cancel;
        if (ip->i_d.di_anextents != 0) {
                error = -EFSCORRUPTED;
                goto trans_cancel;
        }
        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;
        }

        xfs_trans_ijoin(tp, ip, 0);
        xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
        error = xfs_bmap_set_attrforkoff(ip, size, &version);
        if (error)
                goto trans_cancel;
        ASSERT(ip->i_afp == NULL);
        ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, 0);
        ip->i_afp->if_flags = XFS_IFEXTENTS;
        logflags = 0;
        switch (ip->i_d.di_format) {
        case XFS_DINODE_FMT_LOCAL:
                error = xfs_bmap_add_attrfork_local(tp, ip, &logflags);
                break;
        case XFS_DINODE_FMT_EXTENTS:
                error = xfs_bmap_add_attrfork_extents(tp, ip, &logflags);
                break;
        case XFS_DINODE_FMT_BTREE:
                error = xfs_bmap_add_attrfork_btree(tp, ip, &logflags);
                break;
        default:
                error = 0;
                break;
        }
        if (logflags)
                xfs_trans_log_inode(tp, ip, logflags);
        if (error)
                goto trans_cancel;
        if (!xfs_sb_version_hasattr(&mp->m_sb) ||
           (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
                bool log_sb = false;

                spin_lock(&mp->m_sb_lock);
                if (!xfs_sb_version_hasattr(&mp->m_sb)) {
                        xfs_sb_version_addattr(&mp->m_sb);
                        log_sb = true;
                }
                if (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2) {
                        xfs_sb_version_addattr2(&mp->m_sb);
                        log_sb = true;
                }
                spin_unlock(&mp->m_sb_lock);
                if (log_sb)
                        xfs_log_sb(tp);
        }

        error = xfs_trans_commit(tp);
        xfs_iunlock(ip, XFS_ILOCK_EXCL);
        return error;

trans_cancel:
        xfs_trans_cancel(tp);
        xfs_iunlock(ip, XFS_ILOCK_EXCL);
        return error;
}

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

/*
 * Read in extents from a btree-format inode.
 */
int
xfs_iread_extents(
        struct xfs_trans        *tp,
        struct xfs_inode        *ip,
        int                     whichfork)
{
        struct xfs_mount        *mp = ip->i_mount;
        int                     state = xfs_bmap_fork_to_state(whichfork);
        struct xfs_ifork        *ifp = XFS_IFORK_PTR(ip, whichfork);
        xfs_extnum_t            nextents = XFS_IFORK_NEXTENTS(ip, whichfork);
        struct xfs_btree_block  *block = ifp->if_broot;
        struct xfs_iext_cursor  icur;
        struct xfs_bmbt_irec    new;
        xfs_fsblock_t           bno;
        struct xfs_buf          *bp;
        xfs_extnum_t            i, j;
        int                     level;
        __be64                  *pp;
        int                     error;

        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));

        if (unlikely(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE)) {
                XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
                return -EFSCORRUPTED;
        }

        /*
         * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
         */
        level = be16_to_cpu(block->bb_level);
        if (unlikely(level == 0)) {
                XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
                return -EFSCORRUPTED;
        }
        pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
        bno = be64_to_cpu(*pp);

        /*
         * 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, &bp,
                                XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops);
                if (error)
                        goto out;
                block = XFS_BUF_TO_BLOCK(bp);
                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(mp,
                        xfs_verify_fsbno(mp, bno), out_brelse);
                xfs_trans_brelse(tp, bp);
        }

        /*
         * Here with bp and block set to the leftmost leaf node in the tree.
         */
        i = 0;
        xfs_iext_first(ifp, &icur);

        /*
         * 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;

                num_recs = xfs_btree_get_numrecs(block);
                if (unlikely(i + num_recs > nextents)) {
                        xfs_warn(ip->i_mount,
                                "corrupt dinode %Lu, (btree extents).",
                                (unsigned long long) ip->i_ino);
                        xfs_inode_verifier_error(ip, -EFSCORRUPTED,
                                        __func__, block, sizeof(*block),
                                        __this_address);
                        error = -EFSCORRUPTED;
                        goto out_brelse;
                }
                /*
                 * 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);
                for (j = 0; j < num_recs; j++, frp++, i++) {
                        xfs_failaddr_t  fa;

                        xfs_bmbt_disk_get_all(frp, &new);
                        fa = xfs_bmap_validate_extent(ip, whichfork, &new);
                        if (fa) {
                                error = -EFSCORRUPTED;
                                xfs_inode_verifier_error(ip, error,
                                                "xfs_iread_extents(2)",
                                                frp, sizeof(*frp), fa);
                                goto out_brelse;
                        }
                        xfs_iext_insert(ip, &icur, &new, state);
                        trace_xfs_read_extent(ip, &icur, state, _THIS_IP_);
                        xfs_iext_next(ifp, &icur);
                }
                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, &bp,
                                XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops);
                if (error)
                        goto out;
                block = XFS_BUF_TO_BLOCK(bp);
        }

        if (i != XFS_IFORK_NEXTENTS(ip, whichfork)) {
                error = -EFSCORRUPTED;
                goto out;
        }
        ASSERT(i == xfs_iext_count(ifp));

        ifp->if_flags |= XFS_IFEXTENTS;
        return 0;

out_brelse:
        xfs_trans_brelse(tp, bp);
out:
        xfs_iext_destroy(ifp);
        return error;
}

