Merge tag 'incore-rtgroups-6.13_2024-11-05' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into staging-merge

xfs: create incore rt allocation groups [v5.5 04/10]

Add in-memory data structures for sharding the realtime volume into
independent allocation groups.  For existing filesystems, the entire rt
volume is modelled as having a single large group, with (potentially) a
number of rt extents exceeding 2^32 blocks, though these are not likely
to exist because the codebase has been a bit broken for decades.  The
next series fills in the ondisk format and other supporting structures.

With a bit of luck, this should all go splendidly.

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

9 files changed, 983 insertions, 181 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7805a36e98c4..9bfa8247854d 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4094,7 +4094,7 @@ retry:
 
 	fdblocks = indlen;
 	if (XFS_IS_REALTIME_INODE(ip)) {
-		error = xfs_dec_frextents(mp, xfs_rtb_to_rtx(mp, alen));
+		error = xfs_dec_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
 		if (error)
 			goto out_unreserve_quota;
 	} else {
@@ -4129,7 +4129,7 @@ retry:
 
 out_unreserve_frextents:
 	if (XFS_IS_REALTIME_INODE(ip))
-		xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, alen));
+		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
 out_unreserve_quota:
 	if (XFS_IS_QUOTA_ON(mp))
 		xfs_quota_unreserve_blkres(ip, alen);
@@ -5037,7 +5037,7 @@ xfs_bmap_del_extent_delay(
 	fdblocks = da_diff;
 
 	if (isrt)
-		xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, del->br_blockcount));
+		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, del->br_blockcount));
 	else
 		fdblocks += del->br_blockcount;
 
@@ -5116,6 +5116,34 @@ xfs_bmap_del_extent_cow(
 	ip->i_delayed_blks -= del->br_blockcount;
 }
 
+static int
+xfs_bmap_free_rtblocks(
+	struct xfs_trans	*tp,
+	struct xfs_bmbt_irec	*del)
+{
+	struct xfs_rtgroup	*rtg;
+	int			error;
+
+	rtg = xfs_rtgroup_grab(tp->t_mountp, 0);
+	if (!rtg)
+		return -EIO;
+
+	/*
+	 * Ensure the bitmap and summary inodes are locked and joined to the
+	 * transaction before modifying them.
+	 */
+	if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
+		tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP);
+		xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_BITMAP);
+	}
+
+	error = xfs_rtfree_blocks(tp, rtg, del->br_startblock,
+			del->br_blockcount);
+	xfs_rtgroup_rele(rtg);
+	return error;
+}
+
 /*
  * Called by xfs_bmapi to update file extent records and the btree
  * after removing space.
@@ -5331,17 +5359,7 @@ xfs_bmap_del_extent_real(
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
 			xfs_refcount_decrease_extent(tp, del);
 		} else if (xfs_ifork_is_realtime(ip, whichfork)) {
-			/*
-			 * Ensure the bitmap and summary inodes are locked
-			 * and joined to the transaction before modifying them.
-			 */
-			if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
-				tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
-				xfs_rtbitmap_lock(mp);
-				xfs_rtbitmap_trans_join(tp);
-			}
-			error = xfs_rtfree_blocks(tp, del->br_startblock,
-					del->br_blockcount);
+			error = xfs_bmap_free_rtblocks(tp, del);
 		} else {
 			unsigned int	efi_flags = 0;
 
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 616f81045921..867060d60e85 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -176,6 +176,9 @@ typedef struct xfs_sb {
 
 	xfs_ino_t	sb_metadirino;	/* metadata directory tree root */
 
+	xfs_rgnumber_t	sb_rgcount;	/* number of realtime groups */
+	xfs_rtxlen_t	sb_rgextents;	/* size of a realtime group in rtx */
+
 	/* must be padded to 64 bit alignment */
 } xfs_sb_t;
 
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 27a4472402ba..54079edfe10f 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -20,6 +20,7 @@
 #include "xfs_error.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_health.h"
+#include "xfs_sb.h"
 
 /*
  * Realtime allocator bitmap functions shared with userspace.
@@ -90,12 +91,12 @@ xfs_rtbuf_get(
 	if (issum) {
 		cbpp = &args->sumbp;
 		coffp = &args->sumoff;
-		ip = mp->m_rsumip;
+		ip = args->rtg->rtg_inodes[XFS_RTGI_SUMMARY];
 		type = XFS_BLFT_RTSUMMARY_BUF;
 	} else {
 		cbpp = &args->rbmbp;
 		coffp = &args->rbmoff;
-		ip = mp->m_rbmip;
+		ip = args->rtg->rtg_inodes[XFS_RTGI_BITMAP];
 		type = XFS_BLFT_RTBITMAP_BUF;
 	}
 
@@ -503,6 +504,7 @@ xfs_rtmodify_summary(
 {
 	struct xfs_mount	*mp = args->mp;
 	xfs_rtsumoff_t		so = xfs_rtsumoffs(mp, log, bbno);
+	uint8_t			*rsum_cache = args->rtg->rtg_rsum_cache;
 	unsigned int		infoword;
 	xfs_suminfo_t		val;
 	int			error;
@@ -514,11 +516,11 @@ xfs_rtmodify_summary(
 	infoword = xfs_rtsumoffs_to_infoword(mp, so);
 	val = xfs_suminfo_add(args, infoword, delta);
 
-	if (mp->m_rsum_cache) {
-		if (val == 0 && log + 1 == mp->m_rsum_cache[bbno])
-			mp->m_rsum_cache[bbno] = log;
-		if (val != 0 && log >= mp->m_rsum_cache[bbno])
-			mp->m_rsum_cache[bbno] = log + 1;
+	if (rsum_cache) {
+		if (val == 0 && log + 1 == rsum_cache[bbno])
+			rsum_cache[bbno] = log;
+		if (val != 0 && log >= rsum_cache[bbno])
+			rsum_cache[bbno] = log + 1;
 	}
 
 	xfs_trans_log_rtsummary(args, infoword);
@@ -737,7 +739,7 @@ xfs_rtfree_range(
 	/*
 	 * Find the next allocated block (end of allocated extent).
 	 */
-	error = xfs_rtfind_forw(args, end, mp->m_sb.sb_rextents - 1,
+	error = xfs_rtfind_forw(args, end, args->rtg->rtg_extents - 1,
 			&postblock);
 	if (error)
 		return error;
@@ -961,19 +963,22 @@ xfs_rtcheck_alloc_range(
 int
 xfs_rtfree_extent(
 	struct xfs_trans	*tp,	/* transaction pointer */
+	struct xfs_rtgroup	*rtg,
 	xfs_rtxnum_t		start,	/* starting rtext number to free */
 	xfs_rtxlen_t		len)	/* length of extent freed */
 {
 	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
 	struct xfs_rtalloc_args	args = {
 		.mp		= mp,
 		.tp		= tp,
+		.rtg		= rtg,
 	};
 	int			error;
 	struct timespec64	atime;
 
