From 0a4d79741d6f82159dc1742c11e189da8a89511d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:37 -0800
Subject: [PATCH 01/16] xfs: factor out a xfs_iwalk_args helper

Add a helper to share more code between xfs_iwalk and xfs_inobt_walk,
and at the same time do away with the extra flags indirect so that
everyone use the same names for the same flags when using the common
iwalk code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_iwalk.c | 83 ++++++++++++++++++----------------------------
 fs/xfs/xfs_iwalk.h |  7 +---
 2 files changed, 33 insertions(+), 57 deletions(-)

diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index d4ef7485e8f7..a89ae2aef7c4 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -534,6 +534,35 @@ xfs_iwalk_prefetch(
 	return max(inobt_records, 2U);
 }
 
+static int
+xfs_iwalk_args(
+	struct xfs_iwalk_ag	*iwag,
+	unsigned int		flags)
+{
+	struct xfs_mount	*mp = iwag->mp;
+	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, iwag->startino);
+	int			error;
+
+	ASSERT(agno < mp->m_sb.sb_agcount);
+	ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL));
+
+	error = xfs_iwalk_alloc(iwag);
+	if (error)
+		return error;
+
+	for_each_perag_from(mp, agno, iwag->pag) {
+		error = xfs_iwalk_ag(iwag);
+		if (error || (flags & XFS_IWALK_SAME_AG)) {
+			xfs_perag_rele(iwag->pag);
+			break;
+		}
+		iwag->startino = XFS_AGINO_TO_INO(mp, agno + 1, 0);
+	}
+
+	xfs_iwalk_free(iwag);
+	return error;
+}
+
 /*
  * Walk all inodes in the filesystem starting from @startino.  The @iwalk_fn
  * will be called for each allocated inode, being passed the inode's number and
@@ -562,32 +591,8 @@ xfs_iwalk(
 		.pwork		= XFS_PWORK_SINGLE_THREADED,
 		.lastino	= NULLFSINO,
 	};
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, startino);
-	int			error;
 
-	ASSERT(agno < mp->m_sb.sb_agcount);
-	ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL));
-
-	error = xfs_iwalk_alloc(&iwag);
-	if (error)
-		return error;
-
-	for_each_perag_from(mp, agno, pag) {
-		iwag.pag = pag;
-		error = xfs_iwalk_ag(&iwag);
-		if (error)
-			break;
-		iwag.startino = XFS_AGINO_TO_INO(mp, agno + 1, 0);
-		if (flags & XFS_INOBT_WALK_SAME_AG)
-			break;
-		iwag.pag = NULL;
-	}
-
-	if (iwag.pag)
-		xfs_perag_rele(pag);
-	xfs_iwalk_free(&iwag);
-	return error;
+	return xfs_iwalk_args(&iwag, flags);
 }
 
 /* Run per-thread iwalk work. */
@@ -673,7 +678,7 @@ xfs_iwalk_threaded(
 		iwag->lastino = NULLFSINO;
 		xfs_pwork_queue(&pctl, &iwag->pwork);
 		startino = XFS_AGINO_TO_INO(mp, pag->pag_agno + 1, 0);
-		if (flags & XFS_INOBT_WALK_SAME_AG)
+		if (flags & XFS_IWALK_SAME_AG)
 			break;
 	}
 	if (pag)
@@ -747,30 +752,6 @@ xfs_inobt_walk(
 		.pwork		= XFS_PWORK_SINGLE_THREADED,
 		.lastino	= NULLFSINO,
 	};
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, startino);
-	int			error;
 
-	ASSERT(agno < mp->m_sb.sb_agcount);
-	ASSERT(!(flags & ~XFS_INOBT_WALK_FLAGS_ALL));
-
-	error = xfs_iwalk_alloc(&iwag);
-	if (error)
-		return error;
-
-	for_each_perag_from(mp, agno, pag) {
-		iwag.pag = pag;
-		error = xfs_iwalk_ag(&iwag);
-		if (error)
-			break;
-		iwag.startino = XFS_AGINO_TO_INO(mp, pag->pag_agno + 1, 0);
-		if (flags & XFS_INOBT_WALK_SAME_AG)
-			break;
-		iwag.pag = NULL;
-	}
-
-	if (iwag.pag)
-		xfs_perag_rele(pag);
-	xfs_iwalk_free(&iwag);
-	return error;
+	return xfs_iwalk_args(&iwag, flags);
 }
diff --git a/fs/xfs/xfs_iwalk.h b/fs/xfs/xfs_iwalk.h
index 83699089755e..17a5a2c6debb 100644
--- a/fs/xfs/xfs_iwalk.h
+++ b/fs/xfs/xfs_iwalk.h
@@ -25,7 +25,7 @@ int xfs_iwalk_threaded(struct xfs_mount *mp, xfs_ino_t startino,
 		unsigned int flags, xfs_iwalk_fn iwalk_fn,
 		unsigned int inode_records, bool poll, void *data);
 
-/* Only iterate inodes within the same AG as @startino. */
+/* Only iterate within the same AG as @startino. */
 #define XFS_IWALK_SAME_AG	(1U << 0)
 
 #define XFS_IWALK_FLAGS_ALL	(XFS_IWALK_SAME_AG)
@@ -41,9 +41,4 @@ int xfs_inobt_walk(struct xfs_mount *mp, struct xfs_trans *tp,
 		xfs_inobt_walk_fn inobt_walk_fn, unsigned int inobt_records,
 		void *data);
 
-/* Only iterate inobt records within the same AG as @startino. */
-#define XFS_INOBT_WALK_SAME_AG	(XFS_IWALK_SAME_AG)
-
-#define XFS_INOBT_WALK_FLAGS_ALL (XFS_INOBT_WALK_SAME_AG)
-
 #endif /* __XFS_IWALK_H__ */

From e9c4d8bfb26c13c41b73fdf4183d3df2d392101e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:38 -0800
Subject: [PATCH 02/16] xfs: factor out a generic xfs_group structure

Split the lookup and refcount handling of struct xfs_perag into an
embedded xfs_group structure that can be reused for the upcoming
realtime groups.

It will be extended with more features later.

Note that he xg_type field will only need a single bit even with
realtime group support.  For now it fills a hole, but it might be
worth to fold it into another field if we can use this space better.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile                    |   1 +
 fs/xfs/libxfs/xfs_ag.c             | 139 +++++-------------------
 fs/xfs/libxfs/xfs_ag.h             |  81 +++++++++++---
 fs/xfs/libxfs/xfs_ag_resv.c        |  19 ++--
 fs/xfs/libxfs/xfs_alloc.c          |  39 ++++---
 fs/xfs/libxfs/xfs_alloc_btree.c    |   2 +-
 fs/xfs/libxfs/xfs_bmap.c           |   2 +-
 fs/xfs/libxfs/xfs_btree.c          |   6 +-
 fs/xfs/libxfs/xfs_group.c          | 169 +++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_group.h          |  41 +++++++
 fs/xfs/libxfs/xfs_ialloc.c         |  40 +++----
 fs/xfs/libxfs/xfs_ialloc_btree.c   |  16 +--
 fs/xfs/libxfs/xfs_refcount.c       |   4 +-
 fs/xfs/libxfs/xfs_refcount_btree.c |   8 +-
 fs/xfs/libxfs/xfs_rmap.c           |   4 +-
 fs/xfs/libxfs/xfs_rmap_btree.c     |   7 +-
 fs/xfs/libxfs/xfs_sb.c             |   6 +-
 fs/xfs/libxfs/xfs_types.h          |   8 ++
 fs/xfs/scrub/agheader_repair.c     |  22 ++--
 fs/xfs/scrub/alloc_repair.c        |   2 +-
 fs/xfs/scrub/common.h              |   3 +-
 fs/xfs/scrub/ialloc_repair.c       |   2 +-
 fs/xfs/scrub/iscan.c               |   4 +-
 fs/xfs/scrub/newbt.c               |   8 +-
 fs/xfs/scrub/repair.c              |   4 +-
 fs/xfs/scrub/rmap.c                |   2 +-
 fs/xfs/scrub/rmap_repair.c         |  10 +-
 fs/xfs/scrub/trace.h               |  82 +++++++-------
 fs/xfs/xfs_discard.c               |   4 +-
 fs/xfs/xfs_extent_busy.c           |   4 +-
 fs/xfs/xfs_extfree_item.c          |   2 +-
 fs/xfs/xfs_filestream.c            |   8 +-
 fs/xfs/xfs_fsmap.c                 |  12 +-
 fs/xfs/xfs_icache.c                |  55 +++-------
 fs/xfs/xfs_inode.c                 |   6 +-
 fs/xfs/xfs_iwalk.c                 |   6 +-
 fs/xfs/xfs_log_recover.c           |   6 +-
 fs/xfs/xfs_mount.h                 |   6 +-
 fs/xfs/xfs_refcount_item.c         |   2 +-
 fs/xfs/xfs_reflink.c               |   2 +-
 fs/xfs/xfs_rmap_item.c             |   2 +-
 fs/xfs/xfs_super.c                 |  11 +-
 fs/xfs/xfs_trace.c                 |   1 +
 fs/xfs/xfs_trace.h                 | 149 +++++++++++++++----------
 44 files changed, 608 insertions(+), 399 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_group.c
 create mode 100644 fs/xfs/libxfs/xfs_group.h

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index dd692619bed5..94cb8ca9f9da 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -14,6 +14,7 @@ xfs-y				+= xfs_trace.o
 
 # build the libxfs code first
 xfs-y				+= $(addprefix libxfs/, \
+				   xfs_group.o \
 				   xfs_ag.o \
 				   xfs_alloc.o \
 				   xfs_alloc_btree.o \
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index d51e88a4e7e2..9ea20e9cf0d4 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -30,85 +30,7 @@
 #include "xfs_trace.h"
 #include "xfs_inode.h"
 #include "xfs_icache.h"
-
-
-/*
- * Passive reference counting access wrappers to the perag structures.  If the
- * per-ag structure is to be freed, the freeing code is responsible for cleaning
- * up objects with passive references before freeing the structure. This is
- * things like cached buffers.
- */
-struct xfs_perag *
-xfs_perag_get(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		agno)
-{
-	struct xfs_perag	*pag;
-
-	rcu_read_lock();
-	pag = xa_load(&mp->m_perags, agno);
-	if (pag) {
-		trace_xfs_perag_get(pag, _RET_IP_);
-		ASSERT(atomic_read(&pag->pag_ref) >= 0);
-		atomic_inc(&pag->pag_ref);
-	}
-	rcu_read_unlock();
-	return pag;
-}
-
-/* Get a passive reference to the given perag. */
-struct xfs_perag *
-xfs_perag_hold(
-	struct xfs_perag	*pag)
-{
-	ASSERT(atomic_read(&pag->pag_ref) > 0 ||
-	       atomic_read(&pag->pag_active_ref) > 0);
-
-	trace_xfs_perag_hold(pag, _RET_IP_);
-	atomic_inc(&pag->pag_ref);
-	return pag;
-}
-
-void
-xfs_perag_put(
-	struct xfs_perag	*pag)
-{
-	trace_xfs_perag_put(pag, _RET_IP_);
-	ASSERT(atomic_read(&pag->pag_ref) > 0);
-	atomic_dec(&pag->pag_ref);
-}
-
-/*
- * Active references for perag structures. This is for short term access to the
- * per ag structures for walking trees or accessing state. If an AG is being
- * shrunk or is offline, then this will fail to find that AG and return NULL
- * instead.
- */
-struct xfs_perag *
-xfs_perag_grab(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		agno)
-{
-	struct xfs_perag	*pag;
-
-	rcu_read_lock();
-	pag = xa_load(&mp->m_perags, agno);
-	if (pag) {
-		trace_xfs_perag_grab(pag, _RET_IP_);
-		if (!atomic_inc_not_zero(&pag->pag_active_ref))
-			pag = NULL;
-	}
-	rcu_read_unlock();
-	return pag;
-}
-
-void
-xfs_perag_rele(
-	struct xfs_perag	*pag)
-{
-	trace_xfs_perag_rele(pag, _RET_IP_);
-	atomic_dec(&pag->pag_active_ref);
-}
+#include "xfs_group.h"
 
 /*
  * xfs_initialize_perag_data
@@ -183,6 +105,19 @@ xfs_initialize_perag_data(
 	return error;
 }
 
+static void
+xfs_perag_uninit(
+	struct xfs_group	*xg)
+{
+#ifdef __KERNEL__
+	struct xfs_perag	*pag = to_perag(xg);
+
+	xfs_defer_drain_free(&pag->pag_intents_drain);
+	cancel_delayed_work_sync(&pag->pag_blockgc_work);
+	xfs_buf_cache_destroy(&pag->pag_bcache);
+#endif
+}
+
 /*
  * Free up the per-ag resources  within the specified AG range.
  */
@@ -195,22 +130,8 @@ xfs_free_perag_range(
 {
 	xfs_agnumber_t		agno;
 
-	for (agno = first_agno; agno < end_agno; agno++) {
-		struct xfs_perag	*pag = xa_erase(&mp->m_perags, agno);
-
-		ASSERT(pag);
-		XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0);
-		xfs_defer_drain_free(&pag->pag_intents_drain);
-
-		cancel_delayed_work_sync(&pag->pag_blockgc_work);
-		xfs_buf_cache_destroy(&pag->pag_bcache);
-
-		/* drop the mount's active reference */
-		xfs_perag_rele(pag);
-		XFS_IS_CORRUPT(pag->pag_mount,
-				atomic_read(&pag->pag_active_ref) != 0);
-		kfree_rcu_mightsleep(pag);
-	}
+	for (agno = first_agno; agno < end_agno; agno++)
+		xfs_group_free(mp, agno, XG_TYPE_AG, xfs_perag_uninit);
 }
 
 /* Find the size of the AG, in blocks. */
@@ -332,16 +253,9 @@ xfs_perag_alloc(
 	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
 			&pag->agino_max);
 
-	pag->pag_agno = index;
-	pag->pag_mount = mp;
-	/* Active ref owned by mount indicates AG is online. */
-	atomic_set(&pag->pag_active_ref, 1);
-
-	error = xa_insert(&mp->m_perags, index, pag, GFP_KERNEL);
-	if (error) {
-		WARN_ON_ONCE(error == -EBUSY);
+	error = xfs_group_insert(mp, pag_group(pag), index, XG_TYPE_AG);
+	if (error)
 		goto out_buf_cache_destroy;
-	}
 
 	return 0;
 
@@ -833,7 +747,7 @@ xfs_ag_shrink_space(
 	struct xfs_trans	**tpp,
 	xfs_extlen_t		delta)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_alloc_arg	args = {
 		.tp	= *tpp,
 		.mp	= mp,
@@ -850,7 +764,7 @@ xfs_ag_shrink_space(
 	xfs_agblock_t		aglen;
 	int			error, err2;
 
-	ASSERT(pag->pag_agno == mp->m_sb.sb_agcount - 1);
+	ASSERT(pag_agno(pag) == mp->m_sb.sb_agcount - 1);
 	error = xfs_ialloc_read_agi(pag, *tpp, 0, &agibp);
 	if (error)
 		return error;
@@ -947,8 +861,8 @@ xfs_ag_shrink_space(
 
 	/* Update perag geometry */
 	pag->block_count -= delta;
-	__xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min,
-				&pag->agino_max);
+	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+			&pag->agino_max);
 
 	xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH);
 	xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH);
@@ -973,12 +887,13 @@ xfs_ag_extend_space(
 	struct xfs_trans	*tp,
 	xfs_extlen_t		len)
 {
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_buf		*bp;
 	struct xfs_agi		*agi;
 	struct xfs_agf		*agf;
 	int			error;
 
-	ASSERT(pag->pag_agno == pag->pag_mount->m_sb.sb_agcount - 1);
+	ASSERT(pag_agno(pag) == mp->m_sb.sb_agcount - 1);
 
 	error = xfs_ialloc_read_agi(pag, tp, 0, &bp);
 	if (error)
@@ -1018,8 +933,8 @@ xfs_ag_extend_space(
 
 	/* Update perag geometry */
 	pag->block_count = be32_to_cpu(agf->agf_length);
-	__xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min,
-				&pag->agino_max);
+	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+			&pag->agino_max);
 	return 0;
 }
 
@@ -1046,7 +961,7 @@ xfs_ag_get_geometry(
 
 	/* Fill out form. */
 	memset(ageo, 0, sizeof(*ageo));
-	ageo->ag_number = pag->pag_agno;
+	ageo->ag_number = pag_agno(pag);
 
 	agi = agi_bp->b_addr;
 	ageo->ag_icount = be32_to_cpu(agi->agi_count);
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 8787823ae37f..69b934ad2c4a 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -7,6 +7,8 @@
 #ifndef __LIBXFS_AG_H
 #define __LIBXFS_AG_H 1
 
+#include "xfs_group.h"
+
 struct xfs_mount;
 struct xfs_trans;
 struct xfs_perag;
@@ -30,10 +32,7 @@ struct xfs_ag_resv {
  * performance of allocation group selection.
  */
 struct xfs_perag {
-	struct xfs_mount *pag_mount;	/* owner filesystem */
-	xfs_agnumber_t	pag_agno;	/* AG this structure belongs to */
-	atomic_t	pag_ref;	/* passive reference count */
-	atomic_t	pag_active_ref;	/* active reference count */
+	struct xfs_group pag_group;
 	unsigned long	pag_opstate;
 	uint8_t		pagf_bno_level;	/* # of levels in bno btree */
 	uint8_t		pagf_cnt_level;	/* # of levels in cnt btree */
@@ -121,6 +120,26 @@ struct xfs_perag {
 #endif /* __KERNEL__ */
 };
 
+static inline struct xfs_perag *to_perag(struct xfs_group *xg)
+{
+	return container_of(xg, struct xfs_perag, pag_group);
+}
+
+static inline struct xfs_group *pag_group(struct xfs_perag *pag)
+{
+	return &pag->pag_group;
+}
+
+static inline struct xfs_mount *pag_mount(const struct xfs_perag *pag)
+{
+	return pag->pag_group.xg_mount;
+}
+
+static inline xfs_agnumber_t pag_agno(const struct xfs_perag *pag)
+{
+	return pag->pag_group.xg_gno;
+}
+
 /*
  * Per-AG operational state. These are atomic flag bits.
  */
@@ -151,13 +170,43 @@ int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);
 int xfs_update_last_ag_size(struct xfs_mount *mp, xfs_agnumber_t prev_agcount);
 
 /* Passive AG references */
-struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno);
-struct xfs_perag *xfs_perag_hold(struct xfs_perag *pag);
-void xfs_perag_put(struct xfs_perag *pag);
+static inline struct xfs_perag *
+xfs_perag_get(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno)
+{
+	return to_perag(xfs_group_get(mp, agno, XG_TYPE_AG));
+}
+
+static inline struct xfs_perag *
+xfs_perag_hold(
+	struct xfs_perag	*pag)
+{
+	return to_perag(xfs_group_hold(pag_group(pag)));
+}
+
+static inline void
+xfs_perag_put(
+	struct xfs_perag	*pag)
+{
+	xfs_group_put(pag_group(pag));
+}
 
 /* Active AG references */
-struct xfs_perag *xfs_perag_grab(struct xfs_mount *, xfs_agnumber_t);
-void xfs_perag_rele(struct xfs_perag *pag);
+static inline struct xfs_perag *
+xfs_perag_grab(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno)
+{
+	return to_perag(xfs_group_grab(mp, agno, XG_TYPE_AG));
+}
+
+static inline void
+xfs_perag_rele(
+	struct xfs_perag	*pag)
+{
+	xfs_group_rele(pag_group(pag));
+}
 
 /*
  * Per-ag geometry infomation and validation
@@ -233,9 +282,9 @@ xfs_perag_next(
 	xfs_agnumber_t		*agno,
 	xfs_agnumber_t		end_agno)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 
-	*agno = pag->pag_agno + 1;
+	*agno = pag_agno(pag) + 1;
 	xfs_perag_rele(pag);
 	while (*agno <= end_agno) {
 		pag = xfs_perag_grab(mp, *agno);
@@ -266,9 +315,9 @@ xfs_perag_next_wrap(
 	xfs_agnumber_t		restart_agno,
 	xfs_agnumber_t		wrap_agno)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 
-	*agno = pag->pag_agno + 1;
+	*agno = pag_agno(pag) + 1;
 	xfs_perag_rele(pag);
 	while (*agno != stop_agno) {
 		if (*agno >= wrap_agno) {
@@ -335,7 +384,7 @@ xfs_agbno_to_fsb(
 	struct xfs_perag	*pag,
 	xfs_agblock_t		agbno)
 {
-	return XFS_AGB_TO_FSB(pag->pag_mount, pag->pag_agno, agbno);
+	return XFS_AGB_TO_FSB(pag_mount(pag), pag_agno(pag), agbno);
 }
 
 static inline xfs_daddr_t
@@ -343,7 +392,7 @@ xfs_agbno_to_daddr(
 	struct xfs_perag	*pag,
 	xfs_agblock_t		agbno)
 {
-	return XFS_AGB_TO_DADDR(pag->pag_mount, pag->pag_agno, agbno);
+	return XFS_AGB_TO_DADDR(pag_mount(pag), pag_agno(pag), agbno);
 }
 
 static inline xfs_ino_t
@@ -351,7 +400,7 @@ xfs_agino_to_ino(
 	struct xfs_perag	*pag,
 	xfs_agino_t		agino)
 {
-	return XFS_AGINO_TO_INO(pag->pag_mount, pag->pag_agno, agino);
+	return XFS_AGINO_TO_INO(pag_mount(pag), pag_agno(pag), agino);
 }
 
 #endif /* __LIBXFS_AG_H */
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 4b1bd7cc7ba2..f5d853089019 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -70,6 +70,7 @@ xfs_ag_resv_critical(
 	struct xfs_perag		*pag,
 	enum xfs_ag_resv_type		type)
 {
+	struct xfs_mount		*mp = pag_mount(pag);
 	xfs_extlen_t			avail;
 	xfs_extlen_t			orig;
 
@@ -92,8 +93,8 @@ xfs_ag_resv_critical(
 
 	/* Critically low if less than 10% or max btree height remains. */
 	return XFS_TEST_ERROR(avail < orig / 10 ||
-			      avail < pag->pag_mount->m_agbtree_maxlevels,
-			pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL);
+			      avail < mp->m_agbtree_maxlevels,
+			mp, XFS_ERRTAG_AG_RESV_CRITICAL);
 }
 
