1 files changed, 366 insertions, 167 deletions

diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index d29547572a68..299ce7fd11b0 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -30,6 +30,12 @@
 #include "xfs_health.h"
 #include "xfs_buf_mem.h"
 #include "xfs_btree_mem.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_bmap.h"
+#include "xfs_rmap.h"
+#include "xfs_quota.h"
+#include "xfs_metafile.h"
+#include "xfs_rtrefcount_btree.h"
 
 /*
  * Btree magic numbers.
@@ -225,7 +231,7 @@ __xfs_btree_check_agblock(
 	struct xfs_buf		*bp)
 {
 	struct xfs_mount	*mp = cur->bc_mp;
-	struct xfs_perag	*pag = cur->bc_ag.pag;
+	struct xfs_perag	*pag = to_perag(cur->bc_group);
 	xfs_failaddr_t		fa;
 	xfs_agblock_t		agbno;
 
@@ -331,7 +337,7 @@ __xfs_btree_check_ptr(
 			return -EFSCORRUPTED;
 		break;
 	case XFS_BTREE_TYPE_AG:
-		if (!xfs_verify_agbno(cur->bc_ag.pag,
+		if (!xfs_verify_agbno(to_perag(cur->bc_group),
 				be32_to_cpu((&ptr->s)[index])))
 			return -EFSCORRUPTED;
 		break;
@@ -372,7 +378,7 @@ xfs_btree_check_ptr(
 		case XFS_BTREE_TYPE_AG:
 			xfs_err(cur->bc_mp,
 "AG %u: Corrupt %sbt pointer at level %d index %d.",
-				cur->bc_ag.pag->pag_agno, cur->bc_ops->name,
+				cur->bc_group->xg_gno, cur->bc_ops->name,
 				level, index);
 			break;
 		}
@@ -523,20 +529,8 @@ xfs_btree_del_cursor(
 	ASSERT(!xfs_btree_is_bmap(cur->bc_ops) || cur->bc_bmap.allocated == 0 ||
 	       xfs_is_shutdown(cur->bc_mp) || error != 0);
 
-	switch (cur->bc_ops->type) {
-	case XFS_BTREE_TYPE_AG:
-		if (cur->bc_ag.pag)
-			xfs_perag_put(cur->bc_ag.pag);
-		break;
-	case XFS_BTREE_TYPE_INODE:
-		/* nothing to do */
-		break;
-	case XFS_BTREE_TYPE_MEM:
-		if (cur->bc_mem.pag)
-			xfs_perag_put(cur->bc_mem.pag);
-		break;
-	}
-
+	if (cur->bc_group)
+		xfs_group_put(cur->bc_group);
 	kmem_cache_free(cur->bc_cache, cur);
 }
 
@@ -1017,22 +1011,22 @@ xfs_btree_readahead_agblock(
 	struct xfs_btree_block	*block)
 {
 	struct xfs_mount	*mp = cur->bc_mp;
-	xfs_agnumber_t		agno = cur->bc_ag.pag->pag_agno;
+	struct xfs_perag	*pag = to_perag(cur->bc_group);
 	xfs_agblock_t		left = be32_to_cpu(block->bb_u.s.bb_leftsib);
 	xfs_agblock_t		right = be32_to_cpu(block->bb_u.s.bb_rightsib);
 	int			rval = 0;
 
 	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) {
 		xfs_buf_readahead(mp->m_ddev_targp,
-				XFS_AGB_TO_DADDR(mp, agno, left),
-				mp->m_bsize, cur->bc_ops->buf_ops);
+				xfs_agbno_to_daddr(pag, left), mp->m_bsize,
+				cur->bc_ops->buf_ops);
 		rval++;
 	}
 
 	if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLAGBLOCK) {
 		xfs_buf_readahead(mp->m_ddev_targp,
-				XFS_AGB_TO_DADDR(mp, agno, right),
-				mp->m_bsize, cur->bc_ops->buf_ops);
+				xfs_agbno_to_daddr(pag, right), mp->m_bsize,
+				cur->bc_ops->buf_ops);
 		rval++;
 	}
 
