Merge branch 'topic/error' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator into regulator-fixed

1 files changed, 693 insertions, 266 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 932381caef1b..c27344cf38e1 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -24,6 +24,7 @@
 #include "xfs_bit.h"
 #include "xfs_sb.h"
 #include "xfs_mount.h"
+#include "xfs_defer.h"
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 #include "xfs_dir2.h"
@@ -45,6 +46,9 @@
 #include "xfs_symlink.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_filestream.h"
+#include "xfs_rmap.h"
+#include "xfs_ag_resv.h"
+#include "xfs_refcount.h"
 
 
 kmem_zone_t		*xfs_bmap_free_item_zone;
@@ -137,7 +141,8 @@ xfs_bmbt_lookup_ge(
  */
 static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork)
 {
-	return XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
+	return whichfork != XFS_COW_FORK &&
+		XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
 		XFS_IFORK_NEXTENTS(ip, whichfork) >
 			XFS_IFORK_MAXEXT(ip, whichfork);
 }
@@ -147,7 +152,8 @@ static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork)
  */
 static inline bool xfs_bmap_wants_extents(struct xfs_inode *ip, int whichfork)
 {
-	return XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE &&
+	return whichfork != XFS_COW_FORK &&
+		XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE &&
 		XFS_IFORK_NEXTENTS(ip, whichfork) <=
 			XFS_IFORK_MAXEXT(ip, whichfork);
 }
@@ -570,14 +576,13 @@ xfs_bmap_validate_ret(
  */
 void
 xfs_bmap_add_free(
-	xfs_fsblock_t		bno,		/* fs block number of extent */
-	xfs_filblks_t		len,		/* length of extent */
-	xfs_bmap_free_t		*flist,		/* list of extents */
-	xfs_mount_t		*mp)		/* mount point structure */
+	struct xfs_mount		*mp,
+	struct xfs_defer_ops		*dfops,
+	xfs_fsblock_t			bno,
+	xfs_filblks_t			len,
+	struct xfs_owner_info		*oinfo)
 {
-	xfs_bmap_free_item_t	*cur;		/* current (next) element */
-	xfs_bmap_free_item_t	*new;		/* new element */
-	xfs_bmap_free_item_t	*prev;		/* previous element */
+	struct xfs_extent_free_item	*new;		/* new element */
 #ifdef DEBUG
 	xfs_agnumber_t		agno;
 	xfs_agblock_t		agbno;
@@ -594,59 +599,17 @@ xfs_bmap_add_free(
 	ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
 #endif
 	ASSERT(xfs_bmap_free_item_zone != NULL);
-	new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
-	new->xbfi_startblock = bno;
-	new->xbfi_blockcount = (xfs_extlen_t)len;
-	for (prev = NULL, cur = flist->xbf_first;
-	     cur != NULL;
-	     prev = cur, cur = cur->xbfi_next) {
-		if (cur->xbfi_startblock >= bno)
-			break;
-	}
-	if (prev)
-		prev->xbfi_next = new;
-	else
-		flist->xbf_first = new;
-	new->xbfi_next = cur;
-	flist->xbf_count++;
-}
 
-/*
- * Remove the entry "free" from the free item list.  Prev points to the
- * previous entry, unless "free" is the head of the list.
- */
-void
-xfs_bmap_del_free(
-	xfs_bmap_free_t		*flist,	/* free item list header */
-	xfs_bmap_free_item_t	*prev,	/* previous item on list, if any */
-	xfs_bmap_free_item_t	*free)	/* list item to be freed */
-{
-	if (prev)
-		prev->xbfi_next = free->xbfi_next;
+	new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
+	new->xefi_startblock = bno;
+	new->xefi_blockcount = (xfs_extlen_t)len;
+	if (oinfo)
+		new->xefi_oinfo = *oinfo;
 	else
-		flist->xbf_first = free->xbfi_next;
-	flist->xbf_count--;
-	kmem_zone_free(xfs_bmap_free_item_zone, free);
-}
-
-/*
- * Free up any items left in the list.
- */
-void
-xfs_bmap_cancel(
-	xfs_bmap_free_t		*flist)	/* list of bmap_free_items */
-{
-	xfs_bmap_free_item_t	*free;	/* free list item */
-	xfs_bmap_free_item_t	*next;
-
-	if (flist->xbf_count == 0)
-		return;
-	ASSERT(flist->xbf_first != NULL);
-	for (free = flist->xbf_first; free; free = next) {
-		next = free->xbfi_next;
-		xfs_bmap_del_free(flist, NULL, free);
-	}
-	ASSERT(flist->xbf_count == 0);
+		xfs_rmap_skip_owner_update(&new->xefi_oinfo);
+	trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(mp, bno), 0,
+			XFS_FSB_TO_AGBNO(mp, bno), len);
+	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
 }
 
 /*
@@ -676,9 +639,11 @@ xfs_bmap_btree_to_extents(
 	xfs_mount_t		*mp;	/* mount point structure */
 	__be64			*pp;	/* ptr to block address */
 	struct xfs_btree_block	*rblock;/* root btree block */
+	struct xfs_owner_info	oinfo;
 
 	mp = ip->i_mount;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
+	ASSERT(whichfork != XFS_COW_FORK);
 	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
 	rblock = ifp->if_broot;
@@ -699,7 +664,8 @@ xfs_bmap_btree_to_extents(
 	cblock = XFS_BUF_TO_BLOCK(cbp);
 	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
 		return error;
-	xfs_bmap_add_free(cbno, 1, cur->bc_private.b.flist, mp);
+	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
+	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, 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);
@@ -722,7 +688,7 @@ xfs_bmap_extents_to_btree(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	xfs_fsblock_t		*firstblock,	/* first-block-allocated */
-	xfs_bmap_free_t		*flist,		/* blocks freed in xaction */
+	struct xfs_defer_ops	*dfops,		/* blocks freed in xaction */
 	xfs_btree_cur_t		**curp,		/* cursor returned to caller */
 	int			wasdel,		/* converting a delayed alloc */
 	int			*logflagsp,	/* inode logging flags */
@@ -744,6 +710,7 @@ xfs_bmap_extents_to_btree(
 	xfs_bmbt_ptr_t		*pp;		/* root block address pointer */
 
 	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);
 
@@ -771,7 +738,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 	cur->bc_private.b.firstblock = *firstblock;
-	cur->bc_private.b.flist = flist;
+	cur->bc_private.b.dfops = dfops;
 	cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
 	/*
 	 * Convert to a btree with two levels, one record in root.
@@ -780,11 +747,13 @@ xfs_bmap_extents_to_btree(
 	memset(&args, 0, sizeof(args));
 	args.tp = tp;
 	args.mp = mp;
+	xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);
 	args.firstblock = *firstblock;
 	if (*firstblock == NULLFSBLOCK) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
-	} else if (flist->xbf_low) {
+	} else if (dfops->dop_low) {
+try_another_ag:
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = *firstblock;
 	} else {
@@ -799,13 +768,28 @@ xfs_bmap_extents_to_btree(
 		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
 		return error;
 	}
+
+	/*
+	 * During a CoW operation, the allocation and bmbt updates occur in
+	 * different transactions.  The mapping code tries to put new bmbt
+	 * blocks near extents being mapped, but the only way to guarantee this
+	 * is if the alloc and the mapping happen in a single transaction that
+	 * has a block reservation.  That isn't the case here, so if we run out
+	 * of space we'll try again with another AG.
+	 */
+	if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
+	    args.fsbno == NULLFSBLOCK &&
+	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
+		dfops->dop_low = true;
+		goto try_another_ag;
+	}
 	/*
 	 * Allocation can't fail, the space was reserved.
 	 */
 	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(*firstblock == NULLFSBLOCK ||
 	       args.agno == XFS_FSB_TO_AGNO(mp, *firstblock) ||
-	       (flist->xbf_low &&
+	       (dfops->dop_low &&
 		args.agno > XFS_FSB_TO_AGNO(mp, *firstblock)));
 	*firstblock = cur->bc_private.b.firstblock = args.fsbno;
 	cur->bc_private.b.allocated++;
@@ -874,6 +858,7 @@ xfs_bmap_local_to_extents_empty(
 {
 	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);
@@ -926,12 +911,14 @@ xfs_bmap_local_to_extents(
 	memset(&args, 0, sizeof(args));
 	args.tp = tp;
 	args.mp = ip->i_mount;
+	xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);
 	args.firstblock = *firstblock;
 	/*
 	 * Allocate a block.  We know we need only one, since the
 	 * file currently fits in an inode.
 	 */
 	if (*firstblock == NULLFSBLOCK) {
+try_another_ag:
 		args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
@@ -944,6 +931,19 @@ xfs_bmap_local_to_extents(
 	if (error)
 		goto done;
 