 /*
@@ -137,8 +138,8 @@ __xfs_ag_resv_free(
 	trace_xfs_ag_resv_free(pag, type, 0);
 
 	resv = xfs_perag_resv(pag, type);
-	if (pag->pag_agno == 0)
-		pag->pag_mount->m_ag_max_usable += resv->ar_asked;
+	if (pag_agno(pag) == 0)
+		pag_mount(pag)->m_ag_max_usable += resv->ar_asked;
 	/*
 	 * RMAPBT blocks come from the AGFL and AGFL blocks are always
 	 * considered "free", so whatever was reserved at mount time must be
@@ -148,7 +149,7 @@ __xfs_ag_resv_free(
 		oldresv = resv->ar_orig_reserved;
 	else
 		oldresv = resv->ar_reserved;
-	xfs_add_fdblocks(pag->pag_mount, oldresv);
+	xfs_add_fdblocks(pag_mount(pag), oldresv);
 	resv->ar_reserved = 0;
 	resv->ar_asked = 0;
 	resv->ar_orig_reserved = 0;
@@ -170,7 +171,7 @@ __xfs_ag_resv_init(
 	xfs_extlen_t			ask,
 	xfs_extlen_t			used)
 {
-	struct xfs_mount		*mp = pag->pag_mount;
+	struct xfs_mount		*mp = pag_mount(pag);
 	struct xfs_ag_resv		*resv;
 	int				error;
 	xfs_extlen_t			hidden_space;
@@ -209,7 +210,7 @@ __xfs_ag_resv_init(
 		trace_xfs_ag_resv_init_error(pag, error, _RET_IP_);
 		xfs_warn(mp,
 "Per-AG reservation for AG %u failed.  Filesystem may run out of space.",
-				pag->pag_agno);
+				pag_agno(pag));
 		return error;
 	}
 
@@ -219,7 +220,7 @@ __xfs_ag_resv_init(
 	 * counter, we only make the adjustment for AG 0.  This assumes that
 	 * there aren't any AGs hungrier for per-AG reservation than AG 0.
 	 */
-	if (pag->pag_agno == 0)
+	if (pag_agno(pag) == 0)
 		mp->m_ag_max_usable -= ask;
 
 	resv = xfs_perag_resv(pag, type);
@@ -237,7 +238,7 @@ xfs_ag_resv_init(
 	struct xfs_perag		*pag,
 	struct xfs_trans		*tp)
 {
-	struct xfs_mount		*mp = pag->pag_mount;
+	struct xfs_mount		*mp = pag_mount(pag);
 	xfs_extlen_t			ask;
 	xfs_extlen_t			used;
 	int				error = 0, error2;
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index cd5c44a75cd1..bfe7b4321c47 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -275,7 +275,7 @@ xfs_alloc_complain_bad_rec(
 
 	xfs_warn(mp,
 		"%sbt record corruption in AG %d detected at %pS!",
-		cur->bc_ops->name, cur->bc_ag.pag->pag_agno, fa);
+		cur->bc_ops->name, pag_agno(cur->bc_ag.pag), fa);
 	xfs_warn(mp,
 		"start block 0x%x block count 0x%x", irec->ar_startblock,
 		irec->ar_blockcount);
@@ -799,7 +799,7 @@ xfs_agfl_verify(
 	 * use it by using uncached buffers that don't have the perag attached
 	 * so we can detect and avoid this problem.
 	 */
-	if (bp->b_pag && be32_to_cpu(agfl->agfl_seqno) != bp->b_pag->pag_agno)
+	if (bp->b_pag && be32_to_cpu(agfl->agfl_seqno) != pag_agno((bp->b_pag)))
 		return __this_address;
 
 	for (i = 0; i < xfs_agfl_size(mp); i++) {
@@ -879,13 +879,12 @@ xfs_alloc_read_agfl(
 	struct xfs_trans	*tp,
 	struct xfs_buf		**bpp)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_buf		*bp;
 	int			error;
 
-	error = xfs_trans_read_buf(
-			mp, tp, mp->m_ddev_targp,
-			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)),
+	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGFL_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
@@ -2428,7 +2427,7 @@ xfs_alloc_longest_free_extent(
 	 * reservations and AGFL rules in place, we can return this extent.
 	 */
 	if (pag->pagf_longest > delta)
-		return min_t(xfs_extlen_t, pag->pag_mount->m_ag_max_usable,
+		return min_t(xfs_extlen_t, pag_mount(pag)->m_ag_max_usable,
 				pag->pagf_longest - delta);
 
 	/* Otherwise, let the caller try for 1 block if there's space. */
@@ -2611,7 +2610,7 @@ xfs_agfl_reset(
 	xfs_warn(mp,
 	       "WARNING: Reset corrupted AGFL on AG %u. %d blocks leaked. "
 	       "Please unmount and run xfs_repair.",
-	         pag->pag_agno, pag->pagf_flcount);
+		pag_agno(pag), pag->pagf_flcount);
 
 	agf->agf_flfirst = 0;
 	agf->agf_fllast = cpu_to_be32(xfs_agfl_size(mp) - 1);
@@ -3188,7 +3187,7 @@ xfs_validate_ag_length(
 	 * use it by using uncached buffers that don't have the perag attached
 	 * so we can detect and avoid this problem.
 	 */
-	if (bp->b_pag && seqno != bp->b_pag->pag_agno)
+	if (bp->b_pag && seqno != pag_agno(bp->b_pag))
 		return __this_address;
 
 	/*
@@ -3357,13 +3356,13 @@ xfs_read_agf(
 	int			flags,
 	struct xfs_buf		**agfbpp)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	int			error;
 
 	trace_xfs_read_agf(pag);
 
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
-			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)),
+			XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGF_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
@@ -3386,6 +3385,7 @@ xfs_alloc_read_agf(
 	int			flags,
 	struct xfs_buf		**agfbpp)
 {
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_buf		*agfbp;
 	struct xfs_agf		*agf;
 	int			error;
@@ -3412,7 +3412,7 @@ xfs_alloc_read_agf(
 		pag->pagf_cnt_level = be32_to_cpu(agf->agf_cnt_level);
 		pag->pagf_rmap_level = be32_to_cpu(agf->agf_rmap_level);
 		pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
-		if (xfs_agfl_needs_reset(pag->pag_mount, agf))
+		if (xfs_agfl_needs_reset(mp, agf))
 			set_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);
 		else
 			clear_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);
@@ -3425,16 +3425,15 @@ xfs_alloc_read_agf(
 		 * counter only tracks non-root blocks.
 		 */
 		allocbt_blks = pag->pagf_btreeblks;
-		if (xfs_has_rmapbt(pag->pag_mount))
+		if (xfs_has_rmapbt(mp))
 			allocbt_blks -= be32_to_cpu(agf->agf_rmap_blocks) - 1;
 		if (allocbt_blks > 0)
-			atomic64_add(allocbt_blks,
-					&pag->pag_mount->m_allocbt_blks);
+			atomic64_add(allocbt_blks, &mp->m_allocbt_blks);
 
 		set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
 	}
 #ifdef DEBUG
-	else if (!xfs_is_shutdown(pag->pag_mount)) {
+	else if (!xfs_is_shutdown(mp)) {
 		ASSERT(pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks));
 		ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks));
 		ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount));
@@ -3652,7 +3651,7 @@ xfs_alloc_vextent_this_ag(
 	int			error;
 
 	ASSERT(args->pag != NULL);
-	ASSERT(args->pag->pag_agno == agno);
+	ASSERT(pag_agno(args->pag) == agno);
 
 	args->agno = agno;
 	args->agbno = 0;
@@ -3865,7 +3864,7 @@ xfs_alloc_vextent_exact_bno(
 	int			error;
 
 	ASSERT(args->pag != NULL);
-	ASSERT(args->pag->pag_agno == XFS_FSB_TO_AGNO(mp, target));
+	ASSERT(pag_agno(args->pag) == XFS_FSB_TO_AGNO(mp, target));
 
 	args->agno = XFS_FSB_TO_AGNO(mp, target);
 	args->agbno = XFS_FSB_TO_AGBNO(mp, target);
@@ -3904,7 +3903,7 @@ xfs_alloc_vextent_near_bno(
 	int			error;
 
 	if (!needs_perag)
-		ASSERT(args->pag->pag_agno == XFS_FSB_TO_AGNO(mp, target));
+		ASSERT(pag_agno(args->pag) == XFS_FSB_TO_AGNO(mp, target));
 
 	args->agno = XFS_FSB_TO_AGNO(mp, target);
 	args->agbno = XFS_FSB_TO_AGBNO(mp, target);
@@ -3941,7 +3940,7 @@ xfs_free_extent_fix_freelist(
 	memset(&args, 0, sizeof(struct xfs_alloc_arg));
 	args.tp = tp;
 	args.mp = tp->t_mountp;
-	args.agno = pag->pag_agno;
+	args.agno = pag_agno(pag);
 	args.pag = pag;
 
 	/*
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 5175d0b4d32e..88e1545ed4c9 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -178,7 +178,7 @@ xfs_allocbt_init_ptr_from_cur(
 {
 	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno));
+	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agf->agf_seqno));
 
 	if (xfs_btree_is_bno(cur->bc_ops))
 		ptr->s = agf->agf_bno_root;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 36dd08d13293..5eda036cf9bf 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3280,7 +3280,7 @@ xfs_bmap_longest_free_extent(
 	}
 
 	longest = xfs_alloc_longest_free_extent(pag,
-				xfs_alloc_min_freelist(pag->pag_mount, pag),
+				xfs_alloc_min_freelist(pag_mount(pag), pag),
 				xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE));
 	if (*blen < longest)
 		*blen = longest;
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 804a1c969411..9a13dbf5f54a 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -372,7 +372,7 @@ xfs_btree_check_ptr(
 		case XFS_BTREE_TYPE_AG:
 			xfs_err(cur->bc_mp,
 "AG %u: Corrupt %sbt pointer at level %d index %d.",
-				cur->bc_ag.pag->pag_agno, cur->bc_ops->name,
+				pag_agno(cur->bc_ag.pag), cur->bc_ops->name,
 				level, index);
 			break;
 		}
@@ -1312,7 +1312,7 @@ xfs_btree_owner(
 	case XFS_BTREE_TYPE_INODE:
 		return cur->bc_ino.ip->i_ino;
 	case XFS_BTREE_TYPE_AG:
-		return cur->bc_ag.pag->pag_agno;
+		return pag_agno(cur->bc_ag.pag);
 	default:
 		ASSERT(0);
 		return 0;
@@ -4744,7 +4744,7 @@ xfs_btree_agblock_v5hdr_verify(
 		return __this_address;
 	if (block->bb_u.s.bb_blkno != cpu_to_be64(xfs_buf_daddr(bp)))
 		return __this_address;
-	if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
+	if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag_agno(pag))
 		return __this_address;
 	return NULL;
 }
diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c
new file mode 100644
index 000000000000..edf5907845f0
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_group.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Red Hat, Inc.
+ */
+
+#include "xfs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_error.h"
+#include "xfs_trace.h"
+#include "xfs_group.h"
+
+/*
+ * Groups can have passive and active references.
+ *
+ * For passive references the code freeing a group is responsible for cleaning
+ * up objects that hold the passive references (e.g. cached buffers).
+ * Routines manipulating passive references are xfs_group_get, xfs_group_hold
+ * and xfs_group_put.
+ *
+ * Active references are for short term access to the group for walking trees or
+ * accessing state. If a group is being shrunk or offlined, the lookup will fail
+ * to find that group and return NULL instead.
+ * Routines manipulating active references are xfs_group_grab and
+ * xfs_group_rele.
+ */
+
+struct xfs_group *
+xfs_group_get(
+	struct xfs_mount	*mp,
+	uint32_t		index,
+	enum xfs_group_type	type)
+{
+	struct xfs_group	*xg;
+
+	rcu_read_lock();
+	xg = xa_load(&mp->m_groups[type].xa, index);
+	if (xg) {
+		trace_xfs_group_get(xg, _RET_IP_);
+		ASSERT(atomic_read(&xg->xg_ref) >= 0);
+		atomic_inc(&xg->xg_ref);
+	}
+	rcu_read_unlock();
+	return xg;
+}
+
+struct xfs_group *
+xfs_group_hold(
+	struct xfs_group	*xg)
+{
+	ASSERT(atomic_read(&xg->xg_ref) > 0 ||
+	       atomic_read(&xg->xg_active_ref) > 0);
+
+	trace_xfs_group_hold(xg, _RET_IP_);
+	atomic_inc(&xg->xg_ref);
+	return xg;
+}
+
+void
+xfs_group_put(
+	struct xfs_group	*xg)
+{
+	trace_xfs_group_put(xg, _RET_IP_);
+
+	ASSERT(atomic_read(&xg->xg_ref) > 0);
+	atomic_dec(&xg->xg_ref);
+}
+
+struct xfs_group *
+xfs_group_grab(
+	struct xfs_mount	*mp,
+	uint32_t		index,
+	enum xfs_group_type	type)
+{
+	struct xfs_group	*xg;
+
+	rcu_read_lock();
+	xg = xa_load(&mp->m_groups[type].xa, index);
+	if (xg) {
+		trace_xfs_group_grab(xg, _RET_IP_);
+		if (!atomic_inc_not_zero(&xg->xg_active_ref))
+			xg = NULL;
+	}
+	rcu_read_unlock();
+	return xg;
+}
+
+/*
+ * Find the next group after @xg, or the first group if @xg is NULL.
+ */
+struct xfs_group *
+xfs_group_grab_next_mark(
+	struct xfs_mount	*mp,
+	struct xfs_group	*xg,
+	xa_mark_t		mark,
+	enum xfs_group_type	type)
+{
+	unsigned long		index = 0;
+
+	if (xg) {
+		index = xg->xg_gno + 1;
+		xfs_group_rele(xg);
+	}
+
+	rcu_read_lock();
+	xg = xa_find(&mp->m_groups[type].xa, &index, ULONG_MAX, mark);
+	if (xg) {
+		trace_xfs_group_grab_next_tag(xg, _RET_IP_);
+		if (!atomic_inc_not_zero(&xg->xg_active_ref))
+			xg = NULL;
+	}
+	rcu_read_unlock();
+	return xg;
+}
+
+void
+xfs_group_rele(
+	struct xfs_group	*xg)
+{
+	trace_xfs_group_rele(xg, _RET_IP_);
+	atomic_dec(&xg->xg_active_ref);
+}
+
+void
+xfs_group_free(
+	struct xfs_mount	*mp,
+	uint32_t		index,
+	enum xfs_group_type	type,
+	void			(*uninit)(struct xfs_group *xg))
+{
+	struct xfs_group	*xg = xa_erase(&mp->m_groups[type].xa, index);
+
+	XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_ref) != 0);
+
+	if (uninit)
+		uninit(xg);
+
+	/* drop the mount's active reference */
+	xfs_group_rele(xg);
+	XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_active_ref) != 0);
+	kfree_rcu_mightsleep(xg);
+}
+
+int
+xfs_group_insert(
+	struct xfs_mount	*mp,
+	struct xfs_group	*xg,
+	uint32_t		index,
+	enum xfs_group_type	type)
+{
+	int			error;
+
+	xg->xg_mount = mp;
+	xg->xg_gno = index;
+	xg->xg_type = type;
+
+	/* Active ref owned by mount indicates group is online. */
+	atomic_set(&xg->xg_active_ref, 1);
+
+	error = xa_insert(&mp->m_groups[type].xa, index, xg, GFP_KERNEL);
+	if (error) {
+		WARN_ON_ONCE(error == -EBUSY);
+		return error;
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
new file mode 100644
index 000000000000..e3b6be7ff9e8
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018 Red Hat, Inc.
+ */
+#ifndef __LIBXFS_GROUP_H
+#define __LIBXFS_GROUP_H 1
+
+struct xfs_group {
+	struct xfs_mount	*xg_mount;
+	uint32_t		xg_gno;
+	enum xfs_group_type	xg_type;
+	atomic_t		xg_ref;		/* passive reference count */
+	atomic_t		xg_active_ref;	/* active reference count */
+};
+
+struct xfs_group *xfs_group_get(struct xfs_mount *mp, uint32_t index,
+		enum xfs_group_type type);
+struct xfs_group *xfs_group_hold(struct xfs_group *xg);
+void xfs_group_put(struct xfs_group *xg);
+
+struct xfs_group *xfs_group_grab(struct xfs_mount *mp, uint32_t index,
+		enum xfs_group_type type);
+struct xfs_group *xfs_group_grab_next_mark(struct xfs_mount *mp,
+		struct xfs_group *xg, xa_mark_t mark, enum xfs_group_type type);
+void xfs_group_rele(struct xfs_group *xg);
+
+void xfs_group_free(struct xfs_mount *mp, uint32_t index,
+		enum xfs_group_type type, void (*uninit)(struct xfs_group *xg));
+int xfs_group_insert(struct xfs_mount *mp, struct xfs_group *xg,
+		uint32_t index, enum xfs_group_type);
+
+#define xfs_group_set_mark(_xg, _mark) \
+	xa_set_mark(&(_xg)->xg_mount->m_groups[(_xg)->xg_type].xa, \
+			(_xg)->xg_gno, (_mark))
+#define xfs_group_clear_mark(_xg, _mark) \
+	xa_clear_mark(&(_xg)->xg_mount->m_groups[(_xg)->xg_type].xa, \
+			(_xg)->xg_gno, (_mark))
+#define xfs_group_marked(_mp, _type, _mark) \
+	xa_marked(&(_mp)->m_groups[(_type)].xa, (_mark))
+
+#endif /* __LIBXFS_GROUP_H */
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index f5167847f051..78e1920c1ff9 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -142,7 +142,7 @@ xfs_inobt_complain_bad_rec(
 
 	xfs_warn(mp,
 		"%sbt record corruption in AG %d detected at %pS!",
-		cur->bc_ops->name, cur->bc_ag.pag->pag_agno, fa);
+		cur->bc_ops->name, pag_agno(cur->bc_ag.pag), fa);
 	xfs_warn(mp,
 "start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
 		irec->ir_startino, irec->ir_count, irec->ir_freecount,
@@ -551,7 +551,7 @@ xfs_inobt_insert_sprec(
 	struct xfs_buf			*agbp,
 	struct xfs_inobt_rec_incore	*nrec)	/* in/out: new/merged rec. */
 {
-	struct xfs_mount		*mp = pag->pag_mount;
+	struct xfs_mount		*mp = pag_mount(pag);
 	struct xfs_btree_cur		*cur;
 	int				error;
 	int				i;
@@ -645,7 +645,7 @@ xfs_finobt_insert_sprec(
 	struct xfs_buf			*agbp,
 	struct xfs_inobt_rec_incore	*nrec)	/* in/out: new rec. */
 {
-	struct xfs_mount		*mp = pag->pag_mount;
+	struct xfs_mount		*mp = pag_mount(pag);
 	struct xfs_btree_cur		*cur;
 	int				error;
 	int				i;
@@ -880,7 +880,7 @@ xfs_ialloc_ag_alloc(
 	 * rather than a linear progression to prevent the next generation
 	 * number from being easily guessable.
 	 */
-	error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag->pag_agno,
+	error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag_agno(pag),
 			args.agbno, args.len, get_random_u32());
 
 	if (error)
@@ -1071,7 +1071,7 @@ xfs_dialloc_check_ino(
 	if (error)
 		return -EAGAIN;
 
-	error = xfs_imap_to_bp(pag->pag_mount, tp, &imap, &bp);
+	error = xfs_imap_to_bp(pag_mount(pag), tp, &imap, &bp);
 	if (error)
 		return -EAGAIN;
 
@@ -1122,7 +1122,7 @@ xfs_dialloc_ag_inobt(
 	/*
 	 * If in the same AG as the parent, try to get near the parent.
 	 */
-	if (pagno == pag->pag_agno) {
+	if (pagno == pag_agno(pag)) {
 		int		doneleft;	/* done, to the left */
 		int		doneright;	/* done, to the right */
 
@@ -1599,7 +1599,7 @@ xfs_dialloc_ag(
 	 * parent. If so, find the closest available inode to the parent. If
 	 * not, consider the agi hint or find the first free inode in the AG.
 	 */
-	if (pag->pag_agno == pagno)
+	if (pag_agno(pag) == pagno)
 		error = xfs_dialloc_ag_finobt_near(pagino, &cur, &rec);
 	else
 		error = xfs_dialloc_ag_finobt_newino(agi, cur, &rec);
@@ -2053,7 +2053,7 @@ xfs_difree_inobt(
 	struct xfs_icluster		*xic,
 	struct xfs_inobt_rec_incore	*orec)
 {
-	struct xfs_mount		*mp = pag->pag_mount;
+	struct xfs_mount		*mp = pag_mount(pag);
 	struct xfs_agi			*agi = agbp->b_addr;
 	struct xfs_btree_cur		*cur;
 	struct xfs_inobt_rec_incore	rec;
@@ -2187,7 +2187,7 @@ xfs_difree_finobt(
 	xfs_agino_t			agino,
 	struct xfs_inobt_rec_incore	*ibtrec) /* inobt record */
 {
-	struct xfs_mount		*mp = pag->pag_mount;
+	struct xfs_mount		*mp = pag_mount(pag);
 	struct xfs_btree_cur		*cur;
 	struct xfs_inobt_rec_incore	rec;
 	int				offset = agino - ibtrec->ir_startino;
@@ -2310,9 +2310,9 @@ xfs_difree(
 	/*
 	 * Break up inode number into its components.
 	 */
-	if (pag->pag_agno != XFS_INO_TO_AGNO(mp, inode)) {
-		xfs_warn(mp, "%s: agno != pag->pag_agno (%d != %d).",
-			__func__, XFS_INO_TO_AGNO(mp, inode), pag->pag_agno);
+	if (pag_agno(pag) != XFS_INO_TO_AGNO(mp, inode)) {
+		xfs_warn(mp, "%s: agno != pag_agno(pag) (%d != %d).",
+			__func__, XFS_INO_TO_AGNO(mp, inode), pag_agno(pag));
 		ASSERT(0);
 		return -EINVAL;
 	}
@@ -2373,7 +2373,7 @@ xfs_imap_lookup(
 	xfs_agblock_t		*offset_agbno,
 	int			flags)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_inobt_rec_incore rec;
 	struct xfs_btree_cur	*cur;
 	struct xfs_buf		*agbp;
@@ -2384,7 +2384,7 @@ xfs_imap_lookup(
 	if (error) {
 		xfs_alert(mp,
 			"%s: xfs_ialloc_read_agi() returned error %d, agno %d",
-			__func__, error, pag->pag_agno);
+			__func__, error, pag_agno(pag));
 		return error;
 	}
 
@@ -2434,7 +2434,7 @@ xfs_imap(
 	struct xfs_imap		*imap,	/* location map structure */
 	uint			flags)	/* flags for inode btree lookup */
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	xfs_agblock_t		agbno;	/* block number of inode in the alloc group */
 	xfs_agino_t		agino;	/* inode number within alloc group */
 	xfs_agblock_t		chunk_agbno;	/* first block in inode chunk */
@@ -2726,13 +2726,13 @@ xfs_read_agi(
 	xfs_buf_flags_t		flags,
 	struct xfs_buf		**agibpp)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	int			error;
 
 	trace_xfs_read_agi(pag);
 
