Merge tag 'realtime-rmap_2024-12-23' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into for-next

xfs: realtime reverse-mapping support [v6.2 04/14]

This is the latest revision of a patchset that adds to XFS kernel
support for reverse mapping for the realtime device.  This time around
I've fixed some of the bitrot that I've noticed over the past few
months, and most notably have converted rtrmapbt to use the metadata
inode directory feature instead of burning more space in the superblock.

At the beginning of the set are patches to implement storing B+tree
leaves in an inode root, since the realtime rmapbt is rooted in an
inode, unlike the regular rmapbt which is rooted in an AG block.
Prior to this, the only btree that could be rooted in the inode fork
was the block mapping btree; if all the extent records fit in the
inode, format would be switched from 'btree' to 'extents'.

The next few patches enhance the reverse mapping routines to handle
the parts that are specific to rtgroups -- adding the new btree type,
adding a new log intent item type, and wiring up the metadata directory
tree entries.

Finally, implement GETFSMAP with the rtrmapbt and scrub functionality
for the rtrmapbt and rtbitmap and online fsck functionality.

This has been running on the djcloud for months with no problems.  Enjoy!

Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>

1 files changed, 63 insertions, 19 deletions

diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 5128c5ad72f5..a69967f9d88e 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -22,6 +22,7 @@
 #include "xfs_rtalloc.h"
 #include "xfs_sb.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_rtrmap_btree.h"
 #include "xfs_quota.h"
 #include "xfs_log_priv.h"
 #include "xfs_health.h"
@@ -845,6 +846,13 @@ xfs_growfs_rt_init_rtsb(
 	mp->m_rtsb_bp = rtsb_bp;
 	error = xfs_bwrite(rtsb_bp);
 	xfs_buf_unlock(rtsb_bp);
+	if (error)
+		return error;
+
+	/* Initialize the rtrmap to reflect the rtsb. */
+	if (rtg_rmap(args->rtg) != NULL)
+		error = xfs_rtrmapbt_init_rtsb(nargs->mp, args->rtg, args->tp);
+
 	return error;
 }
 
@@ -856,8 +864,8 @@ xfs_growfs_rt_bmblock(
 	xfs_fileoff_t		bmbno)
 {
 	struct xfs_mount	*mp = rtg_mount(rtg);
-	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
-	struct xfs_inode	*rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
+	struct xfs_inode	*rbmip = rtg_bitmap(rtg);
+	struct xfs_inode	*rsumip = rtg_summary(rtg);
 	struct xfs_rtalloc_args	args = {
 		.mp		= mp,
 		.rtg		= rtg,
@@ -893,8 +901,9 @@ xfs_growfs_rt_bmblock(
 		goto out_free;
 	nargs.tp = args.tp;
 
-	xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP);
-	xfs_rtgroup_trans_join(args.tp, args.rtg, XFS_RTGLOCK_BITMAP);
+	xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP);
+	xfs_rtgroup_trans_join(args.tp, args.rtg,
+			XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP);
 
 	/*
 	 * Update the bitmap inode's size ondisk and incore.  We need to update
@@ -980,9 +989,11 @@ xfs_growfs_rt_bmblock(
 		goto out_free;
 
 	/*
-	 * Ensure the mount RT feature flag is now set.
+	 * Ensure the mount RT feature flag is now set, and compute new
+	 * maxlevels for rt btrees.
 	 */
 	mp->m_features |= XFS_FEAT_REALTIME;
+	xfs_rtrmapbt_compute_maxlevels(mp);
 
 	kfree(nmp);
 	return 0;
@@ -1041,8 +1052,8 @@ xfs_growfs_rt_alloc_blocks(
 	xfs_extlen_t		*nrbmblocks)
 {
 	struct xfs_mount	*mp = rtg_mount(rtg);
-	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
-	struct xfs_inode	*rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
+	struct xfs_inode	*rbmip = rtg_bitmap(rtg);
+	struct xfs_inode	*rsumip = rtg_summary(rtg);
 	xfs_extlen_t		orbmblocks = 0;
 	xfs_extlen_t		orsumblocks = 0;
 	struct xfs_mount	*nmp;
@@ -1150,29 +1161,37 @@ out_rele:
 	return error;
 }
 
