Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

* 'for-linus' of git://oss.sgi.com/xfs/xfs:
  xfs: correctly decrement the extent buffer index in xfs_bmap_del_extent
  xfs: check for valid indices in xfs_iext_get_ext and xfs_iext_idx_to_irec
  xfs: fix up asserts in xfs_iflush_fork
  xfs: do not do pointer arithmetic on extent records
  xfs: do not use unchecked extent indices in xfs_bunmapi
  xfs: do not use unchecked extent indices in xfs_bmapi
  xfs: do not use unchecked extent indices in xfs_bmap_add_extent_*
  xfs: remove if_lastex
  xfs: remove the unused XFS_BMAPI_RSVBLOCKS flag
  xfs: do not discard alloc btree blocks
  xfs: add online discard support

15 files changed, 366 insertions, 318 deletions

diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt
index 7bff3e4f35d..3fc0c31a6f5 100644
--- a/Documentation/filesystems/xfs.txt
+++ b/Documentation/filesystems/xfs.txt
@@ -39,6 +39,12 @@ When mounting an XFS filesystem, the following options are accepted.
 	drive level write caching to be enabled, for devices that
 	support write barriers.
 
+  discard
+	Issue command to let the block device reclaim space freed by the
+	filesystem.  This is useful for SSD devices, thinly provisioned
+	LUNs and virtual machine images, but may have a performance
+	impact.  This option is incompatible with the nodelaylog option.
+
   dmapi
 	Enable the DMAPI (Data Management API) event callouts.
 	Use with the "mtpt" option.
diff --git a/fs/xfs/linux-2.6/xfs_discard.c b/fs/xfs/linux-2.6/xfs_discard.c
index d61611c8801..244e797dae3 100644
--- a/fs/xfs/linux-2.6/xfs_discard.c
+++ b/fs/xfs/linux-2.6/xfs_discard.c
@@ -191,3 +191,32 @@ xfs_ioc_trim(
 		return -XFS_ERROR(EFAULT);
 	return 0;
 }
+
+int
+xfs_discard_extents(
+	struct xfs_mount	*mp,
+	struct list_head	*list)
+{
+	struct xfs_busy_extent	*busyp;
+	int			error = 0;
+
+	list_for_each_entry(busyp, list, list) {
+		trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
+					 busyp->length);
+
+		error = -blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
+				XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
+				XFS_FSB_TO_BB(mp, busyp->length),
+				GFP_NOFS, 0);
+		if (error && error != EOPNOTSUPP) {
+			xfs_info(mp,
+	 "discard failed for extent [0x%llu,%u], error %d",
+				 (unsigned long long)busyp->bno,
+				 busyp->length,
+				 error);
+			return error;
+		}
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/linux-2.6/xfs_discard.h b/fs/xfs/linux-2.6/xfs_discard.h
index e82b6dd3e12..344879aea64 100644
--- a/fs/xfs/linux-2.6/xfs_discard.h
+++ b/fs/xfs/linux-2.6/xfs_discard.h
@@ -2,7 +2,9 @@
 #define XFS_DISCARD_H 1
 
 struct fstrim_range;
+struct list_head;
 
 extern int	xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *);
+extern int	xfs_discard_extents(struct xfs_mount *, struct list_head *);
 
 #endif /* XFS_DISCARD_H */
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index b0aa59e51fd..98b9c91fcdf 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -110,8 +110,10 @@ mempool_t *xfs_ioend_pool;
 #define MNTOPT_GQUOTANOENF "gqnoenforce"/* group quota limit enforcement */
 #define MNTOPT_PQUOTANOENF "pqnoenforce"/* project quota limit enforcement */
 #define MNTOPT_QUOTANOENF  "qnoenforce"	/* same as uqnoenforce */
-#define MNTOPT_DELAYLOG   "delaylog"	/* Delayed loging enabled */
-#define MNTOPT_NODELAYLOG "nodelaylog"	/* Delayed loging disabled */
+#define MNTOPT_DELAYLOG    "delaylog"	/* Delayed logging enabled */
+#define MNTOPT_NODELAYLOG  "nodelaylog"	/* Delayed logging disabled */
+#define MNTOPT_DISCARD	   "discard"	/* Discard unused blocks */
+#define MNTOPT_NODISCARD   "nodiscard"	/* Do not discard unused blocks */
 