+	/*
+	 * During a CoW operation, the allocation and bmbt updates occur in
+	 * different transactions.  The mapping code tries to put new bmbt
+	 * blocks near extents being mapped, but the only way to guarantee this
+	 * is if the alloc and the mapping happen in a single transaction that
+	 * has a block reservation.  That isn't the case here, so if we run out
+	 * of space we'll try again with another AG.
+	 */
+	if (xfs_sb_version_hasreflink(&ip->i_mount->m_sb) &&
+	    args.fsbno == NULLFSBLOCK &&
+	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
+		goto try_another_ag;
+	}
 	/* Can't fail, the space was reserved. */
 	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(args.len == 1);
@@ -990,7 +990,7 @@ xfs_bmap_add_attrfork_btree(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	xfs_bmap_free_t		*flist,		/* blocks to free at commit */
+	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* btree cursor */
@@ -1003,7 +1003,7 @@ xfs_bmap_add_attrfork_btree(
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
-		cur->bc_private.b.flist = flist;
+		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.firstblock = *firstblock;
 		if ((error = xfs_bmbt_lookup_ge(cur, 0, 0, 0, &stat)))
 			goto error0;
@@ -1033,7 +1033,7 @@ xfs_bmap_add_attrfork_extents(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	xfs_bmap_free_t		*flist,		/* blocks to free at commit */
+	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
@@ -1042,7 +1042,7 @@ xfs_bmap_add_attrfork_extents(
 	if (ip->i_d.di_nextents * sizeof(xfs_bmbt_rec_t) <= XFS_IFORK_DSIZE(ip))
 		return 0;
 	cur = NULL;
-	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, flist, &cur, 0,
+	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops, &cur, 0,
 		flags, XFS_DATA_FORK);
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
@@ -1068,7 +1068,7 @@ xfs_bmap_add_attrfork_local(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	xfs_bmap_free_t		*flist,		/* blocks to free at commit */
+	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_da_args_t		dargs;		/* args for dir/attr code */
@@ -1081,7 +1081,7 @@ xfs_bmap_add_attrfork_local(
 		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
 		dargs.firstblock = firstblock;
-		dargs.flist = flist;
+		dargs.dfops = dfops;
 		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
@@ -1109,7 +1109,7 @@ xfs_bmap_add_attrfork(
 	int			rsvd)		/* xact may use reserved blks */
 {
 	xfs_fsblock_t		firstblock;	/* 1st block/ag allocated */
-	xfs_bmap_free_t		flist;		/* freed extent records */
+	struct xfs_defer_ops	dfops;		/* freed extent records */
 	xfs_mount_t		*mp;		/* mount structure */
 	xfs_trans_t		*tp;		/* transaction pointer */
 	int			blks;		/* space reservation */
@@ -1175,18 +1175,18 @@ xfs_bmap_add_attrfork(
 	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
 	ip->i_afp->if_flags = XFS_IFEXTENTS;
 	logflags = 0;
-	xfs_bmap_init(&flist, &firstblock);
+	xfs_defer_init(&dfops, &firstblock);
 	switch (ip->i_d.di_format) {
 	case XFS_DINODE_FMT_LOCAL:
-		error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &flist,
+		error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &dfops,
 			&logflags);
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
 		error = xfs_bmap_add_attrfork_extents(tp, ip, &firstblock,
-			&flist, &logflags);
+			&dfops, &logflags);
 		break;
 	case XFS_DINODE_FMT_BTREE:
-		error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock, &flist,
+		error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock, &dfops,
 			&logflags);
 		break;
 	default:
@@ -1215,7 +1215,7 @@ xfs_bmap_add_attrfork(
 			xfs_log_sb(tp);
 	}
 
-	error = xfs_bmap_finish(&tp, &flist, NULL);
+	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)
 		goto bmap_cancel;
 	error = xfs_trans_commit(tp);
@@ -1223,7 +1223,7 @@ xfs_bmap_add_attrfork(
 	return error;
 
 bmap_cancel:
-	xfs_bmap_cancel(&flist);
+	xfs_defer_cancel(&dfops);
 trans_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1425,7 +1425,7 @@ xfs_bmap_search_multi_extents(
  * Else, *lastxp will be set to the index of the found
  * entry; *gotp will contain the entry.
  */
-STATIC xfs_bmbt_rec_host_t *                 /* pointer to found extent entry */
+xfs_bmbt_rec_host_t *                 /* pointer to found extent entry */
 xfs_bmap_search_extents(
 	xfs_inode_t     *ip,            /* incore inode pointer */
 	xfs_fileoff_t   bno,            /* block number searched for */
@@ -1706,7 +1706,8 @@ xfs_bmap_one_block(
  */
 STATIC int				/* error */
 xfs_bmap_add_extent_delay_real(
-	struct xfs_bmalloca	*bma)
+	struct xfs_bmalloca	*bma,
+	int			whichfork)
 {
 	struct xfs_bmbt_irec	*new = &bma->got;
 	int			diff;	/* temp value */
@@ -1724,11 +1725,14 @@ xfs_bmap_add_extent_delay_real(
 	xfs_filblks_t		temp=0;	/* value for da_new calculations */
 	xfs_filblks_t		temp2=0;/* value for da_new calculations */
 	int			tmp_rval;	/* partial logging flags */
-	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp;
+	xfs_extnum_t		*nextents;
 
 	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(bma->idx >= 0);
 	ASSERT(bma->idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
@@ -1742,6 +1746,9 @@ xfs_bmap_add_extent_delay_real(
 #define	RIGHT		r[1]
 #define	PREV		r[2]
 
+	if (whichfork == XFS_COW_FORK)
+		state |= BMAP_COWFORK;
+
 	/*
 	 * Set up a bunch of variables to make the tests simpler.
 	 */
@@ -1828,7 +1835,7 @@ xfs_bmap_add_extent_delay_real(
 		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);
 
 		xfs_iext_remove(bma->ip, bma->idx + 1, 2, state);
-		bma->ip->i_d.di_nextents--;
+		(*nextents)--;
 		if (bma->cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -1930,7 +1937,7 @@ xfs_bmap_add_extent_delay_real(
 		xfs_bmbt_set_startblock(ep, new->br_startblock);
 		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);
 
-		bma->ip->i_d.di_nextents++;
+		(*nextents)++;
 		if (bma->cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2000,7 +2007,7 @@ xfs_bmap_add_extent_delay_real(
 		temp = PREV.br_blockcount - new->br_blockcount;
 		xfs_bmbt_set_blockcount(ep, temp);
 		xfs_iext_insert(bma->ip, bma->idx, 1, new, state);
-		bma->ip->i_d.di_nextents++;
+		(*nextents)++;
 		if (bma->cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2020,7 +2027,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->flist,
+					bma->firstblock, bma->dfops,
 					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -2084,7 +2091,7 @@ xfs_bmap_add_extent_delay_real(
 		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
 		xfs_bmbt_set_blockcount(ep, temp);
 		xfs_iext_insert(bma->ip, bma->idx + 1, 1, new, state);
-		bma->ip->i_d.di_nextents++;
+		(*nextents)++;
 		if (bma->cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2104,7 +2111,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->flist, &bma->cur, 1,
+				bma->firstblock, bma->dfops, &bma->cur, 1,
 				&tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -2153,7 +2160,7 @@ xfs_bmap_add_extent_delay_real(
 		RIGHT.br_blockcount = temp2;
 		/* insert LEFT (r[0]) and RIGHT (r[1]) at the same time */
 		xfs_iext_insert(bma->ip, bma->idx + 1, 2, &LEFT, state);
-		bma->ip->i_d.di_nextents++;
+		(*nextents)++;
 		if (bma->cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2173,7 +2180,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->flist, &bma->cur,
+					bma->firstblock, bma->dfops, &bma->cur,
 					1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -2216,13 +2223,18 @@ xfs_bmap_add_extent_delay_real(
 		ASSERT(0);
 	}
 
