1 files changed, 187 insertions, 102 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 71f2d50f7823..908d7b050e9c 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -26,6 +26,22 @@
 
 static struct kmem_cache	*xfs_bmbt_cur_cache;
 
+void
+xfs_bmbt_init_block(
+	struct xfs_inode		*ip,
+	struct xfs_btree_block		*buf,
+	struct xfs_buf			*bp,
+	__u16				level,
+	__u16				numrecs)
+{
+	if (bp)
+		xfs_btree_init_buf(ip->i_mount, bp, &xfs_bmbt_ops, level,
+				numrecs, ip->i_ino);
+	else
+		xfs_btree_init_block(ip->i_mount, buf, &xfs_bmbt_ops, level,
+				numrecs, ip->i_ino);
+}
+
 /*
  * Convert on-disk form of btree root to in-memory form.
  */
@@ -44,17 +60,15 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
-				 XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
-				 XFS_BTREE_LONG_PTRS);
+	xfs_bmbt_init_block(ip, rblock, NULL, 0, 0);
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
 	rblock->bb_numrecs = dblock->bb_numrecs;
 	dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
-	fkp = XFS_BMDR_KEY_ADDR(dblock, 1);
-	tkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
-	fpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
-	tpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
+	fkp = xfs_bmdr_key_addr(dblock, 1);
+	tkp = xfs_bmbt_key_addr(mp, rblock, 1);
+	fpp = xfs_bmdr_ptr_addr(dblock, 1, dmxr);
+	tpp = xfs_bmap_broot_ptr_addr(mp, rblock, 1, rblocklen);
 	dmxr = be16_to_cpu(dblock->bb_numrecs);
 	memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
 	memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
@@ -154,10 +168,10 @@ xfs_bmbt_to_bmdr(
 	dblock->bb_level = rblock->bb_level;
 	dblock->bb_numrecs = rblock->bb_numrecs;
 	dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
-	fkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
-	tkp = XFS_BMDR_KEY_ADDR(dblock, 1);
-	fpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
-	tpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
+	fkp = xfs_bmbt_key_addr(mp, rblock, 1);
+	tkp = xfs_bmdr_key_addr(dblock, 1);
+	fpp = xfs_bmap_broot_ptr_addr(mp, rblock, 1, rblocklen);
+	tpp = xfs_bmdr_ptr_addr(dblock, 1, dmxr);
 	dmxr = be16_to_cpu(dblock->bb_numrecs);
 	memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
 	memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
@@ -171,13 +185,8 @@ xfs_bmbt_dup_cursor(
 
 	new = xfs_bmbt_init_cursor(cur->bc_mp, cur->bc_tp,
 			cur->bc_ino.ip, cur->bc_ino.whichfork);
-
-	/*
-	 * Copy the firstblock, dfops, and flags values,
-	 * since init cursor doesn't get them.
-	 */
-	new->bc_ino.flags = cur->bc_ino.flags;
-
+	new->bc_flags |= (cur->bc_flags &
+		(XFS_BTREE_BMBT_INVALID_OWNER | XFS_BTREE_BMBT_WASDEL));
 	return new;
 }
 
@@ -189,10 +198,10 @@ xfs_bmbt_update_cursor(
 	ASSERT((dst->bc_tp->t_highest_agno != NULLAGNUMBER) ||
 	       (dst->bc_ino.ip->i_diflags & XFS_DIFLAG_REALTIME));
 
-	dst->bc_ino.allocated += src->bc_ino.allocated;
+	dst->bc_bmap.allocated += src->bc_bmap.allocated;
 	dst->bc_tp->t_highest_agno = src->bc_tp->t_highest_agno;
 
-	src->bc_ino.allocated = 0;
+	src->bc_bmap.allocated = 0;
 }
 
 STATIC int
@@ -211,7 +220,7 @@ xfs_bmbt_alloc_block(
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_ino.ip->i_ino,
 			cur->bc_ino.whichfork);
 	args.minlen = args.maxlen = args.prod = 1;
-	args.wasdel = cur->bc_ino.flags & XFS_BTCUR_BMBT_WASDEL;
+	args.wasdel = cur->bc_flags & XFS_BTREE_BMBT_WASDEL;
 	if (!args.wasdel && args.tp->t_blk_res == 0)
 		return -ENOSPC;
 