-	ASSERT(mp->m_rbmip->i_itemp != NULL);
-	xfs_assert_ilocked(mp->m_rbmip, XFS_ILOCK_EXCL);
+	ASSERT(rbmip->i_itemp != NULL);
+	xfs_assert_ilocked(rbmip, XFS_ILOCK_EXCL);
 
 	error = xfs_rtcheck_alloc_range(&args, start, len);
 	if (error)
@@ -996,13 +1001,13 @@ xfs_rtfree_extent(
 	 */
 	if (tp->t_frextents_delta + mp->m_sb.sb_frextents ==
 	    mp->m_sb.sb_rextents) {
-		if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM))
-			mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
+		if (!(rbmip->i_diflags & XFS_DIFLAG_NEWRTBM))
+			rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
 
-		atime = inode_get_atime(VFS_I(mp->m_rbmip));
+		atime = inode_get_atime(VFS_I(rbmip));
 		atime.tv_sec = 0;
-		inode_set_atime_to_ts(VFS_I(mp->m_rbmip), atime);
-		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
+		inode_set_atime_to_ts(VFS_I(rbmip), atime);
+		xfs_trans_log_inode(tp, rbmip, XFS_ILOG_CORE);
 	}
 	error = 0;
 out:
@@ -1018,6 +1023,7 @@ out:
 int
 xfs_rtfree_blocks(
 	struct xfs_trans	*tp,
+	struct xfs_rtgroup	*rtg,
 	xfs_fsblock_t		rtbno,
 	xfs_filblks_t		rtlen)
 {
@@ -1038,21 +1044,23 @@ xfs_rtfree_blocks(
 		return -EIO;
 	}
 
-	return xfs_rtfree_extent(tp, xfs_rtb_to_rtx(mp, rtbno),
-			xfs_rtb_to_rtx(mp, rtlen));
+	return xfs_rtfree_extent(tp, rtg, xfs_rtb_to_rtx(mp, rtbno),
+			xfs_extlen_to_rtxlen(mp, rtlen));
 }
 
 /* Find all the free records within a given range. */
 int
 xfs_rtalloc_query_range(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	xfs_rtxnum_t			start,
 	xfs_rtxnum_t			end,
 	xfs_rtalloc_query_range_fn	fn,
 	void				*priv)
 {
+	struct xfs_mount		*mp = rtg_mount(rtg);
 	struct xfs_rtalloc_args		args = {
+		.rtg			= rtg,
 		.mp			= mp,
 		.tp			= tp,
 	};
@@ -1060,10 +1068,10 @@ xfs_rtalloc_query_range(
 
 	if (start > end)
 		return -EINVAL;
-	if (start == end || start >= mp->m_sb.sb_rextents)
+	if (start == end || start >= rtg->rtg_extents)
 		return 0;
 
-	end = min(end, mp->m_sb.sb_rextents - 1);
+	end = min(end, rtg->rtg_extents - 1);
 
 	/* Iterate the bitmap, looking for discrepancies. */
 	while (start <= end) {
@@ -1086,7 +1094,7 @@ xfs_rtalloc_query_range(
 			rec.ar_startext = start;
 			rec.ar_extcount = rtend - start + 1;
 
-			error = fn(mp, tp, &rec, priv);
+			error = fn(rtg, tp, &rec, priv);
 			if (error)
 				break;
 		}
@@ -1101,26 +1109,27 @@ xfs_rtalloc_query_range(
 /* Find all the free records. */
 int
 xfs_rtalloc_query_all(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	xfs_rtalloc_query_range_fn	fn,
 	void				*priv)
 {
-	return xfs_rtalloc_query_range(mp, tp, 0, mp->m_sb.sb_rextents - 1, fn,
+	return xfs_rtalloc_query_range(rtg, tp, 0, rtg->rtg_extents - 1, fn,
 			priv);
 }
 
 /* Is the given extent all free? */
 int
 xfs_rtalloc_extent_is_free(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	xfs_rtxnum_t			start,
 	xfs_rtxlen_t			len,
 	bool				*is_free)
 {
 	struct xfs_rtalloc_args		args = {
-		.mp			= mp,
+		.mp			= rtg_mount(rtg),
+		.rtg			= rtg,
 		.tp			= tp,
 	};
 	xfs_rtxnum_t			end;
@@ -1141,83 +1150,38 @@ xfs_rtalloc_extent_is_free(
  * extents.
  */
 xfs_filblks_t
-xfs_rtbitmap_blockcount(
+xfs_rtbitmap_blockcount_len(
 	struct xfs_mount	*mp,
 	xfs_rtbxlen_t		rtextents)
 {
 	return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize);
 }
 
-/* Compute the number of rtsummary blocks needed to track the given rt space. */
-xfs_filblks_t
-xfs_rtsummary_blockcount(
-	struct xfs_mount	*mp,
-	unsigned int		rsumlevels,
-	xfs_extlen_t		rbmblocks)
-{
-	unsigned long long	rsumwords;
-
-	rsumwords = (unsigned long long)rsumlevels * rbmblocks;
-	return XFS_B_TO_FSB(mp, rsumwords << XFS_WORDLOG);
-}
-
-/* Lock both realtime free space metadata inodes for a freespace update. */
-void
-xfs_rtbitmap_lock(
-	struct xfs_mount	*mp)
-{
-	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
-	xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
-}
-
 /*
- * Join both realtime free space metadata inodes to the transaction.  The
- * ILOCKs will be released on transaction commit.
+ * Compute the number of rtbitmap blocks used for a given file system.
  */
-void
-xfs_rtbitmap_trans_join(
-	struct xfs_trans	*tp)
-{
-	xfs_trans_ijoin(tp, tp->t_mountp->m_rbmip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, tp->t_mountp->m_rsumip, XFS_ILOCK_EXCL);
-}
-
-/* Unlock both realtime free space metadata inodes after a freespace update. */
-void
-xfs_rtbitmap_unlock(
+xfs_filblks_t
+xfs_rtbitmap_blockcount(
 	struct xfs_mount	*mp)
 {
-	xfs_iunlock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
-	xfs_iunlock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
+	return xfs_rtbitmap_blockcount_len(mp, mp->m_sb.sb_rextents);
 }
 