+	/* add reverse mapping */
+	error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip, whichfork, new);
+	if (error)
+		goto done;
+
 	/* 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->firstblock, bma->flist, &bma->cur,
+				bma->firstblock, bma->dfops, &bma->cur,
 				da_old > 0, &tmp_logflags, whichfork);
 		bma->logflags |= tmp_logflags;
 		if (error)
@@ -2246,7 +2258,8 @@ xfs_bmap_add_extent_delay_real(
 
 	xfs_bmap_check_leaf_extents(bma->cur, bma->ip, whichfork);
 done:
-	bma->logflags |= rval;
+	if (whichfork != XFS_COW_FORK)
+		bma->logflags |= rval;
 	return error;
 #undef	LEFT
 #undef	RIGHT
@@ -2264,7 +2277,7 @@ xfs_bmap_add_extent_unwritten_real(
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
 	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
-	xfs_bmap_free_t		*flist,	/* list of extents to be freed */
+	struct xfs_defer_ops	*dfops,	/* list of extents to be freed */
 	int			*logflagsp) /* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;	/* btree cursor */
@@ -2752,12 +2765,17 @@ xfs_bmap_add_extent_unwritten_real(
 		ASSERT(0);
 	}
 
+	/* update reverse mappings */
+	error = xfs_rmap_convert_extent(mp, dfops, ip, XFS_DATA_FORK, new);
+	if (error)
+		goto done;
+
 	/* convert to a btree if necessary */
 	if (xfs_bmap_needs_btree(ip, XFS_DATA_FORK)) {
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, first, flist, &cur,
+		error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, &cur,
 				0, &tmp_logflags, XFS_DATA_FORK);
 		*logflagsp |= tmp_logflags;
 		if (error)
@@ -2785,6 +2803,7 @@ done:
 STATIC void
 xfs_bmap_add_extent_hole_delay(
 	xfs_inode_t		*ip,	/* incore inode pointer */
+	int			whichfork,
 	xfs_extnum_t		*idx,	/* extent number to update/insert */
 	xfs_bmbt_irec_t		*new)	/* new data to add to file extents */
 {
@@ -2796,8 +2815,10 @@ xfs_bmap_add_extent_hole_delay(
 	int			state;  /* state bits, accessed thru macros */
 	xfs_filblks_t		temp=0;	/* temp for indirect calculations */
 
-	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	ifp = XFS_IFORK_PTR(ip, whichfork);
 	state = 0;
+	if (whichfork == XFS_COW_FORK)
+		state |= BMAP_COWFORK;
 	ASSERT(isnullstartblock(new->br_startblock));
 
 	/*
@@ -2815,7 +2836,7 @@ xfs_bmap_add_extent_hole_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 (*idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t)) {
+	if (*idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)) {
 		state |= BMAP_RIGHT_VALID;
 		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx), &right);
 
@@ -2949,6 +2970,7 @@ xfs_bmap_add_extent_hole_real(
 	ASSERT(!isnullstartblock(new->br_startblock));
 	ASSERT(!bma->cur ||
 	       !(bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));
+	ASSERT(whichfork != XFS_COW_FORK);
 
 	XFS_STATS_INC(mp, xs_add_exlist);
 
@@ -3144,13 +3166,18 @@ xfs_bmap_add_extent_hole_real(
 		break;
 	}
 
+	/* add reverse mapping */
+	error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip, whichfork, new);
+	if (error)
+		goto done;
+
 	/* 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->firstblock, bma->flist, &bma->cur,
+				bma->firstblock, bma->dfops, &bma->cur,
 				0, &tmp_logflags, whichfork);
 		bma->logflags |= tmp_logflags;
 		if (error)
@@ -3369,7 +3396,8 @@ xfs_bmap_adjacent(
 
 	mp = ap->ip->i_mount;
 	nullfb = *ap->firstblock == NULLFSBLOCK;
-	rt = XFS_IS_REALTIME_INODE(ap->ip) && ap->userdata;
+	rt = XFS_IS_REALTIME_INODE(ap->ip) &&
+		xfs_alloc_is_userdata(ap->datatype);
 	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
 	/*
 	 * If allocating at eof, and there's a previous real block,
@@ -3523,7 +3551,8 @@ xfs_bmap_longest_free_extent(
 	}
 
 	longest = xfs_alloc_longest_free_extent(mp, pag,
-					xfs_alloc_min_freelist(mp, pag));
+				xfs_alloc_min_freelist(mp, pag),
+				xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE));
 	if (*blen < longest)
 		*blen = longest;
 
@@ -3644,7 +3673,7 @@ xfs_bmap_btalloc(
 {
 	xfs_mount_t	*mp;		/* mount point structure */
 	xfs_alloctype_t	atype = 0;	/* type for allocation routines */
-	xfs_extlen_t	align;		/* minimum allocation alignment */
+	xfs_extlen_t	align = 0;	/* minimum allocation alignment */
 	xfs_agnumber_t	fb_agno;	/* ag number of ap->firstblock */
 	xfs_agnumber_t	ag;
 	xfs_alloc_arg_t	args;
@@ -3667,7 +3696,10 @@ xfs_bmap_btalloc(
 	else if (mp->m_dalign)
 		stripe_align = mp->m_dalign;
 
-	align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0;
+	if (ap->flags & XFS_BMAPI_COWFORK)
+		align = xfs_get_cowextsz_hint(ap->ip);
+	else if (xfs_alloc_is_userdata(ap->datatype))
+		align = xfs_get_extsz_hint(ap->ip);
 	if (unlikely(align)) {
 		error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
 						align, 0, ap->eof, 0, ap->conv,
@@ -3680,7 +3712,8 @@ xfs_bmap_btalloc(
 	nullfb = *ap->firstblock == NULLFSBLOCK;
 	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
 	if (nullfb) {
-		if (ap->userdata && xfs_inode_is_filestream(ap->ip)) {
+		if (xfs_alloc_is_userdata(ap->datatype) &&
+		    xfs_inode_is_filestream(ap->ip)) {
 			ag = xfs_filestream_lookup_ag(ap->ip);
 			ag = (ag != NULLAGNUMBER) ? ag : 0;
 			ap->blkno = XFS_AGB_TO_FSB(mp, ag, 0);
@@ -3708,9 +3741,10 @@ xfs_bmap_btalloc(
 	args.tp = ap->tp;
 	args.mp = mp;
 	args.fsbno = ap->blkno;
+	xfs_rmap_skip_owner_update(&args.oinfo);
 
 	/* Trim the allocation back to the maximum an AG can fit. */
-	args.maxlen = MIN(ap->length, XFS_ALLOC_AG_MAX_USABLE(mp));
+	args.maxlen = MIN(ap->length, mp->m_ag_max_usable);
 	args.firstblock = *ap->firstblock;
 	blen = 0;
 	if (nullfb) {
@@ -3719,13 +3753,14 @@ xfs_bmap_btalloc(
 		 * enough for the request.  If one isn't found, then adjust
 		 * the minimum allocation size to the largest space found.
 		 */
-		if (ap->userdata && xfs_inode_is_filestream(ap->ip))
+		if (xfs_alloc_is_userdata(ap->datatype) &&
+		    xfs_inode_is_filestream(ap->ip))
 			error = xfs_bmap_btalloc_filestreams(ap, &args, &blen);
 		else
 			error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
 		if (error)
 			return error;
-	} else if (ap->flist->xbf_low) {
+	} else if (ap->dfops->dop_low) {
 		if (xfs_inode_is_filestream(ap->ip))
 			args.type = XFS_ALLOCTYPE_FIRST_AG;
 		else
@@ -3758,7 +3793,7 @@ xfs_bmap_btalloc(
 	 * is >= the stripe unit and the allocation offset is
 	 * at the end of file.
 	 */
-	if (!ap->flist->xbf_low && ap->aeof) {
+	if (!ap->dfops->dop_low && ap->aeof) {
 		if (!ap->offset) {
 			args.alignment = stripe_align;
 			atype = args.type;
@@ -3802,9 +3837,9 @@ xfs_bmap_btalloc(
 	}
 	args.minleft = ap->minleft;
 	args.wasdel = ap->wasdel;
-	args.isfl = 0;
-	args.userdata = ap->userdata;
-	if (ap->userdata & XFS_ALLOC_USERDATA_ZERO)
+	args.resv = XFS_AG_RESV_NONE;
+	args.datatype = ap->datatype;
+	if (ap->datatype & XFS_ALLOC_USERDATA_ZERO)
 		args.ip = ap->ip;
 