/*
 * Returns the relative block number of the first unused block(s) in the given
 * fork with at least "len" logically contiguous blocks free.  This is the
 * lowest-address hole if the fork has holes, else the first block past the end
 * of fork.  Return 0 if the fork is currently local (in-inode).
 */
int                                             /* error */
xfs_bmap_first_unused(
        struct xfs_trans        *tp,            /* transaction pointer */
        struct xfs_inode        *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 */
{
        struct xfs_ifork        *ifp = XFS_IFORK_PTR(ip, whichfork);
        struct xfs_bmbt_irec    got;
        struct xfs_iext_cursor  icur;
        xfs_fileoff_t           lastaddr = 0;
        xfs_fileoff_t           lowest, max;
        int                     error;

        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;
        }

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

        lowest = max = *first_unused;
        for_each_xfs_iext(ifp, &icur, &got) {
                /*
                 * See if the hole before this extent will work.
                 */
                if (got.br_startoff >= lowest + len &&
                    got.br_startoff - max >= len)
                        break;
                lastaddr = got.br_startoff + got.br_blockcount;
                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(
        struct xfs_trans        *tp,            /* transaction pointer */
        struct xfs_inode        *ip,            /* incore inode */
        xfs_fileoff_t           *last_block,    /* last block */
        int                     whichfork)      /* data or attr fork */
{
        struct xfs_ifork        *ifp = XFS_IFORK_PTR(ip, whichfork);
        struct xfs_bmbt_irec    got;
        struct xfs_iext_cursor  icur;
        int                     error;

        switch (XFS_IFORK_FORMAT(ip, whichfork)) {
        case XFS_DINODE_FMT_LOCAL:
                *last_block = 0;
                return 0;
        case XFS_DINODE_FMT_BTREE:
        case XFS_DINODE_FMT_EXTENTS:
                break;
        default:
                return -EIO;
        }

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

        if (!xfs_iext_lookup_extent_before(ip, ifp, last_block, &icur, &got))
                *last_block = 0;
        return 0;
}

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);
        struct xfs_iext_cursor  icur;
        int                     error;

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

        xfs_iext_last(ifp, &icur);
        if (!xfs_iext_get_extent(ifp, &icur, rec))
                *is_empty = 1;
        else
                *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 1 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 = false;
        error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec,
                                     &is_empty);
        if (error)
                return error;

        if (is_empty) {
                bma->aeof = true;
                return 0;
        }

        /*
         * 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;
}

/*
 * 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_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 -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 */
{
        struct xfs_ifork *ifp;          /* inode fork pointer */
        int             rval;           /* return value */
        xfs_bmbt_irec_t s;              /* internal version of extent */
        struct xfs_iext_cursor icur;

#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);
        xfs_iext_first(ifp, &icur);
        xfs_iext_get_extent(ifp, &icur, &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,
        int                     whichfork)
{
        struct xfs_bmbt_irec    *new = &bma->got;
        int                     error;  /* error return value */
        int                     i;      /* temp state */
        struct xfs_ifork        *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 = xfs_bmap_fork_to_state(whichfork);
        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 */
        int                     tmp_rval;       /* partial logging flags */
        struct xfs_mount        *mp;
        xfs_extnum_t            *nextents;
        struct xfs_bmbt_irec    old;

        mp = bma->ip->i_mount;
        ifp = XFS_IFORK_PTR(bma->ip, whichfork);
        ASSERT(whichfork != XFS_ATTR_FORK);
        nextents = (whichfork == XFS_COW_FORK ? &bma->ip->i_cnextents :
                                                &bma->ip->i_d.di_nextents);

        ASSERT(!isnullstartblock(new->br_startblock));
        ASSERT(!bma->cur ||
               (bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));

        XFS_STATS_INC(mp, 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.
         */
        xfs_iext_get_extent(ifp, &bma->icur, &PREV);
        new_endoff = new->br_startoff + new->br_blockcount;
        ASSERT(isnullstartblock(PREV.br_startblock));
        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 (xfs_iext_peek_prev_extent(ifp, &bma->icur, &LEFT)) {
                state |= BMAP_LEFT_VALID;
                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 (xfs_iext_peek_next_extent(ifp, &bma->icur, &RIGHT)) {
                state |= BMAP_RIGHT_VALID;
                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.
                 */
                LEFT.br_blockcount += PREV.br_blockcount + RIGHT.br_blockcount;

                xfs_iext_remove(bma->ip, &bma->icur, state);
                xfs_iext_remove(bma->ip, &bma->icur, state);
                xfs_iext_prev(ifp, &bma->icur);
                xfs_iext_update_extent(bma->ip, state, &bma->icur, &LEFT);
                (*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, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_btree_delete(bma->cur, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_btree_decrement(bma->cur, 0, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(bma->cur, &LEFT);
                        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.
                 */
                old = LEFT;
                LEFT.br_blockcount += PREV.br_blockcount;

                xfs_iext_remove(bma->ip, &bma->icur, state);
                xfs_iext_prev(ifp, &bma->icur);
                xfs_iext_update_extent(bma->ip, state, &bma->icur, &LEFT);