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
-			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
+			XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGI_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), flags, agibpp, &xfs_agi_buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
@@ -2780,7 +2780,7 @@ xfs_ialloc_read_agi(
 	 * we are in the middle of a forced shutdown.
 	 */
 	ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
-		xfs_is_shutdown(pag->pag_mount));
+		xfs_is_shutdown(pag_mount(pag)));
 	if (agibpp)
 		*agibpp = agibp;
 	else
@@ -3119,13 +3119,13 @@ xfs_ialloc_check_shrink(
 	int			has;
 	int			error;
 
-	if (!xfs_has_sparseinodes(pag->pag_mount))
+	if (!xfs_has_sparseinodes(pag_mount(pag)))
 		return 0;
 
 	cur = xfs_inobt_init_cursor(pag, tp, agibp);
 
 	/* Look up the inobt record that would correspond to the new EOFS. */
-	agino = XFS_AGB_TO_AGINO(pag->pag_mount, new_length);
+	agino = XFS_AGB_TO_AGINO(pag_mount(pag), new_length);
 	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has);
 	if (error || !has)
 		goto out;
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 3291541ae966..91d44be2ce48 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -248,7 +248,7 @@ xfs_inobt_init_ptr_from_cur(
 {
 	struct xfs_agi		*agi = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agi->agi_seqno));
+	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agi->agi_seqno));
 
 	ptr->s = agi->agi_root;
 }
@@ -260,7 +260,7 @@ xfs_finobt_init_ptr_from_cur(
 {
 	struct xfs_agi		*agi = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agi->agi_seqno));
+	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agi->agi_seqno));
 	ptr->s = agi->agi_free_root;
 }
 
@@ -478,7 +478,7 @@ xfs_inobt_init_cursor(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_btree_cur	*cur;
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_inobt_ops,
@@ -504,7 +504,7 @@ xfs_finobt_init_cursor(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_btree_cur	*cur;
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_finobt_ops,
@@ -715,7 +715,7 @@ static xfs_extlen_t
 xfs_inobt_max_size(
 	struct xfs_perag	*pag)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	xfs_agblock_t		agblocks = pag->block_count;
 
 	/* Bail out if we're uninitialized, which can happen in mkfs. */
@@ -727,7 +727,7 @@ xfs_inobt_max_size(
 	 * never be available for the kinds of things that would require btree
 	 * expansion.  We therefore can pretend the space isn't there.
 	 */
-	if (xfs_ag_contains_log(mp, pag->pag_agno))
+	if (xfs_ag_contains_log(mp, pag_agno(pag)))
 		agblocks -= mp->m_sb.sb_logblocks;
 
 	return xfs_btree_calc_size(M_IGEO(mp)->inobt_mnr,
@@ -791,10 +791,10 @@ xfs_finobt_calc_reserves(
 	xfs_extlen_t		tree_len = 0;
 	int			error;
 
-	if (!xfs_has_finobt(pag->pag_mount))
+	if (!xfs_has_finobt(pag_mount(pag)))
 		return 0;
 
-	if (xfs_has_inobtcounts(pag->pag_mount))
+	if (xfs_has_inobtcounts(pag_mount(pag)))
 		error = xfs_finobt_read_blocks(pag, tp, &tree_len);
 	else
 		error = xfs_finobt_count_blocks(pag, tp, &tree_len);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 5e166553a7a6..b8789c42c230 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -154,7 +154,7 @@ xfs_refcount_complain_bad_rec(
 
 	xfs_warn(mp,
  "Refcount BTree record corruption in AG %d detected at %pS!",
-				cur->bc_ag.pag->pag_agno, fa);
+				pag_agno(cur->bc_ag.pag), fa);
 	xfs_warn(mp,
 		"Start block 0x%x, block count 0x%x, references 0x%x",
 		irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
@@ -1321,7 +1321,7 @@ xfs_refcount_continue_op(
 	ri->ri_startblock = xfs_agbno_to_fsb(pag, new_agbno);
 
 	ASSERT(xfs_verify_fsbext(mp, ri->ri_startblock, ri->ri_blockcount));
-	ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, ri->ri_startblock));
+	ASSERT(pag_agno(pag) == XFS_FSB_TO_AGNO(mp, ri->ri_startblock));
 
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index c4b10fbf8892..db389fdbd929 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -81,7 +81,7 @@ xfs_refcountbt_alloc_block(
 		*stat = 0;
 		return 0;
 	}
-	ASSERT(args.agno == cur->bc_ag.pag->pag_agno);
+	ASSERT(args.agno == pag_agno(cur->bc_ag.pag));
 	ASSERT(args.len == 1);
 
 	new->s = cpu_to_be32(args.agbno);
@@ -169,7 +169,7 @@ xfs_refcountbt_init_ptr_from_cur(
 {
 	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno));
+	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agf->agf_seqno));
 
 	ptr->s = agf->agf_refcount_root;
 }
@@ -361,7 +361,7 @@ xfs_refcountbt_init_cursor(
 {
 	struct xfs_btree_cur	*cur;
 
-	ASSERT(pag->pag_agno < mp->m_sb.sb_agcount);
+	ASSERT(pag_agno(pag) < mp->m_sb.sb_agcount);
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_refcountbt_ops,
 			mp->m_refc_maxlevels, xfs_refcountbt_cur_cache);
@@ -514,7 +514,7 @@ xfs_refcountbt_calc_reserves(
 	 * never be available for the kinds of things that would require btree
 	 * expansion.  We therefore can pretend the space isn't there.
 	 */
-	if (xfs_ag_contains_log(mp, pag->pag_agno))
+	if (xfs_ag_contains_log(mp, pag_agno(pag)))
 		agblocks -= mp->m_sb.sb_logblocks;
 
 	*ask += xfs_refcountbt_max_size(mp, agblocks);
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 6ef4687b3aba..b6764d6b3ab8 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -213,7 +213,7 @@ xfs_rmap_check_irec(
 	struct xfs_perag		*pag,
 	const struct xfs_rmap_irec	*irec)
 {
-	struct xfs_mount		*mp = pag->pag_mount;
+	struct xfs_mount		*mp = pag_mount(pag);
 	bool				is_inode;
 	bool				is_unwritten;
 	bool				is_bmbt;
@@ -288,7 +288,7 @@ xfs_rmap_complain_bad_rec(
 	else
 		xfs_warn(mp,
  "Reverse Mapping BTree record corruption in AG %d detected at %pS!",
-			cur->bc_ag.pag->pag_agno, fa);
+			pag_agno(cur->bc_ag.pag), fa);
 	xfs_warn(mp,
 		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
 		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index b49006c1ca7e..6fd460fc7c9c 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -227,7 +227,7 @@ xfs_rmapbt_init_ptr_from_cur(
 {
 	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno));
+	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agf->agf_seqno));
 
 	ptr->s = agf->agf_rmap_root;
 }
@@ -647,9 +647,8 @@ xfs_rmapbt_mem_cursor(
 	struct xfbtree		*xfbt)
 {
 	struct xfs_btree_cur	*cur;
-	struct xfs_mount	*mp = pag->pag_mount;
 
-	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rmapbt_mem_ops,
+	cur = xfs_btree_alloc_cursor(pag_mount(pag), tp, &xfs_rmapbt_mem_ops,
 			xfs_rmapbt_maxlevels_ondisk(), xfs_rmapbt_cur_cache);
 	cur->bc_mem.xfbtree = xfbt;
 	cur->bc_nlevels = xfbt->nlevels;
@@ -863,7 +862,7 @@ xfs_rmapbt_calc_reserves(
 	 * never be available for the kinds of things that would require btree
 	 * expansion.  We therefore can pretend the space isn't there.
 	 */
-	if (xfs_ag_contains_log(mp, pag->pag_agno))
+	if (xfs_ag_contains_log(mp, pag_agno(pag)))
 		agblocks -= mp->m_sb.sb_logblocks;
 
 	/* Reserve 1% of the AG or enough for 1 block per record. */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index d95409f3cba6..d2012fbf07aa 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1120,7 +1120,7 @@ xfs_update_secondary_sbs(
 		struct xfs_buf		*bp;
 
 		error = xfs_buf_get(mp->m_ddev_targp,
-				 XFS_AG_DADDR(mp, pag->pag_agno, XFS_SB_DADDR),
+				 XFS_AG_DADDR(mp, pag_agno(pag), XFS_SB_DADDR),
 				 XFS_FSS_TO_BB(mp, 1), &bp);
 		/*
 		 * If we get an error reading or writing alternate superblocks,
@@ -1132,7 +1132,7 @@ xfs_update_secondary_sbs(
 		if (error) {
 			xfs_warn(mp,
 		"error allocating secondary superblock for ag %d",
-				pag->pag_agno);
+				pag_agno(pag));
 			if (!saved_error)
 				saved_error = error;
 			continue;
@@ -1153,7 +1153,7 @@ xfs_update_secondary_sbs(
 		if (error) {
 			xfs_warn(mp,
 		"write error %d updating a secondary superblock near ag %d",
-				error, pag->pag_agno);
+				error, pag_agno(pag));
 			if (!saved_error)
 				saved_error = error;
 			continue;
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index a8cd44d03ef6..d3cb6ff3b913 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -212,6 +212,14 @@ enum xbtree_recpacking {
 	XBTREE_RECPACKING_FULL,
 };
 
+enum xfs_group_type {
+	XG_TYPE_AG,
+	XG_TYPE_MAX,
+} __packed;
+
+#define XG_TYPE_STRINGS \
+	{ XG_TYPE_AG,	"ag" }
+
 /*
  * Type verifier functions
  */
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 82a850eba6c8..0ea04d6e21cd 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -208,7 +208,7 @@ xrep_agf_init_header(
 	memset(agf, 0, BBTOB(agf_bp->b_length));
 	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
 	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
-	agf->agf_seqno = cpu_to_be32(pag->pag_agno);
+	agf->agf_seqno = cpu_to_be32(pag_agno(pag));
 	agf->agf_length = cpu_to_be32(pag->block_count);
 	agf->agf_flfirst = old_agf->agf_flfirst;
 	agf->agf_fllast = old_agf->agf_fllast;
@@ -384,7 +384,7 @@ xrep_agf(
 	 * was corrupt after xfs_alloc_read_agf failed with -EFSCORRUPTED.
 	 */
 	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
-			XFS_AG_DADDR(mp, sc->sa.pag->pag_agno,
+			XFS_AG_DADDR(mp, pag_agno(sc->sa.pag),
 						XFS_AGF_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &agf_bp, NULL);
 	if (error)
@@ -687,7 +687,7 @@ xrep_agfl_init_header(
 	agfl = XFS_BUF_TO_AGFL(agfl_bp);
 	memset(agfl, 0xFF, BBTOB(agfl_bp->b_length));
 	agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
-	agfl->agfl_seqno = cpu_to_be32(sc->sa.pag->pag_agno);
+	agfl->agfl_seqno = cpu_to_be32(pag_agno(sc->sa.pag));
 	uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
 
 	/*
@@ -741,7 +741,7 @@ xrep_agfl(
 	 * was corrupt after xfs_alloc_read_agfl failed with -EFSCORRUPTED.
 	 */
 	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
-			XFS_AG_DADDR(mp, sc->sa.pag->pag_agno,
+			XFS_AG_DADDR(mp, pag_agno(sc->sa.pag),
 						XFS_AGFL_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL);
 	if (error)
@@ -897,7 +897,7 @@ xrep_agi_init_header(
 	memset(agi, 0, BBTOB(agi_bp->b_length));
 	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
 	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
-	agi->agi_seqno = cpu_to_be32(pag->pag_agno);
+	agi->agi_seqno = cpu_to_be32(pag_agno(pag));
 	agi->agi_length = cpu_to_be32(pag->block_count);
 	agi->agi_newino = cpu_to_be32(NULLAGINO);
 	agi->agi_dirino = cpu_to_be32(NULLAGINO);
@@ -1112,9 +1112,9 @@ xrep_iunlink_igrab(
 	struct xfs_perag	*pag,
 	struct xfs_inode	*ip)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 
-	if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
+	if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag_agno(pag))
 		return false;
 
 	if (!xfs_inode_on_unlinked_list(ip))
@@ -1138,7 +1138,7 @@ xrep_iunlink_visit(
 	unsigned int		bucket;
 	int			error;
 
-	ASSERT(XFS_INO_TO_AGNO(mp, ip->i_ino) == ragi->sc->sa.pag->pag_agno);
+	ASSERT(XFS_INO_TO_AGNO(mp, ip->i_ino) == pag_agno(ragi->sc->sa.pag));
 	ASSERT(xfs_inode_on_unlinked_list(ip));
 
 	agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
@@ -1169,7 +1169,7 @@ xrep_iunlink_mark_incore(
 	struct xrep_agi		*ragi)
 {
 	struct xfs_perag	*pag = ragi->sc->sa.pag;
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	uint32_t		first_index = 0;
 	bool			done = false;
 	unsigned int		nr_found = 0;
@@ -1209,7 +1209,7 @@ xrep_iunlink_mark_incore(
 			 * us to see this inode, so another lookup from the
 			 * same index will not find it again.
 			 */
-			if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
+			if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag_agno(pag))
 				continue;
 			first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
 			if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
@@ -1761,7 +1761,7 @@ xrep_agi(
 	 * was corrupt after xfs_ialloc_read_agi failed with -EFSCORRUPTED.
 	 */
 	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
-			XFS_AG_DADDR(mp, sc->sa.pag->pag_agno,
+			XFS_AG_DADDR(mp, pag_agno(sc->sa.pag),
 						XFS_AGI_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &ragi->agi_bp, NULL);
 	if (error)
diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c
index 1e0c2db6dcf7..ab0084c42496 100644
--- a/fs/xfs/scrub/alloc_repair.c
+++ b/fs/xfs/scrub/alloc_repair.c
@@ -543,7 +543,7 @@ xrep_abt_dispose_one(
 
 	/* Add a deferred rmap for each extent we used. */
 	if (resv->used > 0)
-		xfs_rmap_alloc_extent(sc->tp, pag->pag_agno, resv->agbno,
+		xfs_rmap_alloc_extent(sc->tp, pag_agno(pag), resv->agbno,
 				resv->used, XFS_RMAP_OWN_AG);
 
 	/*
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 47148cc4a833..f3db628b14e1 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -216,7 +216,8 @@ int xchk_metadata_inode_forks(struct xfs_scrub *sc);
 #define xchk_xfile_ag_descr(sc, fmt, ...) \
 	kasprintf(XCHK_GFP_FLAGS, "XFS (%s): AG 0x%x " fmt, \
 			(sc)->mp->m_super->s_id, \
-			(sc)->sa.pag ? (sc)->sa.pag->pag_agno : (sc)->sm->sm_agno, \
+			(sc)->sa.pag ? \
+				pag_agno((sc)->sa.pag) : (sc)->sm->sm_agno, \
 			##__VA_ARGS__)
 #define xchk_xfile_ino_descr(sc, fmt, ...) \
 	kasprintf(XCHK_GFP_FLAGS, "XFS (%s): inode 0x%llx " fmt, \
diff --git a/fs/xfs/scrub/ialloc_repair.c b/fs/xfs/scrub/ialloc_repair.c
index ffa0d67508aa..14e48d3f1912 100644
--- a/fs/xfs/scrub/ialloc_repair.c
+++ b/fs/xfs/scrub/ialloc_repair.c
@@ -814,7 +814,7 @@ xrep_iallocbt(
 	sc->sick_mask = XFS_SICK_AG_INOBT | XFS_SICK_AG_FINOBT;
 
 	/* Set up enough storage to handle an AG with nothing but inodes. */
-	xfs_agino_range(mp, sc->sa.pag->pag_agno, &first_agino, &last_agino);
+	xfs_agino_range(mp, pag_agno(sc->sa.pag), &first_agino, &last_agino);
 	last_agino /= XFS_INODES_PER_CHUNK;
 	descr = xchk_xfile_ag_descr(sc, "inode index records");
 	error = xfarray_create(descr, last_agino,
diff --git a/fs/xfs/scrub/iscan.c b/fs/xfs/scrub/iscan.c
index cf9d983667ce..84f117667ca2 100644
--- a/fs/xfs/scrub/iscan.c
+++ b/fs/xfs/scrub/iscan.c
@@ -67,7 +67,7 @@ xchk_iscan_mask_skipino(
 	xfs_agnumber_t		skip_agno = XFS_INO_TO_AGNO(mp, iscan->skip_ino);
 	xfs_agnumber_t		skip_agino = XFS_INO_TO_AGINO(mp, iscan->skip_ino);
 
-	if (pag->pag_agno != skip_agno)
+	if (pag_agno(pag) != skip_agno)
 		return;
 	if (skip_agino < rec->ir_startino)
 		return;
@@ -95,7 +95,7 @@ xchk_iscan_find_next(
 	struct xfs_btree_cur	*cur;
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_trans	*tp = sc->tp;
-	xfs_agnumber_t		agno = pag->pag_agno;
+	xfs_agnumber_t		agno = pag_agno(pag);
 	xfs_agino_t		lastino = NULLAGINO;
 	xfs_agino_t		first, last;
 	xfs_agino_t		agino = *cursor;
diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c
index 81cad6c4fe6d..70af27d98734 100644
--- a/fs/xfs/scrub/newbt.c
+++ b/fs/xfs/scrub/newbt.c
@@ -58,7 +58,7 @@ xrep_newbt_estimate_slack(
 
 	if (sc->ops->type == ST_PERAG) {
 		free = sc->sa.pag->pagf_freeblks;
-		sz = xfs_ag_block_count(sc->mp, sc->sa.pag->pag_agno);
+		sz = xfs_ag_block_count(sc->mp, pag_agno(sc->sa.pag));
 	} else {
 		free = percpu_counter_sum(&sc->mp->m_fdblocks);
 		sz = sc->mp->m_sb.sb_dblocks;
@@ -205,7 +205,7 @@ xrep_newbt_validate_ag_alloc_hint(
 	struct xfs_scrub	*sc = xnr->sc;
 	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(sc->mp, xnr->alloc_hint);
 
-	if (agno == sc->sa.pag->pag_agno &&
+	if (agno == pag_agno(sc->sa.pag) &&
 	    xfs_verify_fsbno(sc->mp, xnr->alloc_hint))
 		return;
 
@@ -250,8 +250,8 @@ xrep_newbt_alloc_ag_blocks(
 			return -ENOSPC;
 
 		agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
-		if (agno != sc->sa.pag->pag_agno) {
-			ASSERT(agno == sc->sa.pag->pag_agno);
+		if (agno != pag_agno(sc->sa.pag)) {
+			ASSERT(agno == pag_agno(sc->sa.pag));
 			return -EFSCORRUPTED;
 		}
 
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 707ca52650e1..646ac8ade88d 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -413,7 +413,7 @@ xrep_fix_freelist(
 
 	args.mp = sc->mp;
 	args.tp = sc->tp;
-	args.agno = sc->sa.pag->pag_agno;
+	args.agno = pag_agno(sc->sa.pag);
 	args.alignment = 1;
 	args.pag = sc->sa.pag;
 
@@ -972,7 +972,7 @@ xrep_reset_perag_resv(
 	if (error == -ENOSPC) {
 		xfs_err(sc->mp,
 "Insufficient free space to reset per-AG reservation for AG %u after repair.",
-				sc->sa.pag->pag_agno);
+				pag_agno(sc->sa.pag));
 		error = 0;
 	}
 
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index ba5bbc3fb754..26b5c90b3f6a 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -410,7 +410,7 @@ xchk_rmapbt_walk_ag_metadata(
 		goto out;
 
 	/* OWN_LOG: Internal log */
-	if (xfs_ag_contains_log(mp, sc->sa.pag->pag_agno)) {
+	if (xfs_ag_contains_log(mp, pag_agno(sc->sa.pag))) {
 		error = xagb_bitmap_set(&cr->log_owned,
 				XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart),
 				mp->m_sb.sb_logblocks);
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index 57d445f7cb2a..f88f58db9098 100644
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -344,7 +344,7 @@ xrep_rmap_visit_bmbt(
 	int			error;
 
 	if (XFS_FSB_TO_AGNO(mp, rec->br_startblock) !=
-			rf->rr->sc->sa.pag->pag_agno)
+			pag_agno(rf->rr->sc->sa.pag))
 		return 0;
 
 	agbno = XFS_FSB_TO_AGBNO(mp, rec->br_startblock);
@@ -391,7 +391,7 @@ xrep_rmap_visit_iroot_btree_block(
 		return 0;
 
 	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
-	if (XFS_FSB_TO_AGNO(cur->bc_mp, fsbno) != rf->rr->sc->sa.pag->pag_agno)
+	if (XFS_FSB_TO_AGNO(cur->bc_mp, fsbno) != pag_agno(rf->rr->sc->sa.pag))
 		return 0;
 
 	agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
@@ -801,7 +801,7 @@ xrep_rmap_find_log_rmaps(
 {
 	struct xfs_scrub	*sc = rr->sc;
 
-	if (!xfs_ag_contains_log(sc->mp, sc->sa.pag->pag_agno))
+	if (!xfs_ag_contains_log(sc->mp, pag_agno(sc->sa.pag)))
 		return 0;
 
 	return xrep_rmap_stash(rr,
@@ -976,7 +976,7 @@ xrep_rmap_try_reserve(
 {
 	struct xrep_rmap_agfl	ra = {
 		.bitmap		= freesp_blocks,
-		.agno		= rr->sc->sa.pag->pag_agno,
+		.agno		= pag_agno(rr->sc->sa.pag),
 	};
 	struct xfs_scrub	*sc = rr->sc;
 	struct xrep_newbt_resv	*resv, *n;
@@ -1596,7 +1596,7 @@ xrep_rmap_setup_scan(
 