 	error = xfs_alloc_vextent(&args);
@@ -3851,7 +3886,7 @@ xfs_bmap_btalloc(
 		args.minleft = 0;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
-		ap->flist->xbf_low = 1;
+		ap->dfops->dop_low = true;
 	}
 	if (args.fsbno != NULLFSBLOCK) {
 		/*
@@ -3861,7 +3896,7 @@ xfs_bmap_btalloc(
 		ASSERT(*ap->firstblock == NULLFSBLOCK ||
 		       XFS_FSB_TO_AGNO(mp, *ap->firstblock) ==
 		       XFS_FSB_TO_AGNO(mp, args.fsbno) ||
-		       (ap->flist->xbf_low &&
+		       (ap->dfops->dop_low &&
 			XFS_FSB_TO_AGNO(mp, *ap->firstblock) <
 			XFS_FSB_TO_AGNO(mp, args.fsbno)));
 
@@ -3869,9 +3904,10 @@ xfs_bmap_btalloc(
 		if (*ap->firstblock == NULLFSBLOCK)
 			*ap->firstblock = args.fsbno;
 		ASSERT(nullfb || fb_agno == args.agno ||
-		       (ap->flist->xbf_low && fb_agno < args.agno));
+		       (ap->dfops->dop_low && fb_agno < args.agno));
 		ap->length = args.len;
-		ap->ip->i_d.di_nblocks += args.len;
+		if (!(ap->flags & XFS_BMAPI_COWFORK))
+			ap->ip->i_d.di_nblocks += args.len;
 		xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
 		if (ap->wasdel)
 			ap->ip->i_delayed_blks -= args.len;
@@ -3891,6 +3927,63 @@ xfs_bmap_btalloc(
 }
 
 /*
+ * For a remap operation, just "allocate" an extent at the address that the
+ * caller passed in, and ensure that the AGFL is the right size.  The caller
+ * will then map the "allocated" extent into the file somewhere.
+ */
+STATIC int
+xfs_bmap_remap_alloc(
+	struct xfs_bmalloca	*ap)
+{
+	struct xfs_trans	*tp = ap->tp;
+	struct xfs_mount	*mp = tp->t_mountp;
+	xfs_agblock_t		bno;
+	struct xfs_alloc_arg	args;
+	int			error;
+
+	/*
+	 * validate that the block number is legal - the enables us to detect
+	 * and handle a silent filesystem corruption rather than crashing.
+	 */
+	memset(&args, 0, sizeof(struct xfs_alloc_arg));
+	args.tp = ap->tp;
+	args.mp = ap->tp->t_mountp;
+	bno = *ap->firstblock;
+	args.agno = XFS_FSB_TO_AGNO(mp, bno);
+	args.agbno = XFS_FSB_TO_AGBNO(mp, bno);
+	if (args.agno >= mp->m_sb.sb_agcount ||
+	    args.agbno >= mp->m_sb.sb_agblocks)
+		return -EFSCORRUPTED;
+
+	/* "Allocate" the extent from the range we passed in. */
+	trace_xfs_bmap_remap_alloc(ap->ip, *ap->firstblock, ap->length);
+	ap->blkno = bno;
+	ap->ip->i_d.di_nblocks += ap->length;
+	xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
+
+	/* Fix the freelist, like a real allocator does. */
+	args.datatype = ap->datatype;
+	args.pag = xfs_perag_get(args.mp, args.agno);
+	ASSERT(args.pag);
+
+	/*
+	 * The freelist fixing code will decline the allocation if
+	 * the size and shape of the free space doesn't allow for
+	 * allocating the extent and updating all the metadata that
+	 * happens during an allocation.  We're remapping, not
+	 * allocating, so skip that check by pretending to be freeing.
+	 */
+	error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING);
+	if (error)
+		goto error0;
+error0:
+	xfs_perag_put(args.pag);
+	if (error)
+		trace_xfs_bmap_remap_alloc_error(ap->ip, error, _RET_IP_);
+	return error;
+}
+
+/*
  * xfs_bmap_alloc is called by xfs_bmapi to allocate an extent for a file.
  * It figures out where to ask the underlying allocator to put the new extent.
  */
@@ -3898,7 +3991,10 @@ STATIC int
 xfs_bmap_alloc(
 	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
 {
-	if (XFS_IS_REALTIME_INODE(ap->ip) && ap->userdata)
+	if (ap->flags & XFS_BMAPI_REMAP)
+		return xfs_bmap_remap_alloc(ap);
+	if (XFS_IS_REALTIME_INODE(ap->ip) &&
+	    xfs_alloc_is_userdata(ap->datatype))
 		return xfs_bmap_rtalloc(ap);
 	return xfs_bmap_btalloc(ap);
 }
@@ -4026,12 +4122,11 @@ xfs_bmapi_read(
 	int			error;
 	int			eof;
 	int			n = 0;
-	int			whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
-						XFS_ATTR_FORK : XFS_DATA_FORK;
+	int			whichfork = xfs_bmapi_whichfork(flags);
 
 	ASSERT(*nmap >= 1);
 	ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK|XFS_BMAPI_ENTIRE|
-			   XFS_BMAPI_IGSTATE)));
+			   XFS_BMAPI_IGSTATE|XFS_BMAPI_COWFORK)));
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL));
 
 	if (unlikely(XFS_TEST_ERROR(
@@ -4049,6 +4144,16 @@ xfs_bmapi_read(
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 
+	/* No CoW fork?  Return a hole. */
+	if (whichfork == XFS_COW_FORK && !ifp) {
+		mval->br_startoff = bno;
+		mval->br_startblock = HOLESTARTBLOCK;
+		mval->br_blockcount = len;
+		mval->br_state = XFS_EXT_NORM;
+		*nmap = 1;
+		return 0;
+	}
+
 	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
 		error = xfs_iread_extents(NULL, ip, whichfork);
 		if (error)
@@ -4095,9 +4200,10 @@ xfs_bmapi_read(
 	return 0;
 }
 
-STATIC int
+int
 xfs_bmapi_reserve_delalloc(
 	struct xfs_inode	*ip,
+	int			whichfork,
 	xfs_fileoff_t		aoff,
 	xfs_filblks_t		len,
 	struct xfs_bmbt_irec	*got,
@@ -4106,7 +4212,7 @@ xfs_bmapi_reserve_delalloc(
 	int			eof)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
 	xfs_extlen_t		alen;
 	xfs_extlen_t		indlen;
 	char			rt = XFS_IS_REALTIME_INODE(ip);
@@ -4118,7 +4224,10 @@ xfs_bmapi_reserve_delalloc(
 		alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);
 
 	/* Figure out the extent size, adjust alen */
-	extsz = xfs_get_extsz_hint(ip);
+	if (whichfork == XFS_COW_FORK)
+		extsz = xfs_get_cowextsz_hint(ip);
+	else
+		extsz = xfs_get_extsz_hint(ip);
 	if (extsz) {
 		error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof,
 					       1, 0, &aoff, &alen);
@@ -4165,7 +4274,7 @@ xfs_bmapi_reserve_delalloc(
 	got->br_startblock = nullstartblock(indlen);
 	got->br_blockcount = alen;
 	got->br_state = XFS_EXT_NORM;
-	xfs_bmap_add_extent_hole_delay(ip, lastx, got);
+	xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
 	/*
 	 * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay
@@ -4191,98 +4300,12 @@ out_unreserve_quota:
 	return error;
 }
 