                if (bma->cur == NULL)
                        rval = XFS_ILOG_DEXT;
                else {
                        rval = 0;
                        error = xfs_bmbt_lookup_eq(bma->cur, &old, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(bma->cur, &LEFT);
                        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. Take care
                 * with delay -> unwritten extent allocation here because the
                 * delalloc record we are overwriting is always written.
                 */
                PREV.br_startblock = new->br_startblock;
                PREV.br_blockcount += RIGHT.br_blockcount;
                PREV.br_state = new->br_state;

                xfs_iext_next(ifp, &bma->icur);
                xfs_iext_remove(bma->ip, &bma->icur, state);
                xfs_iext_prev(ifp, &bma->icur);
                xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV);

                if (bma->cur == NULL)
                        rval = XFS_ILOG_DEXT;
                else {
                        rval = 0;
                        error = xfs_bmbt_lookup_eq(bma->cur, &RIGHT, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(bma->cur, &PREV);
                        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.
                 */
                PREV.br_startblock = new->br_startblock;
                PREV.br_state = new->br_state;
                xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV);

                (*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, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
                        error = xfs_btree_insert(bma->cur, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, 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.
                 */
                old = LEFT;
                temp = PREV.br_blockcount - new->br_blockcount;
                da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp),
                                startblockval(PREV.br_startblock));

                LEFT.br_blockcount += new->br_blockcount;

                PREV.br_blockcount = temp;
                PREV.br_startoff += new->br_blockcount;
                PREV.br_startblock = nullstartblock(da_new);

                xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV);
                xfs_iext_prev(ifp, &bma->icur);
                xfs_iext_update_extent(bma->ip, state, &bma->icur, &LEFT);

                if (bma->cur == NULL)
                        rval = XFS_ILOG_DEXT;
                else {
                        rval = 0;
                        error = xfs_bmbt_lookup_eq(bma->cur, &old, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(bma->cur, &LEFT);
                        if (error)
                                goto done;
                }
                break;

        case BMAP_LEFT_FILLING:
                /*
                 * Filling in the first part of a previous delayed allocation.
                 * The left neighbor is not contiguous.
                 */
                xfs_iext_update_extent(bma->ip, state, &bma->icur, new);
                (*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, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
                        error = xfs_btree_insert(bma->cur, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                }

                if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
                        error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
                                        &bma->cur, 1, &tmp_rval, whichfork);
                        rval |= tmp_rval;
                        if (error)
                                goto done;
                }

                temp = PREV.br_blockcount - new->br_blockcount;
                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));

                PREV.br_startoff = new_endoff;
                PREV.br_blockcount = temp;
                PREV.br_startblock = nullstartblock(da_new);
                xfs_iext_next(ifp, &bma->icur);
                xfs_iext_insert(bma->ip, &bma->icur, &PREV, state);
                xfs_iext_prev(ifp, &bma->icur);
                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.
                 */
                old = RIGHT;
                RIGHT.br_startoff = new->br_startoff;
                RIGHT.br_startblock = new->br_startblock;
                RIGHT.br_blockcount += new->br_blockcount;

                if (bma->cur == NULL)
                        rval = XFS_ILOG_DEXT;
                else {
                        rval = 0;
                        error = xfs_bmbt_lookup_eq(bma->cur, &old, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(bma->cur, &RIGHT);
                        if (error)
                                goto done;
                }

                temp = PREV.br_blockcount - new->br_blockcount;
                da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp),
                        startblockval(PREV.br_startblock));

                PREV.br_blockcount = temp;
                PREV.br_startblock = nullstartblock(da_new);

                xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV);
                xfs_iext_next(ifp, &bma->icur);
                xfs_iext_update_extent(bma->ip, state, &bma->icur, &RIGHT);
                break;

        case BMAP_RIGHT_FILLING:
                /*
                 * Filling in the last part of a previous delayed allocation.
                 * The right neighbor is not contiguous.
                 */
                xfs_iext_update_extent(bma->ip, state, &bma->icur, new);
                (*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, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
                        error = xfs_btree_insert(bma->cur, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                }

                if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
                        error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
                                &bma->cur, 1, &tmp_rval, whichfork);
                        rval |= tmp_rval;
                        if (error)
                                goto done;
                }

                temp = PREV.br_blockcount - new->br_blockcount;
                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));

                PREV.br_startblock = nullstartblock(da_new);
                PREV.br_blockcount = temp;
                xfs_iext_insert(bma->ip, &bma->icur, &PREV, state);
                xfs_iext_next(ifp, &bma->icur);
                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
                 */
                old = PREV;

                /* LEFT is the new middle */
                LEFT = *new;

                /* RIGHT is the new right */
                RIGHT.br_state = PREV.br_state;
                RIGHT.br_startoff = new_endoff;
                RIGHT.br_blockcount =
                        PREV.br_startoff + PREV.br_blockcount - new_endoff;
                RIGHT.br_startblock =
                        nullstartblock(xfs_bmap_worst_indlen(bma->ip,
                                        RIGHT.br_blockcount));