 /*
  * Table driven mount option parser.
@@ -355,6 +357,10 @@ xfs_parseargs(
 			mp->m_flags |= XFS_MOUNT_DELAYLOG;
 		} else if (!strcmp(this_char, MNTOPT_NODELAYLOG)) {
 			mp->m_flags &= ~XFS_MOUNT_DELAYLOG;
+		} else if (!strcmp(this_char, MNTOPT_DISCARD)) {
+			mp->m_flags |= XFS_MOUNT_DISCARD;
+		} else if (!strcmp(this_char, MNTOPT_NODISCARD)) {
+			mp->m_flags &= ~XFS_MOUNT_DISCARD;
 		} else if (!strcmp(this_char, "ihashsize")) {
 			xfs_warn(mp,
 	"ihashsize no longer used, option is deprecated.");
@@ -388,6 +394,13 @@ xfs_parseargs(
 		return EINVAL;
 	}
 
+	if ((mp->m_flags & XFS_MOUNT_DISCARD) &&
+	    !(mp->m_flags & XFS_MOUNT_DELAYLOG)) {
+		xfs_warn(mp,
+	"the discard option is incompatible with the nodelaylog option");
+		return EINVAL;
+	}
+
 #ifndef CONFIG_XFS_QUOTA
 	if (XFS_IS_QUOTA_RUNNING(mp)) {
 		xfs_warn(mp, "quota support not available in this kernel.");
@@ -488,6 +501,7 @@ xfs_showargs(
 		{ XFS_MOUNT_FILESTREAMS,	"," MNTOPT_FILESTREAM },
 		{ XFS_MOUNT_GRPID,		"," MNTOPT_GRPID },
 		{ XFS_MOUNT_DELAYLOG,		"," MNTOPT_DELAYLOG },
+		{ XFS_MOUNT_DISCARD,		"," MNTOPT_DISCARD },
 		{ 0, NULL }
 	};
 	static struct proc_xfs_info xfs_info_unset[] = {
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index da0a561ffba..6530769a999 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -187,6 +187,9 @@ struct xfs_busy_extent {
 	xfs_agnumber_t	agno;
 	xfs_agblock_t	bno;
 	xfs_extlen_t	length;
+	unsigned int	flags;
+#define XFS_ALLOC_BUSY_DISCARDED	0x01	/* undergoing a discard op. */
+#define XFS_ALLOC_BUSY_SKIP_DISCARD	0x02	/* do not discard */
 };
 
 /*
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index acdced86413..95862bbff56 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -2469,7 +2469,7 @@ xfs_free_extent(
 
 	error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0);
 	if (!error)
-		xfs_alloc_busy_insert(tp, args.agno, args.agbno, len);
+		xfs_alloc_busy_insert(tp, args.agno, args.agbno, len, 0);
 error0:
 	xfs_perag_put(args.pag);
 	return error;
@@ -2480,7 +2480,8 @@ xfs_alloc_busy_insert(
 	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
-	xfs_extlen_t		len)
+	xfs_extlen_t		len,
+	unsigned int		flags)
 {
 	struct xfs_busy_extent	*new;
 	struct xfs_busy_extent	*busyp;
@@ -2504,6 +2505,7 @@ xfs_alloc_busy_insert(
 	new->bno = bno;
 	new->length = len;
 	INIT_LIST_HEAD(&new->list);
+	new->flags = flags;
 
 	/* trace before insert to be able to see failed inserts */
 	trace_xfs_alloc_busy(tp->t_mountp, agno, bno, len);
@@ -2609,6 +2611,18 @@ xfs_alloc_busy_update_extent(
 	xfs_agblock_t		bend = bbno + busyp->length;
 
 	/*
+	 * This extent is currently being discarded.  Give the thread
+	 * performing the discard a chance to mark the extent unbusy
+	 * and retry.
+	 */
+	if (busyp->flags & XFS_ALLOC_BUSY_DISCARDED) {
+		spin_unlock(&pag->pagb_lock);
+		delay(1);
+		spin_lock(&pag->pagb_lock);
+		return false;
+	}
+
+	/*
 	 * If there is a busy extent overlapping a user allocation, we have
 	 * no choice but to force the log and retry the search.
 	 *
@@ -2813,7 +2827,8 @@ restart:
 		 * If this is a metadata allocation, try to reuse the busy
 		 * extent instead of trimming the allocation.
 		 */
-		if (!args->userdata) {
+		if (!args->userdata &&
+		    !(busyp->flags & XFS_ALLOC_BUSY_DISCARDED)) {
 			if (!xfs_alloc_busy_update_extent(args->mp, args->pag,
 							  busyp, fbno, flen,
 							  false))
@@ -2979,10 +2994,16 @@ xfs_alloc_busy_clear_one(
 	kmem_free(busyp);
 }
 
