xfs: wire up a new metafile type for the realtime rmap

Plumb in the pieces we need to embed the root of the realtime rmap btree
in an inode's data fork, complete with new metafile type and on-disk
interpretation functions.

Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>

1 files changed, 251 insertions, 0 deletions

diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c
index 066deadcaac9..af0df0c7e61e 100644
--- a/fs/xfs/libxfs/xfs_rtrmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c
@@ -77,6 +77,39 @@ xfs_rtrmapbt_get_maxrecs(
 	return cur->bc_mp->m_rtrmap_mxr[level != 0];
 }
 
+/* Calculate number of records in the ondisk realtime rmap btree inode root. */
+unsigned int
+xfs_rtrmapbt_droot_maxrecs(
+	unsigned int		blocklen,
+	bool			leaf)
+{
+	blocklen -= sizeof(struct xfs_rtrmap_root);
+
+	if (leaf)
+		return blocklen / sizeof(struct xfs_rmap_rec);
+	return blocklen / (2 * sizeof(struct xfs_rmap_key) +
+			sizeof(xfs_rtrmap_ptr_t));
+}
+
+/*
+ * Get the maximum records we could store in the on-disk format.
+ *
+ * For non-root nodes this is equivalent to xfs_rtrmapbt_get_maxrecs, but
+ * for the root node this checks the available space in the dinode fork
+ * so that we can resize the in-memory buffer to match it.  After a
+ * resize to the maximum size this function returns the same value
+ * as xfs_rtrmapbt_get_maxrecs for the root node, too.
+ */
+STATIC int
+xfs_rtrmapbt_get_dmaxrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	if (level != cur->bc_nlevels - 1)
+		return cur->bc_mp->m_rtrmap_mxr[level != 0];
+	return xfs_rtrmapbt_droot_maxrecs(cur->bc_ino.forksize, level == 0);
+}
+
 /*
  * Convert the ondisk record's offset field into the ondisk key's offset field.
  * Fork and bmbt are significant parts of the rmap record key, but written
@@ -369,6 +402,87 @@ xfs_rtrmapbt_keys_contiguous(
 				 be32_to_cpu(key2->rmap.rm_startblock));
 }
 
+static inline void
+xfs_rtrmapbt_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_rtrmap_broot_ptr_addr(mp, broot, 1, old_size);
+	dptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, new_size);
+	memmove(dptr, sptr, numrecs * sizeof(xfs_rtrmap_ptr_t));
+}
+
+static struct xfs_btree_block *
+xfs_rtrmapbt_broot_realloc(
+	struct xfs_btree_cur	*cur,
+	unsigned int		new_numrecs)
+{
+	struct xfs_mount	*mp = cur->bc_mp;
+	struct xfs_ifork	*ifp = xfs_btree_ifork_ptr(cur);
+	struct xfs_btree_block	*broot;
+	unsigned int		new_size;
+	unsigned int		old_size = ifp->if_broot_bytes;
+	const unsigned int	level = cur->bc_nlevels - 1;
+
+	new_size = xfs_rtrmap_broot_space_calc(mp, level, 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 possibly move the node block pointers because
+		 * those are not butted up against the btree block header.
+		 */
+		old_numrecs = xfs_rtrmapbt_maxrecs(mp, old_size, level == 0);
+		broot = xfs_broot_realloc(ifp, new_size);
+		if (level > 0)
+			xfs_rtrmapbt_move_ptrs(mp, broot, old_size, new_size,
+					old_numrecs);
+		goto out_broot;
+	}
+
+	/*
+	 * We're reducing numrecs.  If we're going all the way to zero, just
+	 * free the block.
+	 */
+	ASSERT(ifp->if_broot != NULL && old_size > 0);
+	if (new_size == 0)
+		return xfs_broot_realloc(ifp, 0);
+
+	/*
+	 * Shrink the btree root by possibly moving the rtrmapbt pointers,
+	 * since they are not butted up against the btree block header.  Then
+	 * reallocate broot.
+	 */
+	if (level > 0)
+		xfs_rtrmapbt_move_ptrs(mp, ifp->if_broot, old_size, new_size,
+				new_numrecs);
+	broot = xfs_broot_realloc(ifp, new_size);
+
+out_broot:
+	ASSERT(xfs_rtrmap_droot_space(broot) <=
+	       xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork));
+	return broot;
+}
+
 const struct xfs_btree_ops xfs_rtrmapbt_ops = {
 	.name			= "rtrmap",
 	.type			= XFS_BTREE_TYPE_INODE,
@@ -388,6 +502,7 @@ const struct xfs_btree_ops xfs_rtrmapbt_ops = {
 	.free_block		= xfs_btree_free_metafile_block,
 	.get_minrecs		= xfs_rtrmapbt_get_minrecs,
 	.get_maxrecs		= xfs_rtrmapbt_get_maxrecs,
+	.get_dmaxrecs		= xfs_rtrmapbt_get_dmaxrecs,
 	.init_key_from_rec	= xfs_rtrmapbt_init_key_from_rec,
 	.init_high_key_from_rec	= xfs_rtrmapbt_init_high_key_from_rec,
 	.init_rec_from_cur	= xfs_rtrmapbt_init_rec_from_cur,
@@ -398,6 +513,7 @@ const struct xfs_btree_ops xfs_rtrmapbt_ops = {
 	.keys_inorder		= xfs_rtrmapbt_keys_inorder,
 	.recs_inorder		= xfs_rtrmapbt_recs_inorder,
 	.keys_contiguous	= xfs_rtrmapbt_keys_contiguous,
+	.broot_realloc		= xfs_rtrmapbt_broot_realloc,
 };
 