                /* truncate PREV */
                PREV.br_blockcount = new->br_startoff - PREV.br_startoff;
                PREV.br_startblock =
                        nullstartblock(xfs_bmap_worst_indlen(bma->ip,
                                        PREV.br_blockcount));
                xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV);

                xfs_iext_next(ifp, &bma->icur);
                xfs_iext_insert(bma->ip, &bma->icur, &RIGHT, state);
                xfs_iext_insert(bma->ip, &bma->icur, &LEFT, state);
                (*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, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
                        error = xfs_btree_insert(bma->cur, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                }

                if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
                        error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
                                        &bma->cur, 1, &tmp_rval, whichfork);
                        rval |= tmp_rval;
                        if (error)
                                goto done;
                }

                da_new = startblockval(PREV.br_startblock) +
                         startblockval(RIGHT.br_startblock);
                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);
        }

        /* add reverse mapping unless caller opted out */
        if (!(bma->flags & XFS_BMAPI_NORMAP))
                xfs_rmap_map_extent(bma->tp, bma->ip, whichfork, new);

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

                ASSERT(bma->cur == NULL);
                error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
                                &bma->cur, da_old > 0, &tmp_logflags,
                                whichfork);

                bma->logflags |= tmp_logflags;
                if (error)
                        goto done;
        }

        if (da_new != da_old)
                xfs_mod_delalloc(mp, (int64_t)da_new - da_old);

        if (bma->cur) {
                da_new += bma->cur->bc_private.b.allocated;
                bma->cur->bc_private.b.allocated = 0;
        }

        /* adjust for changes in reserved delayed indirect blocks */
        if (da_new != da_old) {
                ASSERT(state == 0 || da_new < da_old);
                error = xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new),
                                false);
        }

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

/*
 * Convert an unwritten allocation to a real allocation or vice versa.
 */
int                                     /* error */
xfs_bmap_add_extent_unwritten_real(
        struct xfs_trans        *tp,
        xfs_inode_t             *ip,    /* incore inode pointer */
        int                     whichfork,
        struct xfs_iext_cursor  *icur,
        xfs_btree_cur_t         **curp, /* if *curp is null, not a btree */
        xfs_bmbt_irec_t         *new,   /* new data to add to file extents */
        int                     *logflagsp) /* inode logging flags */
{
        xfs_btree_cur_t         *cur;   /* btree cursor */
        int                     error;  /* error return value */
        int                     i;      /* temp state */
        struct xfs_ifork        *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 = xfs_bmap_fork_to_state(whichfork);
        struct xfs_mount        *mp = ip->i_mount;
        struct xfs_bmbt_irec    old;

        *logflagsp = 0;

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

        ASSERT(!isnullstartblock(new->br_startblock));

        XFS_STATS_INC(mp, 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;
        xfs_iext_get_extent(ifp, icur, &PREV);
        ASSERT(new->br_state != PREV.br_state);
        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 (xfs_iext_peek_prev_extent(ifp, icur, &LEFT)) {
                state |= BMAP_LEFT_VALID;
                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 (xfs_iext_peek_next_extent(ifp, icur, &RIGHT)) {
                state |= BMAP_RIGHT_VALID;
                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;

        /*
         * 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.
                 */
                LEFT.br_blockcount += PREV.br_blockcount + RIGHT.br_blockcount;

                xfs_iext_remove(ip, icur, state);
                xfs_iext_remove(ip, icur, state);
                xfs_iext_prev(ifp, icur);
                xfs_iext_update_extent(ip, state, icur, &LEFT);
                XFS_IFORK_NEXT_SET(ip, whichfork,
                                XFS_IFORK_NEXTENTS(ip, whichfork) - 2);
                if (cur == NULL)
                        rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
                else {
                        rval = XFS_ILOG_CORE;
                        error = xfs_bmbt_lookup_eq(cur, &RIGHT, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        if ((error = xfs_btree_delete(cur, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        if ((error = xfs_btree_decrement(cur, 0, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        if ((error = xfs_btree_delete(cur, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        if ((error = xfs_btree_decrement(cur, 0, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &LEFT);
                        if (error)
                                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.
                 */
                LEFT.br_blockcount += PREV.br_blockcount;

                xfs_iext_remove(ip, icur, state);
                xfs_iext_prev(ifp, icur);
                xfs_iext_update_extent(ip, state, icur, &LEFT);
                XFS_IFORK_NEXT_SET(ip, whichfork,
                                XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
                if (cur == NULL)
                        rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
                else {
                        rval = XFS_ILOG_CORE;
                        error = xfs_bmbt_lookup_eq(cur, &PREV, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        if ((error = xfs_btree_delete(cur, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        if ((error = xfs_btree_decrement(cur, 0, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &LEFT);
                        if (error)
                                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.
                 */
                PREV.br_blockcount += RIGHT.br_blockcount;
                PREV.br_state = new->br_state;

                xfs_iext_next(ifp, icur);
                xfs_iext_remove(ip, icur, state);
                xfs_iext_prev(ifp, icur);
                xfs_iext_update_extent(ip, state, icur, &PREV);