@@ -1091,7 +1085,7 @@ xfs_btree_ptr_to_daddr(
 
 	switch (cur->bc_ops->type) {
 	case XFS_BTREE_TYPE_AG:
-		*daddr = XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+		*daddr = xfs_agbno_to_daddr(to_perag(cur->bc_group),
 				be32_to_cpu(ptr->s));
 		break;
 	case XFS_BTREE_TYPE_INODE:
@@ -1313,7 +1307,7 @@ xfs_btree_owner(
 	case XFS_BTREE_TYPE_INODE:
 		return cur->bc_ino.ip->i_ino;
 	case XFS_BTREE_TYPE_AG:
-		return cur->bc_ag.pag->pag_agno;
+		return cur->bc_group->xg_gno;
 	default:
 		ASSERT(0);
 		return 0;
@@ -1331,30 +1325,6 @@ xfs_btree_init_block_cur(
 			xfs_btree_owner(cur));
 }
 
-/*
- * Return true if ptr is the last record in the btree and
- * we need to track updates to this record.  The decision
- * will be further refined in the update_lastrec method.
- */
-STATIC int
-xfs_btree_is_lastrec(
-	struct xfs_btree_cur	*cur,
-	struct xfs_btree_block	*block,
-	int			level)
-{
-	union xfs_btree_ptr	ptr;
-
-	if (level > 0)
-		return 0;
-	if (!(cur->bc_ops->geom_flags & XFS_BTGEO_LASTREC_UPDATE))
-		return 0;
-
-	xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB);
-	if (!xfs_btree_ptr_is_null(cur, &ptr))
-		return 0;
-	return 1;
-}
-
 STATIC void
 xfs_btree_buf_to_ptr(
 	struct xfs_btree_cur	*cur,
@@ -1573,12 +1543,16 @@ xfs_btree_log_recs(
 	int			first,
 	int			last)
 {
+	if (!bp) {
+		xfs_trans_log_inode(cur->bc_tp, cur->bc_ino.ip,
+				xfs_ilog_fbroot(cur->bc_ino.whichfork));
+		return;
+	}
 
 	xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF);
 	xfs_trans_log_buf(cur->bc_tp, bp,
 			  xfs_btree_rec_offset(cur, first),
 			  xfs_btree_rec_offset(cur, last + 1) - 1);
-
 }
 
 /*
@@ -2420,15 +2394,6 @@ xfs_btree_update(
 	xfs_btree_copy_recs(cur, rp, rec, 1);
 	xfs_btree_log_recs(cur, bp, ptr, ptr);
 
-	/*
-	 * If we are tracking the last record in the tree and
-	 * we are at the far right edge of the tree, update it.
-	 */
-	if (xfs_btree_is_lastrec(cur, block, 0)) {
-		cur->bc_ops->update_lastrec(cur, block, rec,
-					    ptr, LASTREC_UPDATE);
-	}
-
 	/* Pass new key value up to our parent. */
 	if (xfs_btree_needs_key_update(cur, ptr)) {
 		error = xfs_btree_update_keys(cur, 0);
@@ -3123,6 +3088,131 @@ xfs_btree_split(
 #define xfs_btree_split	__xfs_btree_split
 #endif /* __KERNEL__ */
 