+/*
+ * Remove all extents on the passed in list from the busy extents tree.
+ * If do_discard is set skip extents that need to be discarded, and mark
+ * these as undergoing a discard operation instead.
+ */
 void
 xfs_alloc_busy_clear(
 	struct xfs_mount	*mp,
-	struct list_head	*list)
+	struct list_head	*list,
+	bool			do_discard)
 {
 	struct xfs_busy_extent	*busyp, *n;
 	struct xfs_perag	*pag = NULL;
@@ -2999,7 +3020,11 @@ xfs_alloc_busy_clear(
 			agno = busyp->agno;
 		}
 
-		xfs_alloc_busy_clear_one(mp, pag, busyp);
+		if (do_discard && busyp->length &&
+		    !(busyp->flags & XFS_ALLOC_BUSY_SKIP_DISCARD))
+			busyp->flags = XFS_ALLOC_BUSY_DISCARDED;
+		else
+			xfs_alloc_busy_clear_one(mp, pag, busyp);
 	}
 
 	if (pag) {
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 240ad288f2f..2f52b924be7 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -137,10 +137,11 @@ xfs_alloc_longest_free_extent(struct xfs_mount *mp,
 #ifdef __KERNEL__
 void
 xfs_alloc_busy_insert(struct xfs_trans *tp, xfs_agnumber_t agno,
-	xfs_agblock_t bno, xfs_extlen_t len);
+	xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags);
 
 void
-xfs_alloc_busy_clear(struct xfs_mount *mp, struct list_head *list);
+xfs_alloc_busy_clear(struct xfs_mount *mp, struct list_head *list,
+	bool do_discard);
 
 int
 xfs_alloc_busy_search(struct xfs_mount *mp, xfs_agnumber_t agno,
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index 8b469d53599..2b3518826a6 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -120,7 +120,8 @@ xfs_allocbt_free_block(
 	if (error)
 		return error;
 
-	xfs_alloc_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1);
+	xfs_alloc_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
+			      XFS_ALLOC_BUSY_SKIP_DISCARD);
 	xfs_trans_agbtree_delta(cur->bc_tp, -1);
 	return 0;
 }
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index fa00788de2f..e546a33214c 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -89,36 +89,19 @@ xfs_bmap_add_attrfork_local(
 	int			*flags);	/* inode logging flags */
 
 /*
- * Called by xfs_bmapi to update file extent records and the btree
- * after allocating space (or doing a delayed allocation).
- */
-STATIC int				/* error */
-xfs_bmap_add_extent(
-	xfs_inode_t		*ip,	/* incore inode pointer */
-	xfs_extnum_t		idx,	/* extent number to update/insert */
-	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
-	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
-	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
-	xfs_bmap_free_t		*flist,	/* list of extents to be freed */
-	int			*logflagsp, /* inode logging flags */
-	int			whichfork, /* data or attr fork */
-	int			rsvd);	/* OK to allocate reserved blocks */
-
-/*
  * Called by xfs_bmap_add_extent to handle cases converting a delayed
  * allocation to a real allocation.
  */
 STATIC int				/* error */
 xfs_bmap_add_extent_delay_real(
 	xfs_inode_t		*ip,	/* incore inode pointer */
-	xfs_extnum_t		idx,	/* extent number to update/insert */
+	xfs_extnum_t		*idx,	/* extent number to update/insert */
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
 	xfs_filblks_t		*dnew,	/* new delayed-alloc indirect blocks */
 	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
 	xfs_bmap_free_t		*flist,	/* list of extents to be freed */
-	int			*logflagsp, /* inode logging flags */
-	int			rsvd);	/* OK to allocate reserved blocks */
+	int			*logflagsp); /* inode logging flags */
 
 /*
  * Called by xfs_bmap_add_extent to handle cases converting a hole
@@ -127,10 +110,9 @@ xfs_bmap_add_extent_delay_real(
 STATIC int				/* error */
 xfs_bmap_add_extent_hole_delay(
 	xfs_inode_t		*ip,	/* incore inode pointer */
-	xfs_extnum_t		idx,	/* extent number to update/insert */
+	xfs_extnum_t		*idx,	/* extent number to update/insert */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
-	int			*logflagsp,/* inode logging flags */
-	int			rsvd);	/* OK to allocate reserved blocks */
+	int			*logflagsp); /* inode logging flags */
 