 	/* Set up in-memory rmap btree */
 	error = xfs_rmapbt_mem_init(sc->mp, &rr->rmap_btree, sc->xmbtp,
-			sc->sa.pag->pag_agno);
+			pag_agno(sc->sa.pag));
 	if (error)
 		goto out_mutex;
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index a1ec6445ae5f..58cc61f2ed53 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -792,8 +792,8 @@ TRACE_EVENT(xchk_iallocbt_check_cluster,
 		__field(uint16_t, holemask)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->startino = startino;
 		__entry->map_daddr = map_daddr;
 		__entry->map_len = map_len;
@@ -936,8 +936,8 @@ TRACE_EVENT(xchk_refcount_incorrect,
 		__field(xfs_nlink_t, seen)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->domain = irec->rc_domain;
 		__entry->startblock = irec->rc_startblock;
 		__entry->blockcount = irec->rc_blockcount;
@@ -1929,8 +1929,8 @@ DECLARE_EVENT_CLASS(xrep_extent_class,
 		__field(xfs_extlen_t, len)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 	),
@@ -1963,8 +1963,8 @@ DECLARE_EVENT_CLASS(xrep_reap_find_class,
 		__field(bool, crosslinked)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->crosslinked = crosslinked;
@@ -1997,8 +1997,8 @@ TRACE_EVENT(xrep_ibt_walk_rmap,
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = rec->rm_startblock;
 		__entry->len = rec->rm_blockcount;
 		__entry->owner = rec->rm_owner;
@@ -2026,8 +2026,8 @@ TRACE_EVENT(xrep_abt_found,
 		__field(xfs_extlen_t, blockcount)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->startblock = rec->ar_startblock;
 		__entry->blockcount = rec->ar_blockcount;
 	),
@@ -2052,8 +2052,8 @@ TRACE_EVENT(xrep_ibt_found,
 		__field(uint64_t, freemask)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->startino = rec->ir_startino;
 		__entry->holemask = rec->ir_holemask;
 		__entry->count = rec->ir_count;
@@ -2083,8 +2083,8 @@ TRACE_EVENT(xrep_refc_found,
 		__field(xfs_nlink_t, refcount)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->domain = rec->rc_domain;
 		__entry->startblock = rec->rc_startblock;
 		__entry->blockcount = rec->rc_blockcount;
@@ -2144,8 +2144,8 @@ TRACE_EVENT(xrep_rmap_found,
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = rec->rm_startblock;
 		__entry->len = rec->rm_blockcount;
 		__entry->owner = rec->rm_owner;
@@ -2174,8 +2174,8 @@ TRACE_EVENT(xrep_findroot_block,
 		__field(uint16_t, level)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = agbno;
 		__entry->magic = magic;
 		__entry->level = level;
@@ -2201,8 +2201,8 @@ TRACE_EVENT(xrep_calc_ag_resblks,
 		__field(xfs_agblock_t, usedlen)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->icount = icount;
 		__entry->aglen = aglen;
 		__entry->freelen = freelen;
@@ -2230,8 +2230,8 @@ TRACE_EVENT(xrep_calc_ag_resblks_btsize,
 		__field(xfs_agblock_t, refcbt_sz)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->bnobt_sz = bnobt_sz;
 		__entry->inobt_sz = inobt_sz;
 		__entry->rmapbt_sz = rmapbt_sz;
@@ -2282,8 +2282,8 @@ DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
 		__field(int64_t, owner)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->owner = owner;
@@ -2597,8 +2597,8 @@ TRACE_EVENT(xrep_cow_free_staging,
 		__field(xfs_extlen_t, blockcount)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = agbno;
 		__entry->blockcount = blockcount;
 	),
@@ -2657,8 +2657,8 @@ TRACE_EVENT(xrep_rmap_live_update,
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->op = op;
 		__entry->agbno = p->startblock;
 		__entry->len = p->blockcount;
@@ -3317,9 +3317,9 @@ TRACE_EVENT(xrep_iunlink_visit,
 		__field(xfs_agino_t, next_agino)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
-		__entry->agino = XFS_INO_TO_AGINO(pag->pag_mount, ip->i_ino);
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
+		__entry->agino = XFS_INO_TO_AGINO(pag_mount(pag), ip->i_ino);
 		__entry->bucket = bucket;
 		__entry->bucket_agino = bucket_agino;
 		__entry->prev_agino = ip->i_prev_unlinked;
@@ -3405,8 +3405,8 @@ TRACE_EVENT(xrep_iunlink_walk_ondisk_bucket,
 		__field(xfs_agino_t, next_agino)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->bucket = bucket;
 		__entry->prev_agino = prev_agino;
 		__entry->next_agino = next_agino;
@@ -3431,8 +3431,8 @@ DECLARE_EVENT_CLASS(xrep_iunlink_resolve_class,
 		__field(xfs_agino_t, next_agino)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->bucket = bucket;
 		__entry->prev_agino = prev_agino;
 		__entry->next_agino = next_agino;
@@ -3518,8 +3518,8 @@ TRACE_EVENT(xrep_iunlink_add_to_bucket,
 		__field(xfs_agino_t, next_agino)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->bucket = bucket;
 		__entry->agino = agino;
 		__entry->next_agino = curr_head;
@@ -3544,8 +3544,8 @@ TRACE_EVENT(xrep_iunlink_commit_bucket,
 		__field(xfs_agino_t, agino)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->bucket = bucket;
 		__entry->old_agino = old_agino;
 		__entry->agino = agino;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 79648f8c6b27..dfd6edcebb6e 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -159,7 +159,7 @@ xfs_trim_gather_extents(
 	struct xfs_trim_cur	*tcur,
 	struct xfs_busy_extents	*extents)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_trans	*tp;
 	struct xfs_btree_cur	*cur;
 	struct xfs_buf		*agbp;
@@ -365,7 +365,7 @@ xfs_trim_perag_extents(
 		 * list  after this function call, as it may have been freed by
 		 * the time control returns to us.
 		 */
-		error = xfs_discard_extents(pag->pag_mount, extents);
+		error = xfs_discard_extents(pag_mount(pag), extents);
 		if (error)
 			break;
 
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 81099400a171..79b0f833c511 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -283,7 +283,7 @@ xfs_extent_busy_update_extent(
 
 out_force_log:
 	spin_unlock(&pag->pagb_lock);
-	xfs_log_force(pag->pag_mount, XFS_LOG_SYNC);
+	xfs_log_force(pag_mount(pag), XFS_LOG_SYNC);
 	trace_xfs_extent_busy_force(pag, fbno, flen);
 	spin_lock(&pag->pagb_lock);
 	return false;
@@ -659,7 +659,7 @@ xfs_extent_busy_ag_cmp(
 		container_of(l2, struct xfs_extent_busy, list);
 	s32 diff;
 
-	diff = b1->pag->pag_agno - b2->pag->pag_agno;
+	diff = pag_agno(b1->pag) - pag_agno(b2->pag);
 	if (!diff)
 		diff = b1->bno - b2->bno;
 	return diff;
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 7f1be08dbc11..c198962edea1 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -362,7 +362,7 @@ xfs_extent_free_diff_items(
 	struct xfs_extent_free_item	*ra = xefi_entry(a);
 	struct xfs_extent_free_item	*rb = xefi_entry(b);
 
-	return ra->xefi_pag->pag_agno - rb->xefi_pag->pag_agno;
+	return pag_agno(ra->xefi_pag) - pag_agno(rb->xefi_pag);
 }
 
 /* Log a free extent to the intent item. */
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index f2caebb78dd2..a961aa420c48 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -96,7 +96,7 @@ xfs_filestream_pick_ag(
 			maxfree = pag->pagf_freeblks;
 			if (max_pag)
 				xfs_perag_rele(max_pag);
-			atomic_inc(&pag->pag_active_ref);
+			atomic_inc(&pag_group(pag)->xg_active_ref);
 			max_pag = pag;
 		}
 
@@ -222,7 +222,7 @@ xfs_filestream_lookup_association(
 	 * down immediately after we mark the lookup as done.
 	 */
 	pag = container_of(mru, struct xfs_fstrm_item, mru)->pag;
-	atomic_inc(&pag->pag_active_ref);
+	atomic_inc(&pag_group(pag)->xg_active_ref);
 	xfs_mru_cache_done(mp->m_filestream);
 
 	trace_xfs_filestream_lookup(pag, ap->ip->i_ino);
@@ -275,7 +275,7 @@ xfs_filestream_create_association(
 		struct xfs_fstrm_item *item =
 			container_of(mru, struct xfs_fstrm_item, mru);
 
-		agno = (item->pag->pag_agno + 1) % mp->m_sb.sb_agcount;
+		agno = (pag_agno(item->pag) + 1) % mp->m_sb.sb_agcount;
 		xfs_fstrm_free_func(mp, mru);
 	} else if (xfs_is_inode32(mp)) {
 		xfs_agnumber_t	 rotorstep = xfs_rotorstep;
@@ -314,7 +314,7 @@ xfs_filestream_create_association(
 	if (!item)
 		goto out_put_fstrms;
 
-	atomic_inc(&args->pag->pag_active_ref);
+	atomic_inc(&pag_group(args->pag)->xg_active_ref);
 	item->pag = args->pag;
 	error = xfs_mru_cache_insert(mp->m_filestream, pino, &item->mru);
 	if (error)
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index eff198ae1ce3..918e1c38a155 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -353,7 +353,7 @@ xfs_getfsmap_helper(
 		return -ECANCELED;
 
 	trace_xfs_fsmap_mapping(mp, info->dev,
-			info->pag ? info->pag->pag_agno : NULLAGNUMBER, rec);
+			info->pag ? pag_agno(info->pag) : NULLAGNUMBER, rec);
 
 	fmr.fmr_device = info->dev;
 	fmr.fmr_physical = rec_daddr;
@@ -519,7 +519,7 @@ __xfs_getfsmap_datadev(
 		 * is the last AG that we're querying.
 		 */
 		info->pag = pag;
-		if (pag->pag_agno == end_ag) {
+		if (pag_agno(pag) == end_ag) {
 			info->high.rm_startblock = XFS_FSB_TO_AGBNO(mp,
 					end_fsb);
 			info->high.rm_offset = XFS_BB_TO_FSBT(mp,
@@ -541,9 +541,9 @@ __xfs_getfsmap_datadev(
 		if (error)
 			break;
 
-		trace_xfs_fsmap_low_key(mp, info->dev, pag->pag_agno,
+		trace_xfs_fsmap_low_key(mp, info->dev, pag_agno(pag),
 				&info->low);
-		trace_xfs_fsmap_high_key(mp, info->dev, pag->pag_agno,
+		trace_xfs_fsmap_high_key(mp, info->dev, pag_agno(pag),
 				&info->high);
 
 		error = query_fn(tp, info, &bt_cur, priv);
@@ -554,7 +554,7 @@ __xfs_getfsmap_datadev(
 		 * Set the AG low key to the start of the AG prior to
 		 * moving on to the next AG.
 		 */
-		if (pag->pag_agno == start_ag)
+		if (pag_agno(pag) == start_ag)
 			memset(&info->low, 0, sizeof(info->low));
 
 		/*
@@ -562,7 +562,7 @@ __xfs_getfsmap_datadev(
 		 * before we drop the reference to the perag when the loop
 		 * terminates.
 		 */
-		if (pag->pag_agno == end_ag) {
+		if (pag_agno(pag) == end_ag) {
 			info->last = true;
 			error = query_fn(tp, info, &bt_cur, priv);
 			if (error)
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 6b119a7a324f..0a930fc116f5 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -204,7 +204,7 @@ xfs_reclaim_work_queue(
 {
 
 	rcu_read_lock();
-	if (xa_marked(&mp->m_perags, XFS_PERAG_RECLAIM_MARK)) {
+	if (xfs_group_marked(mp, XG_TYPE_AG, XFS_PERAG_RECLAIM_MARK)) {
 		queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
 			msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
 	}
@@ -219,15 +219,14 @@ static inline void
 xfs_blockgc_queue(
 	struct xfs_perag	*pag)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 
 	if (!xfs_is_blockgc_enabled(mp))
 		return;
 
 	rcu_read_lock();
 	if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG))
-		queue_delayed_work(pag->pag_mount->m_blockgc_wq,
-				   &pag->pag_blockgc_work,
+		queue_delayed_work(mp->m_blockgc_wq, &pag->pag_blockgc_work,
 				   msecs_to_jiffies(xfs_blockgc_secs * 1000));
 	rcu_read_unlock();
 }
@@ -239,7 +238,6 @@ xfs_perag_set_inode_tag(
 	xfs_agino_t		agino,
 	unsigned int		tag)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
 	bool			was_tagged;
 
 	lockdep_assert_held(&pag->pag_ici_lock);
@@ -253,13 +251,13 @@ xfs_perag_set_inode_tag(
 	if (was_tagged)
 		return;
 
-	/* propagate the tag up into the perag radix tree */
-	xa_set_mark(&mp->m_perags, pag->pag_agno, ici_tag_to_mark(tag));
+	/* propagate the tag up into the pag xarray tree */
+	xfs_group_set_mark(pag_group(pag), ici_tag_to_mark(tag));
 
 	/* start background work */
 	switch (tag) {
 	case XFS_ICI_RECLAIM_TAG:
-		xfs_reclaim_work_queue(mp);
+		xfs_reclaim_work_queue(pag_mount(pag));
 		break;
 	case XFS_ICI_BLOCKGC_TAG:
 		xfs_blockgc_queue(pag);
@@ -276,8 +274,6 @@ xfs_perag_clear_inode_tag(
 	xfs_agino_t		agino,
 	unsigned int		tag)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
-
 	lockdep_assert_held(&pag->pag_ici_lock);
 
 	/*
@@ -295,9 +291,8 @@ xfs_perag_clear_inode_tag(
 	if (radix_tree_tagged(&pag->pag_ici_root, tag))
 		return;
 
-	/* clear the tag from the perag radix tree */
-	xa_clear_mark(&mp->m_perags, pag->pag_agno, ici_tag_to_mark(tag));
-
+	/* clear the tag from the pag xarray */
+	xfs_group_clear_mark(pag_group(pag), ici_tag_to_mark(tag));
 	trace_xfs_perag_clear_inode_tag(pag, _RET_IP_);
 }
 
@@ -310,22 +305,9 @@ xfs_perag_grab_next_tag(
 	struct xfs_perag	*pag,
 	int			tag)
 {
-	unsigned long		index = 0;
-
-	if (pag) {
-		index = pag->pag_agno + 1;
-		xfs_perag_rele(pag);
-	}
-
-	rcu_read_lock();
-	pag = xa_find(&mp->m_perags, &index, ULONG_MAX, ici_tag_to_mark(tag));
-	if (pag) {
-		trace_xfs_perag_grab_next_tag(pag, _RET_IP_);
-		if (!atomic_inc_not_zero(&pag->pag_active_ref))
-			pag = NULL;
-	}
-	rcu_read_unlock();
-	return pag;
+	return to_perag(xfs_group_grab_next_mark(mp,
+			pag ? pag_group(pag) : NULL,
+			ici_tag_to_mark(tag), XG_TYPE_AG));
 }
 
 /*
@@ -1014,7 +996,7 @@ xfs_reclaim_inodes(
 	if (xfs_want_reclaim_sick(mp))
 		icw.icw_flags |= XFS_ICWALK_FLAG_RECLAIM_SICK;
 
-	while (xa_marked(&mp->m_perags, XFS_PERAG_RECLAIM_MARK)) {
+	while (xfs_group_marked(mp, XG_TYPE_AG, XFS_PERAG_RECLAIM_MARK)) {
 		xfs_ail_push_all_sync(mp->m_ail);
 		xfs_icwalk(mp, XFS_ICWALK_RECLAIM, &icw);
 	}
@@ -1056,7 +1038,7 @@ long
 xfs_reclaim_inodes_count(
 	struct xfs_mount	*mp)
 {
-	XA_STATE		(xas, &mp->m_perags, 0);
+	XA_STATE		(xas, &mp->m_groups[XG_TYPE_AG].xa, 0);
 	long			reclaimable = 0;
 	struct xfs_perag	*pag;
 
@@ -1499,7 +1481,7 @@ xfs_blockgc_worker(
 {
 	struct xfs_perag	*pag = container_of(to_delayed_work(work),
 					struct xfs_perag, pag_blockgc_work);
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	int			error;
 
 	trace_xfs_blockgc_worker(mp, __return_address);
@@ -1507,7 +1489,7 @@ xfs_blockgc_worker(
 	error = xfs_icwalk_ag(pag, XFS_ICWALK_BLOCKGC, NULL);
 	if (error)
 		xfs_info(mp, "AG %u preallocation gc worker failed, err=%d",
-				pag->pag_agno, error);
+				pag_agno(pag), error);
 	xfs_blockgc_queue(pag);
 }
 
@@ -1548,8 +1530,7 @@ xfs_blockgc_flush_all(
 	 * queued, it will not be requeued.  Then flush whatever is left.
 	 */
 	while ((pag = xfs_perag_grab_next_tag(mp, pag, XFS_ICI_BLOCKGC_TAG)))
-		mod_delayed_work(pag->pag_mount->m_blockgc_wq,
-				&pag->pag_blockgc_work, 0);
+		mod_delayed_work(mp->m_blockgc_wq, &pag->pag_blockgc_work, 0);
 
 	while ((pag = xfs_perag_grab_next_tag(mp, pag, XFS_ICI_BLOCKGC_TAG)))
 		flush_delayed_work(&pag->pag_blockgc_work);
@@ -1688,7 +1669,7 @@ xfs_icwalk_ag(
 	enum xfs_icwalk_goal	goal,
 	struct xfs_icwalk	*icw)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	uint32_t		first_index;
 	int			last_error = 0;
 	int			skipped;
@@ -1741,7 +1722,7 @@ xfs_icwalk_ag(
 			 * us to see this inode, so another lookup from the
 			 * same index will not find it again.
 			 */
-			if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
+			if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag_agno(pag))
 				continue;
 			first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
 			if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 5529ff39b640..693770f9bb09 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1514,7 +1514,7 @@ xfs_iunlink_reload_next(
 	xfs_agino_t		next_agino)
 {
 	struct xfs_perag	*pag = agibp->b_pag;
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_inode	*next_ip = NULL;
 	int			error;
 
@@ -1529,7 +1529,7 @@ xfs_iunlink_reload_next(
 
 	xfs_info_ratelimited(mp,
  "Found unrecovered unlinked inode 0x%x in AG 0x%x.  Initiating recovery.",
-			next_agino, pag->pag_agno);
+			next_agino, pag_agno(pag));
 
 	/*
 	 * Use an untrusted lookup just to be cautious in case the AGI has been
@@ -1572,7 +1572,7 @@ xfs_ifree_mark_inode_stale(
 	struct xfs_inode	*free_ip,
 	xfs_ino_t		inum)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_inode_log_item *iip;
 	struct xfs_inode	*ip;
 
diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index a89ae2aef7c4..ec2d56f1840f 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -188,7 +188,7 @@ xfs_iwalk_ag_recs(
 			return 0;
 
 		if (iwag->inobt_walk_fn) {
-			error = iwag->inobt_walk_fn(mp, tp, pag->pag_agno, irec,
+			error = iwag->inobt_walk_fn(mp, tp, pag_agno(pag), irec,
 					iwag->data);
 			if (error)
 				return error;
@@ -405,7 +405,7 @@ xfs_iwalk_ag(
 	int				error = 0;
 
 	/* Set up our cursor at the right place in the inode btree. */
-	ASSERT(pag->pag_agno == XFS_INO_TO_AGNO(mp, iwag->startino));
+	ASSERT(pag_agno(pag) == XFS_INO_TO_AGNO(mp, iwag->startino));
 	agino = XFS_INO_TO_AGINO(mp, iwag->startino);
 	error = xfs_iwalk_ag_start(iwag, agino, &cur, &agi_bp, &has_more);
 
@@ -677,7 +677,7 @@ xfs_iwalk_threaded(
 		iwag->sz_recs = xfs_iwalk_prefetch(inode_records);
 		iwag->lastino = NULLFSINO;
 		xfs_pwork_queue(&pctl, &iwag->pwork);
-		startino = XFS_AGINO_TO_INO(mp, pag->pag_agno + 1, 0);
+		startino = XFS_AGINO_TO_INO(mp, pag_agno(pag) + 1, 0);
 		if (flags & XFS_IWALK_SAME_AG)
 			break;
 	}
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 56772bbd38cd..a285d2d1f68c 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2677,7 +2677,7 @@ xlog_recover_clear_agi_bucket(
 	struct xfs_perag	*pag,
 	int			bucket)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_trans	*tp;
 	struct xfs_agi		*agi;
 	struct xfs_buf		*agibp;
@@ -2708,7 +2708,7 @@ xlog_recover_clear_agi_bucket(
 	xfs_trans_cancel(tp);
 out_error:
 	xfs_warn(mp, "%s: failed to clear agi %d. Continuing.", __func__,
-			pag->pag_agno);
+			pag_agno(pag));
 	return;
 }
 
@@ -2718,7 +2718,7 @@ xlog_recover_iunlink_bucket(
 	struct xfs_agi		*agi,
 	int			bucket)
 {
-	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_mount	*mp = pag_mount(pag);
 	struct xfs_inode	*prev_ip = NULL;
 	struct xfs_inode	*ip;
 	xfs_agino_t		prev_agino, agino;
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 96496f39f551..530d7f025506 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -71,6 +71,10 @@ struct xfs_inodegc {
 	unsigned int		cpu;
 };
 
+struct xfs_groups {
+	struct xarray		xa;
+};
+
 /*
  * The struct xfsmount layout is optimised to separate read-mostly variables
  * from variables that are frequently modified. We put the read-mostly variables
@@ -208,7 +212,7 @@ typedef struct xfs_mount {
 	 */
 	atomic64_t		m_allocbt_blks;
 
-	struct xarray		m_perags;	/* per-ag accounting info */
+	struct xfs_groups	m_groups[XG_TYPE_MAX];
 	uint64_t		m_resblks;	/* total reserved blocks */
 	uint64_t		m_resblks_avail;/* available reserved blocks */
 	uint64_t		m_resblks_save;	/* reserved blks @ remount,ro */
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 27398512b179..29f101005f3e 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -244,7 +244,7 @@ xfs_refcount_update_diff_items(
 	struct xfs_refcount_intent	*ra = ci_entry(a);
 	struct xfs_refcount_intent	*rb = ci_entry(b);
 
-	return ra->ri_pag->pag_agno - rb->ri_pag->pag_agno;
+	return pag_agno(ra->ri_pag) - pag_agno(rb->ri_pag);
 }
 
 /* Log refcount updates in the intent item. */
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 5bf6682e701b..2e82b5b6ed52 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -144,7 +144,7 @@ xfs_reflink_find_shared(
 	if (error)
 		return error;
 
-	cur = xfs_refcountbt_init_cursor(pag->pag_mount, tp, agbp, pag);
+	cur = xfs_refcountbt_init_cursor(pag_mount(pag), tp, agbp, pag);
 
 	error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
 			find_end_of_shared);
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 88b5580e1e19..1b83d09351f0 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -243,7 +243,7 @@ xfs_rmap_update_diff_items(
 	struct xfs_rmap_intent		*ra = ri_entry(a);
 	struct xfs_rmap_intent		*rb = ri_entry(b);
 
-	return ra->ri_pag->pag_agno - rb->ri_pag->pag_agno;
+	return pag_agno(ra->ri_pag) - pag_agno(rb->ri_pag);
 }
 