+/* Move the records from a root leaf block to a separate block. */
+STATIC void
+xfs_btree_promote_leaf_iroot(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block,
+	struct xfs_buf		*cbp,
+	union xfs_btree_ptr	*cptr,
+	struct xfs_btree_block	*cblock)
+{
+	union xfs_btree_rec	*rp;
+	union xfs_btree_rec	*crp;
+	union xfs_btree_key	*kp;
+	union xfs_btree_ptr	*pp;
+	struct xfs_btree_block	*broot;
+	int			numrecs = xfs_btree_get_numrecs(block);
+
+	/* Copy the records from the leaf broot into the new child block. */
+	rp = xfs_btree_rec_addr(cur, 1, block);
+	crp = xfs_btree_rec_addr(cur, 1, cblock);
+	xfs_btree_copy_recs(cur, crp, rp, numrecs);
+
+	/*
+	 * Increment the tree height.
+	 *
+	 * Trickery here: The amount of memory that we need per record for the
+	 * ifork's btree root block may change when we convert the broot from a
+	 * leaf to a node block.  Free the existing leaf broot so that nobody
+	 * thinks we need to migrate node pointers when we realloc the broot
+	 * buffer after bumping nlevels.
+	 */
+	cur->bc_ops->broot_realloc(cur, 0);
+	cur->bc_nlevels++;
+	cur->bc_levels[1].ptr = 1;
+
+	/*
+	 * Allocate a new node broot and initialize it to point to the new
+	 * child block.
+	 */
+	broot = cur->bc_ops->broot_realloc(cur, 1);
+	xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops,
+			cur->bc_nlevels - 1, 1, cur->bc_ino.ip->i_ino);
+
+	pp = xfs_btree_ptr_addr(cur, 1, broot);
+	kp = xfs_btree_key_addr(cur, 1, broot);
+	xfs_btree_copy_ptrs(cur, pp, cptr, 1);
+	xfs_btree_get_keys(cur, cblock, kp);
+
+	/* Attach the new block to the cursor and log it. */
+	xfs_btree_setbuf(cur, 0, cbp);
+	xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS);
+	xfs_btree_log_recs(cur, cbp, 1, numrecs);
+}
+
+/*
+ * Move the keys and pointers from a root block to a separate block.
+ *
+ * Since the keyptr size does not change, all we have to do is increase the
+ * tree height, copy the keyptrs to the new internal node (cblock), shrink
+ * the root, and copy the pointers there.
+ */
+STATIC int
+xfs_btree_promote_node_iroot(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block,
+	int			level,
+	struct xfs_buf		*cbp,
+	union xfs_btree_ptr	*cptr,
+	struct xfs_btree_block	*cblock)
+{
+	union xfs_btree_key	*ckp;
+	union xfs_btree_key	*kp;
+	union xfs_btree_ptr	*cpp;
+	union xfs_btree_ptr	*pp;
+	int			i;
+	int			error;
+	int			numrecs = xfs_btree_get_numrecs(block);
+
+	/*
+	 * Increase tree height, adjusting the root block level to match.
+	 * We cannot change the root btree node size until we've copied the
+	 * block contents to the new child block.
+	 */
+	be16_add_cpu(&block->bb_level, 1);
+	cur->bc_nlevels++;
+	cur->bc_levels[level + 1].ptr = 1;
+
+	/*
+	 * Adjust the root btree record count, then copy the keys from the old
+	 * root to the new child block.
+	 */
+	xfs_btree_set_numrecs(block, 1);
+	kp = xfs_btree_key_addr(cur, 1, block);
+	ckp = xfs_btree_key_addr(cur, 1, cblock);
+	xfs_btree_copy_keys(cur, ckp, kp, numrecs);
+
+	/* Check the pointers and copy them to the new child block. */
+	pp = xfs_btree_ptr_addr(cur, 1, block);
+	cpp = xfs_btree_ptr_addr(cur, 1, cblock);
+	for (i = 0; i < numrecs; i++) {
+		error = xfs_btree_debug_check_ptr(cur, pp, i, level);
+		if (error)
+			return error;
+	}
+	xfs_btree_copy_ptrs(cur, cpp, pp, numrecs);
+
+	/*
+	 * Set the first keyptr to point to the new child block, then shrink
+	 * the memory buffer for the root block.
+	 */
+	error = xfs_btree_debug_check_ptr(cur, cptr, 0, level);
+	if (error)
+		return error;
+	xfs_btree_copy_ptrs(cur, pp, cptr, 1);
+	xfs_btree_get_keys(cur, cblock, kp);
+
+	cur->bc_ops->broot_realloc(cur, 1);
+
+	/* Attach the new block to the cursor and log it. */
+	xfs_btree_setbuf(cur, level, cbp);
+	xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS);
+	xfs_btree_log_keys(cur, cbp, 1, numrecs);
+	xfs_btree_log_ptrs(cur, cbp, 1, numrecs);
+	return 0;
+}
+
 /*
  * Copy the old inode root contents into a real block and make the
  * broot point to it.
@@ -3136,14 +3226,10 @@ xfs_btree_new_iroot(
 	struct xfs_buf		*cbp;		/* buffer for cblock */
 	struct xfs_btree_block	*block;		/* btree block */
 	struct xfs_btree_block	*cblock;	/* child btree block */
-	union xfs_btree_key	*ckp;		/* child key pointer */
-	union xfs_btree_ptr	*cpp;		/* child ptr pointer */
-	union xfs_btree_key	*kp;		/* pointer to btree key */
-	union xfs_btree_ptr	*pp;		/* pointer to block addr */
+	union xfs_btree_ptr	aptr;
 	union xfs_btree_ptr	nptr;		/* new block addr */
 	int			level;		/* btree level */
 	int			error;		/* error return code */
-	int			i;		/* loop counter */
 