-/*
- * Map file blocks to filesystem blocks, adding delayed allocations as needed.
- */
-int
-xfs_bmapi_delay(
-	struct xfs_inode	*ip,	/* incore inode */
-	xfs_fileoff_t		bno,	/* starting file offs. mapped */
-	xfs_filblks_t		len,	/* length to map in file */
-	struct xfs_bmbt_irec	*mval,	/* output: map values */
-	int			*nmap,	/* i/o: mval size/count */
-	int			flags)	/* XFS_BMAPI_... */
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
-	struct xfs_bmbt_irec	got;	/* current file extent record */
-	struct xfs_bmbt_irec	prev;	/* previous file extent record */
-	xfs_fileoff_t		obno;	/* old block number (offset) */
-	xfs_fileoff_t		end;	/* end of mapped file region */
-	xfs_extnum_t		lastx;	/* last useful extent number */
-	int			eof;	/* we've hit the end of extents */
-	int			n = 0;	/* current extent index */
-	int			error = 0;
-
-	ASSERT(*nmap >= 1);
-	ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
-	ASSERT(!(flags & ~XFS_BMAPI_ENTIRE));
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
-	if (unlikely(XFS_TEST_ERROR(
-	    (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
-	     XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
-		XFS_ERROR_REPORT("xfs_bmapi_delay", XFS_ERRLEVEL_LOW, mp);
-		return -EFSCORRUPTED;
-	}
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	XFS_STATS_INC(mp, xs_blk_mapw);
-
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
-		if (error)
-			return error;
-	}
-
-	xfs_bmap_search_extents(ip, bno, XFS_DATA_FORK, &eof, &lastx, &got, &prev);
-	end = bno + len;
-	obno = bno;
-
-	while (bno < end && n < *nmap) {
-		if (eof || got.br_startoff > bno) {
-			error = xfs_bmapi_reserve_delalloc(ip, bno, len, &got,
-							   &prev, &lastx, eof);
-			if (error) {
-				if (n == 0) {
-					*nmap = 0;
-					return error;
-				}
-				break;
-			}
-		}
-
-		/* set up the extent map to return. */
-		xfs_bmapi_trim_map(mval, &got, &bno, len, obno, end, n, flags);
-		xfs_bmapi_update_map(&mval, &bno, &len, obno, end, &n, flags);
-
-		/* If we're done, stop now. */
-		if (bno >= end || n >= *nmap)
-			break;
-
-		/* Else go on to the next record. */
-		prev = got;
-		if (++lastx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t))
-			xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx), &got);
-		else
-			eof = 1;
-	}
-
-	*nmap = n;
-	return 0;
-}
-
-
 static int
 xfs_bmapi_allocate(
 	struct xfs_bmalloca	*bma)
 {
 	struct xfs_mount	*mp = bma->ip->i_mount;
-	int			whichfork = (bma->flags & XFS_BMAPI_ATTRFORK) ?
-						XFS_ATTR_FORK : XFS_DATA_FORK;
+	int			whichfork = xfs_bmapi_whichfork(bma->flags);
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(bma->ip, whichfork);
 	int			tmp_logflags = 0;
 	int			error;
@@ -4308,15 +4331,21 @@ xfs_bmapi_allocate(
 	}
 
 	/*
-	 * Indicate if this is the first user data in the file, or just any
-	 * user data. And if it is userdata, indicate whether it needs to
-	 * be initialised to zero during allocation.
+	 * Set the data type being allocated. For the data fork, the first data
+	 * in the file is treated differently to all other allocations. For the
+	 * attribute fork, we only need to ensure the allocated range is not on
+	 * the busy list.
 	 */
 	if (!(bma->flags & XFS_BMAPI_METADATA)) {
-		bma->userdata = (bma->offset == 0) ?
-			XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA;
+		bma->datatype = XFS_ALLOC_NOBUSY;
+		if (whichfork == XFS_DATA_FORK) {
+			if (bma->offset == 0)
+				bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA;
+			else
+				bma->datatype |= XFS_ALLOC_USERDATA;
+		}
 		if (bma->flags & XFS_BMAPI_ZERO)
-			bma->userdata |= XFS_ALLOC_USERDATA_ZERO;
+			bma->datatype |= XFS_ALLOC_USERDATA_ZERO;
 	}
 
 	bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1;
@@ -4336,7 +4365,7 @@ xfs_bmapi_allocate(
 	if (error)
 		return error;
 
-	if (bma->flist->xbf_low)
+	if (bma->dfops->dop_low)
 		bma->minleft = 0;
 	if (bma->cur)
 		bma->cur->bc_private.b.firstblock = *bma->firstblock;
@@ -4345,7 +4374,7 @@ xfs_bmapi_allocate(
 	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
 		bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork);
 		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.flist = bma->flist;
+		bma->cur->bc_private.b.dfops = bma->dfops;
 	}
 	/*
 	 * Bump the number of extents we've allocated
@@ -4371,7 +4400,7 @@ xfs_bmapi_allocate(
 		bma->got.br_state = XFS_EXT_UNWRITTEN;
 
 	if (bma->wasdel)
-		error = xfs_bmap_add_extent_delay_real(bma);
+		error = xfs_bmap_add_extent_delay_real(bma, whichfork);
 	else
 		error = xfs_bmap_add_extent_hole_real(bma, whichfork);
 
@@ -4401,8 +4430,7 @@ xfs_bmapi_convert_unwritten(
 	xfs_filblks_t		len,
 	int			flags)
 {
-	int			whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
-						XFS_ATTR_FORK : XFS_DATA_FORK;
+	int			whichfork = xfs_bmapi_whichfork(flags);
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(bma->ip, whichfork);
 	int			tmp_logflags = 0;
 	int			error;
@@ -4418,6 +4446,8 @@ xfs_bmapi_convert_unwritten(
 			(XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT))
 		return 0;
 
+	ASSERT(whichfork != XFS_COW_FORK);
+
 	/*
 	 * Modify (by adding) the state flag, if writing.
 	 */
@@ -4426,7 +4456,7 @@ xfs_bmapi_convert_unwritten(
 		bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp,
 					bma->ip, whichfork);
 		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.flist = bma->flist;
+		bma->cur->bc_private.b.dfops = bma->dfops;
 	}
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
@@ -4443,7 +4473,7 @@ xfs_bmapi_convert_unwritten(
 	}
 
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, &bma->idx,
-			&bma->cur, mval, bma->firstblock, bma->flist,
+			&bma->cur, mval, bma->firstblock, bma->dfops,
 			&tmp_logflags);
 	/*
 	 * Log the inode core unconditionally in the unwritten extent conversion
@@ -4497,7 +4527,7 @@ xfs_bmapi_write(
 	xfs_extlen_t		total,		/* total blocks needed */
 	struct xfs_bmbt_irec	*mval,		/* output: map values */
 	int			*nmap,		/* i/o: mval size/count */
-	struct xfs_bmap_free	*flist)		/* i/o: list extents to free */
+	struct xfs_defer_ops	*dfops)		/* i/o: list extents to free */
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
@@ -4524,8 +4554,7 @@ xfs_bmapi_write(
 	orig_mval = mval;
 	orig_nmap = *nmap;
 #endif
-	whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
-		XFS_ATTR_FORK : XFS_DATA_FORK;
+	whichfork = xfs_bmapi_whichfork(flags);
 
 	ASSERT(*nmap >= 1);
 	ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
@@ -4534,6 +4563,11 @@ xfs_bmapi_write(
 	ASSERT(len > 0);
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(!(flags & XFS_BMAPI_REMAP) || whichfork == XFS_DATA_FORK);
+	ASSERT(!(flags & XFS_BMAPI_PREALLOC) || !(flags & XFS_BMAPI_REMAP));
+	ASSERT(!(flags & XFS_BMAPI_CONVERT) || !(flags & XFS_BMAPI_REMAP));
+	ASSERT(!(flags & XFS_BMAPI_PREALLOC) || whichfork != XFS_COW_FORK);
+	ASSERT(!(flags & XFS_BMAPI_CONVERT) || whichfork != XFS_COW_FORK);
 
 	/* zeroing is for currently only for data extents, not metadata */
 	ASSERT((flags & (XFS_BMAPI_METADATA | XFS_BMAPI_ZERO)) !=
@@ -4586,8 +4620,8 @@ xfs_bmapi_write(
 	bma.tp = tp;
 	bma.ip = ip;
 	bma.total = total;
-	bma.userdata = 0;
-	bma.flist = flist;
+	bma.datatype = 0;
+	bma.dfops = dfops;
 	bma.firstblock = firstblock;
 
 	while (bno < end && n < *nmap) {
@@ -4595,6 +4629,14 @@ xfs_bmapi_write(
 		wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
 