 /* Log rmap updates in the intent item. */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index fbb3a1594c0d..457c2d70968d 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -238,7 +238,7 @@ xfs_set_inode_alloc_perag(
 	xfs_ino_t		ino,
 	xfs_agnumber_t		max_metadata)
 {
-	if (!xfs_is_inode32(pag->pag_mount)) {
+	if (!xfs_is_inode32(pag_mount(pag))) {
 		set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate);
 		clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
 		return false;
@@ -251,7 +251,7 @@ xfs_set_inode_alloc_perag(
 	}
 
 	set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate);
-	if (pag->pag_agno < max_metadata)
+	if (pag_agno(pag) < max_metadata)
 		set_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
 	else
 		clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
@@ -2011,17 +2011,20 @@ static const struct fs_context_operations xfs_context_ops = {
  * mount option parsing having already been performed as this can be called from
  * fsopen() before any parameters have been set.
  */
-static int xfs_init_fs_context(
+static int
+xfs_init_fs_context(
 	struct fs_context	*fc)
 {
 	struct xfs_mount	*mp;
+	int			i;
 
 	mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL | __GFP_NOFAIL);
 	if (!mp)
 		return -ENOMEM;
 
 	spin_lock_init(&mp->m_sb_lock);
-	xa_init(&mp->m_perags);
+	for (i = 0; i < XG_TYPE_MAX; i++)
+		xa_init(&mp->m_groups[i].xa);
 	mutex_init(&mp->m_growlock);
 	INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker);
 	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 7ef501072246..17164b2d0472 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -11,6 +11,7 @@
 #include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_group.h"
 #include "xfs_defer.h"
 #include "xfs_da_format.h"
 #include "xfs_inode.h"
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index dcd0452fc7e4..14e7f6a26a23 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -72,6 +72,7 @@ struct xfs_btree_cur;
 struct xfs_defer_op_type;
 struct xfs_refcount_irec;
 struct xfs_fsmap;
+struct xfs_group;
 struct xfs_rmap_irec;
 struct xfs_icreate_log;
 struct xfs_iunlink_item;
@@ -192,10 +193,11 @@ DECLARE_EVENT_CLASS(xfs_perag_class,
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
-		__entry->refcount = atomic_read(&pag->pag_ref);
-		__entry->active_refcount = atomic_read(&pag->pag_active_ref);
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
+		__entry->refcount = atomic_read(&pag->pag_group.xg_ref);
+		__entry->active_refcount =
+			atomic_read(&pag->pag_group.xg_active_ref);
 		__entry->caller_ip = caller_ip;
 	),
 	TP_printk("dev %d:%d agno 0x%x passive refs %d active refs %d caller %pS",
@@ -210,16 +212,51 @@ DECLARE_EVENT_CLASS(xfs_perag_class,
 DEFINE_EVENT(xfs_perag_class, name,	\
 	TP_PROTO(const struct xfs_perag *pag, unsigned long caller_ip), \
 	TP_ARGS(pag, caller_ip))
-DEFINE_PERAG_REF_EVENT(xfs_perag_get);
-DEFINE_PERAG_REF_EVENT(xfs_perag_hold);
-DEFINE_PERAG_REF_EVENT(xfs_perag_put);
-DEFINE_PERAG_REF_EVENT(xfs_perag_grab);
-DEFINE_PERAG_REF_EVENT(xfs_perag_grab_next_tag);
-DEFINE_PERAG_REF_EVENT(xfs_perag_rele);
 DEFINE_PERAG_REF_EVENT(xfs_perag_set_inode_tag);
 DEFINE_PERAG_REF_EVENT(xfs_perag_clear_inode_tag);
 DEFINE_PERAG_REF_EVENT(xfs_reclaim_inodes_count);
 
+TRACE_DEFINE_ENUM(XG_TYPE_AG);
+
+DECLARE_EVENT_CLASS(xfs_group_class,
+	TP_PROTO(struct xfs_group *xg, unsigned long caller_ip),
+	TP_ARGS(xg, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(enum xfs_group_type, type)
+		__field(xfs_agnumber_t, agno)
+		__field(int, refcount)
+		__field(int, active_refcount)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = xg->xg_mount->m_super->s_dev;
+		__entry->type = xg->xg_type;
+		__entry->agno = xg->xg_gno;
+		__entry->refcount = atomic_read(&xg->xg_ref);
+		__entry->active_refcount = atomic_read(&xg->xg_active_ref);
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d %sno 0x%x passive refs %d active refs %d caller %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
+		  __entry->agno,
+		  __entry->refcount,
+		  __entry->active_refcount,
+		  (char *)__entry->caller_ip)
+);
+
+#define DEFINE_GROUP_REF_EVENT(name)	\
+DEFINE_EVENT(xfs_group_class, name,	\
+	TP_PROTO(struct xfs_group *xg, unsigned long caller_ip), \
+	TP_ARGS(xg, caller_ip))
+DEFINE_GROUP_REF_EVENT(xfs_group_get);
+DEFINE_GROUP_REF_EVENT(xfs_group_hold);
+DEFINE_GROUP_REF_EVENT(xfs_group_put);
+DEFINE_GROUP_REF_EVENT(xfs_group_grab);
+DEFINE_GROUP_REF_EVENT(xfs_group_grab_next_tag);
+DEFINE_GROUP_REF_EVENT(xfs_group_rele);
+
 TRACE_EVENT(xfs_inodegc_worker,
 	TP_PROTO(struct xfs_mount *mp, unsigned int shrinker_hits),
 	TP_ARGS(mp, shrinker_hits),
@@ -307,8 +344,8 @@ DECLARE_EVENT_CLASS(xfs_ag_class,
 		__field(xfs_agnumber_t, agno)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 	),
 	TP_printk("dev %d:%d agno 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -672,9 +709,9 @@ DECLARE_EVENT_CLASS(xfs_filestream_class,
 		__field(int, streams)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
 		__entry->ino = ino;
-		__entry->agno = pag->pag_agno;
+		__entry->agno = pag_agno(pag);
 		__entry->streams = atomic_read(&pag->pagf_fstrms);
 	),
 	TP_printk("dev %d:%d ino 0x%llx agno 0x%x streams %d",
@@ -702,9 +739,9 @@ TRACE_EVENT(xfs_filestream_pick,
 		__field(xfs_extlen_t, free)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
 		__entry->ino = ino;
-		__entry->agno = pag->pag_agno;
+		__entry->agno = pag_agno(pag);
 		__entry->streams = atomic_read(&pag->pagf_fstrms);
 		__entry->free = pag->pagf_freeblks;
 	),
@@ -908,8 +945,8 @@ TRACE_EVENT(xfs_irec_merge_pre,
 		__field(uint16_t, nholemask)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agino = rec->ir_startino;
 		__entry->holemask = rec->ir_holemask;
 		__entry->nagino = nrec->ir_startino;
@@ -935,8 +972,8 @@ TRACE_EVENT(xfs_irec_merge_post,
 		__field(uint16_t, holemask)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agino = nrec->ir_startino;
 		__entry->holemask = nrec->ir_holemask;
 	),
@@ -1646,8 +1683,8 @@ DECLARE_EVENT_CLASS(xfs_extent_busy_class,
 		__field(xfs_extlen_t, len)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 	),
@@ -1680,8 +1717,8 @@ TRACE_EVENT(xfs_extent_busy_trim,
 		__field(xfs_extlen_t, tlen)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->tbno = tbno;
@@ -1773,8 +1810,8 @@ TRACE_EVENT(xfs_free_extent,
 		__field(int, haveright)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->resv = resv;
@@ -2437,8 +2474,8 @@ DECLARE_EVENT_CLASS(xfs_discard_class,
 		__field(xfs_extlen_t, len)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 	),
@@ -2543,7 +2580,7 @@ TRACE_EVENT(xfs_btree_alloc_block,
 			__entry->ino = cur->bc_ino.ip->i_ino;
 			break;
 		case XFS_BTREE_TYPE_AG:
-			__entry->agno = cur->bc_ag.pag->pag_agno;
+			__entry->agno = pag_agno(cur->bc_ag.pag);
 			__entry->ino = 0;
 			break;
 		case XFS_BTREE_TYPE_MEM:
@@ -2799,7 +2836,7 @@ DECLARE_EVENT_CLASS(xfs_rmap_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->owner = oinfo->oi_owner;
@@ -2844,7 +2881,7 @@ DECLARE_EVENT_CLASS(xfs_btree_error_class,
 			__entry->ino = cur->bc_ino.ip->i_ino;
 			break;
 		case XFS_BTREE_TYPE_AG:
-			__entry->agno = cur->bc_ag.pag->pag_agno;
+			__entry->agno = pag_agno(cur->bc_ag.pag);
 			__entry->ino = 0;
 			break;
 		case XFS_BTREE_TYPE_MEM:
@@ -2898,7 +2935,7 @@ TRACE_EVENT(xfs_rmap_convert_state,
 			__entry->ino = cur->bc_ino.ip->i_ino;
 			break;
 		case XFS_BTREE_TYPE_AG:
-			__entry->agno = cur->bc_ag.pag->pag_agno;
+			__entry->agno = pag_agno(cur->bc_ag.pag);
 			__entry->ino = 0;
 			break;
 		case XFS_BTREE_TYPE_MEM:
@@ -2933,7 +2970,7 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->owner = owner;
@@ -3106,8 +3143,8 @@ DECLARE_EVENT_CLASS(xfs_ag_resv_class,
 	TP_fast_assign(
 		struct xfs_ag_resv	*r = xfs_perag_resv(pag, resv);
 
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->resv = resv;
 		__entry->freeblks = pag->pagf_freeblks;
 		__entry->flcount = pag->pagf_flcount;
@@ -3151,8 +3188,8 @@ TRACE_EVENT(xfs_ag_resv_init_error,
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->error = error;
 		__entry->caller_ip = caller_ip;
 	),
@@ -3177,7 +3214,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->agbno = agbno;
 		__entry->len = len;
 	),
@@ -3208,7 +3245,7 @@ TRACE_EVENT(xfs_refcount_lookup,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->agbno = agbno;
 		__entry->dir = dir;
 	),
@@ -3234,7 +3271,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->domain = irec->rc_domain;
 		__entry->startblock = irec->rc_startblock;
 		__entry->blockcount = irec->rc_blockcount;
@@ -3270,7 +3307,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->domain = irec->rc_domain;
 		__entry->startblock = irec->rc_startblock;
 		__entry->blockcount = irec->rc_blockcount;
@@ -3312,7 +3349,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
@@ -3362,7 +3399,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
@@ -3417,7 +3454,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
@@ -4040,8 +4077,8 @@ TRACE_EVENT(xfs_iunlink_update_bucket,
 		__field(xfs_agino_t, new_ptr)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->bucket = bucket;
 		__entry->old_ptr = old_ptr;
 		__entry->new_ptr = new_ptr;
@@ -4065,8 +4102,8 @@ TRACE_EVENT(xfs_iunlink_update_dinode,
 		__field(xfs_agino_t, new_ptr)
 	),
 	TP_fast_assign(
-		__entry->dev = iup->pag->pag_mount->m_super->s_dev;
-		__entry->agno = iup->pag->pag_agno;
+		__entry->dev = pag_mount(iup->pag)->m_super->s_dev;
+		__entry->agno = pag_agno(iup->pag);
 		__entry->agino =
 			XFS_INO_TO_AGINO(iup->ip->i_mount, iup->ip->i_ino);
 		__entry->old_ptr = old_ptr;
@@ -4187,8 +4224,8 @@ DECLARE_EVENT_CLASS(xfs_ag_corrupt_class,
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->flags = flags;
 	),
 	TP_printk("dev %d:%d agno 0x%x flags 0x%x",
@@ -4241,8 +4278,8 @@ TRACE_EVENT(xfs_iwalk_ag_rec,
 		__field(uint64_t, freemask)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->startino = irec->ir_startino;
 		__entry->freemask = irec->ir_free;
 	),
@@ -4304,7 +4341,7 @@ TRACE_EVENT(xfs_btree_commit_afakeroot,
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
 		__assign_str(name);
-		__entry->agno = cur->bc_ag.pag->pag_agno;
+		__entry->agno = pag_agno(cur->bc_ag.pag);
 		__entry->agbno = cur->bc_ag.afake->af_root;
 		__entry->levels = cur->bc_ag.afake->af_levels;
 		__entry->blocks = cur->bc_ag.afake->af_blocks;
@@ -4419,7 +4456,7 @@ TRACE_EVENT(xfs_btree_bload_block,
 			__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsb);
 			__entry->agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsb);
 		} else {
-			__entry->agno = cur->bc_ag.pag->pag_agno;
+			__entry->agno = pag_agno(cur->bc_ag.pag);
 			__entry->agbno = be32_to_cpu(ptr->s);
 		}
 		__entry->nr_records = nr_records;
@@ -4654,8 +4691,8 @@ DECLARE_EVENT_CLASS(xfs_perag_intents_class,
 		__field(void *, caller_ip)
 	),
 	TP_fast_assign(
-		__entry->dev = pag->pag_mount->m_super->s_dev;
-		__entry->agno = pag->pag_agno;
+		__entry->dev = pag_mount(pag)->m_super->s_dev;
+		__entry->agno = pag_agno(pag);
 		__entry->nr_intents = atomic_read(&pag->pag_intents_drain.dr_count);
 		__entry->caller_ip = caller_ip;
 	),

From 819928770bd91960f88f5a4dfa21b35a1bade61b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:39 -0800
Subject: [PATCH 03/16] xfs: add a xfs_group_next_range helper

Add a helper to iterate over iterate over all groups, which can be used
as a simple while loop:

	struct xfs_group		*xg = NULL;

	while ((xg = xfs_group_next_range(mp, xg, 0, MAX_GROUP))) {
		...
	}

This will be wrapped by the realtime group code first, and eventually
replace the for_each_rtgroup_from and for_each_rtgroup_range helpers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_group.c | 26 ++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_group.h |  3 +++
 2 files changed, 29 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c
index edf5907845f0..59e08cfaf9bf 100644
--- a/fs/xfs/libxfs/xfs_group.c
+++ b/fs/xfs/libxfs/xfs_group.c
@@ -87,6 +87,32 @@ xfs_group_grab(
 	return xg;
 }
 
+/*
+ * Iterate to the next group.  To start the iteration at @start_index, a %NULL
+ * @xg is passed, else the previous group returned from this function.  The
+ * caller should break out of the loop when this returns %NULL.  If the caller
+ * wants to break out of a loop that did not finish it needs to release the
+ * active reference to @xg using xfs_group_rele() itself.
+ */
+struct xfs_group *
+xfs_group_next_range(
+	struct xfs_mount	*mp,
+	struct xfs_group	*xg,
+	uint32_t		start_index,
+	uint32_t		end_index,
+	enum xfs_group_type	type)
+{
+	uint32_t		index = start_index;
+
+	if (xg) {
+		index = xg->xg_gno + 1;
+		xfs_group_rele(xg);
+	}
+	if (index > end_index)
+		return NULL;
+	return xfs_group_grab(mp, index, type);
+}
+
 /*
  * Find the next group after @xg, or the first group if @xg is NULL.
  */
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index e3b6be7ff9e8..dd7da9044305 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -20,6 +20,9 @@ void xfs_group_put(struct xfs_group *xg);
 
 struct xfs_group *xfs_group_grab(struct xfs_mount *mp, uint32_t index,
 		enum xfs_group_type type);
+struct xfs_group *xfs_group_next_range(struct xfs_mount *mp,
+		struct xfs_group *xg, uint32_t start_index, uint32_t end_index,
+		enum xfs_group_type type);
 struct xfs_group *xfs_group_grab_next_mark(struct xfs_mount *mp,
 		struct xfs_group *xg, xa_mark_t mark, enum xfs_group_type type);
 void xfs_group_rele(struct xfs_group *xg);

From 86437e6abbd2ef040f42ef190264819db6118415 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:39 -0800
Subject: [PATCH 04/16] xfs: switch perag iteration from the for_each macros to
 a while based iterator

The current for_each_perag* macros are a bit annoying in that they
require the caller to both provide an object and an index iterator, and
also somewhat obsfucate the underlying control flow mechanism.

Switch to open coded while loops using new xfs_perag_next{,_from,_range}
helpers that return the next pag structure to iterate on based on the
previous one or NULL for the loop start.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.h      | 62 +++++++++++++++++--------------------
 fs/xfs/libxfs/xfs_sb.c      | 15 +++------
 fs/xfs/libxfs/xfs_types.c   |  5 ++-
 fs/xfs/scrub/bmap.c         |  5 ++-
 fs/xfs/scrub/bmap_repair.c  |  5 ++-
 fs/xfs/scrub/fscounters.c   | 10 +++---
 fs/xfs/scrub/health.c       | 11 +++----
 fs/xfs/scrub/inode_repair.c |  5 ++-
 fs/xfs/xfs_discard.c        |  6 ++--
 fs/xfs/xfs_extent_busy.c    |  5 ++-
 fs/xfs/xfs_fsmap.c          |  7 ++---
 fs/xfs/xfs_fsops.c          | 10 +++---
 fs/xfs/xfs_health.c         |  5 ++-
 fs/xfs/xfs_icache.c         |  5 ++-
 fs/xfs/xfs_iwalk.c          | 18 ++++++-----
 fs/xfs/xfs_log_recover.c    |  5 ++-
 fs/xfs/xfs_reflink.c        |  5 ++-
 17 files changed, 79 insertions(+), 105 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 69b934ad2c4a..80969682dc47 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -208,6 +208,34 @@ xfs_perag_rele(
 	xfs_group_rele(pag_group(pag));
 }
 
+static inline struct xfs_perag *
+xfs_perag_next_range(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
+	xfs_agnumber_t		start_agno,
+	xfs_agnumber_t		end_agno)
+{
+	return to_perag(xfs_group_next_range(mp, pag ? pag_group(pag) : NULL,
+			start_agno, end_agno, XG_TYPE_AG));
+}
+
+static inline struct xfs_perag *
+xfs_perag_next_from(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
+	xfs_agnumber_t		start_agno)
+{
+	return xfs_perag_next_range(mp, pag, start_agno, mp->m_sb.sb_agcount - 1);
+}
+
+static inline struct xfs_perag *
+xfs_perag_next(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag)
+{
+	return xfs_perag_next_from(mp, pag, 0);
+}
+
 /*
  * Per-ag geometry infomation and validation
  */
@@ -273,40 +301,6 @@ xfs_ag_contains_log(struct xfs_mount *mp, xfs_agnumber_t agno)
 	       agno == XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart);
 }
 
-/*
- * Perag iteration APIs
- */
-static inline struct xfs_perag *
-xfs_perag_next(
-	struct xfs_perag	*pag,
-	xfs_agnumber_t		*agno,
-	xfs_agnumber_t		end_agno)
-{
-	struct xfs_mount	*mp = pag_mount(pag);
-
-	*agno = pag_agno(pag) + 1;
-	xfs_perag_rele(pag);
-	while (*agno <= end_agno) {
-		pag = xfs_perag_grab(mp, *agno);
-		if (pag)
-			return pag;
-		(*agno)++;
-	}
-	return NULL;
-}
-
-#define for_each_perag_range(mp, agno, end_agno, pag) \
-	for ((pag) = xfs_perag_grab((mp), (agno)); \
-		(pag) != NULL; \
-		(pag) = xfs_perag_next((pag), &(agno), (end_agno)))
-
-#define for_each_perag_from(mp, agno, pag) \
-	for_each_perag_range((mp), (agno), (mp)->m_sb.sb_agcount - 1, (pag))
-
-#define for_each_perag(mp, agno, pag) \
-	(agno) = 0; \
-	for_each_perag_from((mp), (agno), (pag))
-
 static inline struct xfs_perag *
 xfs_perag_next_wrap(
 	struct xfs_perag	*pag,
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index d2012fbf07aa..061c8c961d5b 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1109,14 +1109,13 @@ int
 xfs_update_secondary_sbs(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno = 1;
+	struct xfs_perag	*pag = NULL;
 	int			saved_error = 0;
 	int			error = 0;
 	LIST_HEAD		(buffer_list);
 
 	/* update secondary superblocks. */
-	for_each_perag_from(mp, agno, pag) {
+	while ((pag = xfs_perag_next_from(mp, pag, 1))) {
 		struct xfs_buf		*bp;
 
 		error = xfs_buf_get(mp->m_ddev_targp,
@@ -1146,7 +1145,7 @@ xfs_update_secondary_sbs(
 		xfs_buf_relse(bp);
 
 		/* don't hold too many buffers at once */
-		if (agno % 16)
+		if (pag_agno(pag) % 16)
 			continue;
 
 		error = xfs_buf_delwri_submit(&buffer_list);
@@ -1160,12 +1159,8 @@ xfs_update_secondary_sbs(
 		}
 	}
 	error = xfs_buf_delwri_submit(&buffer_list);
-	if (error) {
-		xfs_warn(mp,
-		"write error %d updating a secondary superblock near ag %d",
-			error, agno);
-	}
-
+	if (error)
+		xfs_warn(mp, "error %d writing secondary superblocks", error);
 	return saved_error ? saved_error : error;
 }
 
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index c299b16c9365..c91db4f51407 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -170,13 +170,12 @@ xfs_icount_range(
 	unsigned long long	*max)
 {
 	unsigned long long	nr_inos = 0;
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 
 	/* root, rtbitmap, rtsum all live in the first chunk */
 	*min = XFS_INODES_PER_CHUNK;
 
-	for_each_perag(mp, agno, pag)
+	while ((pag = xfs_perag_next(mp, pag)))
 		nr_inos += pag->agino_max - pag->agino_min + 1;
 	*max = nr_inos;
 }
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index a43912227dd4..fb022b403716 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -760,11 +760,10 @@ xchk_bmap_check_rmaps(
 	struct xfs_scrub	*sc,
 	int			whichfork)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 	int			error;
 
-	for_each_perag(sc->mp, agno, pag) {
+	while ((pag = xfs_perag_next(sc->mp, pag))) {
 		error = xchk_bmap_check_ag_rmaps(sc, whichfork, pag);
 		if (error ||
 		    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
diff --git a/fs/xfs/scrub/bmap_repair.c b/fs/xfs/scrub/bmap_repair.c
index dc8fdd2da174..be408e50484b 100644
--- a/fs/xfs/scrub/bmap_repair.c
+++ b/fs/xfs/scrub/bmap_repair.c
@@ -407,12 +407,11 @@ xrep_bmap_find_mappings(
 	struct xrep_bmap	*rb)
 {
 	struct xfs_scrub	*sc = rb->sc;
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 	int			error = 0;
 
 	/* Iterate the rmaps for extents. */
-	for_each_perag(sc->mp, agno, pag) {
+	while ((pag = xfs_perag_next(sc->mp, pag))) {
 		error = xrep_bmap_scan_ag(rb, pag);
 		if (error) {
 			xfs_perag_rele(pag);
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index 1d3e98346933..28db0c83819c 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -74,10 +74,9 @@ xchk_fscount_warmup(
 	struct xfs_buf		*agi_bp = NULL;
 	struct xfs_buf		*agf_bp = NULL;
 	struct xfs_perag	*pag = NULL;
-	xfs_agnumber_t		agno;
 	int			error = 0;
 
-	for_each_perag(mp, agno, pag) {
+	while ((pag = xfs_perag_next(mp, pag))) {
 		if (xchk_should_terminate(sc, &error))
 			break;
 		if (xfs_perag_initialised_agi(pag) &&
@@ -295,9 +294,8 @@ xchk_fscount_aggregate_agcounts(
 	struct xchk_fscounters	*fsc)
 {
 	struct xfs_mount	*mp = sc->mp;
-	struct xfs_perag	*pag;
+	struct xfs_perag	*pag = NULL;
 	uint64_t		delayed;
-	xfs_agnumber_t		agno;
 	int			tries = 8;
 	int			error = 0;
 