                XFS_IFORK_NEXT_SET(ip, whichfork,
                                XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
                if (cur == NULL)
                        rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
                else {
                        rval = XFS_ILOG_CORE;
                        error = xfs_bmbt_lookup_eq(cur, &RIGHT, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        if ((error = xfs_btree_delete(cur, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        if ((error = xfs_btree_decrement(cur, 0, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &PREV);
                        if (error)
                                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.
                 */
                PREV.br_state = new->br_state;
                xfs_iext_update_extent(ip, state, icur, &PREV);

                if (cur == NULL)
                        rval = XFS_ILOG_DEXT;
                else {
                        rval = 0;
                        error = xfs_bmbt_lookup_eq(cur, new, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &PREV);
                        if (error)
                                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.
                 */
                LEFT.br_blockcount += new->br_blockcount;

                old = PREV;
                PREV.br_startoff += new->br_blockcount;
                PREV.br_startblock += new->br_blockcount;
                PREV.br_blockcount -= new->br_blockcount;

                xfs_iext_update_extent(ip, state, icur, &PREV);
                xfs_iext_prev(ifp, icur);
                xfs_iext_update_extent(ip, state, icur, &LEFT);

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

                xfs_iext_update_extent(ip, state, icur, &PREV);
                xfs_iext_insert(ip, icur, new, state);
                XFS_IFORK_NEXT_SET(ip, whichfork,
                                XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
                if (cur == NULL)
                        rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
                else {
                        rval = XFS_ILOG_CORE;
                        error = xfs_bmbt_lookup_eq(cur, &old, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &PREV);
                        if (error)
                                goto done;
                        cur->bc_rec.b = *new;
                        if ((error = xfs_btree_insert(cur, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, 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.
                 */
                old = PREV;
                PREV.br_blockcount -= new->br_blockcount;

                RIGHT.br_startoff = new->br_startoff;
                RIGHT.br_startblock = new->br_startblock;
                RIGHT.br_blockcount += new->br_blockcount;

                xfs_iext_update_extent(ip, state, icur, &PREV);
                xfs_iext_next(ifp, icur);
                xfs_iext_update_extent(ip, state, icur, &RIGHT);

                if (cur == NULL)
                        rval = XFS_ILOG_DEXT;
                else {
                        rval = 0;
                        error = xfs_bmbt_lookup_eq(cur, &old, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &PREV);
                        if (error)
                                goto done;
                        error = xfs_btree_increment(cur, 0, &i);
                        if (error)
                                goto done;
                        error = xfs_bmbt_update(cur, &RIGHT);
                        if (error)
                                goto done;
                }
                break;

        case BMAP_RIGHT_FILLING:
                /*
                 * Setting the last part of a previous oldext extent to newext.
                 * The right neighbor is not contiguous.
                 */
                old = PREV;
                PREV.br_blockcount -= new->br_blockcount;

                xfs_iext_update_extent(ip, state, icur, &PREV);
                xfs_iext_next(ifp, icur);
                xfs_iext_insert(ip, icur, new, state);

                XFS_IFORK_NEXT_SET(ip, whichfork,
                                XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
                if (cur == NULL)
                        rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
                else {
                        rval = XFS_ILOG_CORE;
                        error = xfs_bmbt_lookup_eq(cur, &old, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &PREV);
                        if (error)
                                goto done;
                        error = xfs_bmbt_lookup_eq(cur, new, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
                        if ((error = xfs_btree_insert(cur, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                }
                break;

        case 0:
                /*
                 * Setting the middle part of a previous oldext extent to
                 * newext.  Contiguity is impossible here.
                 * One extent becomes three extents.
                 */
                old = PREV;
                PREV.br_blockcount = new->br_startoff - PREV.br_startoff;

                r[0] = *new;
                r[1].br_startoff = new_endoff;
                r[1].br_blockcount =
                        old.br_startoff + old.br_blockcount - new_endoff;
                r[1].br_startblock = new->br_startblock + new->br_blockcount;
                r[1].br_state = PREV.br_state;

                xfs_iext_update_extent(ip, state, icur, &PREV);
                xfs_iext_next(ifp, icur);
                xfs_iext_insert(ip, icur, &r[1], state);
                xfs_iext_insert(ip, icur, &r[0], state);

                XFS_IFORK_NEXT_SET(ip, whichfork,
                                XFS_IFORK_NEXTENTS(ip, whichfork) + 2);
                if (cur == NULL)
                        rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
                else {
                        rval = XFS_ILOG_CORE;
                        error = xfs_bmbt_lookup_eq(cur, &old, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        /* new right extent - oldext */
                        error = xfs_bmbt_update(cur, &r[1]);
                        if (error)
                                goto done;
                        /* new left extent - oldext */
                        cur->bc_rec.b = PREV;
                        if ((error = xfs_btree_insert(cur, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        /*
                         * Reset the cursor to the position of the new extent
                         * we are about to insert as we can't trust it after
                         * the previous insert.
                         */
                        error = xfs_bmbt_lookup_eq(cur, new, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
                        /* new middle extent - newext */
                        if ((error = xfs_btree_insert(cur, &i)))
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                }
                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);
        }

        /* update reverse mappings */
        xfs_rmap_convert_extent(mp, tp, ip, whichfork, new);

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

                ASSERT(cur == NULL);
                error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
                                &tmp_logflags, whichfork);
                *logflagsp |= tmp_logflags;
                if (error)
                        goto done;
        }