 /*
  * Called by xfs_bmap_add_extent to handle cases converting a hole
@@ -139,7 +121,7 @@ xfs_bmap_add_extent_hole_delay(
 STATIC int				/* error */
 xfs_bmap_add_extent_hole_real(
 	xfs_inode_t		*ip,	/* incore inode pointer */
-	xfs_extnum_t		idx,	/* extent number to update/insert */
+	xfs_extnum_t		*idx,	/* extent number to update/insert */
 	xfs_btree_cur_t		*cur,	/* if null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
 	int			*logflagsp, /* inode logging flags */
@@ -152,7 +134,7 @@ xfs_bmap_add_extent_hole_real(
 STATIC int				/* error */
 xfs_bmap_add_extent_unwritten_real(
 	xfs_inode_t		*ip,	/* incore inode pointer */
-	xfs_extnum_t		idx,	/* extent number to update/insert */
+	xfs_extnum_t		*idx,	/* extent number to update/insert */
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
 	int			*logflagsp); /* inode logging flags */
@@ -180,22 +162,6 @@ xfs_bmap_btree_to_extents(
 	int			whichfork); /* data or attr fork */
 
 /*
- * Called by xfs_bmapi to update file extent records and the btree
- * after removing space (or undoing a delayed allocation).
- */
-STATIC int				/* error */
-xfs_bmap_del_extent(
-	xfs_inode_t		*ip,	/* incore inode pointer */
-	xfs_trans_t		*tp,	/* current trans pointer */
-	xfs_extnum_t		idx,	/* extent number to update/insert */
-	xfs_bmap_free_t		*flist,	/* list of extents to be freed */
-	xfs_btree_cur_t		*cur,	/* if null, not a btree */
-	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
-	int			*logflagsp,/* inode logging flags */
-	int			whichfork, /* data or attr fork */
-	int			rsvd);	 /* OK to allocate reserved blocks */
-
-/*
  * Remove the entry "free" from the free item list.  Prev points to the
  * previous entry, unless "free" is the head of the list.
  */
@@ -474,14 +440,13 @@ xfs_bmap_add_attrfork_local(
 STATIC int				/* error */
 xfs_bmap_add_extent(
 	xfs_inode_t		*ip,	/* incore inode pointer */
-	xfs_extnum_t		idx,	/* extent number to update/insert */
+	xfs_extnum_t		*idx,	/* extent number to update/insert */
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
 	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
 	xfs_bmap_free_t		*flist,	/* list of extents to be freed */
 	int			*logflagsp, /* inode logging flags */
-	int			whichfork, /* data or attr fork */
-	int			rsvd)	/* OK to use reserved data blocks */
+	int			whichfork) /* data or attr fork */
 {
 	xfs_btree_cur_t		*cur;	/* btree cursor or null */
 	xfs_filblks_t		da_new; /* new count del alloc blocks used */
@@ -492,23 +457,27 @@ xfs_bmap_add_extent(
 	xfs_extnum_t		nextents; /* number of extents in file now */
 
 	XFS_STATS_INC(xs_add_exlist);
+
 	cur = *curp;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
-	ASSERT(idx <= nextents);
 	da_old = da_new = 0;
 	error = 0;
+
+	ASSERT(*idx >= 0);
+	ASSERT(*idx <= nextents);
+
 	/*
 	 * This is the first extent added to a new/empty file.
 	 * Special case this one, so other routines get to assume there are
 	 * already extents in the list.
 	 */
 	if (nextents == 0) {
-		xfs_iext_insert(ip, 0, 1, new,
+		xfs_iext_insert(ip, *idx, 1, new,
 				whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0);
 
 		ASSERT(cur == NULL);
-		ifp->if_lastex = 0;
+
 		if (!isnullstartblock(new->br_startblock)) {
 			XFS_IFORK_NEXT_SET(ip, whichfork, 1);
 			logflags = XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
@@ -522,27 +491,25 @@ xfs_bmap_add_extent(
 		if (cur)
 			ASSERT((cur->bc_private.b.flags &
 				XFS_BTCUR_BPRV_WASDEL) == 0);
-		if ((error = xfs_bmap_add_extent_hole_delay(ip, idx, new,
-				&logflags, rsvd)))
-			goto done;
+		error = xfs_bmap_add_extent_hole_delay(ip, idx, new,
+						       &logflags);
 	}
 	/*
 	 * Real allocation off the end of the file.
 	 */
-	else if (idx == nextents) {
+	else if (*idx == nextents) {
 		if (cur)
 			ASSERT((cur->bc_private.b.flags &
 				XFS_BTCUR_BPRV_WASDEL) == 0);
-		if ((error = xfs_bmap_add_extent_hole_real(ip, idx, cur, new,
-				&logflags, whichfork)))
-			goto done;
+		error = xfs_bmap_add_extent_hole_real(ip, idx, cur, new,
+				&logflags, whichfork);
 	} else {
 		xfs_bmbt_irec_t	prev;	/* old extent at offset idx */
 