@@ -306,7 +304,7 @@ xchk_fscount_aggregate_agcounts(
 	fsc->ifree = 0;
 	fsc->fdblocks = 0;
 
-	for_each_perag(mp, agno, pag) {
+	while ((pag = xfs_perag_next(mp, pag))) {
 		if (xchk_should_terminate(sc, &error))
 			break;
 
@@ -327,7 +325,7 @@ xchk_fscount_aggregate_agcounts(
 		if (xfs_has_lazysbcount(sc->mp)) {
 			fsc->fdblocks += pag->pagf_btreeblks;
 		} else {
-			error = xchk_fscount_btreeblks(sc, fsc, agno);
+			error = xchk_fscount_btreeblks(sc, fsc, pag_agno(pag));
 			if (error)
 				break;
 		}
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index b712a8bd34f5..112dd05e5551 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -160,12 +160,11 @@ STATIC void
 xchk_mark_all_healthy(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 
 	xfs_fs_mark_healthy(mp, XFS_SICK_FS_INDIRECT);
 	xfs_rt_mark_healthy(mp, XFS_SICK_RT_INDIRECT);
-	for_each_perag(mp, agno, pag)
+	while ((pag = xfs_perag_next(mp, pag)))
 		xfs_ag_mark_healthy(pag, XFS_SICK_AG_INDIRECT);
 }
 
@@ -294,9 +293,7 @@ xchk_health_record(
 	struct xfs_scrub	*sc)
 {
 	struct xfs_mount	*mp = sc->mp;
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
-
+	struct xfs_perag	*pag = NULL;
 	unsigned int		sick;
 	unsigned int		checked;
 
@@ -308,7 +305,7 @@ xchk_health_record(
 	if (sick & XFS_SICK_RT_PRIMARY)
 		xchk_set_corrupt(sc);
 
-	for_each_perag(mp, agno, pag) {
+	while ((pag = xfs_perag_next(mp, pag))) {
 		xfs_ag_measure_sickness(pag, &sick, &checked);
 		if (sick & XFS_SICK_AG_PRIMARY)
 			xchk_set_corrupt(sc);
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 3e45b9b72312..5da9e1a387a8 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -761,14 +761,13 @@ STATIC int
 xrep_dinode_count_rmaps(
 	struct xrep_inode	*ri)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 	int			error;
 
 	if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp))
 		return -EOPNOTSUPP;
 
-	for_each_perag(ri->sc->mp, agno, pag) {
+	while ((pag = xfs_perag_next(ri->sc->mp, pag))) {
 		error = xrep_dinode_count_ag_rmaps(ri, pag);
 		if (error) {
 			xfs_perag_rele(pag);
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index dfd6edcebb6e..739ec69c4428 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -387,8 +387,8 @@ xfs_trim_datadev_extents(
 {
 	xfs_agnumber_t		start_agno, end_agno;
 	xfs_agblock_t		start_agbno, end_agbno;
+	struct xfs_perag	*pag = NULL;
 	xfs_daddr_t		ddev_end;
-	struct xfs_perag	*pag;
 	int			last_error = 0, error;
 
 	ddev_end = min_t(xfs_daddr_t, end,
@@ -399,10 +399,10 @@ xfs_trim_datadev_extents(
 	end_agno = xfs_daddr_to_agno(mp, ddev_end);
 	end_agbno = xfs_daddr_to_agbno(mp, ddev_end);
 
-	for_each_perag_range(mp, start_agno, end_agno, pag) {
+	while ((pag = xfs_perag_next_range(mp, pag, start_agno, end_agno))) {
 		xfs_agblock_t	agend = pag->block_count;
 
-		if (start_agno == end_agno)
+		if (pag_agno(pag) == end_agno)
 			agend = end_agbno;
 		error = xfs_trim_perag_extents(pag, start_agbno, agend, minlen);
 		if (error)
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 79b0f833c511..3d5a57d7ac5e 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -629,11 +629,10 @@ void
 xfs_extent_busy_wait_all(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
+	struct xfs_perag	*pag = NULL;
 	DEFINE_WAIT		(wait);
-	xfs_agnumber_t		agno;
 
-	for_each_perag(mp, agno, pag) {
+	while ((pag = xfs_perag_next(mp, pag))) {
 		do {
 			prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
 			if  (RB_EMPTY_ROOT(&pag->pagb_tree))
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 918e1c38a155..a26fb054346b 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -460,11 +460,11 @@ __xfs_getfsmap_datadev(
 	void				*priv)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_perag		*pag;
+	struct xfs_perag		*pag = NULL;
 	struct xfs_btree_cur		*bt_cur = NULL;
 	xfs_fsblock_t			start_fsb;
 	xfs_fsblock_t			end_fsb;
-	xfs_agnumber_t			start_ag, end_ag, ag;
+	xfs_agnumber_t			start_ag, end_ag;
 	uint64_t			eofs;
 	int				error = 0;
 
@@ -512,8 +512,7 @@ __xfs_getfsmap_datadev(
 	start_ag = XFS_FSB_TO_AGNO(mp, start_fsb);
 	end_ag = XFS_FSB_TO_AGNO(mp, end_fsb);
 
-	ag = start_ag;
-	for_each_perag_range(mp, ag, end_ag, pag) {
+	while ((pag = xfs_perag_next_range(mp, pag, start_ag, end_ag))) {
 		/*
 		 * Set the AG high key from the fsmap high key if this
 		 * is the last AG that we're querying.
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index b247d895c276..82812a458cf1 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -528,13 +528,12 @@ int
 xfs_fs_reserve_ag_blocks(
 	struct xfs_mount	*mp)
 {
-	xfs_agnumber_t		agno;
-	struct xfs_perag	*pag;
+	struct xfs_perag	*pag = NULL;
 	int			error = 0;
 	int			err2;
 
 	mp->m_finobt_nores = false;
-	for_each_perag(mp, agno, pag) {
+	while ((pag = xfs_perag_next(mp, pag))) {
 		err2 = xfs_ag_resv_init(pag, NULL);
 		if (err2 && !error)
 			error = err2;
@@ -556,9 +555,8 @@ void
 xfs_fs_unreserve_ag_blocks(
 	struct xfs_mount	*mp)
 {
-	xfs_agnumber_t		agno;
-	struct xfs_perag	*pag;
+	struct xfs_perag	*pag = NULL;
 
-	for_each_perag(mp, agno, pag)
+	while ((pag = xfs_perag_next(mp, pag)))
 		xfs_ag_resv_free(pag);
 }
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index d6492128582a..ff5aca875ab0 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -28,8 +28,7 @@ void
 xfs_health_unmount(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 	unsigned int		sick = 0;
 	unsigned int		checked = 0;
 	bool			warn = false;
@@ -38,7 +37,7 @@ xfs_health_unmount(
 		return;
 
 	/* Measure AG corruption levels. */
-	for_each_perag(mp, agno, pag) {
+	while ((pag = xfs_perag_next(mp, pag))) {
 		xfs_ag_measure_sickness(pag, &sick, &checked);
 		if (sick) {
 			trace_xfs_ag_unfixed_corruption(pag, sick);
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 0a930fc116f5..383c24548202 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1383,13 +1383,12 @@ void
 xfs_blockgc_stop(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 
 	if (!xfs_clear_blockgc_enabled(mp))
 		return;
 
-	for_each_perag(mp, agno, pag)
+	while ((pag = xfs_perag_next(mp, pag)))
 		cancel_delayed_work_sync(&pag->pag_blockgc_work);
 	trace_xfs_blockgc_stop(mp, __return_address);
 }
diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index ec2d56f1840f..7db3ece370b1 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -540,23 +540,25 @@ xfs_iwalk_args(
 	unsigned int		flags)
 {
 	struct xfs_mount	*mp = iwag->mp;
-	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, iwag->startino);
+	xfs_agnumber_t		start_agno;
 	int			error;
 
-	ASSERT(agno < mp->m_sb.sb_agcount);
+	start_agno = XFS_INO_TO_AGNO(iwag->mp, iwag->startino);
+	ASSERT(start_agno < iwag->mp->m_sb.sb_agcount);
 	ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL));
 
 	error = xfs_iwalk_alloc(iwag);
 	if (error)
 		return error;
 
-	for_each_perag_from(mp, agno, iwag->pag) {
+	while ((iwag->pag = xfs_perag_next_from(mp, iwag->pag, start_agno))) {
 		error = xfs_iwalk_ag(iwag);
 		if (error || (flags & XFS_IWALK_SAME_AG)) {
 			xfs_perag_rele(iwag->pag);
 			break;
 		}
-		iwag->startino = XFS_AGINO_TO_INO(mp, agno + 1, 0);
+		iwag->startino =
+			XFS_AGINO_TO_INO(mp, pag_agno(iwag->pag) + 1, 0);
 	}
 
 	xfs_iwalk_free(iwag);
@@ -644,19 +646,19 @@ xfs_iwalk_threaded(
 	bool			polled,
 	void			*data)
 {
+	xfs_agnumber_t		start_agno = XFS_INO_TO_AGNO(mp, startino);
 	struct xfs_pwork_ctl	pctl;
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, startino);
+	struct xfs_perag	*pag = NULL;
 	int			error;
 
-	ASSERT(agno < mp->m_sb.sb_agcount);
+	ASSERT(start_agno < mp->m_sb.sb_agcount);
 	ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL));
 
 	error = xfs_pwork_init(mp, &pctl, xfs_iwalk_ag_work, "xfs_iwalk");
 	if (error)
 		return error;
 
-	for_each_perag_from(mp, agno, pag) {
+	while ((pag = xfs_perag_next_from(mp, pag, start_agno))) {
 		struct xfs_iwalk_ag	*iwag;
 
 		if (xfs_pwork_ctl_want_abort(&pctl))
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index a285d2d1f68c..55e412a82148 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2845,10 +2845,9 @@ static void
 xlog_recover_process_iunlinks(
 	struct xlog	*log)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 
-	for_each_perag(log->l_mp, agno, pag)
+	while ((pag = xfs_perag_next(log->l_mp, pag)))
 		xlog_recover_iunlink_ag(pag);
 }
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 2e82b5b6ed52..b11769c009ef 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -894,14 +894,13 @@ int
 xfs_reflink_recover_cow(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag = NULL;
 	int			error = 0;
 
 	if (!xfs_has_reflink(mp))
 		return 0;
 
-	for_each_perag(mp, agno, pag) {
+	while ((pag = xfs_perag_next(mp, pag))) {
 		error = xfs_refcount_recover_cow_leftovers(mp, pag);
 		if (error) {
 			xfs_perag_rele(pag);

From 5c8483cec3fe261a5c1ede7430bab042ed156361 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:40 -0800
Subject: [PATCH 05/16] xfs: move metadata health tracking to the generic group
 structure

Prepare for also tracking the health status of the upcoming realtime
groups by moving the health tracking code to the generic xfs_group
structure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c     |  1 -
 fs/xfs/libxfs/xfs_ag.h     |  9 -----
 fs/xfs/libxfs/xfs_group.c  |  4 +++
 fs/xfs/libxfs/xfs_group.h  | 12 +++++++
 fs/xfs/libxfs/xfs_health.h | 45 +++++++++---------------
 fs/xfs/scrub/health.c      |  8 ++---
 fs/xfs/xfs_health.c        | 71 ++++++++++++++++++++------------------
 fs/xfs/xfs_trace.h         | 35 ++++++++++---------
 8 files changed, 94 insertions(+), 91 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 9ea20e9cf0d4..84bd3831297e 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -232,7 +232,6 @@ xfs_perag_alloc(
 	/* Place kernel structure only init below this point. */
 	spin_lock_init(&pag->pag_ici_lock);
 	spin_lock_init(&pag->pagb_lock);
-	spin_lock_init(&pag->pag_state_lock);
 	INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker);
 	INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
 	xfs_defer_drain_init(&pag->pag_intents_drain);
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 80969682dc47..8271cb72c883 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -69,13 +69,6 @@ struct xfs_perag {
 #ifdef __KERNEL__
 	/* -- kernel only structures below this line -- */
 
-	/*
-	 * Bitsets of per-ag metadata that have been checked and/or are sick.
-	 * Callers should hold pag_state_lock before accessing this field.
-	 */
-	uint16_t	pag_checked;
-	uint16_t	pag_sick;
-
 #ifdef CONFIG_XFS_ONLINE_REPAIR
 	/*
 	 * Alternate btree heights so that online repair won't trip the write
@@ -87,8 +80,6 @@ struct xfs_perag {
 	uint8_t		pagf_repair_rmap_level;
 #endif
 
-	spinlock_t	pag_state_lock;
-
 	spinlock_t	pagb_lock;	/* lock for pagb_tree */
 	struct rb_root	pagb_tree;	/* ordered tree of busy extents */
 	unsigned int	pagb_gen;	/* generation count for pagb_tree */
diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c
index 59e08cfaf9bf..927e72c0882b 100644
--- a/fs/xfs/libxfs/xfs_group.c
+++ b/fs/xfs/libxfs/xfs_group.c
@@ -182,6 +182,10 @@ xfs_group_insert(
 	xg->xg_gno = index;
 	xg->xg_type = type;
 
+#ifdef __KERNEL__
+	spin_lock_init(&xg->xg_state_lock);
+#endif
+
 	/* Active ref owned by mount indicates group is online. */
 	atomic_set(&xg->xg_active_ref, 1);
 
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index dd7da9044305..d2c61dd1f43e 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -11,6 +11,18 @@ struct xfs_group {
 	enum xfs_group_type	xg_type;
 	atomic_t		xg_ref;		/* passive reference count */
 	atomic_t		xg_active_ref;	/* active reference count */
+
+#ifdef __KERNEL__
+	/* -- kernel only structures below this line -- */
+
+	/*
+	 * Bitsets of per-ag metadata that have been checked and/or are sick.
+	 * Callers should hold xg_state_lock before accessing this field.
+	 */
+	uint16_t		xg_checked;
+	uint16_t		xg_sick;
+	spinlock_t		xg_state_lock;
+#endif /* __KERNEL__ */
 };
 
 struct xfs_group *xfs_group_get(struct xfs_mount *mp, uint32_t index,
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index b0edb4288e59..13301420a2f6 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -6,6 +6,8 @@
 #ifndef __XFS_HEALTH_H__
 #define __XFS_HEALTH_H__
 
+struct xfs_group;
+
 /*
  * In-Core Filesystem Health Assessments
  * =====================================
@@ -197,10 +199,12 @@ void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
 
 void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
 		unsigned int mask);
-void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask);
-void xfs_ag_mark_corrupt(struct xfs_perag *pag, unsigned int mask);
-void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask);
-void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick,
+void xfs_group_mark_sick(struct xfs_group *xg, unsigned int mask);
+#define xfs_ag_mark_sick(pag, mask) \
+	xfs_group_mark_sick(pag_group(pag), (mask))
+void xfs_group_mark_corrupt(struct xfs_group *xg, unsigned int mask);
+void xfs_group_mark_healthy(struct xfs_group *xg, unsigned int mask);
+void xfs_group_measure_sickness(struct xfs_group *xg, unsigned int *sick,
 		unsigned int *checked);
 
 void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask);
@@ -227,22 +231,19 @@ xfs_fs_has_sickness(struct xfs_mount *mp, unsigned int mask)
 }
 
 static inline bool
-xfs_rt_has_sickness(struct xfs_mount *mp, unsigned int mask)
+xfs_group_has_sickness(
+	struct xfs_group	*xg,
+	unsigned int		mask)
 {
-	unsigned int	sick, checked;
+	unsigned int		sick, checked;
 
-	xfs_rt_measure_sickness(mp, &sick, &checked);
-	return sick & mask;
-}
-
-static inline bool
-xfs_ag_has_sickness(struct xfs_perag *pag, unsigned int mask)
-{
-	unsigned int	sick, checked;
-
-	xfs_ag_measure_sickness(pag, &sick, &checked);
+	xfs_group_measure_sickness(xg, &sick, &checked);
 	return sick & mask;
 }
+#define xfs_ag_has_sickness(pag, mask) \
+	xfs_group_has_sickness(pag_group(pag), (mask))
+#define xfs_ag_is_healthy(pag) \
+	(!xfs_ag_has_sickness((pag), UINT_MAX))
 
 static inline bool
 xfs_inode_has_sickness(struct xfs_inode *ip, unsigned int mask)
@@ -259,18 +260,6 @@ xfs_fs_is_healthy(struct xfs_mount *mp)
 	return !xfs_fs_has_sickness(mp, -1U);
 }
 
-static inline bool
-xfs_rt_is_healthy(struct xfs_mount *mp)
-{
-	return !xfs_rt_has_sickness(mp, -1U);
-}
-
-static inline bool
-xfs_ag_is_healthy(struct xfs_perag *pag)
-{
-	return !xfs_ag_has_sickness(pag, -1U);
-}
-
 static inline bool
 xfs_inode_is_healthy(struct xfs_inode *ip)
 {
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 112dd05e5551..fce04444c37c 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -165,7 +165,7 @@ xchk_mark_all_healthy(
 	xfs_fs_mark_healthy(mp, XFS_SICK_FS_INDIRECT);
 	xfs_rt_mark_healthy(mp, XFS_SICK_RT_INDIRECT);
 	while ((pag = xfs_perag_next(mp, pag)))
-		xfs_ag_mark_healthy(pag, XFS_SICK_AG_INDIRECT);
+		xfs_group_mark_healthy(pag_group(pag), XFS_SICK_AG_INDIRECT);
 }
 
 /*
@@ -206,9 +206,9 @@ xchk_update_health(
 	case XHG_AG:
 		pag = xfs_perag_get(sc->mp, sc->sm->sm_agno);
 		if (bad)
-			xfs_ag_mark_corrupt(pag, sc->sick_mask);
+			xfs_group_mark_corrupt(pag_group(pag), sc->sick_mask);
 		else
-			xfs_ag_mark_healthy(pag, sc->sick_mask);
+			xfs_group_mark_healthy(pag_group(pag), sc->sick_mask);
 		xfs_perag_put(pag);
 		break;
 	case XHG_INO:
@@ -306,7 +306,7 @@ xchk_health_record(
 		xchk_set_corrupt(sc);
 
 	while ((pag = xfs_perag_next(mp, pag))) {
-		xfs_ag_measure_sickness(pag, &sick, &checked);
+		xfs_group_measure_sickness(pag_group(pag), &sick, &checked);
 		if (sick & XFS_SICK_AG_PRIMARY)
 			xchk_set_corrupt(sc);
 	}
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index ff5aca875ab0..732246f46680 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -38,9 +38,10 @@ xfs_health_unmount(
 
 	/* Measure AG corruption levels. */
 	while ((pag = xfs_perag_next(mp, pag))) {
-		xfs_ag_measure_sickness(pag, &sick, &checked);
+		xfs_group_measure_sickness(pag_group(pag), &sick, &checked);
 		if (sick) {
-			trace_xfs_ag_unfixed_corruption(pag, sick);
+			trace_xfs_group_unfixed_corruption(pag_group(pag),
+					sick);
 			warn = true;
 		}
 	}
@@ -227,61 +228,65 @@ xfs_agno_mark_sick(
 
 /* Mark unhealthy per-ag metadata. */
 void
-xfs_ag_mark_sick(
-	struct xfs_perag	*pag,
+xfs_group_mark_sick(
+	struct xfs_group	*xg,
 	unsigned int		mask)
 {
 	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
-	trace_xfs_ag_mark_sick(pag, mask);
+	trace_xfs_group_mark_sick(xg, mask);
 
-	spin_lock(&pag->pag_state_lock);
-	pag->pag_sick |= mask;
-	spin_unlock(&pag->pag_state_lock);
+	spin_lock(&xg->xg_state_lock);
+	xg->xg_sick |= mask;
+	spin_unlock(&xg->xg_state_lock);
 }
 
-/* Mark per-ag metadata as having been checked and found unhealthy by fsck. */
+/*
+ * Mark per-group metadata as having been checked and found unhealthy by fsck.
+ */
 void
-xfs_ag_mark_corrupt(
-	struct xfs_perag	*pag,
+xfs_group_mark_corrupt(
+	struct xfs_group	*xg,
 	unsigned int		mask)
 {
 	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
-	trace_xfs_ag_mark_corrupt(pag, mask);
+	trace_xfs_group_mark_corrupt(xg, mask);
 
-	spin_lock(&pag->pag_state_lock);
-	pag->pag_sick |= mask;
-	pag->pag_checked |= mask;
-	spin_unlock(&pag->pag_state_lock);
+	spin_lock(&xg->xg_state_lock);
+	xg->xg_sick |= mask;
+	xg->xg_checked |= mask;
+	spin_unlock(&xg->xg_state_lock);
 }
 
-/* Mark per-ag metadata ok. */
+/*
+ * Mark per-group metadata ok.
+ */
 void
-xfs_ag_mark_healthy(
-	struct xfs_perag	*pag,
+xfs_group_mark_healthy(
+	struct xfs_group	*xg,
 	unsigned int		mask)
 {
 	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
-	trace_xfs_ag_mark_healthy(pag, mask);
+	trace_xfs_group_mark_healthy(xg, mask);
 
-	spin_lock(&pag->pag_state_lock);
-	pag->pag_sick &= ~mask;
-	if (!(pag->pag_sick & XFS_SICK_AG_PRIMARY))
-		pag->pag_sick &= ~XFS_SICK_AG_SECONDARY;
-	pag->pag_checked |= mask;
-	spin_unlock(&pag->pag_state_lock);
+	spin_lock(&xg->xg_state_lock);
+	xg->xg_sick &= ~mask;
+	if (!(xg->xg_sick & XFS_SICK_AG_PRIMARY))
+		xg->xg_sick &= ~XFS_SICK_AG_SECONDARY;
+	xg->xg_checked |= mask;
+	spin_unlock(&xg->xg_state_lock);
 }
 
 /* Sample which per-ag metadata are unhealthy. */
 void
-xfs_ag_measure_sickness(
-	struct xfs_perag	*pag,
+xfs_group_measure_sickness(
+	struct xfs_group	*xg,
 	unsigned int		*sick,
 	unsigned int		*checked)
 {
-	spin_lock(&pag->pag_state_lock);
-	*sick = pag->pag_sick;
-	*checked = pag->pag_checked;
-	spin_unlock(&pag->pag_state_lock);
+	spin_lock(&xg->xg_state_lock);
+	*sick = xg->xg_sick;
+	*checked = xg->xg_checked;
+	spin_unlock(&xg->xg_state_lock);
 }
 
 /* Mark the unhealthy parts of an inode. */
@@ -447,7 +452,7 @@ xfs_ag_geom_health(
 	ageo->ag_sick = 0;
 	ageo->ag_checked = 0;
 
-	xfs_ag_measure_sickness(pag, &sick, &checked);
+	xfs_group_measure_sickness(pag_group(pag), &sick, &checked);
 	for (m = ag_map; m->sick_mask; m++) {
 		if (checked & m->sick_mask)
 			ageo->ag_checked |= m->ioctl_mask;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 14e7f6a26a23..fd597a410b02 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -4215,31 +4215,34 @@ DEFINE_FS_CORRUPT_EVENT(xfs_rt_mark_corrupt);
 DEFINE_FS_CORRUPT_EVENT(xfs_rt_mark_healthy);
 DEFINE_FS_CORRUPT_EVENT(xfs_rt_unfixed_corruption);
 
