[16/44] xfs: allow internal RT devices for zoned mode

Commit Message

Christoph Hellwig Feb. 26, 2025, 6:56 p.m. UTC

Allow creating an RT subvolume on the same device as the main data
device.  This is mostly used for SMR HDDs where the conventional zones
are used for the data device and the sequential write required zones
for the zoned RT section.

Signed-off-by: Christoph Hellwig <[e-mail]>
Reviewed-by: "Darrick J. Wong" <[e-mail]>
---
 fs/xfs/libxfs/xfs_group.h   |  6 ++++--
 fs/xfs/libxfs/xfs_rtgroup.h |  8 +++++---
 fs/xfs/libxfs/xfs_sb.c      |  1 +
 fs/xfs/xfs_file.c           |  2 +-
 fs/xfs/xfs_fsops.c          |  4 ++++
 fs/xfs/xfs_mount.h          |  7 +++++++
 fs/xfs/xfs_rtalloc.c        |  3 ++-
 fs/xfs/xfs_super.c          | 12 ++++++++++--
 8 files changed, 34 insertions(+), 9 deletions(-)

Patch

diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index 242b05627c7a..a70096113384 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -107,9 +107,11 @@  xfs_gbno_to_daddr(
 	xfs_agblock_t		gbno)
 {
 	struct xfs_mount	*mp = xg->xg_mount;
-	uint32_t		blocks = mp->m_groups[xg->xg_type].blocks;
+	struct xfs_groups	*g = &mp->m_groups[xg->xg_type];
+	xfs_fsblock_t		fsbno;
 
-	return XFS_FSB_TO_BB(mp, (xfs_fsblock_t)xg->xg_gno * blocks + gbno);
+	fsbno = (xfs_fsblock_t)xg->xg_gno * g->blocks + gbno;
+	return XFS_FSB_TO_BB(mp, g->start_fsb + fsbno);
 }
 
 static inline uint32_t
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 9c7e03f913cb..e35d1d798327 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -230,7 +230,8 @@  xfs_rtb_to_daddr(
 	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, start_bno + (rtbno & g->blkmask));
+	return XFS_FSB_TO_BB(mp,
+		g->start_fsb + start_bno + (rtbno & g->blkmask));
 }
 
 static inline xfs_rtblock_t
@@ -238,10 +239,11 @@  xfs_daddr_to_rtb(
 	struct xfs_mount	*mp,
 	xfs_daddr_t		daddr)
 {
-	xfs_rfsblock_t		bno = XFS_BB_TO_FSBT(mp, daddr);
+	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
+	xfs_rfsblock_t		bno;
 
+	bno = XFS_BB_TO_FSBT(mp, daddr) - g->start_fsb;
 	if (xfs_has_rtgroups(mp)) {
-		struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG];
 		xfs_rgnumber_t	rgno;
 		uint32_t	rgbno;
 
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index b13d88a10ace..52a04aae44e8 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1204,6 +1204,7 @@  xfs_sb_mount_rextsize(
 		rgs->blocks = sbp->sb_rgextents * sbp->sb_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;
 	} else {
 		rgs->blocks = 0;
 		rgs->blklog = 0;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index d88a771d4c23..807e85e16a52 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -150,7 +150,7 @@  xfs_file_fsync(
 	 * ensure newly written file data make it to disk before logging the new
 	 * inode size in case of an extending write.
 	 */
-	if (XFS_IS_REALTIME_INODE(ip))
+	if (XFS_IS_REALTIME_INODE(ip) && mp->m_rtdev_targp != mp->m_ddev_targp)
 		error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev);
 	else if (mp->m_logdev_targp != mp->m_ddev_targp)
 		error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index b2c733791011..ee2cefbd5df8 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -308,6 +308,10 @@  xfs_growfs_data(
 	if (!mutex_trylock(&mp->m_growlock))
 		return -EWOULDBLOCK;
 
+	/* we can't grow the data section when an internal RT section exists */
+	if (in->newblocks != mp->m_sb.sb_dblocks && mp->m_sb.sb_rtstart)
+		return -EINVAL;
+
 	/* update imaxpct separately to the physical grow of the filesystem */
 	if (in->imaxpct != mp->m_sb.sb_imax_pct) {
 		error = xfs_growfs_imaxpct(mp, in->imaxpct);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 790847d565e0..f08bba9ddb2b 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -103,6 +103,13 @@  struct xfs_groups {
 	 * rtgroup, so this mask must be 64-bit.
 	 */
 	uint64_t		blkmask;
+
+	/*
+	 * Start of the first group in the device.  This is used to support a
+	 * RT device following the data device on the same block device for
+	 * SMR hard drives.
+	 */
+	xfs_fsblock_t		start_fsb;
 };
 
 struct xfs_freecounter {
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index c3a8efc7f09b..a0fd1dc5d362 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1266,7 +1266,8 @@  xfs_rt_check_size(
 		return -EFBIG;
 	}
 
-	error = xfs_buf_read_uncached(mp->m_rtdev_targp, daddr,
+	error = xfs_buf_read_uncached(mp->m_rtdev_targp,
+			XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart) + daddr,
 			XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
 	if (error)
 		xfs_warn(mp, "cannot read last RT device sector (%lld)",
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 817aae726ec1..86d61f3d83cd 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -533,7 +533,15 @@  xfs_setup_devices(
 		if (error)
 			return error;
 	}
-	if (mp->m_rtdev_targp) {
+
+	if (mp->m_sb.sb_rtstart) {
+		if (mp->m_rtdev_targp) {
+			xfs_warn(mp,
+		"can't use internal and external rtdev at the same time");
+			return -EINVAL;
+		}
+		mp->m_rtdev_targp = mp->m_ddev_targp;
+	} else if (mp->m_rtname) {
 		error = xfs_setsize_buftarg(mp->m_rtdev_targp,
 					    mp->m_sb.sb_sectsize);
 		if (error)
@@ -757,7 +765,7 @@  xfs_mount_free(
 {
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_logdev_targp);
-	if (mp->m_rtdev_targp)
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_rtdev_targp);
 	if (mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_ddev_targp);