 		/*
 		 * Get the record referred to by idx.
 		 */
-		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &prev);
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx), &prev);
 		/*
 		 * If it's a real allocation record, and the new allocation ends
 		 * after the start of the referred to record, then we're filling
@@ -557,22 +524,18 @@ xfs_bmap_add_extent(
 				if (cur)
 					ASSERT(cur->bc_private.b.flags &
 						XFS_BTCUR_BPRV_WASDEL);
-				if ((error = xfs_bmap_add_extent_delay_real(ip,
-					idx, &cur, new, &da_new, first, flist,
-					&logflags, rsvd)))
-					goto done;
-			} else if (new->br_state == XFS_EXT_NORM) {
-				ASSERT(new->br_state == XFS_EXT_NORM);
-				if ((error = xfs_bmap_add_extent_unwritten_real(
-					ip, idx, &cur, new, &logflags)))
-					goto done;
+				error = xfs_bmap_add_extent_delay_real(ip,
+						idx, &cur, new, &da_new,
+						first, flist, &logflags);
 			} else {
-				ASSERT(new->br_state == XFS_EXT_UNWRITTEN);
-				if ((error = xfs_bmap_add_extent_unwritten_real(
-					ip, idx, &cur, new, &logflags)))
+				ASSERT(new->br_state == XFS_EXT_NORM ||
+				       new->br_state == XFS_EXT_UNWRITTEN);
+
+				error = xfs_bmap_add_extent_unwritten_real(ip,
+						idx, &cur, new, &logflags);
+				if (error)
 					goto done;
 			}
-			ASSERT(*curp == cur || *curp == NULL);
 		}
 		/*
 		 * Otherwise we're filling in a hole with an allocation.
@@ -581,13 +544,15 @@ xfs_bmap_add_extent(
 			if (cur)
 				ASSERT((cur->bc_private.b.flags &
 					XFS_BTCUR_BPRV_WASDEL) == 0);
-			if ((error = xfs_bmap_add_extent_hole_real(ip, idx, cur,
-					new, &logflags, whichfork)))
-				goto done;
+			error = xfs_bmap_add_extent_hole_real(ip, idx, cur,
+					new, &logflags, whichfork);
 		}
 	}
 
+	if (error)
+		goto done;
 	ASSERT(*curp == cur || *curp == NULL);
+
 	/*
 	 * Convert to a btree if necessary.
 	 */
@@ -615,7 +580,7 @@ xfs_bmap_add_extent(
 		ASSERT(nblks <= da_old);
 		if (nblks < da_old)
 			xfs_icsb_modify_counters(ip->i_mount, XFS_SBS_FDBLOCKS,
-				(int64_t)(da_old - nblks), rsvd);
+				(int64_t)(da_old - nblks), 0);
 	}
 	/*
 	 * Clear out the allocated field, done with it now in any case.
@@ -640,14 +605,13 @@ done:
 STATIC int				/* error */
 xfs_bmap_add_extent_delay_real(
 	xfs_inode_t		*ip,	/* incore inode pointer */
-	xfs_extnum_t		idx,	/* extent number to update/insert */
+	xfs_extnum_t		*idx,	/* extent number to update/insert */
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
 	xfs_filblks_t		*dnew,	/* new delayed-alloc indirect blocks */
 	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
 	xfs_bmap_free_t		*flist,	/* list of extents to be freed */
-	int			*logflagsp, /* inode logging flags */
-	int			rsvd)	/* OK to use reserved data block allocation */
+	int			*logflagsp) /* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;	/* btree cursor */
 	int			diff;	/* temp value */
@@ -673,7 +637,7 @@ xfs_bmap_add_extent_delay_real(
 	 */
 	cur = *curp;
 	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
-	ep = xfs_iext_get_ext(ifp, idx);
+	ep = xfs_iext_get_ext(ifp, *idx);
 	xfs_bmbt_get_all(ep, &PREV);
 	new_endoff = new->br_startoff + new->br_blockcount;
 	ASSERT(PREV.br_startoff <= new->br_startoff);
@@ -692,9 +656,9 @@ xfs_bmap_add_extent_delay_real(
 	 * Check and set flags if this segment has a left neighbor.
 	 * Don't set contiguous if the combined extent would be too large.
 	 */
-	if (idx > 0) {
+	if (*idx > 0) {
 		state |= BMAP_LEFT_VALID;
-		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx - 1), &LEFT);
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx - 1), &LEFT);
 
 		if (isnullstartblock(LEFT.br_startblock))
 			state |= BMAP_LEFT_DELAY;
@@ -712,9 +676,9 @@ xfs_bmap_add_extent_delay_real(
 	 * Don't set contiguous if the combined extent would be too large.
 	 * Also check for all-three-contiguous being too large.
 	 */
-	if (idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
+	if (*idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
 		state |= BMAP_RIGHT_VALID;
-		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx + 1), &RIGHT);
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx + 1), &RIGHT);
 