-DECLARE_EVENT_CLASS(xfs_ag_corrupt_class,
-	TP_PROTO(const struct xfs_perag *pag, unsigned int flags),
-	TP_ARGS(pag, flags),
+DECLARE_EVENT_CLASS(xfs_group_corrupt_class,
+	TP_PROTO(const struct xfs_group *xg, unsigned int flags),
+	TP_ARGS(xg, flags),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_group_type, type)
+		__field(uint32_t, index)
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
-		__entry->dev = pag_mount(pag)->m_super->s_dev;
-		__entry->agno = pag_agno(pag);
+		__entry->dev = xg->xg_mount->m_super->s_dev;
+		__entry->type = xg->xg_type;
+		__entry->index = xg->xg_gno;
 		__entry->flags = flags;
 	),
-	TP_printk("dev %d:%d agno 0x%x flags 0x%x",
+	TP_printk("dev %d:%d %sno 0x%x flags 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->agno, __entry->flags)
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
+		  __entry->index, __entry->flags)
 );
-#define DEFINE_AG_CORRUPT_EVENT(name)	\
-DEFINE_EVENT(xfs_ag_corrupt_class, name,	\
-	TP_PROTO(const struct xfs_perag *pag, unsigned int flags), \
-	TP_ARGS(pag, flags))
-DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_sick);
-DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_corrupt);
-DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_healthy);
-DEFINE_AG_CORRUPT_EVENT(xfs_ag_unfixed_corruption);
+#define DEFINE_GROUP_CORRUPT_EVENT(name)	\
+DEFINE_EVENT(xfs_group_corrupt_class, name,	\
+	TP_PROTO(const struct xfs_group *xg, unsigned int flags), \
+	TP_ARGS(xg, flags))
+DEFINE_GROUP_CORRUPT_EVENT(xfs_group_mark_sick);
+DEFINE_GROUP_CORRUPT_EVENT(xfs_group_mark_corrupt);
+DEFINE_GROUP_CORRUPT_EVENT(xfs_group_mark_healthy);
+DEFINE_GROUP_CORRUPT_EVENT(xfs_group_unfixed_corruption);
 
 DECLARE_EVENT_CLASS(xfs_inode_corrupt_class,
 	TP_PROTO(struct xfs_inode *ip, unsigned int flags),

From 2ed27a54641550352830bb7ff3b542e65dfffd68 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:41 -0800
Subject: [PATCH 06/16] xfs: mark xfs_perag_intent_{hold,rele} static

These two functions are only used inside of xfs_drain.c, so mark them
static.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_drain.c | 42 +++++++++++++++++++++---------------------
 fs/xfs/xfs_drain.h |  6 ------
 2 files changed, 21 insertions(+), 27 deletions(-)

diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c
index 7bdb9688c0f5..3f280971b498 100644
--- a/fs/xfs/xfs_drain.c
+++ b/fs/xfs/xfs_drain.c
@@ -93,6 +93,27 @@ static inline int xfs_defer_drain_wait(struct xfs_defer_drain *dr)
 	return wait_event_killable(dr->dr_waiters, !xfs_defer_drain_busy(dr));
 }
 
+/*
+ * Declare an intent to update AG metadata.  Other threads that need exclusive
+ * access can decide to back off if they see declared intentions.
+ */
+static void
+xfs_perag_intent_hold(
+	struct xfs_perag	*pag)
+{
+	trace_xfs_perag_intent_hold(pag, __return_address);
+	xfs_defer_drain_grab(&pag->pag_intents_drain);
+}
+
+/* Release our intent to update this AG's metadata. */
+static void
+xfs_perag_intent_rele(
+	struct xfs_perag	*pag)
+{
+	trace_xfs_perag_intent_rele(pag, __return_address);
+	xfs_defer_drain_rele(&pag->pag_intents_drain);
+}
+
 /*
  * Get a passive reference to the AG that contains a fsbno and declare an intent
  * to update its metadata.
@@ -124,27 +145,6 @@ xfs_perag_intent_put(
 	xfs_perag_put(pag);
 }
 
-/*
- * Declare an intent to update AG metadata.  Other threads that need exclusive
- * access can decide to back off if they see declared intentions.
- */
-void
-xfs_perag_intent_hold(
-	struct xfs_perag	*pag)
-{
-	trace_xfs_perag_intent_hold(pag, __return_address);
-	xfs_defer_drain_grab(&pag->pag_intents_drain);
-}
-
-/* Release our intent to update this AG's metadata. */
-void
-xfs_perag_intent_rele(
-	struct xfs_perag	*pag)
-{
-	trace_xfs_perag_intent_rele(pag, __return_address);
-	xfs_defer_drain_rele(&pag->pag_intents_drain);
-}
-
 /*
  * Wait for the intent update count for this AG to hit zero.
  * Callers must not hold any AG header buffers.
diff --git a/fs/xfs/xfs_drain.h b/fs/xfs/xfs_drain.h
index 775164f54ea6..f39c90946ab7 100644
--- a/fs/xfs/xfs_drain.h
+++ b/fs/xfs/xfs_drain.h
@@ -65,9 +65,6 @@ struct xfs_perag *xfs_perag_intent_get(struct xfs_mount *mp,
 		xfs_fsblock_t fsbno);
 void xfs_perag_intent_put(struct xfs_perag *pag);
 
-void xfs_perag_intent_hold(struct xfs_perag *pag);
-void xfs_perag_intent_rele(struct xfs_perag *pag);
-
 int xfs_perag_intent_drain(struct xfs_perag *pag);
 bool xfs_perag_intent_busy(struct xfs_perag *pag);
 #else
@@ -80,9 +77,6 @@ struct xfs_defer_drain { /* empty */ };
 	xfs_perag_get((mp), XFS_FSB_TO_AGNO(mp, fsbno))
 #define xfs_perag_intent_put(pag)		xfs_perag_put(pag)
 
-static inline void xfs_perag_intent_hold(struct xfs_perag *pag) { }
-static inline void xfs_perag_intent_rele(struct xfs_perag *pag) { }
-
 #endif /* CONFIG_XFS_DRAIN_INTENTS */
 
 #endif /* XFS_DRAIN_H_ */

From 34cf3a6f3952ecabd54b4fe3d431aa44ce98fe45 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:41 -0800
Subject: [PATCH 07/16] xfs: move draining of deferred operations to the
 generic group structure

Prepare supporting the upcoming realtime groups feature by moving the
deferred operation draining to the generic xfs_group structure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c    |  7 ++----
 fs/xfs/libxfs/xfs_ag.h    |  9 --------
 fs/xfs/libxfs/xfs_group.c |  4 ++++
 fs/xfs/libxfs/xfs_group.h |  9 ++++++++
 fs/xfs/scrub/common.c     |  4 ++--
 fs/xfs/xfs_drain.c        | 46 +++++++++++++++++++++------------------
 fs/xfs/xfs_drain.h        |  6 +++--
 fs/xfs/xfs_trace.h        | 36 ++++++++++++++++--------------
 8 files changed, 66 insertions(+), 55 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 84bd3831297e..c2f1f830d299 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -112,7 +112,6 @@ xfs_perag_uninit(
 #ifdef __KERNEL__
 	struct xfs_perag	*pag = to_perag(xg);
 
-	xfs_defer_drain_free(&pag->pag_intents_drain);
 	cancel_delayed_work_sync(&pag->pag_blockgc_work);
 	xfs_buf_cache_destroy(&pag->pag_bcache);
 #endif
@@ -234,7 +233,6 @@ xfs_perag_alloc(
 	spin_lock_init(&pag->pagb_lock);
 	INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker);
 	INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
-	xfs_defer_drain_init(&pag->pag_intents_drain);
 	init_waitqueue_head(&pag->pagb_wait);
 	pag->pagb_tree = RB_ROOT;
 	xfs_hooks_init(&pag->pag_rmap_update_hooks);
@@ -242,7 +240,7 @@ xfs_perag_alloc(
 
 	error = xfs_buf_cache_init(&pag->pag_bcache);
 	if (error)
-		goto out_defer_drain_free;
+		goto out_free_perag;
 
 	/*
 	 * Pre-calculated geometry
@@ -260,8 +258,7 @@ xfs_perag_alloc(
 
 out_buf_cache_destroy:
 	xfs_buf_cache_destroy(&pag->pag_bcache);
-out_defer_drain_free:
-	xfs_defer_drain_free(&pag->pag_intents_drain);
+out_free_perag:
 	kfree(pag);
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 8271cb72c883..45f8de06cdbc 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -97,15 +97,6 @@ struct xfs_perag {
 	/* background prealloc block trimming */
 	struct delayed_work	pag_blockgc_work;
 
-	/*
-	 * We use xfs_drain to track the number of deferred log intent items
-	 * that have been queued (but not yet processed) so that waiters (e.g.
-	 * scrub) will not lock resources when other threads are in the middle
-	 * of processing a chain of intent items only to find momentary
-	 * inconsistencies.
-	 */
-	struct xfs_defer_drain	pag_intents_drain;
-
 	/* Hook to feed rmapbt updates to an active online repair. */
 	struct xfs_hooks	pag_rmap_update_hooks;
 #endif /* __KERNEL__ */
diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c
index 927e72c0882b..6737f009dd38 100644
--- a/fs/xfs/libxfs/xfs_group.c
+++ b/fs/xfs/libxfs/xfs_group.c
@@ -160,6 +160,8 @@ xfs_group_free(
 
 	XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_ref) != 0);
 
+	xfs_defer_drain_free(&xg->xg_intents_drain);
+
 	if (uninit)
 		uninit(xg);
 
@@ -185,6 +187,7 @@ xfs_group_insert(
 #ifdef __KERNEL__
 	spin_lock_init(&xg->xg_state_lock);
 #endif
+	xfs_defer_drain_init(&xg->xg_intents_drain);
 
 	/* Active ref owned by mount indicates group is online. */
 	atomic_set(&xg->xg_active_ref, 1);
@@ -192,6 +195,7 @@ xfs_group_insert(
 	error = xa_insert(&mp->m_groups[type].xa, index, xg, GFP_KERNEL);
 	if (error) {
 		WARN_ON_ONCE(error == -EBUSY);
+		xfs_defer_drain_free(&xg->xg_intents_drain);
 		return error;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index d2c61dd1f43e..ebefbba7d98c 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -22,6 +22,15 @@ struct xfs_group {
 	uint16_t		xg_checked;
 	uint16_t		xg_sick;
 	spinlock_t		xg_state_lock;
+
+	/*
+	 * We use xfs_drain to track the number of deferred log intent items
+	 * that have been queued (but not yet processed) so that waiters (e.g.
+	 * scrub) will not lock resources when other threads are in the middle
+	 * of processing a chain of intent items only to find momentary
+	 * inconsistencies.
+	 */
+	struct xfs_defer_drain	xg_intents_drain;
 #endif /* __KERNEL__ */
 };
 
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 28095ed490fb..e8b5e73bab60 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -513,7 +513,7 @@ xchk_perag_drain_and_lock(
 		 * Obviously, this should be slanted against scrub and in favor
 		 * of runtime threads.
 		 */
-		if (!xfs_perag_intent_busy(sa->pag))
+		if (!xfs_group_intent_busy(pag_group(sa->pag)))
 			return 0;
 
 		if (sa->agf_bp) {
@@ -528,7 +528,7 @@ xchk_perag_drain_and_lock(
 
 		if (!(sc->flags & XCHK_FSGATES_DRAIN))
 			return -ECHRNG;
-		error = xfs_perag_intent_drain(sa->pag);
+		error = xfs_group_intent_drain(pag_group(sa->pag));
 		if (error == -ERESTARTSYS)
 			error = -EINTR;
 	} while (!error);
diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c
index 3f280971b498..a72d08947d6d 100644
--- a/fs/xfs/xfs_drain.c
+++ b/fs/xfs/xfs_drain.c
@@ -94,24 +94,26 @@ static inline int xfs_defer_drain_wait(struct xfs_defer_drain *dr)
 }
 
 /*
- * Declare an intent to update AG metadata.  Other threads that need exclusive
- * access can decide to back off if they see declared intentions.
+ * Declare an intent to update group metadata.  Other threads that need
+ * exclusive access can decide to back off if they see declared intentions.
  */
 static void
-xfs_perag_intent_hold(
-	struct xfs_perag	*pag)
+xfs_group_intent_hold(
+	struct xfs_group	*xg)
 {
-	trace_xfs_perag_intent_hold(pag, __return_address);
-	xfs_defer_drain_grab(&pag->pag_intents_drain);
+	trace_xfs_group_intent_hold(xg, __return_address);
+	xfs_defer_drain_grab(&xg->xg_intents_drain);
 }
 
-/* Release our intent to update this AG's metadata. */
+/*
+ * Release our intent to update this groups metadata.
+ */
 static void
-xfs_perag_intent_rele(
-	struct xfs_perag	*pag)
+xfs_group_intent_rele(
+	struct xfs_group	*xg)
 {
-	trace_xfs_perag_intent_rele(pag, __return_address);
-	xfs_defer_drain_rele(&pag->pag_intents_drain);
+	trace_xfs_group_intent_rele(xg, __return_address);
+	xfs_defer_drain_rele(&xg->xg_intents_drain);
 }
 
 /*
@@ -129,7 +131,7 @@ xfs_perag_intent_get(
 	if (!pag)
 		return NULL;
 
-	xfs_perag_intent_hold(pag);
+	xfs_group_intent_hold(pag_group(pag));
 	return pag;
 }
 
@@ -141,7 +143,7 @@ void
 xfs_perag_intent_put(
 	struct xfs_perag	*pag)
 {
-	xfs_perag_intent_rele(pag);
+	xfs_group_intent_rele(pag_group(pag));
 	xfs_perag_put(pag);
 }
 
@@ -150,17 +152,19 @@ xfs_perag_intent_put(
  * Callers must not hold any AG header buffers.
  */
 int
-xfs_perag_intent_drain(
-	struct xfs_perag	*pag)
+xfs_group_intent_drain(
+	struct xfs_group	*xg)
 {
-	trace_xfs_perag_wait_intents(pag, __return_address);
-	return xfs_defer_drain_wait(&pag->pag_intents_drain);
+	trace_xfs_group_wait_intents(xg, __return_address);
+	return xfs_defer_drain_wait(&xg->xg_intents_drain);
 }
 
-/* Has anyone declared an intent to update this AG? */
+/*
+ * Has anyone declared an intent to update this group?
+ */
 bool
-xfs_perag_intent_busy(
-	struct xfs_perag	*pag)
+xfs_group_intent_busy(
+	struct xfs_group	*xg)
 {
-	return xfs_defer_drain_busy(&pag->pag_intents_drain);
+	return xfs_defer_drain_busy(&xg->xg_intents_drain);
 }
diff --git a/fs/xfs/xfs_drain.h b/fs/xfs/xfs_drain.h
index f39c90946ab7..3e6143572e52 100644
--- a/fs/xfs/xfs_drain.h
+++ b/fs/xfs/xfs_drain.h
@@ -6,6 +6,7 @@
 #ifndef XFS_DRAIN_H_
 #define XFS_DRAIN_H_
 
+struct xfs_group;
 struct xfs_perag;
 
 #ifdef CONFIG_XFS_DRAIN_INTENTS
@@ -65,8 +66,9 @@ struct xfs_perag *xfs_perag_intent_get(struct xfs_mount *mp,
 		xfs_fsblock_t fsbno);
 void xfs_perag_intent_put(struct xfs_perag *pag);
 
-int xfs_perag_intent_drain(struct xfs_perag *pag);
-bool xfs_perag_intent_busy(struct xfs_perag *pag);
+int xfs_group_intent_drain(struct xfs_group *xg);
+bool xfs_group_intent_busy(struct xfs_group *xg);
+
 #else
 struct xfs_defer_drain { /* empty */ };
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index fd597a410b02..29e8be9b6829 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -4684,35 +4684,39 @@ TRACE_EVENT(xfs_force_shutdown,
 );
 
 #ifdef CONFIG_XFS_DRAIN_INTENTS
-DECLARE_EVENT_CLASS(xfs_perag_intents_class,
-	TP_PROTO(const struct xfs_perag *pag, void *caller_ip),
-	TP_ARGS(pag, caller_ip),
+DECLARE_EVENT_CLASS(xfs_group_intents_class,
+	TP_PROTO(const struct xfs_group *xg, void *caller_ip),
+	TP_ARGS(xg, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_group_type, type)
+		__field(uint32_t, index)
 		__field(long, nr_intents)
 		__field(void *, caller_ip)
 	),
 	TP_fast_assign(
-		__entry->dev = pag_mount(pag)->m_super->s_dev;
-		__entry->agno = pag_agno(pag);
-		__entry->nr_intents = atomic_read(&pag->pag_intents_drain.dr_count);
+		__entry->dev = xg->xg_mount->m_super->s_dev;
+		__entry->type = xg->xg_type;
+		__entry->index = xg->xg_gno;
+		__entry->nr_intents =
+			atomic_read(&xg->xg_intents_drain.dr_count);
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d agno 0x%x intents %ld caller %pS",
+	TP_printk("dev %d:%d %sno 0x%x intents %ld caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->agno,
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
+		  __entry->index,
 		  __entry->nr_intents,
 		  __entry->caller_ip)
 );
 
-#define DEFINE_PERAG_INTENTS_EVENT(name)	\
-DEFINE_EVENT(xfs_perag_intents_class, name,					\
-	TP_PROTO(const struct xfs_perag *pag, void *caller_ip), \
-	TP_ARGS(pag, caller_ip))
-DEFINE_PERAG_INTENTS_EVENT(xfs_perag_intent_hold);
-DEFINE_PERAG_INTENTS_EVENT(xfs_perag_intent_rele);
-DEFINE_PERAG_INTENTS_EVENT(xfs_perag_wait_intents);
+#define DEFINE_GROUP_INTENTS_EVENT(name)	\
+DEFINE_EVENT(xfs_group_intents_class, name,					\
+	TP_PROTO(const struct xfs_group *xg, void *caller_ip), \
+	TP_ARGS(xg, caller_ip))
+DEFINE_GROUP_INTENTS_EVENT(xfs_group_intent_hold);
+DEFINE_GROUP_INTENTS_EVENT(xfs_group_intent_rele);
+DEFINE_GROUP_INTENTS_EVENT(xfs_group_wait_intents);
 
 #endif /* CONFIG_XFS_DRAIN_INTENTS */
 

From eb4a84a3c2bd09efe770fa940fb68e349f90c8c6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:42 -0800
Subject: [PATCH 08/16] xfs: move the online repair rmap hooks to the generic
 group structure

Prepare for the upcoming realtime groups feature by moving the online
repair rmap hooks to based to the generic xfs_group structure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c     |  1 -
 fs/xfs/libxfs/xfs_ag.h     |  3 ---
 fs/xfs/libxfs/xfs_group.c  |  1 +
 fs/xfs/libxfs/xfs_group.h  |  5 +++++
 fs/xfs/libxfs/xfs_rmap.c   | 24 +++++++++++++-----------
 fs/xfs/libxfs/xfs_rmap.h   |  4 ++--
 fs/xfs/scrub/rmap_repair.c |  4 ++--
 7 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index c2f1f830d299..e60469fee875 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -235,7 +235,6 @@ xfs_perag_alloc(
 	INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
 	init_waitqueue_head(&pag->pagb_wait);
 	pag->pagb_tree = RB_ROOT;
-	xfs_hooks_init(&pag->pag_rmap_update_hooks);
 #endif /* __KERNEL__ */
 
 	error = xfs_buf_cache_init(&pag->pag_bcache);
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 45f8de06cdbc..042ee0913fb9 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -96,9 +96,6 @@ struct xfs_perag {
 
 	/* background prealloc block trimming */
 	struct delayed_work	pag_blockgc_work;
-
-	/* Hook to feed rmapbt updates to an active online repair. */
-	struct xfs_hooks	pag_rmap_update_hooks;
 #endif /* __KERNEL__ */
 };
 
diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c
index 6737f009dd38..8532dc2f8628 100644
--- a/fs/xfs/libxfs/xfs_group.c
+++ b/fs/xfs/libxfs/xfs_group.c
@@ -186,6 +186,7 @@ xfs_group_insert(
 
 #ifdef __KERNEL__
 	spin_lock_init(&xg->xg_state_lock);
+	xfs_hooks_init(&xg->xg_rmap_update_hooks);
 #endif
 	xfs_defer_drain_init(&xg->xg_intents_drain);
 
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index ebefbba7d98c..a87b9b80ef75 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -31,6 +31,11 @@ struct xfs_group {
 	 * inconsistencies.
 	 */
 	struct xfs_defer_drain	xg_intents_drain;
+
+	/*
+	 * Hook to feed rmapbt updates to an active online repair.
+	 */
+	struct xfs_hooks	xg_rmap_update_hooks;
 #endif /* __KERNEL__ */
 };
 
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index b6764d6b3ab8..984120b128fb 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -835,7 +835,7 @@ xfs_rmap_hook_enable(void)
 static inline void
 xfs_rmap_update_hook(
 	struct xfs_trans		*tp,
-	struct xfs_perag		*pag,
+	struct xfs_group		*xg,
 	enum xfs_rmap_intent_type	op,
 	xfs_agblock_t			startblock,
 	xfs_extlen_t			blockcount,
@@ -850,27 +850,27 @@ xfs_rmap_update_hook(
 			.oinfo		= *oinfo, /* struct copy */
 		};
 
-		if (pag)
-			xfs_hooks_call(&pag->pag_rmap_update_hooks, op, &p);
+		if (xg)
+			xfs_hooks_call(&xg->xg_rmap_update_hooks, op, &p);
 	}
 }
 
 /* Call the specified function during a reverse mapping update. */
 int
 xfs_rmap_hook_add(
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	struct xfs_rmap_hook	*hook)
 {
-	return xfs_hooks_add(&pag->pag_rmap_update_hooks, &hook->rmap_hook);
+	return xfs_hooks_add(&xg->xg_rmap_update_hooks, &hook->rmap_hook);
 }
 
 /* Stop calling the specified function during a reverse mapping update. */
 void
 xfs_rmap_hook_del(
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	struct xfs_rmap_hook	*hook)
 {
-	xfs_hooks_del(&pag->pag_rmap_update_hooks, &hook->rmap_hook);
+	xfs_hooks_del(&xg->xg_rmap_update_hooks, &hook->rmap_hook);
 }
 
 /* Configure rmap update hook functions. */
@@ -905,7 +905,8 @@ xfs_rmap_free(
 		return 0;
 