@@ -247,7 +256,7 @@ xfs_bmbt_alloc_block(
 	}
 
 	ASSERT(args.len == 1);
-	cur->bc_ino.allocated++;
+	cur->bc_bmap.allocated++;
 	cur->bc_ino.ip->i_nblocks++;
 	xfs_trans_log_inode(args.tp, cur->bc_ino.ip, XFS_ILOG_CORE);
 	xfs_trans_mod_dquot_byino(args.tp, cur->bc_ino.ip,
@@ -273,7 +282,7 @@ xfs_bmbt_free_block(
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
 	error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo,
-			XFS_AG_RESV_NONE, false);
+			XFS_AG_RESV_NONE, 0);
 	if (error)
 		return error;
 
@@ -360,14 +369,6 @@ xfs_bmbt_init_rec_from_cur(
 	xfs_bmbt_disk_set_all(&rec->bmbt, &cur->bc_rec.b);
 }
 
-STATIC void
-xfs_bmbt_init_ptr_from_cur(
-	struct xfs_btree_cur	*cur,
-	union xfs_btree_ptr	*ptr)
-{
-	ptr->l = 0;
-}
-
 STATIC int64_t
 xfs_bmbt_key_diff(
 	struct xfs_btree_cur		*cur,
@@ -419,7 +420,7 @@ xfs_bmbt_verify(
 		 * XXX: need a better way of verifying the owner here. Right now
 		 * just make sure there has been one set.
 		 */
-		fa = xfs_btree_lblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN);
+		fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN);
 		if (fa)
 			return fa;
 	}
@@ -435,7 +436,7 @@ xfs_bmbt_verify(
 	if (level > max(mp->m_bm_maxlevels[0], mp->m_bm_maxlevels[1]))
 		return __this_address;
 
-	return xfs_btree_lblock_verify(bp, mp->m_bmap_dmxr[level != 0]);
+	return xfs_btree_fsblock_verify(bp, mp->m_bmap_dmxr[level != 0]);
 }
 
 static void
@@ -444,7 +445,7 @@ xfs_bmbt_read_verify(
 {
 	xfs_failaddr_t	fa;
 
-	if (!xfs_btree_lblock_verify_crc(bp))
+	if (!xfs_btree_fsblock_verify_crc(bp))
 		xfs_verifier_error(bp, -EFSBADCRC, __this_address);
 	else {
 		fa = xfs_bmbt_verify(bp);
@@ -468,7 +469,7 @@ xfs_bmbt_write_verify(
 		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
 		return;
 	}
-	xfs_btree_lblock_calc_crc(bp);
+	xfs_btree_fsblock_calc_crc(bp);
 }
 
 const struct xfs_buf_ops xfs_bmbt_buf_ops = {
@@ -515,9 +516,126 @@ xfs_bmbt_keys_contiguous(
 				 be64_to_cpu(key2->bmbt.br_startoff));
 }
 