 /*
- * Lock the realtime free space metadata inodes for a freespace scan.  Callers
- * must walk metadata blocks in order of increasing file offset.
+ * Compute the geometry of the rtsummary file needed to track the given rt
+ * space.
  */
-void
-xfs_rtbitmap_lock_shared(
+xfs_filblks_t
+xfs_rtsummary_blockcount(
 	struct xfs_mount	*mp,
-	unsigned int		rbmlock_flags)
+	unsigned int		*rsumlevels)
 {
-	if (rbmlock_flags & XFS_RBMLOCK_BITMAP)
-		xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
-
-	if (rbmlock_flags & XFS_RBMLOCK_SUMMARY)
-		xfs_ilock(mp->m_rsumip, XFS_ILOCK_SHARED | XFS_ILOCK_RTSUM);
-}
+	unsigned long long	rsumwords;
 
-/* Unlock the realtime free space metadata inodes after a freespace scan. */
-void
-xfs_rtbitmap_unlock_shared(
-	struct xfs_mount	*mp,
-	unsigned int		rbmlock_flags)
-{
-	if (rbmlock_flags & XFS_RBMLOCK_SUMMARY)
-		xfs_iunlock(mp->m_rsumip, XFS_ILOCK_SHARED | XFS_ILOCK_RTSUM);
+	*rsumlevels = xfs_compute_rextslog(mp->m_sb.sb_rextents) + 1;
 
-	if (rbmlock_flags & XFS_RBMLOCK_BITMAP)
-		xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+	rsumwords = xfs_rtbitmap_blockcount(mp) * (*rsumlevels);
+	return XFS_B_TO_FSB(mp, rsumwords << XFS_WORDLOG);
 }
 
 static int
@@ -1260,21 +1224,25 @@ out_trans_cancel:
 /* Get a buffer for the block. */
 static int
 xfs_rtfile_initialize_block(
-	struct xfs_inode	*ip,
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type,
 	xfs_fsblock_t		fsbno,
 	void			*data)
 {
-	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_inode	*ip = rtg->rtg_inodes[type];
 	struct xfs_trans	*tp;
 	struct xfs_buf		*bp;
 	const size_t		copylen = mp->m_blockwsize << XFS_WORDLOG;
 	enum xfs_blft		buf_type;
 	int			error;
 
-	if (ip == mp->m_rsumip)
+	if (type == XFS_RTGI_BITMAP)
+		buf_type = XFS_BLFT_RTBITMAP_BUF;
+	else if (type == XFS_RTGI_SUMMARY)
 		buf_type = XFS_BLFT_RTSUMMARY_BUF;
 	else
-		buf_type = XFS_BLFT_RTBITMAP_BUF;
+		return -EINVAL;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtzero, 0, 0, 0, &tp);
 	if (error)
@@ -1306,12 +1274,13 @@ xfs_rtfile_initialize_block(
  */
 int
 xfs_rtfile_initialize_blocks(
-	struct xfs_inode	*ip,		/* inode (bitmap/summary) */
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type,
 	xfs_fileoff_t		offset_fsb,	/* offset to start from */
 	xfs_fileoff_t		end_fsb,	/* offset to allocate to */
 	void			*data)		/* data to fill the blocks */
 {
-	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_mount	*mp = rtg_mount(rtg);
 	const size_t		copylen = mp->m_blockwsize << XFS_WORDLOG;
 
 	while (offset_fsb < end_fsb) {
@@ -1319,8 +1288,8 @@ xfs_rtfile_initialize_blocks(
 		xfs_filblks_t		i;
 		int			error;
 
-		error = xfs_rtfile_alloc_blocks(ip, offset_fsb,
-				end_fsb - offset_fsb, &map);
+		error = xfs_rtfile_alloc_blocks(rtg->rtg_inodes[type],
+				offset_fsb, end_fsb - offset_fsb, &map);
 		if (error)
 			return error;
 
@@ -1330,7 +1299,7 @@ xfs_rtfile_initialize_blocks(
 		 * Do this one block per transaction, to keep it simple.
 		 */
 		for (i = 0; i < map.br_blockcount; i++) {
-			error = xfs_rtfile_initialize_block(ip,
+			error = xfs_rtfile_initialize_block(rtg, type,
 					map.br_startblock + i, data);
 			if (error)
 				return error;
@@ -1343,3 +1312,35 @@ xfs_rtfile_initialize_blocks(
 
 	return 0;
 }
+
+int
+xfs_rtbitmap_create(
+	struct xfs_rtgroup	*rtg,
+	struct xfs_inode	*ip,
+	struct xfs_trans	*tp,
+	bool			init)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	ip->i_disk_size = mp->m_sb.sb_rbmblocks * mp->m_sb.sb_blocksize;
+	if (init && !xfs_has_rtgroups(mp)) {
+		ip->i_diflags |= XFS_DIFLAG_NEWRTBM;
+		inode_set_atime(VFS_I(ip), 0, 0);
+	}
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return 0;
+}
+
+int
+xfs_rtsummary_create(
+	struct xfs_rtgroup	*rtg,
+	struct xfs_inode	*ip,
+	struct xfs_trans	*tp,
+	bool			init)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	ip->i_disk_size = mp->m_rsumblocks * mp->m_sb.sb_blocksize;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 140513d1d6bc..b2b9e59a87a2 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -6,7 +6,10 @@
 #ifndef __XFS_RTBITMAP_H__
 #define	__XFS_RTBITMAP_H__
 
+#include "xfs_rtgroup.h"
+
 struct xfs_rtalloc_args {
+	struct xfs_rtgroup	*rtg;
 	struct xfs_mount	*mp;
 	struct xfs_trans	*tp;
 
@@ -19,13 +22,37 @@ struct xfs_rtalloc_args {
 
 static inline xfs_rtblock_t
 xfs_rtx_to_rtb(
-	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
 	xfs_rtxnum_t		rtx)
 {
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	xfs_rtblock_t		start = xfs_rgno_start_rtb(mp, rtg_rgno(rtg));
+
+	if (mp->m_rtxblklog >= 0)
+		return start + (rtx << mp->m_rtxblklog);
+	return start + (rtx * mp->m_sb.sb_rextsize);
+}
+
+/* Convert an rgbno into an rt extent number. */
+static inline xfs_rtxnum_t
+xfs_rgbno_to_rtx(
+	struct xfs_mount	*mp,
+	xfs_rgblock_t		rgbno)
+{
+	if (likely(mp->m_rtxblklog >= 0))
+		return rgbno >> mp->m_rtxblklog;
+	return rgbno / mp->m_sb.sb_rextsize;
+}
+
+static inline uint64_t
+xfs_rtbxlen_to_blen(
+	struct xfs_mount	*mp,
+	xfs_rtbxlen_t		rtbxlen)
+{
 	if (mp->m_rtxblklog >= 0)
-		return rtx << mp->m_rtxblklog;
+		return rtbxlen << mp->m_rtxblklog;
 