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

        xfs_bmap_check_leaf_extents(*curp, ip, whichfork);
done:
        *logflagsp |= rval;
        return error;
#undef  LEFT
#undef  RIGHT
#undef  PREV
}

/*
 * Convert a hole to a delayed allocation.
 */
STATIC void
xfs_bmap_add_extent_hole_delay(
        xfs_inode_t             *ip,    /* incore inode pointer */
        int                     whichfork,
        struct xfs_iext_cursor  *icur,
        xfs_bmbt_irec_t         *new)   /* new data to add to file extents */
{
        struct xfs_ifork        *ifp;   /* inode fork pointer */
        xfs_bmbt_irec_t         left;   /* left neighbor extent entry */
        xfs_filblks_t           newlen=0;       /* new indirect size */
        xfs_filblks_t           oldlen=0;       /* old indirect size */
        xfs_bmbt_irec_t         right;  /* right neighbor extent entry */
        int                     state = xfs_bmap_fork_to_state(whichfork);
        xfs_filblks_t           temp;    /* temp for indirect calculations */

        ifp = XFS_IFORK_PTR(ip, whichfork);
        ASSERT(isnullstartblock(new->br_startblock));

        /*
         * Check and set flags if this segment has a left neighbor
         */
        if (xfs_iext_peek_prev_extent(ifp, icur, &left)) {
                state |= BMAP_LEFT_VALID;
                if (isnullstartblock(left.br_startblock))
                        state |= BMAP_LEFT_DELAY;
        }

        /*
         * Check and set flags if the current (right) segment exists.
         * If it doesn't exist, we're converting the hole at end-of-file.
         */
        if (xfs_iext_get_extent(ifp, icur, &right)) {
                state |= BMAP_RIGHT_VALID;
                if (isnullstartblock(right.br_startblock))
                        state |= BMAP_RIGHT_DELAY;
        }

        /*
         * Set contiguity flags on the left and right neighbors.
         * Don't let extents get too large, even if the pieces are contiguous.
         */
        if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) &&
            left.br_startoff + left.br_blockcount == new->br_startoff &&
            left.br_blockcount + new->br_blockcount <= MAXEXTLEN)
                state |= BMAP_LEFT_CONTIG;

        if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) &&
            new->br_startoff + new->br_blockcount == right.br_startoff &&
            new->br_blockcount + right.br_blockcount <= MAXEXTLEN &&
            (!(state & BMAP_LEFT_CONTIG) ||
             (left.br_blockcount + new->br_blockcount +
              right.br_blockcount <= MAXEXTLEN)))
                state |= BMAP_RIGHT_CONTIG;

        /*
         * Switch out based on the contiguity flags.
         */
        switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
        case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
                /*
                 * New allocation is contiguous with delayed allocations
                 * on the left and on the right.
                 * Merge all three into a single extent record.
                 */
                temp = left.br_blockcount + new->br_blockcount +
                        right.br_blockcount;

                oldlen = startblockval(left.br_startblock) +
                        startblockval(new->br_startblock) +
                        startblockval(right.br_startblock);
                newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
                                         oldlen);
                left.br_startblock = nullstartblock(newlen);
                left.br_blockcount = temp;

                xfs_iext_remove(ip, icur, state);
                xfs_iext_prev(ifp, icur);
                xfs_iext_update_extent(ip, state, icur, &left);
                break;

        case BMAP_LEFT_CONTIG:
                /*
                 * New allocation is contiguous with a delayed allocation
                 * on the left.
                 * Merge the new allocation with the left neighbor.
                 */
                temp = left.br_blockcount + new->br_blockcount;

                oldlen = startblockval(left.br_startblock) +
                        startblockval(new->br_startblock);
                newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
                                         oldlen);
                left.br_blockcount = temp;
                left.br_startblock = nullstartblock(newlen);

                xfs_iext_prev(ifp, icur);
                xfs_iext_update_extent(ip, state, icur, &left);
                break;

        case BMAP_RIGHT_CONTIG:
                /*
                 * New allocation is contiguous with a delayed allocation
                 * on the right.
                 * Merge the new allocation with the right neighbor.
                 */
                temp = new->br_blockcount + right.br_blockcount;
                oldlen = startblockval(new->br_startblock) +
                        startblockval(right.br_startblock);
                newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
                                         oldlen);
                right.br_startoff = new->br_startoff;
                right.br_startblock = nullstartblock(newlen);
                right.br_blockcount = temp;
                xfs_iext_update_extent(ip, state, icur, &right);
                break;

        case 0:
                /*
                 * New allocation is not contiguous with another
                 * delayed allocation.
                 * Insert a new entry.
                 */
                oldlen = newlen = 0;
                xfs_iext_insert(ip, icur, new, state);
                break;
        }
        if (oldlen != newlen) {
                ASSERT(oldlen > newlen);
                xfs_mod_fdblocks(ip->i_mount, (int64_t)(oldlen - newlen),
                                 false);
                /*
                 * Nothing to do for disk quota accounting here.
                 */
                xfs_mod_delalloc(ip->i_mount, (int64_t)newlen - oldlen);
        }
}

