xfs: support zone gaps

Zoned devices can have gaps beyond the usable capacity of a zone and the
end in the LBA/daddr address space.  In other words, the hardware
equivalent to the RT groups already takes care of the power of 2
alignment for us.  In this case the sparse FSB/RTB address space maps 1:1
to the device address space.

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

Author: Christoph Hellwig

fs/xfs/libxfs/xfs_format.h

@@ -398,6 +398,7 @@ xfs_sb_has_ro_compat_feature(
 #define XFS_SB_FEAT_INCOMPAT_PARENT	(1 << 7)  /* parent pointers */
 #define XFS_SB_FEAT_INCOMPAT_METADIR	(1 << 8)  /* metadata dir tree */
 #define XFS_SB_FEAT_INCOMPAT_ZONED	(1 << 9)  /* zoned RT allocator */
+#define XFS_SB_FEAT_INCOMPAT_ZONE_GAPS	(1 << 10) /* RTGs have LBA gaps */
 
 #define XFS_SB_FEAT_INCOMPAT_ALL \
 		(XFS_SB_FEAT_INCOMPAT_FTYPE | \
@@ -409,7 +410,8 @@ xfs_sb_has_ro_compat_feature(
 		 XFS_SB_FEAT_INCOMPAT_EXCHRANGE | \
 		 XFS_SB_FEAT_INCOMPAT_PARENT | \
 		 XFS_SB_FEAT_INCOMPAT_METADIR | \
-		 XFS_SB_FEAT_INCOMPAT_ZONED)
+		 XFS_SB_FEAT_INCOMPAT_ZONED | \
+		 XFS_SB_FEAT_INCOMPAT_ZONE_GAPS)
 
 #define XFS_SB_FEAT_INCOMPAT_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_ALL
 static inline bool

fs/xfs/libxfs/xfs_group.h

@@ -123,7 +123,11 @@ xfs_gbno_to_daddr(
 	struct xfs_groups	*g = &mp->m_groups[xg->xg_type];
 	xfs_fsblock_t		fsbno;
 
-	fsbno = (xfs_fsblock_t)xg->xg_gno * g->blocks + gbno;
+	if (g->has_daddr_gaps)
+		fsbno = xfs_gbno_to_fsb(xg, gbno);
+	else
+		fsbno = (xfs_fsblock_t)xg->xg_gno * g->blocks + gbno;
+
 	return XFS_FSB_TO_BB(mp, g->start_fsb + fsbno);
 }
 

fs/xfs/libxfs/xfs_rtgroup.h

@@ -245,11 +245,14 @@ xfs_rtb_to_daddr(
 	xfs_rtblock_t		rtbno)
 {
 	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
-	xfs_rgnumber_t		rgno = xfs_rtb_to_rgno(mp, rtbno);
-	uint64_t		start_bno = (xfs_rtblock_t)rgno * g->blocks;
 
-	return XFS_FSB_TO_BB(mp,
-		g->start_fsb + start_bno + (rtbno & g->blkmask));
+	if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) {
+		xfs_rgnumber_t	rgno = xfs_rtb_to_rgno(mp, rtbno);
+
+		rtbno = (xfs_rtblock_t)rgno * g->blocks + (rtbno & g->blkmask);
+	}
+
+	return XFS_FSB_TO_BB(mp, g->start_fsb + rtbno);
 }
 
 static inline xfs_rtblock_t
@@ -261,7 +264,7 @@ xfs_daddr_to_rtb(
 	xfs_rfsblock_t		bno;
 
 	bno = XFS_BB_TO_FSBT(mp, daddr) - g->start_fsb;
-	if (xfs_has_rtgroups(mp)) {
+	if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) {
 		xfs_rgnumber_t	rgno;
 		uint32_t	rgbno;
 

fs/xfs/libxfs/xfs_sb.c

@@ -1205,6 +1205,9 @@ xfs_sb_mount_rextsize(
 		rgs->blklog = mp->m_sb.sb_rgblklog;
 		rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog);
 		rgs->start_fsb = mp->m_sb.sb_rtstart;
+		if (xfs_sb_has_incompat_feature(sbp,
+				XFS_SB_FEAT_INCOMPAT_ZONE_GAPS))
+			rgs->has_daddr_gaps = true;
 	} else {
 		rgs->blocks = 0;
 		rgs->blklog = 0;

fs/xfs/libxfs/xfs_zones.c

@@ -137,6 +137,7 @@ xfs_zone_validate(
 {
 	struct xfs_mount	*mp = rtg_mount(rtg);
 	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
+	uint32_t		expected_size;
 
 	/*
 	 * Check that the zone capacity matches the rtgroup size stored in the
@@ -151,11 +152,25 @@ xfs_zone_validate(
 		return false;
 	}
 
-	if (XFS_BB_TO_FSB(mp, zone->len) != 1 << g->blklog) {
+	if (g->has_daddr_gaps) {
+		expected_size = 1 << g->blklog;
+	} else {
+		if (zone->len != zone->capacity) {
+			xfs_warn(mp,
+"zone %u has capacity != size ((0x%llx vs 0x%llx)",
+				rtg_rgno(rtg),
+				XFS_BB_TO_FSB(mp, zone->len),
+				XFS_BB_TO_FSB(mp, zone->capacity));
+			return false;
+		}
+		expected_size = g->blocks;
+	}
+
+	if (XFS_BB_TO_FSB(mp, zone->len) != expected_size) {
 		xfs_warn(mp,
 "zone %u length (0x%llx) does match geometry (0x%x).",
 			rtg_rgno(rtg), XFS_BB_TO_FSB(mp, zone->len),
-			1 << g->blklog);
+			expected_size);
 	}
 
 	switch (zone->type) {

fs/xfs/xfs_mount.h

@@ -97,6 +97,15 @@ struct xfs_groups {
 	 */
 	uint8_t			blklog;
 
+	/*
+	 * Zoned devices can have gaps beyond the usable capacity of a zone and
+	 * the end in the LBA/daddr address space.  In other words, the hardware
+	 * equivalent to the RT groups already takes care of the power of 2
+	 * alignment for us.  In this case the sparse FSB/RTB address space maps
+	 * 1:1 to the device address space.
+	 */
+	bool			has_daddr_gaps;
+
 	/*
 	 * Mask to extract the group-relative block number from a FSB.
 	 * For a pre-rtgroups filesystem we pretend to have one very large