 	XFS_BTREE_STATS_INC(cur, newroot);
 
@@ -3152,10 +3238,15 @@ xfs_btree_new_iroot(
 	level = cur->bc_nlevels - 1;
 
 	block = xfs_btree_get_iroot(cur);
-	pp = xfs_btree_ptr_addr(cur, 1, block);
+	ASSERT(level > 0 || (cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS));
+	if (level > 0)
+		aptr = *xfs_btree_ptr_addr(cur, 1, block);
+	else
+		aptr.l = cpu_to_be64(XFS_INO_TO_FSB(cur->bc_mp,
+				cur->bc_ino.ip->i_ino));
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = xfs_btree_alloc_block(cur, pp, &nptr, stat);
+	error = xfs_btree_alloc_block(cur, &aptr, &nptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
@@ -3181,47 +3272,16 @@ xfs_btree_new_iroot(
 			cblock->bb_u.s.bb_blkno = bno;
 	}
 
-	be16_add_cpu(&block->bb_level, 1);
-	xfs_btree_set_numrecs(block, 1);
-	cur->bc_nlevels++;
-	ASSERT(cur->bc_nlevels <= cur->bc_maxlevels);
-	cur->bc_levels[level + 1].ptr = 1;
-
-	kp = xfs_btree_key_addr(cur, 1, block);
-	ckp = xfs_btree_key_addr(cur, 1, cblock);
-	xfs_btree_copy_keys(cur, ckp, kp, xfs_btree_get_numrecs(cblock));
-
-	cpp = xfs_btree_ptr_addr(cur, 1, cblock);
-	for (i = 0; i < be16_to_cpu(cblock->bb_numrecs); i++) {
-		error = xfs_btree_debug_check_ptr(cur, pp, i, level);
+	if (level > 0) {
+		error = xfs_btree_promote_node_iroot(cur, block, level, cbp,
+				&nptr, cblock);
 		if (error)
 			goto error0;
+	} else {
+		xfs_btree_promote_leaf_iroot(cur, block, cbp, &nptr, cblock);
 	}
 
-	xfs_btree_copy_ptrs(cur, cpp, pp, xfs_btree_get_numrecs(cblock));
-
-	error = xfs_btree_debug_check_ptr(cur, &nptr, 0, level);
-	if (error)
-		goto error0;
-
-	xfs_btree_copy_ptrs(cur, pp, &nptr, 1);
-
-	xfs_iroot_realloc(cur->bc_ino.ip,
-			  1 - xfs_btree_get_numrecs(cblock),
-			  cur->bc_ino.whichfork);
-
-	xfs_btree_setbuf(cur, level, cbp);
-
-	/*
-	 * Do all this logging at the end so that
-	 * the root is at the right level.
-	 */
-	xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS);
-	xfs_btree_log_keys(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs));
-	xfs_btree_log_ptrs(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs));
-
-	*logflags |=
-		XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork);
+	*logflags |= XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork);
 	*stat = 1;
 	return 0;
 error0:
@@ -3392,7 +3452,7 @@ xfs_btree_make_block_unfull(
 
 		if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) {
 			/* A root block that can be made bigger. */
-			xfs_iroot_realloc(ip, 1, cur->bc_ino.whichfork);
+			cur->bc_ops->broot_realloc(cur, numrecs + 1);
 			*stat = 1;
 		} else {
 			/* A root block that needs replacing */
@@ -3602,14 +3662,31 @@ xfs_btree_insrec(
 	xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS);
 