 /* Allocate a new rt rmap btree cursor. */
@@ -581,3 +697,138 @@ xfs_rtrmapbt_calc_reserves(
 	return max_t(xfs_filblks_t, blocks / 100,
 			xfs_rtrmapbt_max_size(mp, blocks));
 }
+
+/* Convert on-disk form of btree root to in-memory form. */
+STATIC void
+xfs_rtrmapbt_from_disk(
+	struct xfs_inode	*ip,
+	struct xfs_rtrmap_root	*dblock,
+	unsigned int		dblocklen,
+	struct xfs_btree_block	*rblock)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_rmap_key	*fkp;
+	__be64			*fpp;
+	struct xfs_rmap_key	*tkp;
+	__be64			*tpp;
+	struct xfs_rmap_rec	*frp;
+	struct xfs_rmap_rec	*trp;
+	unsigned int		rblocklen = xfs_rtrmap_broot_space(mp, dblock);
+	unsigned int		numrecs;
+	unsigned int		maxrecs;
+
+	xfs_btree_init_block(mp, rblock, &xfs_rtrmapbt_ops, 0, 0, ip->i_ino);
+
+	rblock->bb_level = dblock->bb_level;
+	rblock->bb_numrecs = dblock->bb_numrecs;
+	numrecs = be16_to_cpu(dblock->bb_numrecs);
+
+	if (be16_to_cpu(rblock->bb_level) > 0) {
+		maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false);
+		fkp = xfs_rtrmap_droot_key_addr(dblock, 1);
+		tkp = xfs_rtrmap_key_addr(rblock, 1);
+		fpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs);
+		tpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen);
+		memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs);
+		memcpy(tpp, fpp, sizeof(*fpp) * numrecs);
+	} else {
+		frp = xfs_rtrmap_droot_rec_addr(dblock, 1);
+		trp = xfs_rtrmap_rec_addr(rblock, 1);
+		memcpy(trp, frp, sizeof(*frp) * numrecs);
+	}
+}
+
+/* Load a realtime reverse mapping btree root in from disk. */
+int
+xfs_iformat_rtrmap(
+	struct xfs_inode	*ip,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_rtrmap_root	*dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+	struct xfs_btree_block	*broot;
+	unsigned int		numrecs;
+	unsigned int		level;
+	int			dsize;
+
+	/*
+	 * growfs must create the rtrmap inodes before adding a realtime volume
+	 * to the filesystem, so we cannot use the rtrmapbt predicate here.
+	 */
+	if (!xfs_has_rmapbt(ip->i_mount))
+		return -EFSCORRUPTED;
+
+	dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK);
+	numrecs = be16_to_cpu(dfp->bb_numrecs);
+	level = be16_to_cpu(dfp->bb_level);
+
+	if (level > mp->m_rtrmap_maxlevels ||
+	    xfs_rtrmap_droot_space_calc(level, numrecs) > dsize)
+		return -EFSCORRUPTED;
+
+	broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK),
+			xfs_rtrmap_broot_space_calc(mp, level, numrecs));
+	if (broot)
+		xfs_rtrmapbt_from_disk(ip, dfp, dsize, broot);
+	return 0;
+}
+
+/* Convert in-memory form of btree root to on-disk form. */
+void
+xfs_rtrmapbt_to_disk(
+	struct xfs_mount	*mp,
+	struct xfs_btree_block	*rblock,
+	unsigned int		rblocklen,
+	struct xfs_rtrmap_root	*dblock,
+	unsigned int		dblocklen)
+{
+	struct xfs_rmap_key	*fkp;
+	__be64			*fpp;
+	struct xfs_rmap_key	*tkp;
+	__be64			*tpp;
+	struct xfs_rmap_rec	*frp;
+	struct xfs_rmap_rec	*trp;
+	unsigned int		numrecs;
+	unsigned int		maxrecs;
+
+	ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTRMAP_CRC_MAGIC));
+	ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid));
+	ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL));
+	ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK));
+	ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK));
+
+	dblock->bb_level = rblock->bb_level;
+	dblock->bb_numrecs = rblock->bb_numrecs;
+	numrecs = be16_to_cpu(rblock->bb_numrecs);
+
+	if (be16_to_cpu(rblock->bb_level) > 0) {
+		maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false);
+		fkp = xfs_rtrmap_key_addr(rblock, 1);
+		tkp = xfs_rtrmap_droot_key_addr(dblock, 1);
+		fpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen);
+		tpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs);
+		memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs);
+		memcpy(tpp, fpp, sizeof(*fpp) * numrecs);
+	} else {
+		frp = xfs_rtrmap_rec_addr(rblock, 1);
+		trp = xfs_rtrmap_droot_rec_addr(dblock, 1);
+		memcpy(trp, frp, sizeof(*frp) * numrecs);
+	}
+}
+
+/* Flush a realtime reverse mapping btree root out to disk. */
+void
+xfs_iflush_rtrmap(
+	struct xfs_inode	*ip,
+	struct xfs_dinode	*dip)
+{
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+	struct xfs_rtrmap_root	*dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+
+	ASSERT(ifp->if_broot != NULL);
+	ASSERT(ifp->if_broot_bytes > 0);
+	ASSERT(xfs_rtrmap_droot_space(ifp->if_broot) <=
+			xfs_inode_fork_size(ip, XFS_DATA_FORK));
+	xfs_rtrmapbt_to_disk(ip->i_mount, ifp->if_broot, ifp->if_broot_bytes,
+			dfp, XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK));
+}