 		if (isnullstartblock(RIGHT.br_startblock))
 			state |= BMAP_RIGHT_DELAY;
@@ -745,14 +709,14 @@ xfs_bmap_add_extent_delay_real(
 		 * Filling in all of a previously delayed allocation extent.
 		 * The left and right neighbors are both contiguous with new.
 		 */
-		trace_xfs_bmap_pre_update(ip, idx - 1, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, idx - 1),
+		--*idx;
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx),
 			LEFT.br_blockcount + PREV.br_blockcount +
 			RIGHT.br_blockcount);
-		trace_xfs_bmap_post_update(ip, idx - 1, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
-		xfs_iext_remove(ip, idx, 2, state);
-		ip->i_df.if_lastex = idx - 1;
+		xfs_iext_remove(ip, *idx + 1, 2, state);
 		ip->i_d.di_nextents--;
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
@@ -784,13 +748,14 @@ xfs_bmap_add_extent_delay_real(
 		 * Filling in all of a previously delayed allocation extent.
 		 * The left neighbor is contiguous, the right is not.
 		 */
-		trace_xfs_bmap_pre_update(ip, idx - 1, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, idx - 1),
+		--*idx;
+
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx),
 			LEFT.br_blockcount + PREV.br_blockcount);
-		trace_xfs_bmap_post_update(ip, idx - 1, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
-		ip->i_df.if_lastex = idx - 1;
-		xfs_iext_remove(ip, idx, 1, state);
+		xfs_iext_remove(ip, *idx + 1, 1, state);
 		if (cur == NULL)
 			rval = XFS_ILOG_DEXT;
 		else {
@@ -814,14 +779,13 @@ xfs_bmap_add_extent_delay_real(
 		 * Filling in all of a previously delayed allocation extent.
 		 * The right neighbor is contiguous, the left is not.
 		 */
-		trace_xfs_bmap_pre_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
 		xfs_bmbt_set_startblock(ep, new->br_startblock);
 		xfs_bmbt_set_blockcount(ep,
 			PREV.br_blockcount + RIGHT.br_blockcount);
-		trace_xfs_bmap_post_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
-		ip->i_df.if_lastex = idx;
-		xfs_iext_remove(ip, idx + 1, 1, state);
+		xfs_iext_remove(ip, *idx + 1, 1, state);
 		if (cur == NULL)
 			rval = XFS_ILOG_DEXT;
 		else {
@@ -837,6 +801,7 @@ xfs_bmap_add_extent_delay_real(
 					RIGHT.br_blockcount, PREV.br_state)))
 				goto done;
 		}
+
 		*dnew = 0;
 		break;
 
@@ -846,11 +811,10 @@ xfs_bmap_add_extent_delay_real(
 		 * Neither the left nor right neighbors are contiguous with
 		 * the new one.
 		 */
-		trace_xfs_bmap_pre_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
 		xfs_bmbt_set_startblock(ep, new->br_startblock);
-		trace_xfs_bmap_post_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
-		ip->i_df.if_lastex = idx;
 		ip->i_d.di_nextents++;
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
@@ -866,6 +830,7 @@ xfs_bmap_add_extent_delay_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
+
 		*dnew = 0;
 		break;
 
@@ -874,17 +839,16 @@ xfs_bmap_add_extent_delay_real(
 		 * Filling in the first part of a previous delayed allocation.
 		 * The left neighbor is contiguous.
 		 */
-		trace_xfs_bmap_pre_update(ip, idx - 1, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, idx - 1),
+		trace_xfs_bmap_pre_update(ip, *idx - 1, state, _THIS_IP_);
+		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx - 1),
 			LEFT.br_blockcount + new->br_blockcount);
 		xfs_bmbt_set_startoff(ep,
 			PREV.br_startoff + new->br_blockcount);
-		trace_xfs_bmap_post_update(ip, idx - 1, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx - 1, state, _THIS_IP_);
 
 		temp = PREV.br_blockcount - new->br_blockcount;
-		trace_xfs_bmap_pre_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
 		xfs_bmbt_set_blockcount(ep, temp);
-		ip->i_df.if_lastex = idx - 1;
 		if (cur == NULL)
 			rval = XFS_ILOG_DEXT;
 		else {
@@ -904,7 +868,9 @@ xfs_bmap_add_extent_delay_real(
 		temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
 			startblockval(PREV.br_startblock));
 		xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-		trace_xfs_bmap_post_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+
+		--*idx;
 		*dnew = temp;
 		break;
 