-	return rtx * mp->m_sb.sb_rextsize;
+	return rtbxlen * mp->m_sb.sb_rextsize;
 }
 
 static inline xfs_extlen_t
@@ -62,16 +89,29 @@ xfs_extlen_to_rtxlen(
 	return len / mp->m_sb.sb_rextsize;
 }
 
+/* Convert an rt block count into an rt extent count. */
+static inline xfs_rtbxlen_t
+xfs_blen_to_rtbxlen(
+	struct xfs_mount	*mp,
+	uint64_t		blen)
+{
+	if (likely(mp->m_rtxblklog >= 0))
+		return blen >> mp->m_rtxblklog;
+
+	return div_u64(blen, mp->m_sb.sb_rextsize);
+}
+
 /* Convert an rt block number into an rt extent number. */
 static inline xfs_rtxnum_t
 xfs_rtb_to_rtx(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
-	if (likely(mp->m_rtxblklog >= 0))
-		return rtbno >> mp->m_rtxblklog;
+	uint64_t		__rgbno = __xfs_rtb_to_rgbno(mp, rtbno);
 
-	return div_u64(rtbno, mp->m_sb.sb_rextsize);
+	if (likely(mp->m_rtxblklog >= 0))
+		return __rgbno >> mp->m_rtxblklog;
+	return div_u64(__rgbno, mp->m_sb.sb_rextsize);
 }
 
 /* Return the offset of an rt block number within an rt extent. */
@@ -86,26 +126,6 @@ xfs_rtb_to_rtxoff(
 	return do_div(rtbno, mp->m_sb.sb_rextsize);
 }
 
-/*
- * Convert an rt block number into an rt extent number, rounding up to the next
- * rt extent if the rt block is not aligned to an rt extent boundary.
- */
-static inline xfs_rtxnum_t
-xfs_rtb_to_rtxup(
-	struct xfs_mount	*mp,
-	xfs_rtblock_t		rtbno)
-{
-	if (likely(mp->m_rtxblklog >= 0)) {
-		if (rtbno & mp->m_rtxblkmask)
-			return (rtbno >> mp->m_rtxblklog) + 1;
-		return rtbno >> mp->m_rtxblklog;
-	}
-
-	if (do_div(rtbno, mp->m_sb.sb_rextsize))
-		rtbno++;
-	return rtbno;
-}
-
 /* Round this rtblock up to the nearest rt extent size. */
 static inline xfs_rtblock_t
 xfs_rtb_roundup_rtx(
@@ -268,7 +288,7 @@ struct xfs_rtalloc_rec {
 };
 
 typedef int (*xfs_rtalloc_query_range_fn)(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	const struct xfs_rtalloc_rec	*rec,
 	void				*priv);
@@ -291,53 +311,42 @@ int xfs_rtmodify_summary(struct xfs_rtalloc_args *args, int log,
 		xfs_fileoff_t bbno, int delta);
 int xfs_rtfree_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
 		xfs_rtxlen_t len);
-int xfs_rtalloc_query_range(struct xfs_mount *mp, struct xfs_trans *tp,
+int xfs_rtalloc_query_range(struct xfs_rtgroup *rtg, struct xfs_trans *tp,
 		xfs_rtxnum_t start, xfs_rtxnum_t end,
 		xfs_rtalloc_query_range_fn fn, void *priv);
-int xfs_rtalloc_query_all(struct xfs_mount *mp, struct xfs_trans *tp,
-			  xfs_rtalloc_query_range_fn fn,
-			  void *priv);
-int xfs_rtalloc_extent_is_free(struct xfs_mount *mp, struct xfs_trans *tp,
-			       xfs_rtxnum_t start, xfs_rtxlen_t len,
-			       bool *is_free);
-/*
- * Free an extent in the realtime subvolume.  Length is expressed in
- * realtime extents, as is the block number.
- */
-int					/* error */
-xfs_rtfree_extent(
-	struct xfs_trans	*tp,	/* transaction pointer */
-	xfs_rtxnum_t		start,	/* starting rtext number to free */
-	xfs_rtxlen_t		len);	/* length of extent freed */
-
+int xfs_rtalloc_query_all(struct xfs_rtgroup *rtg, struct xfs_trans *tp,
+		xfs_rtalloc_query_range_fn fn, void *priv);
+int xfs_rtalloc_extent_is_free(struct xfs_rtgroup *rtg, struct xfs_trans *tp,
+		xfs_rtxnum_t start, xfs_rtxlen_t len, bool *is_free);
+int xfs_rtfree_extent(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
+		xfs_rtxnum_t start, xfs_rtxlen_t len);
 /* Same as above, but in units of rt blocks. */
-int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
-		xfs_filblks_t rtlen);
+int xfs_rtfree_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
+		xfs_fsblock_t rtbno, xfs_filblks_t rtlen);
 
-xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
-		rtextents);
+xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp);
+xfs_filblks_t xfs_rtbitmap_blockcount_len(struct xfs_mount *mp,
+		xfs_rtbxlen_t rtextents);
 xfs_filblks_t xfs_rtsummary_blockcount(struct xfs_mount *mp,
-		unsigned int rsumlevels, xfs_extlen_t rbmblocks);
-
-int xfs_rtfile_initialize_blocks(struct xfs_inode *ip,
-		xfs_fileoff_t offset_fsb, xfs_fileoff_t end_fsb, void *data);
+		unsigned int *rsumlevels);
 
-void xfs_rtbitmap_lock(struct xfs_mount *mp);
-void xfs_rtbitmap_unlock(struct xfs_mount *mp);
-void xfs_rtbitmap_trans_join(struct xfs_trans *tp);
+int xfs_rtfile_initialize_blocks(struct xfs_rtgroup *rtg,
+		enum xfs_rtg_inodes type, xfs_fileoff_t offset_fsb,
+		xfs_fileoff_t end_fsb, void *data);
+int xfs_rtbitmap_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip,
+		struct xfs_trans *tp, bool init);
+int xfs_rtsummary_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip,
+		struct xfs_trans *tp, bool init);
 