 		/*
+		 * Make sure we only reflink into a hole.
+		 */
+		if (flags & XFS_BMAPI_REMAP)
+			ASSERT(inhole);
+		if (flags & XFS_BMAPI_COWFORK)
+			ASSERT(!inhole);
+
+		/*
 		 * First, deal with the hole before the allocated space
 		 * that we found, if any.
 		 */
@@ -4624,6 +4666,17 @@ xfs_bmapi_write(
 				goto error0;
 			if (bma.blkno == NULLFSBLOCK)
 				break;
+
+			/*
+			 * If this is a CoW allocation, record the data in
+			 * the refcount btree for orphan recovery.
+			 */
+			if (whichfork == XFS_COW_FORK) {
+				error = xfs_refcount_alloc_cow_extent(mp, dfops,
+						bma.blkno, bma.length);
+				if (error)
+					goto error0;
+			}
 		}
 
 		/* Deal with the allocated space we found.  */
@@ -4701,7 +4754,7 @@ error0:
 			       XFS_FSB_TO_AGNO(mp, *firstblock) ==
 			       XFS_FSB_TO_AGNO(mp,
 				       bma.cur->bc_private.b.firstblock) ||
-			       (flist->xbf_low &&
+			       (dfops->dop_low &&
 				XFS_FSB_TO_AGNO(mp, *firstblock) <
 				XFS_FSB_TO_AGNO(mp,
 					bma.cur->bc_private.b.firstblock)));
@@ -4785,11 +4838,12 @@ xfs_bmap_del_extent(
 	xfs_inode_t		*ip,	/* incore inode pointer */
 	xfs_trans_t		*tp,	/* current transaction pointer */
 	xfs_extnum_t		*idx,	/* extent number to update/delete */
-	xfs_bmap_free_t		*flist,	/* list of extents to be freed */
+	struct xfs_defer_ops	*dfops,	/* list of extents to be freed */
 	xfs_btree_cur_t		*cur,	/* if null, not a btree */
 	xfs_bmbt_irec_t		*del,	/* data to remove from extents */
 	int			*logflagsp, /* inode logging flags */
-	int			whichfork) /* data or attr fork */
+	int			whichfork, /* data or attr fork */
+	int			bflags)	/* bmapi flags */
 {
 	xfs_filblks_t		da_new;	/* new delay-alloc indirect blocks */
 	xfs_filblks_t		da_old;	/* old delay-alloc indirect blocks */
@@ -4818,6 +4872,8 @@ xfs_bmap_del_extent(
 
 	if (whichfork == XFS_ATTR_FORK)
 		state |= BMAP_ATTRFORK;
+	else if (whichfork == XFS_COW_FORK)
+		state |= BMAP_COWFORK;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	ASSERT((*idx >= 0) && (*idx < ifp->if_bytes /
@@ -4887,6 +4943,7 @@ xfs_bmap_del_extent(
 		nblks = 0;
 		do_fx = 0;
 	}
+
 	/*
 	 * Set flag value to use in switch statement.
 	 * Left-contig is 2, right-contig is 1.
@@ -4897,6 +4954,7 @@ xfs_bmap_del_extent(
 		/*
 		 * Matches the whole extent.  Delete the entry.
 		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
 		xfs_iext_remove(ip, *idx, 1,
 				whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0);
 		--*idx;
@@ -5069,12 +5127,27 @@ xfs_bmap_del_extent(
 		++*idx;
 		break;
 	}
+
+	/* remove reverse mapping */
+	if (!delay) {
+		error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, del);
+		if (error)
+			goto done;
+	}
+
 	/*
 	 * If we need to, add to list of extents to delete.
 	 */
-	if (do_fx)
-		xfs_bmap_add_free(del->br_startblock, del->br_blockcount, flist,
-			mp);
+	if (do_fx && !(bflags & XFS_BMAPI_REMAP)) {
+		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
+			error = xfs_refcount_decrease_extent(mp, dfops, del);
+			if (error)
+				goto done;
+		} else
+			xfs_bmap_add_free(mp, dfops, del->br_startblock,
+					del->br_blockcount, NULL);
+	}
+
 	/*
 	 * Adjust inode # blocks in the file.
 	 */
@@ -5083,7 +5156,7 @@ xfs_bmap_del_extent(
 	/*
 	 * Adjust quota data.
 	 */
-	if (qfield)
+	if (qfield && !(bflags & XFS_BMAPI_REMAP))
 		xfs_trans_mod_dquot_byino(tp, ip, qfield, (long)-nblks);
 
 	/*
@@ -5098,6 +5171,175 @@ done:
 	return error;
 }
 
+/* Remove an extent from the CoW fork.  Similar to xfs_bmap_del_extent. */
+int
+xfs_bunmapi_cow(
+	struct xfs_inode		*ip,
+	struct xfs_bmbt_irec		*del)
+{
+	xfs_filblks_t			da_new;
+	xfs_filblks_t			da_old;
+	xfs_fsblock_t			del_endblock = 0;
+	xfs_fileoff_t			del_endoff;
+	int				delay;
+	struct xfs_bmbt_rec_host	*ep;
+	int				error;
+	struct xfs_bmbt_irec		got;
+	xfs_fileoff_t			got_endoff;
+	struct xfs_ifork		*ifp;
+	struct xfs_mount		*mp;
+	xfs_filblks_t			nblks;
+	struct xfs_bmbt_irec		new;
+	/* REFERENCED */
+	uint				qfield;
+	xfs_filblks_t			temp;
+	xfs_filblks_t			temp2;
+	int				state = BMAP_COWFORK;
+	int				eof;
+	xfs_extnum_t			eidx;
+
+	mp = ip->i_mount;
+	XFS_STATS_INC(mp, xs_del_exlist);
+
+	ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof,
+			&eidx, &got, &new);
+
+	ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ifp = ifp;
+	ASSERT((eidx >= 0) && (eidx < ifp->if_bytes /
+		(uint)sizeof(xfs_bmbt_rec_t)));
+	ASSERT(del->br_blockcount > 0);
+	ASSERT(got.br_startoff <= del->br_startoff);
+	del_endoff = del->br_startoff + del->br_blockcount;
+	got_endoff = got.br_startoff + got.br_blockcount;
+	ASSERT(got_endoff >= del_endoff);
+	delay = isnullstartblock(got.br_startblock);
+	ASSERT(isnullstartblock(del->br_startblock) == delay);
+	qfield = 0;
+	error = 0;
+	/*
+	 * If deleting a real allocation, must free up the disk space.
+	 */
+	if (!delay) {
+		nblks = del->br_blockcount;
+		qfield = XFS_TRANS_DQ_BCOUNT;
+		/*
+		 * Set up del_endblock and cur for later.
+		 */
+		del_endblock = del->br_startblock + del->br_blockcount;
+		da_old = da_new = 0;
+	} else {
+		da_old = startblockval(got.br_startblock);
+		da_new = 0;
+		nblks = 0;
+	}
+	qfield = qfield;
+	nblks = nblks;
+
+	/*
+	 * Set flag value to use in switch statement.
+	 * Left-contig is 2, right-contig is 1.
+	 */
+	switch (((got.br_startoff == del->br_startoff) << 1) |
+		(got_endoff == del_endoff)) {
+	case 3:
+		/*
+		 * Matches the whole extent.  Delete the entry.
+		 */
+		xfs_iext_remove(ip, eidx, 1, BMAP_COWFORK);
+		--eidx;
+		break;
+
+	case 2:
+		/*
+		 * Deleting the first part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
+		xfs_bmbt_set_startoff(ep, del_endoff);
+		temp = got.br_blockcount - del->br_blockcount;
+		xfs_bmbt_set_blockcount(ep, temp);
+		if (delay) {
+			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
+				da_old);
+			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
+			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
+			da_new = temp;
+			break;
+		}
+		xfs_bmbt_set_startblock(ep, del_endblock);
+		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
+		break;
+
+	case 1:
+		/*
+		 * Deleting the last part of the extent.
+		 */
+		temp = got.br_blockcount - del->br_blockcount;
+		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
+		xfs_bmbt_set_blockcount(ep, temp);
+		if (delay) {
+			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
+				da_old);
+			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
+			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
+			da_new = temp;
+			break;
+		}
+		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
+		break;
+
+	case 0:
+		/*
+		 * Deleting the middle of the extent.
+		 */
+		temp = del->br_startoff - got.br_startoff;
+		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
+		xfs_bmbt_set_blockcount(ep, temp);
+		new.br_startoff = del_endoff;
+		temp2 = got_endoff - del_endoff;
+		new.br_blockcount = temp2;
+		new.br_state = got.br_state;
+		if (!delay) {
+			new.br_startblock = del_endblock;
+		} else {
+			temp = xfs_bmap_worst_indlen(ip, temp);
+			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
+			temp2 = xfs_bmap_worst_indlen(ip, temp2);
+			new.br_startblock = nullstartblock((int)temp2);
+			da_new = temp + temp2;
+			while (da_new > da_old) {
+				if (temp) {
+					temp--;
+					da_new--;
+					xfs_bmbt_set_startblock(ep,
+						nullstartblock((int)temp));
+				}
+				if (da_new == da_old)
+					break;
+				if (temp2) {
+					temp2--;
+					da_new--;
+					new.br_startblock =
+						nullstartblock((int)temp2);
+				}
+			}
+		}
+		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
+		xfs_iext_insert(ip, eidx + 1, 1, &new, state);
+		++eidx;
+		break;
+	}
+
+	/*
+	 * Account for change in delayed indirect blocks.
+	 * Nothing to do for disk quota accounting here.
+	 */
+	ASSERT(da_old >= da_new);
+	if (da_old > da_new)
+		xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false);
+
+	return error;
+}
+
 /*
  * Unmap (remove) blocks from a file.
  * If nexts is nonzero then the number of extents to remove is limited to
@@ -5105,17 +5347,16 @@ done:
  * *done is set.
  */
 int						/* error */
-xfs_bunmapi(
+__xfs_bunmapi(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	struct xfs_inode	*ip,		/* incore inode */
 	xfs_fileoff_t		bno,		/* starting offset to unmap */
-	xfs_filblks_t		len,		/* length to unmap in file */
+	xfs_filblks_t		*rlen,		/* i/o: amount remaining */
 	int			flags,		/* misc flags */
 	xfs_extnum_t		nexts,		/* number of extents max */
 	xfs_fsblock_t		*firstblock,	/* first allocated block
 						   controls a.g. for allocs */
-	xfs_bmap_free_t		*flist,		/* i/o: list extents to free */
-	int			*done)		/* set if not done yet */
+	struct xfs_defer_ops	*dfops)		/* i/o: deferred updates */
 {
 	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
 	xfs_bmbt_irec_t		del;		/* extent being deleted */
@@ -5137,11 +5378,12 @@ xfs_bunmapi(
 	int			wasdel;		/* was a delayed alloc extent */
 	int			whichfork;	/* data or attribute fork */
 	xfs_fsblock_t		sum;
+	xfs_filblks_t		len = *rlen;	/* length to unmap in file */
 