 	/*
-	 * If we just inserted into a new tree block, we have to
-	 * recalculate nkey here because nkey is out of date.
+	 * Update btree keys to reflect the newly added record or keyptr.
+	 * There are three cases here to be aware of.  Normally, all we have to
+	 * do is walk towards the root, updating keys as necessary.
 	 *
-	 * Otherwise we're just updating an existing block (having shoved
-	 * some records into the new tree block), so use the regular key
-	 * update mechanism.
+	 * If the caller had us target a full block for the insertion, we dealt
+	 * with that by calling the _make_block_unfull function.  If the
+	 * "make unfull" function splits the block, it'll hand us back the key
+	 * and pointer of the new block.  We haven't yet added the new block to
+	 * the next level up, so if we decide to add the new record to the new
+	 * block (bp->b_bn != old_bn), we have to update the caller's pointer
+	 * so that the caller adds the new block with the correct key.
+	 *
+	 * However, there is a third possibility-- if the selected block is the
+	 * root block of an inode-rooted btree and cannot be expanded further,
+	 * the "make unfull" function moves the root block contents to a new
+	 * block and updates the root block to point to the new block.  In this
+	 * case, no block pointer is passed back because the block has already
+	 * been added to the btree.  In this case, we need to use the regular
+	 * key update function, just like the first case.  This is critical for
+	 * overlapping btrees, because the high key must be updated to reflect
+	 * the entire tree, not just the subtree accessible through the first
+	 * child of the root (which is now two levels down from the root).
 	 */
-	if (bp && xfs_buf_daddr(bp) != old_bn) {
+	if (!xfs_btree_ptr_is_null(cur, &nptr) &&
+	    bp && xfs_buf_daddr(bp) != old_bn) {
 		xfs_btree_get_keys(cur, block, lkey);
 	} else if (xfs_btree_needs_key_update(cur, optr)) {
 		error = xfs_btree_update_keys(cur, level);
@@ -3618,15 +3695,6 @@ xfs_btree_insrec(
 	}
 
 	/*
-	 * If we are tracking the last record in the tree and
-	 * we are at the far right edge of the tree, update it.
-	 */
-	if (xfs_btree_is_lastrec(cur, block, level)) {
-		cur->bc_ops->update_lastrec(cur, block, rec,
-					    ptr, LASTREC_INSREC);
-	}
-
-	/*
 	 * Return the new block number, if any.
 	 * If there is one, give back a record value and a cursor too.
 	 */
@@ -3730,6 +3798,97 @@ error0:
 	return error;
 }
 
+/* Move the records from a child leaf block to the root block. */
+STATIC void
+xfs_btree_demote_leaf_child(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*cblock,
+	int			numrecs)
+{
+	union xfs_btree_rec	*rp;
+	union xfs_btree_rec	*crp;
+	struct xfs_btree_block	*broot;
+
+	/*
+	 * Decrease the tree height.
+	 *
+	 * Trickery here: The amount of memory that we need per record for the
+	 * ifork's btree root block may change when we convert the broot from a
+	 * node to a leaf.  Free the old node broot so that we can get a fresh
+	 * leaf broot.
+	 */
+	cur->bc_ops->broot_realloc(cur, 0);
+	cur->bc_nlevels--;
+
+	/*
+	 * Allocate a new leaf broot and copy the records from the old child.
+	 * Detach the old child from the cursor.
+	 */
+	broot = cur->bc_ops->broot_realloc(cur, numrecs);
+	xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, 0, numrecs,
+			cur->bc_ino.ip->i_ino);
+
+	rp = xfs_btree_rec_addr(cur, 1, broot);
+	crp = xfs_btree_rec_addr(cur, 1, cblock);
+	xfs_btree_copy_recs(cur, rp, crp, numrecs);
+
+	cur->bc_levels[0].bp = NULL;
+}
+
+/*
+ * Move the keyptrs from a child node block to the root block.
+ *
+ * Since the keyptr size does not change, all we have to do is increase the
+ * tree height, copy the keyptrs to the new internal node (cblock), shrink
+ * the root, and copy the pointers there.
+ */
+STATIC int
+xfs_btree_demote_node_child(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*cblock,
+	int			level,
+	int			numrecs)
+{
+	struct xfs_btree_block	*block;
+	union xfs_btree_key	*ckp;
+	union xfs_btree_key	*kp;
+	union xfs_btree_ptr	*cpp;
+	union xfs_btree_ptr	*pp;
+	int			i;
+	int			error;
+
+	/*
+	 * Adjust the root btree node size and the record count to match the
+	 * doomed child so that we can copy the keyptrs ahead of changing the
+	 * tree shape.
+	 */
+	block = cur->bc_ops->broot_realloc(cur, numrecs);
+
+	xfs_btree_set_numrecs(block, numrecs);
+	ASSERT(block->bb_numrecs == cblock->bb_numrecs);
+
+	/* Copy keys from the doomed block. */
+	kp = xfs_btree_key_addr(cur, 1, block);
+	ckp = xfs_btree_key_addr(cur, 1, cblock);
+	xfs_btree_copy_keys(cur, kp, ckp, numrecs);
+
+	/* Copy pointers from the doomed block. */
+	pp = xfs_btree_ptr_addr(cur, 1, block);
+	cpp = xfs_btree_ptr_addr(cur, 1, cblock);
+	for (i = 0; i < numrecs; i++) {
+		error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1);
+		if (error)
+			return error;
+	}
+	xfs_btree_copy_ptrs(cur, pp, cpp, numrecs);
+
+	/* Decrease tree height, adjusting the root block level to match. */
+	cur->bc_levels[level - 1].bp = NULL;
+	be16_add_cpu(&block->bb_level, -1);
+	cur->bc_nlevels--;
+	return 0;
+}
+
 /*
  * Try to merge a non-leaf block back into the inode root.
  *
@@ -3742,34 +3901,31 @@ STATIC int
 xfs_btree_kill_iroot(
 	struct xfs_btree_cur	*cur)
 {
-	int			whichfork = cur->bc_ino.whichfork;
 	struct xfs_inode	*ip = cur->bc_ino.ip;
-	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
 	struct xfs_btree_block	*block;
 	struct xfs_btree_block	*cblock;
-	union xfs_btree_key	*kp;
-	union xfs_btree_key	*ckp;
-	union xfs_btree_ptr	*pp;
-	union xfs_btree_ptr	*cpp;
 	struct xfs_buf		*cbp;
 	int			level;
-	int			index;
 	int			numrecs;
 	int			error;
 #ifdef DEBUG
 	union xfs_btree_ptr	ptr;
 #endif
-	int			i;
 