-/* Lock the rt bitmap inode in shared mode */
-#define XFS_RBMLOCK_BITMAP	(1U << 0)
-/* Lock the rt summary inode in shared mode */
-#define XFS_RBMLOCK_SUMMARY	(1U << 1)
-
-void xfs_rtbitmap_lock_shared(struct xfs_mount *mp,
-		unsigned int rbmlock_flags);
-void xfs_rtbitmap_unlock_shared(struct xfs_mount *mp,
-		unsigned int rbmlock_flags);
 #else /* CONFIG_XFS_RT */
 # define xfs_rtfree_extent(t,b,l)			(-ENOSYS)
-# define xfs_rtfree_blocks(t,rb,rl)			(-ENOSYS)
+
+static inline int xfs_rtfree_blocks(struct xfs_trans *tp,
+		struct xfs_rtgroup *rtg, xfs_fsblock_t rtbno,
+		xfs_filblks_t rtlen)
+{
+	return -ENOSYS;
+}
 # define xfs_rtalloc_query_range(m,t,l,h,f,p)		(-ENOSYS)
 # define xfs_rtalloc_query_all(m,t,f,p)			(-ENOSYS)
 # define xfs_rtbitmap_read_buf(a,b)			(-ENOSYS)
@@ -345,17 +354,11 @@ void xfs_rtbitmap_unlock_shared(struct xfs_mount *mp,
 # define xfs_rtbuf_cache_relse(a)			(0)
 # define xfs_rtalloc_extent_is_free(m,t,s,l,i)		(-ENOSYS)
 static inline xfs_filblks_t
-xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
+xfs_rtbitmap_blockcount_len(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 {
 	/* shut up gcc */
 	return 0;
 }
-# define xfs_rtsummary_blockcount(mp, l, b)		(0)
-# define xfs_rtbitmap_lock(mp)			do { } while (0)
-# define xfs_rtbitmap_trans_join(tp)		do { } while (0)
-# define xfs_rtbitmap_unlock(mp)		do { } while (0)
-# define xfs_rtbitmap_lock_shared(mp, lf)	do { } while (0)
-# define xfs_rtbitmap_unlock_shared(mp, lf)	do { } while (0)
 #endif /* CONFIG_XFS_RT */
 