/*
 * Convert a hole to a real allocation.
 */
STATIC int                              /* error */
xfs_bmap_add_extent_hole_real(
        struct xfs_trans        *tp,
        struct xfs_inode        *ip,
        int                     whichfork,
        struct xfs_iext_cursor  *icur,
        struct xfs_btree_cur    **curp,
        struct xfs_bmbt_irec    *new,
        int                     *logflagsp,
        int                     flags)
{
        struct xfs_ifork        *ifp = XFS_IFORK_PTR(ip, whichfork);
        struct xfs_mount        *mp = ip->i_mount;
        struct xfs_btree_cur    *cur = *curp;
        int                     error;  /* error return value */
        int                     i;      /* temp state */
        xfs_bmbt_irec_t         left;   /* left neighbor extent entry */
        xfs_bmbt_irec_t         right;  /* right neighbor extent entry */
        int                     rval=0; /* return value (logging flags) */
        int                     state = xfs_bmap_fork_to_state(whichfork);
        struct xfs_bmbt_irec    old;

        ASSERT(!isnullstartblock(new->br_startblock));
        ASSERT(!cur || !(cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));

        XFS_STATS_INC(mp, xs_add_exlist);

        /*
         * Check and set flags if this segment has a left neighbor.
         */
        if (xfs_iext_peek_prev_extent(ifp, icur, &left)) {
                state |= BMAP_LEFT_VALID;
                if (isnullstartblock(left.br_startblock))
                        state |= BMAP_LEFT_DELAY;
        }

        /*
         * Check and set flags if this segment has a current value.
         * Not true if we're inserting into the "hole" at eof.
         */
        if (xfs_iext_get_extent(ifp, icur, &right)) {
                state |= BMAP_RIGHT_VALID;
                if (isnullstartblock(right.br_startblock))
                        state |= BMAP_RIGHT_DELAY;
        }

        /*
         * We're inserting a real allocation between "left" and "right".
         * Set the contiguity flags.  Don't let extents get too large.
         */
        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;

        if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) &&
            new->br_startoff + new->br_blockcount == 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) ||
             left.br_blockcount + new->br_blockcount +
             right.br_blockcount <= MAXEXTLEN))
                state |= BMAP_RIGHT_CONTIG;

        error = 0;
        /*
         * Select which case we're in here, and implement it.
         */
        switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
        case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
                /*
                 * New allocation is contiguous with real allocations on the
                 * left and on the right.
                 * Merge all three into a single extent record.
                 */
                left.br_blockcount += new->br_blockcount + right.br_blockcount;

                xfs_iext_remove(ip, icur, state);
                xfs_iext_prev(ifp, icur);
                xfs_iext_update_extent(ip, state, icur, &left);

                XFS_IFORK_NEXT_SET(ip, whichfork,
                        XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
                if (cur == NULL) {
                        rval = XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
                } else {
                        rval = XFS_ILOG_CORE;
                        error = xfs_bmbt_lookup_eq(cur, &right, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_btree_delete(cur, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_btree_decrement(cur, 0, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &left);
                        if (error)
                                goto done;
                }
                break;

        case BMAP_LEFT_CONTIG:
                /*
                 * New allocation is contiguous with a real allocation
                 * on the left.
                 * Merge the new allocation with the left neighbor.
                 */
                old = left;
                left.br_blockcount += new->br_blockcount;

                xfs_iext_prev(ifp, icur);
                xfs_iext_update_extent(ip, state, icur, &left);

                if (cur == NULL) {
                        rval = xfs_ilog_fext(whichfork);
                } else {
                        rval = 0;
                        error = xfs_bmbt_lookup_eq(cur, &old, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &left);
                        if (error)
                                goto done;
                }
                break;

        case BMAP_RIGHT_CONTIG:
                /*
                 * New allocation is contiguous with a real allocation
                 * on the right.
                 * Merge the new allocation with the right neighbor.
                 */
                old = right;

                right.br_startoff = new->br_startoff;
                right.br_startblock = new->br_startblock;
                right.br_blockcount += new->br_blockcount;
                xfs_iext_update_extent(ip, state, icur, &right);

                if (cur == NULL) {
                        rval = xfs_ilog_fext(whichfork);
                } else {
                        rval = 0;
                        error = xfs_bmbt_lookup_eq(cur, &old, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                        error = xfs_bmbt_update(cur, &right);
                        if (error)
                                goto done;
                }
                break;

        case 0:
                /*
                 * New allocation is not contiguous with another
                 * real allocation.
                 * Insert a new entry.
                 */
                xfs_iext_insert(ip, icur, new, state);
                XFS_IFORK_NEXT_SET(ip, whichfork,
                        XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
                if (cur == NULL) {
                        rval = XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
                } else {
                        rval = XFS_ILOG_CORE;
                        error = xfs_bmbt_lookup_eq(cur, new, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
                        error = xfs_btree_insert(cur, &i);
                        if (error)
                                goto done;
                        XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
                }
                break;
        }

        /* add reverse mapping unless caller opted out */
        if (!(flags & XFS_BMAPI_NORMAP))
                xfs_rmap_map_extent(tp, ip, whichfork, new);

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

                ASSERT(cur == NULL);
                error = xfs_bmap_extents_to_btree(tp, ip, curp, 0,
                                &tmp_logflags, whichfork);
                *logflagsp |= tmp_logflags;
                cur = *curp;
                if (error)
                        goto done;
        }