-static int
+int
 xfs_growfs_check_rtgeom(
 	const struct xfs_mount	*mp,
+	xfs_rfsblock_t		dblocks,
 	xfs_rfsblock_t		rblocks,
 	xfs_extlen_t		rextsize)
 {
+	xfs_extlen_t		min_logfsbs;
 	struct xfs_mount	*nmp;
-	int			error = 0;
 
 	nmp = xfs_growfs_rt_alloc_fake_mount(mp, rblocks, rextsize);
 	if (!nmp)
 		return -ENOMEM;
+	nmp->m_sb.sb_dblocks = dblocks;
+
+	xfs_rtrmapbt_compute_maxlevels(nmp);
+	xfs_trans_resv_calc(nmp, M_RES(nmp));
 
 	/*
 	 * New summary size can't be more than half the size of the log.  This
 	 * prevents us from getting a log overflow, since we'll log basically
 	 * the whole summary file at once.
 	 */
-	if (nmp->m_rsumblocks > (mp->m_sb.sb_logblocks >> 1))
-		error = -EINVAL;
+	min_logfsbs = min_t(xfs_extlen_t, xfs_log_calc_minimum_size(nmp),
+			nmp->m_rsumblocks * 2);
 
 	kfree(nmp);
-	return error;
+
+	if (min_logfsbs > mp->m_sb.sb_logblocks)
+		return -EINVAL;
+	return 0;
 }
 
 /*
@@ -1263,11 +1282,15 @@ xfs_growfs_rt(
 	    XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE)
 		goto out_unlock;
 
-	/* Unsupported realtime features. */
+	/* Check for features supported only on rtgroups filesystems. */
 	error = -EOPNOTSUPP;
-	if (xfs_has_quota(mp) && !xfs_has_rtgroups(mp))
-		goto out_unlock;
-	if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp))
+	if (!xfs_has_rtgroups(mp)) {
+		if (xfs_has_rmapbt(mp))
+			goto out_unlock;
+		if (xfs_has_quota(mp))
+			goto out_unlock;
+	}
+	if (xfs_has_reflink(mp))
 		goto out_unlock;
 
 	error = xfs_sb_validate_fsb_count(&mp->m_sb, in->newblocks);
@@ -1291,7 +1314,8 @@ xfs_growfs_rt(
 		goto out_unlock;
 
 	/* Make sure the new fs size won't cause problems with the log. */
-	error = xfs_growfs_check_rtgeom(mp, in->newblocks, in->extsize);
+	error = xfs_growfs_check_rtgeom(mp, mp->m_sb.sb_dblocks, in->newblocks,
+			in->extsize);
 	if (error)
 		goto out_unlock;
 
@@ -1498,6 +1522,13 @@ void
 xfs_rt_resv_free(
 	struct xfs_mount	*mp)
 {
+	struct xfs_rtgroup	*rtg = NULL;
+	unsigned int		i;
+
+	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+		for (i = 0; i < XFS_RTGI_MAX; i++)
+			xfs_metafile_resv_free(rtg->rtg_inodes[i]);
+	}
 }
 
 /* Reserve space for rt metadata inodes' space expansion. */
@@ -1505,7 +1536,20 @@ int
 xfs_rt_resv_init(
 	struct xfs_mount	*mp)
 {
-	return 0;
+	struct xfs_rtgroup	*rtg = NULL;
+	xfs_filblks_t		ask;
+	int			error = 0;
+
+	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+		int		err2;
+
+		ask = xfs_rtrmapbt_calc_reserves(mp);
+		err2 = xfs_metafile_resv_init(rtg_rmap(rtg), ask);
+		if (err2 && !error)
+			error = err2;
+	}
+
+	return error;
 }
 
 /*
@@ -1622,7 +1666,7 @@ xfs_rtpick_extent(
 	xfs_rtxlen_t		len)		/* allocation length (rtextents) */
 {
 	struct xfs_mount	*mp = rtg_mount(rtg);
-	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
+	struct xfs_inode	*rbmip = rtg_bitmap(rtg);
 	xfs_rtxnum_t		b = 0;		/* result rtext */
 	int			log2;		/* log of sequence number */
 	uint64_t		resid;		/* residual after log removed */