 #endif /* __XFS_RTBITMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
new file mode 100644
index 000000000000..da29f41e51f1
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -0,0 +1,484 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_ag.h"
+#include "xfs_ag_resv.h"
+#include "xfs_health.h"
+#include "xfs_error.h"
+#include "xfs_bmap.h"
+#include "xfs_defer.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_trace.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_metafile.h"
+#include "xfs_metadir.h"
+
+int
+xfs_rtgroup_alloc(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgnumber_t		rgcount,
+	xfs_rtbxlen_t		rextents)
+{
+	struct xfs_rtgroup	*rtg;
+	int			error;
+
+	rtg = kzalloc(sizeof(struct xfs_rtgroup), GFP_KERNEL);
+	if (!rtg)
+		return -ENOMEM;
+
+	error = xfs_group_insert(mp, rtg_group(rtg), rgno, XG_TYPE_RTG);
+	if (error)
+		goto out_free_rtg;
+	return 0;
+
+out_free_rtg:
+	kfree(rtg);
+	return error;
+}
+
+void
+xfs_rtgroup_free(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	xfs_group_free(mp, rgno, XG_TYPE_RTG, NULL);
+}
+
+/* Free a range of incore rtgroup objects. */
+void
+xfs_free_rtgroups(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		first_rgno,
+	xfs_rgnumber_t		end_rgno)
+{
+	xfs_rgnumber_t		rgno;
+
+	for (rgno = first_rgno; rgno < end_rgno; rgno++)
+		xfs_rtgroup_free(mp, rgno);
+}
+
+/* Initialize some range of incore rtgroup objects. */
+int
+xfs_initialize_rtgroups(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		first_rgno,
+	xfs_rgnumber_t		end_rgno,
+	xfs_rtbxlen_t		rextents)
+{
+	xfs_rgnumber_t		index;
+	int			error;
+
+	if (first_rgno >= end_rgno)
+		return 0;
+
+	for (index = first_rgno; index < end_rgno; index++) {
+		error = xfs_rtgroup_alloc(mp, index, end_rgno, rextents);
+		if (error)
+			goto out_unwind_new_rtgs;
+	}
+
+	return 0;
+
+out_unwind_new_rtgs:
+	xfs_free_rtgroups(mp, first_rgno, index);
+	return error;
+}
+
+/* Compute the number of rt extents in this realtime group. */
+xfs_rtxnum_t
+__xfs_rtgroup_extents(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgnumber_t		rgcount,
+	xfs_rtbxlen_t		rextents)
+{
+	ASSERT(rgno < rgcount);
+	if (rgno == rgcount - 1)
+		return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents);
+
+	ASSERT(xfs_has_rtgroups(mp));
+	return mp->m_sb.sb_rgextents;
+}
+
+xfs_rtxnum_t
+xfs_rtgroup_extents(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount,
+			mp->m_sb.sb_rextents);
+}
+
+/*
+ * Update the rt extent count of the previous tail rtgroup if it changed during
+ * recovery (i.e. recovery of a growfs).
+ */
+int
+xfs_update_last_rtgroup_size(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		prev_rgcount)
+{
+	struct xfs_rtgroup	*rtg;
+
+	ASSERT(prev_rgcount > 0);
+
+	rtg = xfs_rtgroup_grab(mp, prev_rgcount - 1);
+	if (!rtg)
+		return -EFSCORRUPTED;
+	rtg->rtg_extents = __xfs_rtgroup_extents(mp, prev_rgcount - 1,
+			mp->m_sb.sb_rgcount, mp->m_sb.sb_rextents);
+	xfs_rtgroup_rele(rtg);
+	return 0;
+}
+
+/* Lock metadata inodes associated with this rt group. */
+void
+xfs_rtgroup_lock(
+	struct xfs_rtgroup	*rtg,
+	unsigned int		rtglock_flags)
+{
+	ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
+	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
+	       !(rtglock_flags & XFS_RTGLOCK_BITMAP));
+
+	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+		/*
+		 * Lock both realtime free space metadata inodes for a freespace
+		 * update.
+		 */
+		xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL);
+		xfs_ilock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL);
+	} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
+		xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED);
+	}
+}
+
+/* Unlock metadata inodes associated with this rt group. */
+void
+xfs_rtgroup_unlock(
+	struct xfs_rtgroup	*rtg,
+	unsigned int		rtglock_flags)
+{
+	ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
+	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
+	       !(rtglock_flags & XFS_RTGLOCK_BITMAP));
+
+	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+		xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL);
+		xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL);
+	} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
+		xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED);
+	}
+}
+
+/*
+ * Join realtime group metadata inodes to the transaction.  The ILOCKs will be
+ * released on transaction commit.
+ */
+void
+xfs_rtgroup_trans_join(
+	struct xfs_trans	*tp,
+	struct xfs_rtgroup	*rtg,
+	unsigned int		rtglock_flags)
+{
+	ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
+	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED));
+
+	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+		xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_BITMAP],
+				XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_SUMMARY],
+				XFS_ILOCK_EXCL);
+	}
+}
+
+#ifdef CONFIG_PROVE_LOCKING
+static struct lock_class_key xfs_rtginode_lock_class;
+
+static int
+xfs_rtginode_ilock_cmp_fn(
+	const struct lockdep_map	*m1,
+	const struct lockdep_map	*m2)
+{
+	const struct xfs_inode *ip1 =
+		container_of(m1, struct xfs_inode, i_lock.dep_map);
+	const struct xfs_inode *ip2 =
+		container_of(m2, struct xfs_inode, i_lock.dep_map);
+
+	if (ip1->i_projid < ip2->i_projid)
+		return -1;
+	if (ip1->i_projid > ip2->i_projid)
+		return 1;
+	return 0;
+}
+
+static inline void
+xfs_rtginode_ilock_print_fn(
+	const struct lockdep_map	*m)
+{
+	const struct xfs_inode *ip =
+		container_of(m, struct xfs_inode, i_lock.dep_map);
+
+	printk(KERN_CONT " rgno=%u", ip->i_projid);
+}
+
+/*
+ * Most of the time each of the RTG inode locks are only taken one at a time.
+ * But when committing deferred ops, more than one of a kind can be taken.
+ * However, deferred rt ops will be committed in rgno order so there is no
+ * potential for deadlocks.  The code here is needed to tell lockdep about this
+ * order.
+ */
+static inline void
+xfs_rtginode_lockdep_setup(
+	struct xfs_inode	*ip,
+	xfs_rgnumber_t		rgno,
+	enum xfs_rtg_inodes	type)
+{
+	lockdep_set_class_and_subclass(&ip->i_lock, &xfs_rtginode_lock_class,
+			type);
+	lock_set_cmp_fn(&ip->i_lock, xfs_rtginode_ilock_cmp_fn,
+			xfs_rtginode_ilock_print_fn);
+}
+#else
+#define xfs_rtginode_lockdep_setup(ip, rgno, type)	do { } while (0)
+#endif /* CONFIG_PROVE_LOCKING */
+
+struct xfs_rtginode_ops {
+	const char		*name;	/* short name */
+
+	enum xfs_metafile_type	metafile_type;
+
+	/* Does the fs have this feature? */
+	bool			(*enabled)(struct xfs_mount *mp);
+
+	/* Create this rtgroup metadata inode and initialize it. */
+	int			(*create)(struct xfs_rtgroup *rtg,
+					  struct xfs_inode *ip,
+					  struct xfs_trans *tp,
+					  bool init);
+};
+
+static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
+	[XFS_RTGI_BITMAP] = {
+		.name		= "bitmap",
+		.metafile_type	= XFS_METAFILE_RTBITMAP,
+		.create		= xfs_rtbitmap_create,
+	},
+	[XFS_RTGI_SUMMARY] = {
+		.name		= "summary",
+		.metafile_type	= XFS_METAFILE_RTSUMMARY,
+		.create		= xfs_rtsummary_create,
+	},
+};
+
+/* Return the shortname of this rtgroup inode. */
+const char *
+xfs_rtginode_name(
+	enum xfs_rtg_inodes	type)
+{
+	return xfs_rtginode_ops[type].name;
+}
+
+/* Return the metafile type of this rtgroup inode. */
+enum xfs_metafile_type
+xfs_rtginode_metafile_type(
+	enum xfs_rtg_inodes	type)
+{
+	return xfs_rtginode_ops[type].metafile_type;
+}
+
+/* Should this rtgroup inode be present? */
+bool
+xfs_rtginode_enabled(
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type)
+{
+	const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
+
+	if (!ops->enabled)
+		return true;
+	return ops->enabled(rtg_mount(rtg));
+}
+
+/* Load and existing rtgroup inode into the rtgroup structure. */
+int
+xfs_rtginode_load(
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type,
+	struct xfs_trans	*tp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_inode	*ip;
+	const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
+	int			error;
+
+	if (!xfs_rtginode_enabled(rtg, type))
+		return 0;
+
+	if (!xfs_has_rtgroups(mp)) {
+		xfs_ino_t	ino;
+
+		switch (type) {
+		case XFS_RTGI_BITMAP:
+			ino = mp->m_sb.sb_rbmino;
+			break;
+		case XFS_RTGI_SUMMARY:
+			ino = mp->m_sb.sb_rsumino;
+			break;
+		default:
+			/* None of the other types exist on !rtgroups */
+			return 0;
+		}
+
+		error = xfs_trans_metafile_iget(tp, ino, ops->metafile_type,
+				&ip);
+	} else {
+		const char	*path;
+
+		if (!mp->m_rtdirip)
+			return -EFSCORRUPTED;
+
+		path = xfs_rtginode_path(rtg_rgno(rtg), type);
+		if (!path)
+			return -ENOMEM;
+		error = xfs_metadir_load(tp, mp->m_rtdirip, path,
+				ops->metafile_type, &ip);
+		kfree(path);
+	}
+
+	if (error)
+		return error;
+
+	if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
+			       ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) {
+		xfs_irele(ip);
+		return -EFSCORRUPTED;
+	}
+
+	if (XFS_IS_CORRUPT(mp, ip->i_projid != rtg_rgno(rtg))) {
+		xfs_irele(ip);
+		return -EFSCORRUPTED;
+	}
+
+	xfs_rtginode_lockdep_setup(ip, rtg_rgno(rtg), type);
+	rtg->rtg_inodes[type] = ip;
+	return 0;
+}
+
+/* Release an rtgroup metadata inode. */