@@ -913,12 +879,11 @@ xfs_bmap_add_extent_delay_real(
 		 * Filling in the first part of a previous delayed allocation.
 		 * The left neighbor is not contiguous.
 		 */
-		trace_xfs_bmap_pre_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
 		xfs_bmbt_set_startoff(ep, new_endoff);
 		temp = PREV.br_blockcount - new->br_blockcount;
 		xfs_bmbt_set_blockcount(ep, temp);
-		xfs_iext_insert(ip, idx, 1, new, state);
-		ip->i_df.if_lastex = idx;
+		xfs_iext_insert(ip, *idx, 1, new, state);
 		ip->i_d.di_nextents++;
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
@@ -946,9 +911,10 @@ xfs_bmap_add_extent_delay_real(
 		temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
 			startblockval(PREV.br_startblock) -
 			(cur ? cur->bc_private.b.allocated : 0));
-		ep = xfs_iext_get_ext(ifp, idx + 1);
+		ep = xfs_iext_get_ext(ifp, *idx + 1);
 		xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-		trace_xfs_bmap_post_update(ip, idx + 1, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx + 1, state, _THIS_IP_);
+
 		*dnew = temp;
 		break;
 
@@ -958,15 +924,13 @@ xfs_bmap_add_extent_delay_real(
 		 * The right neighbor is contiguous with the new allocation.
 		 */
 		temp = PREV.br_blockcount - new->br_blockcount;
-		trace_xfs_bmap_pre_update(ip, idx, state, _THIS_IP_);
-		trace_xfs_bmap_pre_update(ip, idx + 1, state, _THIS_IP_);
+		trace_xfs_bmap_pre_update(ip, *idx + 1, state, _THIS_IP_);
 		xfs_bmbt_set_blockcount(ep, temp);
-		xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, idx + 1),
+		xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, *idx + 1),
 			new->br_startoff, new->br_startblock,
 			new->br_blockcount + RIGHT.br_blockcount,
 			RIGHT.br_state);
-		trace_xfs_bmap_post_update(ip, idx + 1, state, _THIS_IP_);
-		ip->i_df.if_lastex = idx + 1;
+		trace_xfs_bmap_post_update(ip, *idx + 1, state, _THIS_IP_);
 		if (cur == NULL)
 			rval = XFS_ILOG_DEXT;
 		else {
@@ -983,10 +947,14 @@ xfs_bmap_add_extent_delay_real(
 					RIGHT.br_state)))
 				goto done;
 		}
+
 		temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
 			startblockval(PREV.br_startblock));
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
 		xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-		trace_xfs_bmap_post_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+
+		++*idx;
 		*dnew = temp;
 		break;
 
@@ -996,10 +964,9 @@ xfs_bmap_add_extent_delay_real(
 		 * The right neighbor is not contiguous.
 		 */
 		temp = PREV.br_blockcount - new->br_blockcount;
-		trace_xfs_bmap_pre_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
 		xfs_bmbt_set_blockcount(ep, temp);
-		xfs_iext_insert(ip, idx + 1, 1, new, state);
-		ip->i_df.if_lastex = idx + 1;
+		xfs_iext_insert(ip, *idx + 1, 1, new, state);
 		ip->i_d.di_nextents++;
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
@@ -1027,9 +994,11 @@ xfs_bmap_add_extent_delay_real(
 		temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
 			startblockval(PREV.br_startblock) -
 			(cur ? cur->bc_private.b.allocated : 0));
-		ep = xfs_iext_get_ext(ifp, idx);
+		ep = xfs_iext_get_ext(ifp, *idx);
 		xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-		trace_xfs_bmap_post_update(ip, idx, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+
+		++*idx;
 		*dnew = temp;
 		break;
 