 	ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE);
-	ASSERT(cur->bc_nlevels > 1);
+	ASSERT((cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS) ||
+	       cur->bc_nlevels > 1);
 
 	/*
 	 * Don't deal with the root block needs to be a leaf case.
 	 * We're just going to turn the thing back into extents anyway.
 	 */
 	level = cur->bc_nlevels - 1;
-	if (level == 1)
+	if (level == 1 && !(cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS))
+		goto out0;
+
+	/* If we're already a leaf, jump out. */
+	if (level == 0)
 		goto out0;
 
 	/*
@@ -3799,40 +3955,20 @@ xfs_btree_kill_iroot(
 	ASSERT(xfs_btree_ptr_is_null(cur, &ptr));
 #endif
 
-	index = numrecs - cur->bc_ops->get_maxrecs(cur, level);
-	if (index) {
-		xfs_iroot_realloc(cur->bc_ino.ip, index,
-				  cur->bc_ino.whichfork);
-		block = ifp->if_broot;
-	}
-
-	be16_add_cpu(&block->bb_numrecs, index);
-	ASSERT(block->bb_numrecs == cblock->bb_numrecs);
-
-	kp = xfs_btree_key_addr(cur, 1, block);
-	ckp = xfs_btree_key_addr(cur, 1, cblock);
-	xfs_btree_copy_keys(cur, kp, ckp, numrecs);
-
-	pp = xfs_btree_ptr_addr(cur, 1, block);
-	cpp = xfs_btree_ptr_addr(cur, 1, cblock);
-
-	for (i = 0; i < numrecs; i++) {
-		error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1);
+	if (level > 1) {
+		error = xfs_btree_demote_node_child(cur, cblock, level,
+				numrecs);
 		if (error)
 			return error;
-	}
-
-	xfs_btree_copy_ptrs(cur, pp, cpp, numrecs);
+	} else
+		xfs_btree_demote_leaf_child(cur, cblock, numrecs);
 
 	error = xfs_btree_free_block(cur, cbp);
 	if (error)
 		return error;
 
-	cur->bc_levels[level - 1].bp = NULL;
-	be16_add_cpu(&block->bb_level, -1);
 	xfs_trans_log_inode(cur->bc_tp, ip,
 		XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork));
-	cur->bc_nlevels--;
 out0:
 	return 0;
 }
@@ -3984,21 +4120,12 @@ xfs_btree_delrec(
 	xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS);
 