+void
+xfs_rtginode_irele(
+	struct xfs_inode	**ipp)
+{
+	if (*ipp)
+		xfs_irele(*ipp);
+	*ipp = NULL;
+}
+
+/* Add a metadata inode for a realtime rmap btree. */
+int
+xfs_rtginode_create(
+	struct xfs_rtgroup		*rtg,
+	enum xfs_rtg_inodes		type,
+	bool				init)
+{
+	const struct xfs_rtginode_ops	*ops = &xfs_rtginode_ops[type];
+	struct xfs_mount		*mp = rtg_mount(rtg);
+	struct xfs_metadir_update	upd = {
+		.dp			= mp->m_rtdirip,
+		.metafile_type		= ops->metafile_type,
+	};
+	int				error;
+
+	if (!xfs_rtginode_enabled(rtg, type))
+		return 0;
+
+	if (!mp->m_rtdirip)
+		return -EFSCORRUPTED;
+
+	upd.path = xfs_rtginode_path(rtg_rgno(rtg), type);
+	if (!upd.path)
+		return -ENOMEM;
+
+	error = xfs_metadir_start_create(&upd);
+	if (error)
+		goto out_path;
+
+	error = xfs_metadir_create(&upd, S_IFREG);
+	if (error)
+		return error;
+
+	xfs_rtginode_lockdep_setup(upd.ip, rtg_rgno(rtg), type);
+
+	upd.ip->i_projid = rtg_rgno(rtg);
+	error = ops->create(rtg, upd.ip, upd.tp, init);
+	if (error)
+		goto out_cancel;
+
+	error = xfs_metadir_commit(&upd);
+	if (error)
+		goto out_path;
+
+	kfree(upd.path);
+	xfs_finish_inode_setup(upd.ip);
+	rtg->rtg_inodes[type] = upd.ip;
+	return 0;
+
+out_cancel:
+	xfs_metadir_cancel(&upd, error);
+	/* Have to finish setting up the inode to ensure it's deleted. */
+	if (upd.ip) {
+		xfs_finish_inode_setup(upd.ip);
+		xfs_irele(upd.ip);
+	}
+out_path:
+	kfree(upd.path);
+	return error;
+}
+
+/* Create the parent directory for all rtgroup inodes and load it. */
+int
+xfs_rtginode_mkdir_parent(
+	struct xfs_mount	*mp)
+{
+	if (!mp->m_metadirip)
+		return -EFSCORRUPTED;
+
+	return xfs_metadir_mkdir(mp->m_metadirip, "rtgroups", &mp->m_rtdirip);
+}
+
+/* Load the parent directory of all rtgroup inodes. */
+int
+xfs_rtginode_load_parent(
+	struct xfs_trans	*tp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+
+	if (!mp->m_metadirip)
+		return -EFSCORRUPTED;
+
+	return xfs_metadir_load(tp, mp->m_metadirip, "rtgroups",
+			XFS_METAFILE_DIR, &mp->m_rtdirip);
+}
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
new file mode 100644
index 000000000000..6ccf31bb6bc7
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -0,0 +1,274 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __LIBXFS_RTGROUP_H
+#define __LIBXFS_RTGROUP_H 1
+
+#include "xfs_group.h"
+
+struct xfs_mount;
+struct xfs_trans;
+
+enum xfs_rtg_inodes {
+	XFS_RTGI_BITMAP,	/* allocation bitmap */
+	XFS_RTGI_SUMMARY,	/* allocation summary */
+
+	XFS_RTGI_MAX,
+};
+
+#ifdef MAX_LOCKDEP_SUBCLASSES
+static_assert(XFS_RTGI_MAX <= MAX_LOCKDEP_SUBCLASSES);
+#endif
+
+/*
+ * Realtime group incore structure, similar to the per-AG structure.
+ */
+struct xfs_rtgroup {
+	struct xfs_group	rtg_group;
+
+	/* per-rtgroup metadata inodes */
+	struct xfs_inode	*rtg_inodes[XFS_RTGI_MAX];
+
+	/* Number of blocks in this group */
+	xfs_rtxnum_t		rtg_extents;
+
+	/*
+	 * Cache of rt summary level per bitmap block with the invariant that
+	 * rtg_rsum_cache[bbno] > the maximum i for which rsum[i][bbno] != 0,
+	 * or 0 if rsum[i][bbno] == 0 for all i.
+	 *
+	 * Reads and writes are serialized by the rsumip inode lock.
+	 */
+	uint8_t			*rtg_rsum_cache;
+};
+
+static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg)
+{
+	return container_of(xg, struct xfs_rtgroup, rtg_group);
+}
+
+static inline struct xfs_group *rtg_group(struct xfs_rtgroup *rtg)
+{
+	return &rtg->rtg_group;
+}
+
+static inline struct xfs_mount *rtg_mount(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_mount;
+}
+
+static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_gno;
+}
+
+/* Passive rtgroup references */
+static inline struct xfs_rtgroup *
+xfs_rtgroup_get(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return to_rtg(xfs_group_get(mp, rgno, XG_TYPE_RTG));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_hold(
+	struct xfs_rtgroup	*rtg)
+{
+	return to_rtg(xfs_group_hold(rtg_group(rtg)));
+}
+
+static inline void
+xfs_rtgroup_put(
+	struct xfs_rtgroup	*rtg)
+{
+	xfs_group_put(rtg_group(rtg));
+}
+
+/* Active rtgroup references */
+static inline struct xfs_rtgroup *
+xfs_rtgroup_grab(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return to_rtg(xfs_group_grab(mp, rgno, XG_TYPE_RTG));
+}
+
+static inline void
+xfs_rtgroup_rele(
+	struct xfs_rtgroup	*rtg)
+{
+	xfs_group_rele(rtg_group(rtg));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_next_range(
+	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgnumber_t		start_rgno,
+	xfs_rgnumber_t		end_rgno)
+{
+	return to_rtg(xfs_group_next_range(mp, rtg ? rtg_group(rtg) : NULL,
+			start_rgno, end_rgno, XG_TYPE_RTG));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_next(
+	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg)
+{
+	return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1);
+}
+
+static inline xfs_rtblock_t
+xfs_rgno_start_rtb(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	if (mp->m_rgblklog >= 0)
+		return ((xfs_rtblock_t)rgno << mp->m_rgblklog);
+	return ((xfs_rtblock_t)rgno * mp->m_rgblocks);
+}
+
+static inline xfs_rtblock_t
+__xfs_rgbno_to_rtb(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgblock_t		rgbno)
+{
+	return xfs_rgno_start_rtb(mp, rgno) + rgbno;
+}
+
+static inline xfs_rtblock_t
+xfs_rgbno_to_rtb(
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		rgbno)
+{
+	return __xfs_rgbno_to_rtb(rtg_mount(rtg), rtg_rgno(rtg), rgbno);
+}
+
+static inline xfs_rgnumber_t
+xfs_rtb_to_rgno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	if (!xfs_has_rtgroups(mp))
+		return 0;
+
+	if (mp->m_rgblklog >= 0)
+		return rtbno >> mp->m_rgblklog;
+
+	return div_u64(rtbno, mp->m_rgblocks);
+}
+
+static inline uint64_t
+__xfs_rtb_to_rgbno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	uint32_t		rem;
+
+	if (!xfs_has_rtgroups(mp))
+		return rtbno;
+
+	if (mp->m_rgblklog >= 0)
+		return rtbno & mp->m_rgblkmask;
+
+	div_u64_rem(rtbno, mp->m_rgblocks, &rem);
+	return rem;
+}
+
+static inline xfs_rgblock_t
+xfs_rtb_to_rgbno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return __xfs_rtb_to_rgbno(mp, rtbno);
+}
+
+static inline xfs_daddr_t
+xfs_rtb_to_daddr(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return rtbno << mp->m_blkbb_log;
+}
+
+static inline xfs_rtblock_t
+xfs_daddr_to_rtb(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		daddr)
+{
+	return daddr >> mp->m_blkbb_log;
+}
+
+#ifdef CONFIG_XFS_RT
+int xfs_rtgroup_alloc(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
+void xfs_rtgroup_free(struct xfs_mount *mp, xfs_rgnumber_t rgno);
+
+void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
+		xfs_rgnumber_t end_rgno);
+int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
+		xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents);
+
+xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
+xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno);
+
+int xfs_update_last_rtgroup_size(struct xfs_mount *mp,
+		xfs_rgnumber_t prev_rgcount);
+
+/* Lock the rt bitmap inode in exclusive mode */
+#define XFS_RTGLOCK_BITMAP		(1U << 0)
+/* Lock the rt bitmap inode in shared mode */
+#define XFS_RTGLOCK_BITMAP_SHARED	(1U << 1)
+
+#define XFS_RTGLOCK_ALL_FLAGS	(XFS_RTGLOCK_BITMAP | \
+				 XFS_RTGLOCK_BITMAP_SHARED)
+
+void xfs_rtgroup_lock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
+void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
+void xfs_rtgroup_trans_join(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
+		unsigned int rtglock_flags);
+
+int xfs_rtginode_mkdir_parent(struct xfs_mount *mp);
+int xfs_rtginode_load_parent(struct xfs_trans *tp);
+
+const char *xfs_rtginode_name(enum xfs_rtg_inodes type);
+enum xfs_metafile_type xfs_rtginode_metafile_type(enum xfs_rtg_inodes type);
+bool xfs_rtginode_enabled(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type);
+int xfs_rtginode_load(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
+		struct xfs_trans *tp);
+int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
+		bool init);
+void xfs_rtginode_irele(struct xfs_inode **ipp);
+
+static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno,
+		enum xfs_rtg_inodes type)
+{
+	return kasprintf(GFP_KERNEL, "%u.%s", rgno, xfs_rtginode_name(type));
+}
+#else
+static inline void xfs_free_rtgroups(struct xfs_mount *mp,
+		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno)
+{
+}
+
+static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
+		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno,
+		xfs_rtbxlen_t rextents)
+{
+	return 0;
+}
+
+# define xfs_rtgroup_extents(mp, rgno)		(0)
+# define xfs_update_last_rtgroup_size(mp, rgno)	(-EOPNOTSUPP)
+# define xfs_rtgroup_lock(rtg, gf)		((void)0)
+# define xfs_rtgroup_unlock(rtg, gf)		((void)0)
+# define xfs_rtgroup_trans_join(tp, rtg, gf)	((void)0)
+#endif /* CONFIG_XFS_RT */
+
+#endif /* __LIBXFS_RTGROUP_H */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index e6fad3512220..5ca11c3c4711 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -710,6 +710,9 @@ __xfs_sb_from_disk(
 		to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
 	else
 		to->sb_metadirino = NULLFSINO;
+
+	to->sb_rgcount = 1;
+	to->sb_rgextents = 0;
 }
 