-static const struct xfs_btree_ops xfs_bmbt_ops = {
+static inline void
+xfs_bmbt_move_ptrs(
+	struct xfs_mount	*mp,
+	struct xfs_btree_block	*broot,
+	short			old_size,
+	size_t			new_size,
+	unsigned int		numrecs)
+{
+	void			*dptr;
+	void			*sptr;
+
+	sptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, old_size);
+	dptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, new_size);
+	memmove(dptr, sptr, numrecs * sizeof(xfs_bmbt_ptr_t));
+}
+
+/*
+ * Reallocate the space for if_broot based on the number of records.  Move the
+ * records and pointers in if_broot to fit the new size.  When shrinking this
+ * will eliminate holes between the records and pointers created by the caller.
+ * When growing this will create holes to be filled in by the caller.
+ *
+ * The caller must not request to add more records than would fit in the
+ * on-disk inode root.  If the if_broot is currently NULL, then if we are
+ * adding records, one will be allocated.  The caller must also not request
+ * that the number of records go below zero, although it can go to zero.
+ *
+ * ip -- the inode whose if_broot area is changing
+ * whichfork -- which inode fork to change
+ * new_numrecs -- the new number of records requested for the if_broot array
+ *
+ * Returns the incore btree root block.
+ */
+struct xfs_btree_block *
+xfs_bmap_broot_realloc(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	unsigned int		new_numrecs)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
+	struct xfs_btree_block	*broot;
+	unsigned int		new_size;
+	unsigned int		old_size = ifp->if_broot_bytes;
+
+	/*
+	 * Block mapping btrees do not support storing zero records; if this
+	 * happens, the fork is being changed to FMT_EXTENTS.  Free the broot
+	 * and get out.
+	 */
+	if (new_numrecs == 0)
+		return xfs_broot_realloc(ifp, 0);
+
+	new_size = xfs_bmap_broot_space_calc(mp, new_numrecs);
+
+	/* Handle the nop case quietly. */
+	if (new_size == old_size)
+		return ifp->if_broot;
+
+	if (new_size > old_size) {
+		unsigned int	old_numrecs;
+
+		/*
+		 * If there wasn't any memory allocated before, just
+		 * allocate it now and get out.
+		 */
+		if (old_size == 0)
+			return xfs_broot_realloc(ifp, new_size);
+
+		/*
+		 * If there is already an existing if_broot, then we need
+		 * to realloc() it and shift the pointers to their new
+		 * location.  The records don't change location because
+		 * they are kept butted up against the btree block header.
+		 */
+		old_numrecs = xfs_bmbt_maxrecs(mp, old_size, false);
+		broot = xfs_broot_realloc(ifp, new_size);
+		ASSERT(xfs_bmap_bmdr_space(broot) <=
+			xfs_inode_fork_size(ip, whichfork));
+		xfs_bmbt_move_ptrs(mp, broot, old_size, new_size, old_numrecs);
+		return broot;
+	}
+
+	/*
+	 * We're reducing, but not totally eliminating, numrecs.  In this case,
+	 * we are shrinking the if_broot buffer, so it must already exist.
+	 */
+	ASSERT(ifp->if_broot != NULL && old_size > 0 && new_size > 0);
+
+	/*
+	 * Shrink the btree root by moving the bmbt pointers, since they are
+	 * not butted up against the btree block header, then reallocating
+	 * broot.
+	 */
+	xfs_bmbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, new_numrecs);
+	broot = xfs_broot_realloc(ifp, new_size);
+	ASSERT(xfs_bmap_bmdr_space(broot) <=
+	       xfs_inode_fork_size(ip, whichfork));
+	return broot;
+}
+
+static struct xfs_btree_block *
+xfs_bmbt_broot_realloc(
+	struct xfs_btree_cur	*cur,
+	unsigned int		new_numrecs)
+{
+	return xfs_bmap_broot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork,
+			new_numrecs);
+}
+
+const struct xfs_btree_ops xfs_bmbt_ops = {
+	.name			= "bmap",
+	.type			= XFS_BTREE_TYPE_INODE,
+
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
 	.key_len		= sizeof(xfs_bmbt_key_t),
+	.ptr_len		= XFS_BTREE_LONG_PTR_LEN,
+
+	.lru_refs		= XFS_BMAP_BTREE_REF,
+	.statoff		= XFS_STATS_CALC_INDEX(xs_bmbt_2),
 
 	.dup_cursor		= xfs_bmbt_dup_cursor,
 	.update_cursor		= xfs_bmbt_update_cursor,
@@ -529,44 +647,19 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.init_key_from_rec	= xfs_bmbt_init_key_from_rec,
 	.init_high_key_from_rec	= xfs_bmbt_init_high_key_from_rec,
 	.init_rec_from_cur	= xfs_bmbt_init_rec_from_cur,
-	.init_ptr_from_cur	= xfs_bmbt_init_ptr_from_cur,
 	.key_diff		= xfs_bmbt_key_diff,
 	.diff_two_keys		= xfs_bmbt_diff_two_keys,
 	.buf_ops		= &xfs_bmbt_buf_ops,
 	.keys_inorder		= xfs_bmbt_keys_inorder,
 	.recs_inorder		= xfs_bmbt_recs_inorder,
 	.keys_contiguous	= xfs_bmbt_keys_contiguous,
+	.broot_realloc		= xfs_bmbt_broot_realloc,
 };
 