 	trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_);
 
-	whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
-		XFS_ATTR_FORK : XFS_DATA_FORK;
+	whichfork = xfs_bmapi_whichfork(flags);
+	ASSERT(whichfork != XFS_COW_FORK);
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	if (unlikely(
 	    XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
@@ -5163,7 +5405,7 @@ xfs_bunmapi(
 		return error;
 	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
 	if (nextents == 0) {
-		*done = 1;
+		*rlen = 0;
 		return 0;
 	}
 	XFS_STATS_INC(mp, xs_blk_unmap);
@@ -5187,7 +5429,7 @@ xfs_bunmapi(
 		ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.flist = flist;
+		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	} else
 		cur = NULL;
@@ -5196,8 +5438,10 @@ xfs_bunmapi(
 		/*
 		 * Synchronize by locking the bitmap inode.
 		 */
-		xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
+		xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP);
 		xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+		xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM);
+		xfs_trans_ijoin(tp, mp->m_rsumip, XFS_ILOCK_EXCL);
 	}
 
 	extno = 0;
@@ -5279,7 +5523,7 @@ xfs_bunmapi(
 			}
 			del.br_state = XFS_EXT_UNWRITTEN;
 			error = xfs_bmap_add_extent_unwritten_real(tp, ip,
-					&lastx, &cur, &del, firstblock, flist,
+					&lastx, &cur, &del, firstblock, dfops,
 					&logflags);
 			if (error)
 				goto error0;
@@ -5338,7 +5582,7 @@ xfs_bunmapi(
 				lastx--;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, &lastx, &cur, &prev,
-						firstblock, flist, &logflags);
+						firstblock, dfops, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5347,7 +5591,7 @@ xfs_bunmapi(
 				del.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, &lastx, &cur, &del,
-						firstblock, flist, &logflags);
+						firstblock, dfops, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5405,8 +5649,8 @@ xfs_bunmapi(
 		} else if (cur)
 			cur->bc_private.b.flags &= ~XFS_BTCUR_BPRV_WASDEL;
 
-		error = xfs_bmap_del_extent(ip, tp, &lastx, flist, cur, &del,
-				&tmp_logflags, whichfork);
+		error = xfs_bmap_del_extent(ip, tp, &lastx, dfops, cur, &del,
+				&tmp_logflags, whichfork, flags);
 		logflags |= tmp_logflags;
 		if (error)
 			goto error0;
@@ -5432,14 +5676,17 @@ nodelete:
 			extno++;
 		}
 	}
-	*done = bno == (xfs_fileoff_t)-1 || bno < start || lastx < 0;
+	if (bno == (xfs_fileoff_t)-1 || bno < start || lastx < 0)
+		*rlen = 0;
+	else
+		*rlen = bno - start + 1;
 
 	/*
 	 * Convert to a btree if necessary.
 	 */
 	if (xfs_bmap_needs_btree(ip, whichfork)) {
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstblock, flist,
+		error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops,
 			&cur, 0, &tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 		if (error)
@@ -5488,6 +5735,27 @@ error0:
 	return error;
 }
 
+/* Unmap a range of a file. */
+int
+xfs_bunmapi(
+	xfs_trans_t		*tp,
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		bno,
+	xfs_filblks_t		len,
+	int			flags,
+	xfs_extnum_t		nexts,
+	xfs_fsblock_t		*firstblock,
+	struct xfs_defer_ops	*dfops,
+	int			*done)
+{
+	int			error;
+
+	error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts, firstblock,
+			dfops);
+	*done = (len == 0);
+	return error;
+}
+
 /*
  * Determine whether an extent shift can be accomplished by a merge with the
  * extent that precedes the target hole of the shift.
@@ -5606,7 +5874,8 @@ xfs_bmse_shift_one(
 	struct xfs_bmbt_rec_host	*gotp,
 	struct xfs_btree_cur		*cur,
 	int				*logflags,
-	enum shift_direction		direction)
+	enum shift_direction		direction,
+	struct xfs_defer_ops		*dfops)
 {
 	struct xfs_ifork		*ifp;
 	struct xfs_mount		*mp;
@@ -5654,9 +5923,13 @@ xfs_bmse_shift_one(
 		/* check whether to merge the extent or shift it down */
 		if (xfs_bmse_can_merge(&adj_irec, &got,
 				       offset_shift_fsb)) {
-			return xfs_bmse_merge(ip, whichfork, offset_shift_fsb,
-					      *current_ext, gotp, adj_irecp,
-					      cur, logflags);
+			error = xfs_bmse_merge(ip, whichfork, offset_shift_fsb,
+					       *current_ext, gotp, adj_irecp,
+					       cur, logflags);
+			if (error)
+				return error;
+			adj_irec = got;
+			goto update_rmap;
 		}
 	} else {
 		startoff = got.br_startoff + offset_shift_fsb;
@@ -5693,9 +5966,10 @@ update_current_ext:
 		(*current_ext)--;
 	xfs_bmbt_set_startoff(gotp, startoff);
 	*logflags |= XFS_ILOG_CORE;
+	adj_irec = got;
 	if (!cur) {
 		*logflags |= XFS_ILOG_DEXT;
-		return 0;
+		goto update_rmap;
 	}
 
 	error = xfs_bmbt_lookup_eq(cur, got.br_startoff, got.br_startblock,
@@ -5705,8 +5979,18 @@ update_current_ext:
 	XFS_WANT_CORRUPTED_RETURN(mp, i == 1);
 
 	got.br_startoff = startoff;
-	return xfs_bmbt_update(cur, got.br_startoff, got.br_startblock,
-			       got.br_blockcount, got.br_state);
+	error = xfs_bmbt_update(cur, got.br_startoff, got.br_startblock,
+			got.br_blockcount, got.br_state);
+	if (error)
+		return error;
+
+update_rmap:
+	/* update reverse mapping */
+	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, &adj_irec);
+	if (error)
+		return error;
+	adj_irec.br_startoff = startoff;
+	return xfs_rmap_map_extent(mp, dfops, ip, whichfork, &adj_irec);
 }
 