@@ -1056,7 +1025,7 @@ xfs_bmap_add_extent_delay_real(
 		 */
 		temp = new->br_startoff - PREV.br_startoff;
 		temp2 = PREV.br_startoff + PREV.br_blockcount - new_endoff;
-		trace_xfs_bmap_pre_update(ip, idx, 0, _THIS_IP_);
+		trace_xfs_bmap_pre_update(ip, *idx, 0, _THIS_IP_);
 		xfs_bmbt_set_blockcount(ep, temp);	/* truncate PREV */
 		LEFT = *new;
 		RIGHT.br_state = PREV.br_state;
@@ -1065,8 +1034,7 @@ xfs_bmap_add_extent_delay_real(
 		RIGHT.br_startoff = new_endoff;
 		RIGHT.br_blockcount = temp2;
 		/* insert LEFT (r[0]) and RIGHT (r[1]) at the same time */
-		xfs_iext_insert(ip, idx + 1, 2, &LEFT, state);
-		ip->i_df.if_lastex = idx + 1;
+		xfs_iext_insert(ip, *idx + 1, 2, &LEFT, state);
 		ip->i_d.di_nextents++;
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
@@ -1097,7 +1065,7 @@ xfs_bmap_add_extent_delay_real(
 			(cur ? cur->bc_private.b.allocated : 0));
 		if (diff > 0 &&
 		    xfs_icsb_modify_counters(ip->i_mount, XFS_SBS_FDBLOCKS,
-					     -((int64_t)diff), rsvd)) {
+					     -((int64_t)diff), 0)) {
 			/*
 			 * Ick gross gag me with a spoon.
 			 */
@@ -1109,7 +1077,7 @@ xfs_bmap_add_extent_delay_real(
 					if (!diff ||
 					    !xfs_icsb_modify_counters(ip->i_mount,
 						    XFS_SBS_FDBLOCKS,
-						    -((int64_t)diff), rsvd))
+						    -((int64_t)diff), 0))
 						break;
 				}
 				if (temp2) {
@@ -1118,18 +1086,20 @@ xfs_bmap_add_extent_delay_real(
 					if (!diff ||
 					    !xfs_icsb_modify_counters(ip->i_mount,
 						    XFS_SBS_FDBLOCKS,
-						    -((int64_t)diff), rsvd))
+						    -((int64_t)diff), 0))
 						break;
 				}
 			}
 		}
-		ep = xfs_iext_get_ext(ifp, idx);
+		ep = xfs_iext_get_ext(ifp, *idx);
 		xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-		trace_xfs_bmap_post_update(ip, idx, state, _THIS_IP_);
-		trace_xfs_bmap_pre_update(ip, idx + 2, state, _THIS_IP_);
-		xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, idx + 2),
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		trace_xfs_bmap_pre_update(ip, *idx + 2, state, _THIS_IP_);
+		xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, *idx + 2),
 			nullstartblock((int)temp2));
-		trace_xfs_bmap_post_update(ip, idx + 2, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx + 2, state, _THIS_IP_);
+
+		++*idx;
 		*dnew = temp + temp2;
 		break;
 
@@ -1161,7 +1131,7 @@ done:
 STATIC int				/* error */
 xfs_bmap_add_extent_unwritten_real(
 	xfs_inode_t		*ip,	/* incore inode pointer */
-	xfs_extnum_t		idx,	/* extent number to update/insert */
+	xfs_extnum_t		*idx,	/* extent number to update/insert */
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
 	int			*logflagsp) /* inode logging flags */
@@ -1188,7 +1158,7 @@ xfs_bmap_add_extent_unwritten_real(
 	error = 0;
 	cur = *curp;
 	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
-	ep = xfs_iext_get_ext(ifp, idx);
+	ep = xfs_iext_get_ext(ifp, *idx);
 	xfs_bmbt_get_all(ep, &PREV);
 	newext = new->br_state;
 	oldext = (newext == XFS_EXT_UNWRITTEN) ?
@@ -1211,9 +1181,9 @@ xfs_bmap_add_extent_unwritten_real(
 	 * Check and set flags if this segment has a left neighbor.
 	 * Don't set contiguous if the combined extent would be too large.
 	 */
-	if (idx > 0) {
+	if (*idx > 0) {
 		state |= BMAP_LEFT_VALID;
-		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx - 1), &LEFT);
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx - 1), &LEFT);
 
 		if (isnullstartblock(LEFT.br_startblock))
 			state |= BMAP_LEFT_DELAY;
@@ -1231,9 +1201,9 @@ xfs_bmap_add_extent_unwritten_real(
 	 * Don't set contiguous if the combined extent would be too large.
 	 * Also check for all-three-contiguous being too large.
 	 */
-	if (idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
+	if (*idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
 		state |= BMAP_RIGHT_VALID;
-		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx + 1), &RIGHT);
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx + 1), &RIGHT);
 		if (isnullstartblock(RIGHT.br_startblock))
 			state |= BMAP_RIGHT_DELAY;
 	}
@@ -1262,14 +1232,15 @@ xfs_bmap_add_extent_unwritten_real(
 		 * Setting all of a previous oldext extent to newext.
 		 * The left and right neighbors are both contiguous with new.
 		 */
-		trace_xfs_bmap_pre_update(ip, idx - 1, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, idx - 1),
+		--*idx;
+
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx),
 			LEFT.br_blockcount + PREV.br_blockcount +
 			RIGHT.br_blockcount);
-		trace_xfs_bmap_pos