 void
@@ -994,8 +997,18 @@ xfs_mount_sb_set_rextsize(
 	struct xfs_mount	*mp,
 	struct xfs_sb		*sbp)
 {
+	struct xfs_groups	*rgs = &mp->m_groups[XG_TYPE_RTG];
+
 	mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize);
 	mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize);
+
+	mp->m_rgblocks = 0;
+	mp->m_rgblklog = 0;
+	mp->m_rgblkmask = (uint64_t)-1;
+
+	rgs->blocks = 0;
+	rgs->blklog = 0;
+	rgs->blkmask = (uint64_t)-1;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 1a7f95bcf069..bab402340b5d 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -224,7 +224,7 @@ xfs_rtalloc_block_count(
 	xfs_rtxlen_t		rtxlen;
 
 	rtxlen = xfs_extlen_to_rtxlen(mp, XFS_MAX_BMBT_EXTLEN);
-	rtbmp_blocks = xfs_rtbitmap_blockcount(mp, rtxlen);
+	rtbmp_blocks = xfs_rtbitmap_blockcount_len(mp, rtxlen);
 	return (rtbmp_blocks + 1) * num_ops;
 }
 
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 25053a66c225..bf33c2b1e43e 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -9,10 +9,12 @@
 typedef uint32_t	prid_t;		/* project ID */
 
 typedef uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
+typedef uint32_t	xfs_rgblock_t;	/* blockno in realtime group */
 typedef uint32_t	xfs_agino_t;	/* inode # within allocation grp */
 typedef uint32_t	xfs_extlen_t;	/* extent length in blocks */
 typedef uint32_t	xfs_rtxlen_t;	/* file extent length in rtextents */
 typedef uint32_t	xfs_agnumber_t;	/* allocation group number */
+typedef uint32_t	xfs_rgnumber_t;	/* realtime group number */
 typedef uint64_t	xfs_extnum_t;	/* # of extents in a file */
 typedef uint32_t	xfs_aextnum_t;	/* # extents in an attribute fork */
 typedef int64_t		xfs_fsize_t;	/* bytes in a file */
@@ -53,7 +55,9 @@ typedef void *		xfs_failaddr_t;
 #define	NULLFILEOFF	((xfs_fileoff_t)-1)
 
 #define	NULLAGBLOCK	((xfs_agblock_t)-1)
+#define NULLRGBLOCK	((xfs_rgblock_t)-1)
 #define	NULLAGNUMBER	((xfs_agnumber_t)-1)
+#define	NULLRGNUMBER	((xfs_rgnumber_t)-1)
 
 #define NULLCOMMITLSN	((xfs_lsn_t)-1)
 
@@ -214,11 +218,13 @@ enum xbtree_recpacking {
 
 enum xfs_group_type {
 	XG_TYPE_AG,
+	XG_TYPE_RTG,
 	XG_TYPE_MAX,
 } __packed;
 
 #define XG_TYPE_STRINGS \
-	{ XG_TYPE_AG,	"ag" }
+	{ XG_TYPE_AG,	"ag" }, \
+	{ XG_TYPE_RTG,	"rtg" }
 
 /*
  * Type verifier functions