 /*
@@ -5728,7 +6012,7 @@ xfs_bmap_shift_extents(
 	int			*done,
 	xfs_fileoff_t		stop_fsb,
 	xfs_fsblock_t		*firstblock,
-	struct xfs_bmap_free	*flist,
+	struct xfs_defer_ops	*dfops,
 	enum shift_direction	direction,
 	int			num_exts)
 {
@@ -5773,7 +6057,7 @@ xfs_bmap_shift_extents(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.flist = flist;
+		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5834,7 +6118,7 @@ xfs_bmap_shift_extents(
 	while (nexts++ < num_exts) {
 		error = xfs_bmse_shift_one(ip, whichfork, offset_shift_fsb,
 					   &current_ext, gotp, cur, &logflags,
-					   direction);
+					   direction, dfops);
 		if (error)
 			goto del_cursor;
 		/*
@@ -5882,7 +6166,7 @@ xfs_bmap_split_extent_at(
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		split_fsb,
 	xfs_fsblock_t		*firstfsb,
-	struct xfs_bmap_free	*free_list)
+	struct xfs_defer_ops	*dfops)
 {
 	int				whichfork = XFS_DATA_FORK;
 	struct xfs_btree_cur		*cur = NULL;
@@ -5944,7 +6228,7 @@ xfs_bmap_split_extent_at(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstfsb;
-		cur->bc_private.b.flist = free_list;
+		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 		error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
 				got.br_startblock,
@@ -5997,7 +6281,7 @@ xfs_bmap_split_extent_at(
 		int tmp_logflags; /* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, free_list,
+		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, dfops,
 				&cur, 0, &tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 	}
@@ -6021,7 +6305,7 @@ xfs_bmap_split_extent(
 {
 	struct xfs_mount        *mp = ip->i_mount;
 	struct xfs_trans        *tp;
-	struct xfs_bmap_free    free_list;
+	struct xfs_defer_ops    dfops;
 	xfs_fsblock_t           firstfsb;
 	int                     error;
 
@@ -6033,21 +6317,164 @@ xfs_bmap_split_extent(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-	xfs_bmap_init(&free_list, &firstfsb);
+	xfs_defer_init(&dfops, &firstfsb);
 
 	error = xfs_bmap_split_extent_at(tp, ip, split_fsb,
-			&firstfsb, &free_list);
+			&firstfsb, &dfops);
 	if (error)
 		goto out;
 
-	error = xfs_bmap_finish(&tp, &free_list, NULL);
+	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)
 		goto out;
 
 	return xfs_trans_commit(tp);
 
 out:
-	xfs_bmap_cancel(&free_list);
+	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
+
+/* Deferred mapping is only for real extents in the data fork. */
+static bool
+xfs_bmap_is_update_needed(
+	struct xfs_bmbt_irec	*bmap)
+{
+	return  bmap->br_startblock != HOLESTARTBLOCK &&
+		bmap->br_startblock != DELAYSTARTBLOCK;
+}
+
+/* Record a bmap intent. */
+static int
+__xfs_bmap_add(
+	struct xfs_mount		*mp,
+	struct xfs_defer_ops		*dfops,
+	enum xfs_bmap_intent_type	type,
+	struct xfs_inode		*ip,
+	int				whichfork,
+	struct xfs_bmbt_irec		*bmap)
+{
+	int				error;
+	struct xfs_bmap_intent		*bi;
+
+	trace_xfs_bmap_defer(mp,
+			XFS_FSB_TO_AGNO(mp, bmap->br_startblock),
+			type,
+			XFS_FSB_TO_AGBNO(mp, bmap->br_startblock),
+			ip->i_ino, whichfork,
+			bmap->br_startoff,
+			bmap->br_blockcount,
+			bmap->br_state);
+
+	bi = kmem_alloc(sizeof(struct xfs_bmap_intent), KM_SLEEP | KM_NOFS);
+	INIT_LIST_HEAD(&bi->bi_list);
+	bi->bi_type = type;
+	bi->bi_owner = ip;
+	bi->bi_whichfork = whichfork;
+	bi->bi_bmap = *bmap;
+
+	error = xfs_defer_join(dfops, bi->bi_owner);
+	if (error) {
+		kmem_free(bi);
+		return error;
+	}
+
+	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
+	return 0;
+}
+
+/* Map an extent into a file. */
+int
+xfs_bmap_map_extent(
+	struct xfs_mount	*mp,
+	struct xfs_defer_ops	*dfops,
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*PREV)
+{
+	if (!xfs_bmap_is_update_needed(PREV))
+		return 0;
+
+	return __xfs_bmap_add(mp, dfops, XFS_BMAP_MAP, ip,
+			XFS_DATA_FORK, PREV);
+}
+
+/* Unmap an extent out of a file. */
+int
+xfs_bmap_unmap_extent(
+	struct xfs_mount	*mp,
+	struct xfs_defer_ops	*dfops,
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*PREV)
+{
+	if (!xfs_bmap_is_update_needed(PREV))
+		return 0;
+
+	return __xfs_bmap_add(mp, dfops, XFS_BMAP_UNMAP, ip,
+			XFS_DATA_FORK, PREV);
+}
+
+/*
+ * Process one of the deferred bmap operations.  We pass back the
+ * btree cursor to maintain our lock on the bmapbt between calls.
+ */
+int
+xfs_bmap_finish_one(
+	struct xfs_trans		*tp,
+	struct xfs_defer_ops		*dfops,
+	struct xfs_inode		*ip,
+	enum xfs_bmap_intent_type	type,
+	int				whichfork,
+	xfs_fileoff_t			startoff,
+	xfs_fsblock_t			startblock,
+	xfs_filblks_t			blockcount,
+	xfs_exntst_t			state)
+{
+	struct xfs_bmbt_irec		bmap;
+	int				nimaps = 1;
+	xfs_fsblock_t			firstfsb;
+	int				flags = XFS_BMAPI_REMAP;
+	int				done;
+	int				error = 0;
+
+	bmap.br_startblock = startblock;
+	bmap.br_startoff = startoff;
+	bmap.br_blockcount = blockcount;
+	bmap.br_state = state;
+
+	trace_xfs_bmap_deferred(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
+			XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
+			ip->i_ino, whichfork, startoff, blockcount, state);
+
+	if (whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK)
+		return -EFSCORRUPTED;
+	if (whichfork == XFS_ATTR_FORK)
+		flags |= XFS_BMAPI_ATTRFORK;
+
+	if (XFS_TEST_ERROR(false, tp->t_mountp,
+			XFS_ERRTAG_BMAP_FINISH_ONE,
+			XFS_RANDOM_BMAP_FINISH_ONE))
+		return -EIO;
+
+	switch (type) {
+	case XFS_BMAP_MAP:
+		firstfsb = bmap.br_startblock;
+		error = xfs_bmapi_write(tp, ip, bmap.br_startoff,
+					bmap.br_blockcount, flags, &firstfsb,
+					bmap.br_blockcount, &bmap, &nimaps,
+					dfops);
+		break;
+	case XFS_BMAP_UNMAP:
+		error = xfs_bunmapi(tp, ip, bmap.br_startoff,
+				bmap.br_blockcount, flags, 1, &firstfsb,
+				dfops, &done);
+		ASSERT(done);
+		break;
+	default:
+		ASSERT(0);
+		error = -EFSCORRUPTED;
+	}
+
+	return error;
+}