 	/*
-	 * If we are tracking the last record in the tree and
-	 * we are at the far right edge of the tree, update it.
-	 */
-	if (xfs_btree_is_lastrec(cur, block, level)) {
-		cur->bc_ops->update_lastrec(cur, block, NULL,
-					    ptr, LASTREC_DELREC);
-	}
-
-	/*
 	 * We're at the root level.  First, shrink the root block in-memory.
 	 * Try to get rid of the next level down.  If we can't then there's
-	 * nothing left to do.
+	 * nothing left to do.  numrecs was decremented above.
 	 */
 	if (xfs_btree_at_iroot(cur, level)) {
-		xfs_iroot_realloc(cur->bc_ino.ip, -1, cur->bc_ino.whichfork);
+		cur->bc_ops->broot_realloc(cur, numrecs);
 
 		error = xfs_btree_kill_iroot(cur);
 		if (error)
@@ -4796,7 +4923,7 @@ xfs_btree_agblock_v5hdr_verify(
 		return __this_address;
 	if (block->bb_u.s.bb_blkno != cpu_to_be64(xfs_buf_daddr(bp)))
 		return __this_address;
-	if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
+	if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag_agno(pag))
 		return __this_address;
 	return NULL;
 }
@@ -5207,7 +5334,7 @@ xfs_btree_count_blocks_helper(
 	int			level,
 	void			*data)
 {
-	xfs_extlen_t		*blocks = data;
+	xfs_filblks_t		*blocks = data;
 	(*blocks)++;
 
 	return 0;
@@ -5217,7 +5344,7 @@ xfs_btree_count_blocks_helper(
 int
 xfs_btree_count_blocks(
 	struct xfs_btree_cur	*cur,
-	xfs_extlen_t		*blocks)
+	xfs_filblks_t		*blocks)
 {
 	*blocks = 0;
 	return xfs_btree_visit_blocks(cur, xfs_btree_count_blocks_helper,
@@ -5406,6 +5533,12 @@ xfs_btree_init_cur_caches(void)
 	error = xfs_refcountbt_init_cur_cache();
 	if (error)
 		goto err;
+	error = xfs_rtrmapbt_init_cur_cache();
+	if (error)
+		goto err;
+	error = xfs_rtrefcountbt_init_cur_cache();
+	if (error)
+		goto err;
 
 	return 0;
 err:
@@ -5422,6 +5555,8 @@ xfs_btree_destroy_cur_caches(void)
 	xfs_bmbt_destroy_cur_cache();
 	xfs_rmapbt_destroy_cur_cache();
 	xfs_refcountbt_destroy_cur_cache();
+	xfs_rtrmapbt_destroy_cur_cache();
+	xfs_rtrefcountbt_destroy_cur_cache();
 }
 
 /* Move the btree cursor before the first record. */
@@ -5450,3 +5585,67 @@ xfs_btree_goto_left_edge(
 
 	return 0;
 }
+
+/* Allocate a block for an inode-rooted metadata btree. */
+int
+xfs_btree_alloc_metafile_block(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*start,
+	union xfs_btree_ptr		*new,
+	int				*stat)
+{
+	struct xfs_alloc_arg		args = {
+		.mp			= cur->bc_mp,
+		.tp			= cur->bc_tp,
+		.resv			= XFS_AG_RESV_METAFILE,
+		.minlen			= 1,
+		.maxlen			= 1,
+		.prod			= 1,
+	};
+	struct xfs_inode		*ip = cur->bc_ino.ip;
+	int				error;
+
+	ASSERT(xfs_is_metadir_inode(ip));
+
+	xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, cur->bc_ino.whichfork);
+	error = xfs_alloc_vextent_start_ag(&args,
+			XFS_INO_TO_FSB(cur->bc_mp, ip->i_ino));
+	if (error)
+		return error;
+	if (args.fsbno == NULLFSBLOCK) {
+		*stat = 0;
+		return 0;
+	}
+	ASSERT(args.len == 1);
+
+	xfs_metafile_resv_alloc_space(ip, &args);
+
+	new->l = cpu_to_be64(args.fsbno);
+	*stat = 1;
+	return 0;
+}
+
+/* Free a block from an inode-rooted metadata btree. */
+int
+xfs_btree_free_metafile_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = cur->bc_mp;
+	struct xfs_inode	*ip = cur->bc_ino.ip;
+	struct xfs_trans	*tp = cur->bc_tp;
+	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
+	int			error;
+
+	ASSERT(xfs_is_metadir_inode(ip));
+
+	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
+	error = xfs_free_extent_later(tp, fsbno, 1, &oinfo, XFS_AG_RESV_METAFILE,
+			0);
+	if (error)
+		return error;
+
+	xfs_metafile_resv_free_space(ip, tp, 1);
+	return 0;
+}