-static struct xfs_btree_cur *
-xfs_bmbt_init_common(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
-	struct xfs_inode	*ip,
-	int			whichfork)
-{
-	struct xfs_btree_cur	*cur;
-
-	ASSERT(whichfork != XFS_COW_FORK);
-
-	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
-			mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
-	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
-
-	cur->bc_ops = &xfs_bmbt_ops;
-	cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
-	if (xfs_has_crc(mp))
-		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
-	cur->bc_ino.ip = ip;
-	cur->bc_ino.allocated = 0;
-	cur->bc_ino.flags = 0;
-
-	return cur;
-}
-
 /*
- * Allocate a new bmap btree cursor.
+ * Create a new bmap btree cursor.
+ *
+ * For staging cursors -1 in passed in whichfork.
  */
 struct xfs_btree_cur *
 xfs_bmbt_init_cursor(
@@ -575,15 +668,34 @@ xfs_bmbt_init_cursor(
 	struct xfs_inode	*ip,
 	int			whichfork)
 {
-	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
 	struct xfs_btree_cur	*cur;
+	unsigned int		maxlevels;
 
-	cur = xfs_bmbt_init_common(mp, tp, ip, whichfork);
+	ASSERT(whichfork != XFS_COW_FORK);
 
-	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
-	cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
+	/*
+	 * The Data fork always has larger maxlevel, so use that for staging
+	 * cursors.
+	 */
+	switch (whichfork) {
+	case XFS_STAGING_FORK:
+		maxlevels = mp->m_bm_maxlevels[XFS_DATA_FORK];
+		break;
+	default:
+		maxlevels = mp->m_bm_maxlevels[whichfork];
+		break;
+	}
+	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_bmbt_ops, maxlevels,
+			xfs_bmbt_cur_cache);
+	cur->bc_ino.ip = ip;
 	cur->bc_ino.whichfork = whichfork;
+	cur->bc_bmap.allocated = 0;
+	if (whichfork != XFS_STAGING_FORK) {
+		struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
 
+		cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
+		cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
+	}
 	return cur;
 }
 
@@ -599,33 +711,6 @@ xfs_bmbt_block_maxrecs(
 }
 
 /*
- * Allocate a new bmap btree cursor for reloading an inode block mapping data
- * structure.  Note that callers can use the staged cursor to reload extents
- * format inode forks if they rebuild the iext tree and commit the staged
- * cursor immediately.
- */
-struct xfs_btree_cur *
-xfs_bmbt_stage_cursor(
-	struct xfs_mount	*mp,
-	struct xfs_inode	*ip,
-	struct xbtree_ifakeroot	*ifake)
-{
-	struct xfs_btree_cur	*cur;
-	struct xfs_btree_ops	*ops;
-
-	/* data fork always has larger maxheight */
-	cur = xfs_bmbt_init_common(mp, NULL, ip, XFS_DATA_FORK);
-	cur->bc_nlevels = ifake->if_levels;
-	cur->bc_ino.forksize = ifake->if_fork_size;
-
-	/* Don't let anyone think we're attached to the real fork yet. */
-	cur->bc_ino.whichfork = -1;
-	xfs_btree_stage_ifakeroot(cur, ifake, &ops);
-	ops->update_cursor = NULL;
-	return cur;
-}
-
-/*
  * Swap in the new inode fork root.  Once we pass this point the newly rebuilt
  * mappings are in place and we have to kill off any old btree blocks.
  */
@@ -665,19 +750,19 @@ xfs_bmbt_commit_staged_btree(
 		break;
 	}
 	xfs_trans_log_inode(tp, cur->bc_ino.ip, flags);
-	xfs_btree_commit_ifakeroot(cur, tp, whichfork, &xfs_bmbt_ops);
+	xfs_btree_commit_ifakeroot(cur, tp, whichfork);
 }
 
 /*
  * Calculate number of records in a bmap btree block.
  */
-int
+unsigned int
 xfs_bmbt_maxrecs(
 	struct xfs_mount	*mp,
-	int			blocklen,
-	int			leaf)
+	unsigned int		blocklen,
+	bool			leaf)
 {
-	blocklen -= XFS_BMBT_BLOCK_LEN(mp);
+	blocklen -= xfs_bmbt_block_len(mp);
 	return xfs_bmbt_block_maxrecs(blocklen, leaf);
 }
 
@@ -751,7 +836,7 @@ xfs_bmbt_change_owner(
 	ASSERT(xfs_ifork_ptr(ip, whichfork)->if_format == XFS_DINODE_FMT_BTREE);
 
 	cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork);
-	cur->bc_ino.flags |= XFS_BTCUR_BMBT_INVALID_OWNER;
+	cur->bc_flags |= XFS_BTREE_BMBT_INVALID_OWNER;
 
 	error = xfs_btree_change_owner(cur, new_owner, buffer_list);
 	xfs_btree_del_cursor(cur, error);