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

        xfs_bmap_check_leaf_extents(cur, ip, whichfork);
done:
        *logflagsp |= rval;
        return error;
}

/*
 * Functions used in the extent read, allocate and remove paths
 */

/*
 * Adjust the size of the new extent based on di_extsize and rt extsize.
 */
int
xfs_bmap_extsize_align(
        xfs_mount_t     *mp,
        xfs_bmbt_irec_t *gotp,          /* next extent pointer */
        xfs_bmbt_irec_t *prevp,         /* previous extent pointer */
        xfs_extlen_t    extsz,          /* align to this extent size */
        int             rt,             /* is this a realtime inode? */
        int             eof,            /* is extent at end-of-file? */
        int             delay,          /* creating delalloc extent? */
        int             convert,        /* overwriting unwritten extent? */
        xfs_fileoff_t   *offp,          /* in/out: aligned offset */
        xfs_extlen_t    *lenp)          /* in/out: aligned length */
{
        xfs_fileoff_t   orig_off;       /* original offset */
        xfs_extlen_t    orig_alen;      /* original length */
        xfs_fileoff_t   orig_end;       /* original off+len */
        xfs_fileoff_t   nexto;          /* next file offset */
        xfs_fileoff_t   prevo;          /* previous file offset */
        xfs_fileoff_t   align_off;      /* temp for offset */
        xfs_extlen_t    align_alen;     /* temp for length */
        xfs_extlen_t    temp;           /* temp for calculations */

        if (convert)
                return 0;

        orig_off = align_off = *offp;
        orig_alen = align_alen = *lenp;
        orig_end = orig_off + orig_alen;

        /*
         * If this request overlaps an existing extent, then don't
         * attempt to perform any additional alignment.
         */
        if (!delay && !eof &&
            (orig_off >= gotp->br_startoff) &&
            (orig_end <= gotp->br_startoff + gotp->br_blockcount)) {
                return 0;
        }

        /*
         * If the file offset is unaligned vs. the extent size
         * we need to align it.  This will be possible unless
         * the file was previously written with a kernel that didn't
         * perform this alignment, or if a truncate shot us in the
         * foot.
         */
        div_u64_rem(orig_off, extsz, &temp);
        if (temp) {
                align_alen += temp;
                align_off -= temp;
        }

        /* Same adjustment for the end of the requested area. */
        temp = (align_alen % extsz);
        if (temp)
                align_alen += extsz - temp;

        /*
         * For large extent hint sizes, the aligned extent might be larger than
         * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls
         * the length back under MAXEXTLEN. The outer allocation loops handle
         * short allocation just fine, so it is safe to do this. We only want to
         * do it when we are forced to, though, because it means more allocation
         * operations are required.
         */
        while (align_alen > MAXEXTLEN)
                align_alen -= extsz;
        ASSERT(align_alen <= MAXEXTLEN);

        /*
         * If the previous block overlaps with this proposed allocation
         * then move the start forward without adjusting the length.
         */
        if (prevp->br_startoff != NULLFILEOFF) {
                if (prevp->br_startblock == HOLESTARTBLOCK)
                        prevo = prevp->br_startoff;
                else
                        prevo = prevp->br_startoff + prevp->br_blockcount;
        } else
                prevo = 0;
        if (align_off != orig_off && align_off < prevo)
                align_off = prevo;
        /*
         * If the next block overlaps with this proposed allocation
         * then move the start back without adjusting the length,
         * but not before offset 0.
         * This may of course make the start overlap previous block,
         * and if we hit the offset 0 limit then the next block
         * can still overlap too.
         */
        if (!eof && gotp->br_startoff != NULLFILEOFF) {
                if ((delay && gotp->br_startblock == HOLESTARTBLOCK) ||
                    (!delay && gotp->br_startblock == DELAYSTARTBLOCK))
                        nexto = gotp->br_startoff + gotp->br_blockcount;
                else
                        nexto = gotp->br_startoff;
        } else
                nexto = NULLFILEOFF;
        if (!eof &&
            align_off + align_alen != orig_end &&
            align_off + align_alen > nexto)
                align_off = nexto > align_alen ? nexto - align_alen : 0;
        /*
         * If we're now overlapping the next or previous extent that
         * means we can't fit an extsz piece in this hole.  Just move
         * the start forward to the first valid spot and set
         * the length so we hit the end.
         */
        if (align_off != orig_off && align_off < prevo)
                align_off = prevo;
        if (align_off + align_alen != orig_end &&
            align_off + align_alen > nexto &&
            nexto != NULLFILEOFF) {
                ASSERT(nexto > prevo);
                align_alen = nexto - align_off;
        }

        /*
         * If realtime, and the result isn't a multiple of the realtime
         * extent size we need to remove blocks until it is.
         */
        if (rt && (temp = (align_alen % mp->m_sb.sb_rextsize))) {
                /*
                 * We're not covering the original request, or
                 * we won't be able to once we fix the length.
                 */
                if (orig_off < align_off ||
                    orig_end > align_off + align_alen ||
                    align_alen - temp < orig_alen)
                        return -EINVAL;
                /*
                 * Try to fix it by moving the start up.
                 */
                if (align_off + temp <= orig_off) {
                        align_alen -= temp;
                        align_off += temp;