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
-	xfs_rmap_update_hook(tp, pag, XFS_RMAP_UNMAP, bno, len, false, oinfo);
+	xfs_rmap_update_hook(tp, pag_group(pag), XFS_RMAP_UNMAP, bno, len,
+			false, oinfo);
 	error = xfs_rmap_unmap(cur, bno, len, false, oinfo);
 
 	xfs_btree_del_cursor(cur, error);
@@ -1149,7 +1150,8 @@ xfs_rmap_alloc(
 		return 0;
 
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
-	xfs_rmap_update_hook(tp, pag, XFS_RMAP_MAP, bno, len, false, oinfo);
+	xfs_rmap_update_hook(tp, pag_group(pag), XFS_RMAP_MAP, bno, len, false,
+			oinfo);
 	error = xfs_rmap_map(cur, bno, len, false, oinfo);
 
 	xfs_btree_del_cursor(cur, error);
@@ -2620,8 +2622,8 @@ xfs_rmap_finish_one(
 	if (error)
 		return error;
 
-	xfs_rmap_update_hook(tp, ri->ri_pag, ri->ri_type, bno,
-			ri->ri_bmap.br_blockcount, unwritten, &oinfo);
+	xfs_rmap_update_hook(tp, pag_group(ri->ri_pag), ri->ri_type, bno,
+			     ri->ri_bmap.br_blockcount, unwritten, &oinfo);
 	return 0;
 }
 
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index b783dd4dd95d..d409b463bc66 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -264,8 +264,8 @@ struct xfs_rmap_hook {
 void xfs_rmap_hook_disable(void);
 void xfs_rmap_hook_enable(void);
 
-int xfs_rmap_hook_add(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
-void xfs_rmap_hook_del(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
+int xfs_rmap_hook_add(struct xfs_group *xg, struct xfs_rmap_hook *hook);
+void xfs_rmap_hook_del(struct xfs_group *xg, struct xfs_rmap_hook *hook);
 void xfs_rmap_hook_setup(struct xfs_rmap_hook *hook, notifier_fn_t mod_fn);
 #endif
 
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index f88f58db9098..6c420ec7dacd 100644
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -1611,7 +1611,7 @@ xrep_rmap_setup_scan(
 	 */
 	ASSERT(sc->flags & XCHK_FSGATES_RMAP);
 	xfs_rmap_hook_setup(&rr->rhook, xrep_rmapbt_live_update);
-	error = xfs_rmap_hook_add(sc->sa.pag, &rr->rhook);
+	error = xfs_rmap_hook_add(pag_group(sc->sa.pag), &rr->rhook);
 	if (error)
 		goto out_iscan;
 	return 0;
@@ -1632,7 +1632,7 @@ xrep_rmap_teardown(
 	struct xfs_scrub	*sc = rr->sc;
 
 	xchk_iscan_abort(&rr->iscan);
-	xfs_rmap_hook_del(sc->sa.pag, &rr->rhook);
+	xfs_rmap_hook_del(pag_group(sc->sa.pag), &rr->rhook);
 	xchk_iscan_teardown(&rr->iscan);
 	xfbtree_destroy(&rr->rmap_btree);
 	mutex_destroy(&rr->lock);

From 6af1300d47d92fb4bb327886ffa63c287d63a5db Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:42 -0800
Subject: [PATCH 09/16] xfs: return the busy generation from
 xfs_extent_busy_list_empty

This avoid having to poke into the internals of the busy tracking in
xrep_setup_ag_allocbt.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/alloc_repair.c | 9 +++------
 fs/xfs/xfs_extent_busy.c    | 4 +++-
 fs/xfs/xfs_extent_busy.h    | 2 +-
 3 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c
index ab0084c42496..f07cd93012c6 100644
--- a/fs/xfs/scrub/alloc_repair.c
+++ b/fs/xfs/scrub/alloc_repair.c
@@ -132,16 +132,12 @@ int
 xrep_setup_ag_allocbt(
 	struct xfs_scrub	*sc)
 {
-	unsigned int		busy_gen;
-
 	/*
 	 * Make sure the busy extent list is clear because we can't put extents
 	 * on there twice.
 	 */
-	busy_gen = READ_ONCE(sc->sa.pag->pagb_gen);
-	if (xfs_extent_busy_list_empty(sc->sa.pag))
+	if (xfs_extent_busy_list_empty(sc->sa.pag, &busy_gen))
 		return 0;
-
 	return xfs_extent_busy_flush(sc->tp, sc->sa.pag, busy_gen, 0);
 }
 
@@ -849,6 +845,7 @@ xrep_allocbt(
 {
 	struct xrep_abt		*ra;
 	struct xfs_mount	*mp = sc->mp;
+	unsigned int		busy_gen;
 	char			*descr;
 	int			error;
 
@@ -869,7 +866,7 @@ xrep_allocbt(
 	 * on there twice.  In theory we cleared this before we started, but
 	 * let's not risk the filesystem.
 	 */
-	if (!xfs_extent_busy_list_empty(sc->sa.pag)) {
+	if (!xfs_extent_busy_list_empty(sc->sa.pag, &busy_gen)) {
 		error = -EDEADLOCK;
 		goto out_ra;
 	}
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 3d5a57d7ac5e..2806fc6ab480 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -667,12 +667,14 @@ xfs_extent_busy_ag_cmp(
 /* Are there any busy extents in this AG? */
 bool
 xfs_extent_busy_list_empty(
-	struct xfs_perag	*pag)
+	struct xfs_perag	*pag,
+	unsigned		*busy_gen)
 {
 	bool			res;
 
 	spin_lock(&pag->pagb_lock);
 	res = RB_EMPTY_ROOT(&pag->pagb_tree);
+	*busy_gen = READ_ONCE(pag->pagb_gen);
 	spin_unlock(&pag->pagb_lock);
 	return res;
 }
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index 7241035ce4ef..c803dcd124a6 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -83,6 +83,6 @@ static inline void xfs_extent_busy_sort(struct list_head *list)
 	list_sort(NULL, list, xfs_extent_busy_ag_cmp);
 }
 
-bool xfs_extent_busy_list_empty(struct xfs_perag *pag);
+bool xfs_extent_busy_list_empty(struct xfs_perag *pag, unsigned int *busy_gen);
 
 #endif /* __XFS_EXTENT_BUSY_H__ */

From 0e10cb98f149aa62b381a81b09c479661149a0b2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:43 -0800
Subject: [PATCH 10/16] xfs: convert extent busy tracepoints to the generic
 group structure

Prepare for tracking busy RT extents by passing the generic group
structure to the xfs_extent_busy_class tracepoints.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_extent_busy.c | 12 +++++++-----
 fs/xfs/xfs_trace.h       | 34 +++++++++++++++++++++-------------
 2 files changed, 28 insertions(+), 18 deletions(-)

diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 2806fc6ab480..9c5c6279ae21 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -41,7 +41,7 @@ xfs_extent_busy_insert_list(
 	new->flags = flags;
 
 	/* trace before insert to be able to see failed inserts */
-	trace_xfs_extent_busy(pag, bno, len);
+	trace_xfs_extent_busy(pag_group(pag), bno, len);
 
 	spin_lock(&pag->pagb_lock);
 	rbp = &pag->pagb_tree.rb_node;
@@ -278,13 +278,13 @@ xfs_extent_busy_update_extent(
 		ASSERT(0);
 	}
 
-	trace_xfs_extent_busy_reuse(pag, fbno, flen);
+	trace_xfs_extent_busy_reuse(pag_group(pag), fbno, flen);
 	return true;
 
 out_force_log:
 	spin_unlock(&pag->pagb_lock);
 	xfs_log_force(pag_mount(pag), XFS_LOG_SYNC);
-	trace_xfs_extent_busy_force(pag, fbno, flen);
+	trace_xfs_extent_busy_force(pag_group(pag), fbno, flen);
 	spin_lock(&pag->pagb_lock);
 	return false;
 }
@@ -496,7 +496,8 @@ xfs_extent_busy_trim(
 out:
 
 	if (fbno != *bno || flen != *len) {
-		trace_xfs_extent_busy_trim(args->pag, *bno, *len, fbno, flen);
+		trace_xfs_extent_busy_trim(pag_group(args->pag), *bno, *len,
+					   fbno, flen);
 		*bno = fbno;
 		*len = flen;
 		*busy_gen = args->pag->pagb_gen;
@@ -525,7 +526,8 @@ xfs_extent_busy_clear_one(
 			busyp->flags = XFS_EXTENT_BUSY_DISCARDED;
 			return false;
 		}
-		trace_xfs_extent_busy_clear(pag, busyp->bno, busyp->length);
+		trace_xfs_extent_busy_clear(pag_group(pag), busyp->bno,
+				busyp->length);
 		rb_erase(&busyp->rb_node, &pag->pagb_tree);
 	}
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 29e8be9b6829..562e0ad1c6cf 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1673,43 +1673,48 @@ TRACE_EVENT(xfs_bunmap,
 );
 
 DECLARE_EVENT_CLASS(xfs_extent_busy_class,
-	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
+	TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno,
 		 xfs_extlen_t len),
-	TP_ARGS(pag, agbno, len),
+	TP_ARGS(xg, agbno, len),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
+		__field(enum xfs_group_type, type)
 		__field(xfs_agnumber_t, agno)
 		__field(xfs_agblock_t, agbno)
 		__field(xfs_extlen_t, len)
 	),
 	TP_fast_assign(
-		__entry->dev = pag_mount(pag)->m_super->s_dev;
-		__entry->agno = pag_agno(pag);
+		__entry->dev = xg->xg_mount->m_super->s_dev;
+		__entry->type = xg->xg_type;
+		__entry->agno = xg->xg_gno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x",
+	TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agbno,
 		  __entry->len)
 );
 #define DEFINE_BUSY_EVENT(name) \
 DEFINE_EVENT(xfs_extent_busy_class, name, \
-	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \
-			xfs_extlen_t len), \
-	TP_ARGS(pag, agbno, len))
+	TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, \
+		 xfs_extlen_t len), \
+	TP_ARGS(xg, agbno, len))
 DEFINE_BUSY_EVENT(xfs_extent_busy);
 DEFINE_BUSY_EVENT(xfs_extent_busy_force);
 DEFINE_BUSY_EVENT(xfs_extent_busy_reuse);
 DEFINE_BUSY_EVENT(xfs_extent_busy_clear);
 
 TRACE_EVENT(xfs_extent_busy_trim,
-	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
+	TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno,
 		 xfs_extlen_t len, xfs_agblock_t tbno, xfs_extlen_t tlen),
-	TP_ARGS(pag, agbno, len, tbno, tlen),
+	TP_ARGS(xg, agbno, len, tbno, tlen),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
+		__field(enum xfs_group_type, type)
 		__field(xfs_agnumber_t, agno)
 		__field(xfs_agblock_t, agbno)
 		__field(xfs_extlen_t, len)
@@ -1717,16 +1722,19 @@ TRACE_EVENT(xfs_extent_busy_trim,
 		__field(xfs_extlen_t, tlen)
 	),
 	TP_fast_assign(
-		__entry->dev = pag_mount(pag)->m_super->s_dev;
-		__entry->agno = pag_agno(pag);
+		__entry->dev = xg->xg_mount->m_super->s_dev;
+		__entry->type = xg->xg_type;
+		__entry->agno = xg->xg_gno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->tbno = tbno;
 		__entry->tlen = tlen;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x found_agbno 0x%x found_fsbcount 0x%x",
+	TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x found_agbno 0x%x found_fsbcount 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agbno,
 		  __entry->len,
 		  __entry->tbno,

From adbc76aa0fedcb6da2d1ceb1ce786d1f963afee8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:43 -0800
Subject: [PATCH 11/16] xfs: convert busy extent tracking to the generic group
 structure

Split busy extent tracking from struct xfs_perag into its own private
structure, which can be pointed to by the generic group structure.

Note that this structure is now dynamically allocated instead of embedded
as the upcoming zone XFS code doesn't need it and will also have an
unusually high number of groups due to hardware constraints.  Dynamically
allocating the structure this is a big memory saver for this case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c          |   3 -
 fs/xfs/libxfs/xfs_ag.h          |   5 -
 fs/xfs/libxfs/xfs_alloc.c       |  29 +++--
 fs/xfs/libxfs/xfs_alloc_btree.c |   4 +-
 fs/xfs/libxfs/xfs_group.c       |  16 ++-
 fs/xfs/libxfs/xfs_group.h       |   5 +
 fs/xfs/libxfs/xfs_rmap_btree.c  |   4 +-
 fs/xfs/scrub/alloc_repair.c     |   9 +-
 fs/xfs/scrub/reap.c             |   2 +-
 fs/xfs/xfs_discard.c            |  10 +-
 fs/xfs/xfs_extent_busy.c        | 198 +++++++++++++++++++-------------
 fs/xfs/xfs_extent_busy.h        |  59 ++++------
 12 files changed, 193 insertions(+), 151 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index e60469fee875..47e90dbb852b 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -230,11 +230,8 @@ xfs_perag_alloc(
 #ifdef __KERNEL__
 	/* Place kernel structure only init below this point. */
 	spin_lock_init(&pag->pag_ici_lock);
-	spin_lock_init(&pag->pagb_lock);
 	INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker);
 	INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
-	init_waitqueue_head(&pag->pagb_wait);
-	pag->pagb_tree = RB_ROOT;
 #endif /* __KERNEL__ */
 
 	error = xfs_buf_cache_init(&pag->pag_bcache);
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 042ee0913fb9..7290148fa6e6 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -80,11 +80,6 @@ struct xfs_perag {
 	uint8_t		pagf_repair_rmap_level;
 #endif
 
-	spinlock_t	pagb_lock;	/* lock for pagb_tree */
-	struct rb_root	pagb_tree;	/* ordered tree of busy extents */
-	unsigned int	pagb_gen;	/* generation count for pagb_tree */
-	wait_queue_head_t pagb_wait;	/* woken when pagb_gen changes */
-
 	atomic_t        pagf_fstrms;    /* # of filestreams active in this AG */
 
 	spinlock_t	pag_ici_lock;	/* incore inode cache lock */
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index bfe7b4321c47..4ddd05c97a29 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -331,7 +331,8 @@ xfs_alloc_compute_aligned(
 	bool		busy;
 
 	/* Trim busy sections out of found extent */
-	busy = xfs_extent_busy_trim(args, &bno, &len, busy_gen);
+	busy = xfs_extent_busy_trim(pag_group(args->pag), args->minlen,
+			args->maxlen, &bno, &len, busy_gen);
 
 	/*
 	 * If we have a largish extent that happens to start before min_agbno,
@@ -1251,7 +1252,7 @@ xfs_alloc_ag_vextent_small(
 	if (fbno == NULLAGBLOCK)
 		goto out;
 
-	xfs_extent_busy_reuse(args->pag, fbno, 1,
+	xfs_extent_busy_reuse(pag_group(args->pag), fbno, 1,
 			      (args->datatype & XFS_ALLOC_NOBUSY));
 
 	if (args->datatype & XFS_ALLOC_USERDATA) {
@@ -1364,7 +1365,8 @@ xfs_alloc_ag_vextent_exact(
 	 */
 	tbno = fbno;
 	tlen = flen;
-	xfs_extent_busy_trim(args, &tbno, &tlen, &busy_gen);
+	xfs_extent_busy_trim(pag_group(args->pag), args->minlen, args->maxlen,
+			&tbno, &tlen, &busy_gen);
 
 	/*
 	 * Give up if the start of the extent is busy, or the freespace isn't
@@ -1757,8 +1759,9 @@ xfs_alloc_ag_vextent_near(
 			 * the allocation can be retried.
 			 */
 			trace_xfs_alloc_near_busy(args);
-			error = xfs_extent_busy_flush(args->tp, args->pag,
-					acur.busy_gen, alloc_flags);
+			error = xfs_extent_busy_flush(args->tp,
+					pag_group(args->pag), acur.busy_gen,
+					alloc_flags);
 			if (error)
 				goto out;
 
@@ -1873,8 +1876,9 @@ xfs_alloc_ag_vextent_size(
 			 * the allocation can be retried.
 			 */
 			trace_xfs_alloc_size_busy(args);
-			error = xfs_extent_busy_flush(args->tp, args->pag,
-					busy_gen, alloc_flags);
+			error = xfs_extent_busy_flush(args->tp,
+					pag_group(args->pag), busy_gen,
+					alloc_flags);
 			if (error)
 				goto error0;
 
@@ -1972,8 +1976,9 @@ xfs_alloc_ag_vextent_size(
 			 * the allocation can be retried.
 			 */
 			trace_xfs_alloc_size_busy(args);
-			error = xfs_extent_busy_flush(args->tp, args->pag,
-					busy_gen, alloc_flags);
+			error = xfs_extent_busy_flush(args->tp,
+					pag_group(args->pag), busy_gen,
+					alloc_flags);
 			if (error)
 				goto error0;
 
@@ -3615,8 +3620,8 @@ xfs_alloc_vextent_finish(
 		if (error)
 			goto out_drop_perag;
 
-		ASSERT(!xfs_extent_busy_search(args->pag, args->agbno,
-				args->len));
+		ASSERT(!xfs_extent_busy_search(pag_group(args->pag),
+				args->agbno, args->len));
 	}
 
 	xfs_ag_resv_alloc_extent(args->pag, args->resv, args);
@@ -4014,7 +4019,7 @@ __xfs_free_extent(
 
 	if (skip_discard)
 		busy_flags |= XFS_EXTENT_BUSY_SKIP_DISCARD;
-	xfs_extent_busy_insert(tp, pag, agbno, len, busy_flags);
+	xfs_extent_busy_insert(tp, pag_group(pag), agbno, len, busy_flags);
 	return 0;
 
 err_release:
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 88e1545ed4c9..e69a1bb13f7f 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -86,7 +86,7 @@ xfs_allocbt_alloc_block(
 	}
 
 	atomic64_inc(&cur->bc_mp->m_allocbt_blks);
-	xfs_extent_busy_reuse(cur->bc_ag.pag, bno, 1, false);
+	xfs_extent_busy_reuse(pag_group(cur->bc_ag.pag), bno, 1, false);
 
 	new->s = cpu_to_be32(bno);
 
@@ -110,7 +110,7 @@ xfs_allocbt_free_block(
 		return error;
 
 	atomic64_dec(&cur->bc_mp->m_allocbt_blks);
-	xfs_extent_busy_insert(cur->bc_tp, agbp->b_pag, bno, 1,
+	xfs_extent_busy_insert(cur->bc_tp, pag_group(agbp->b_pag), bno, 1,
 			      XFS_EXTENT_BUSY_SKIP_DISCARD);
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c
index 8532dc2f8628..5c6fa5d76a91 100644
--- a/fs/xfs/libxfs/xfs_group.c
+++ b/fs/xfs/libxfs/xfs_group.c
@@ -10,6 +10,7 @@
 #include "xfs_mount.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
+#include "xfs_extent_busy.h"
 #include "xfs_group.h"
 
 /*
@@ -161,6 +162,9 @@ xfs_group_free(
 	XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_ref) != 0);
 
 	xfs_defer_drain_free(&xg->xg_intents_drain);
+#ifdef __KERNEL__
+	kfree(xg->xg_busy_extents);
+#endif
 
 	if (uninit)
 		uninit(xg);
@@ -185,6 +189,9 @@ xfs_group_insert(
 	xg->xg_type = type;
 
 #ifdef __KERNEL__
+	xg->xg_busy_extents = xfs_extent_busy_alloc();
+	if (!xg->xg_busy_extents)
+		return -ENOMEM;
 	spin_lock_init(&xg->xg_state_lock);
 	xfs_hooks_init(&xg->xg_rmap_update_hooks);
 #endif
@@ -196,9 +203,14 @@ xfs_group_insert(
 	error = xa_insert(&mp->m_groups[type].xa, index, xg, GFP_KERNEL);
 	if (error) {
 		WARN_ON_ONCE(error == -EBUSY);
-		xfs_defer_drain_free(&xg->xg_intents_drain);
-		return error;
+		goto out_drain;
 	}
 
 	return 0;
+out_drain:
+	xfs_defer_drain_free(&xg->xg_intents_drain);
+#ifdef __KERNEL__
+	kfree(xg->xg_busy_extents);
+#endif
+	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index a87b9b80ef75..0ff6e1d5635c 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -15,6 +15,11 @@ struct xfs_group {
 #ifdef __KERNEL__
 	/* -- kernel only structures below this line -- */
 
+	/*
+	 * Track freed but not yet committed extents.
+	 */
+	struct xfs_extent_busy_tree *xg_busy_extents;
+
 	/*
 	 * Bitsets of per-ag metadata that have been checked and/or are sick.
 	 * Callers should hold xg_state_lock before accessing this field.
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 6fd460fc7c9c..b37eaf37c7fd 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -102,7 +102,7 @@ xfs_rmapbt_alloc_block(
 		return 0;
 	}
 
-	xfs_extent_busy_reuse(pag, bno, 1, false);
+	xfs_extent_busy_reuse(pag_group(pag), bno, 1, false);
 
 	new->s = cpu_to_be32(bno);
 	be32_add_cpu(&agf->agf_rmap_blocks, 1);
@@ -136,7 +136,7 @@ xfs_rmapbt_free_block(
 	if (error)
 		return error;
 
-	xfs_extent_busy_insert(cur->bc_tp, pag, bno, 1,
+	xfs_extent_busy_insert(cur->bc_tp, pag_group(pag), bno, 1,
 			      XFS_EXTENT_BUSY_SKIP_DISCARD);
 
 	xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1);
diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c
index f07cd93012c6..0433363a90b6 100644
--- a/fs/xfs/scrub/alloc_repair.c
+++ b/fs/xfs/scrub/alloc_repair.c
@@ -132,13 +132,16 @@ int
 xrep_setup_ag_allocbt(
 	struct xfs_scrub	*sc)
 {
+	struct xfs_group	*xg = pag_group(sc->sa.pag);
+	unsigned int		busy_gen;
+
 	/*
 	 * Make sure the busy extent list is clear because we can't put extents
 	 * on there twice.
 	 */
-	if (xfs_extent_busy_list_empty(sc->sa.pag, &busy_gen))
+	if (xfs_extent_busy_list_empty(xg, &busy_gen))
 		return 0;
-	return xfs_extent_busy_flush(sc->tp, sc->sa.pag, busy_gen, 0);
+	return xfs_extent_busy_flush(sc->tp, xg, busy_gen, 0);
 }
 
 /* Check for any obvious conflicts in the free extent. */
@@ -866,7 +869,7 @@ xrep_allocbt(
 	 * on there twice.  In theory we cleared this before we started, but
 	 * let's not risk the filesystem.
 	 */
-	if (!xfs_extent_busy_list_empty(sc->sa.pag, &busy_gen)) {
+	if (!xfs_extent_busy_list_empty(pag_group(sc->sa.pag), &busy_gen)) {
 		error = -EDEADLOCK;
 		goto out_ra;
 	}
diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c
index d65ad6aa856f..08230952053b 100644
--- a/fs/xfs/scrub/reap.c
+++ b/fs/xfs/scrub/reap.c
@@ -137,7 +137,7 @@ xreap_put_freelist(
 			agfl_bp, agbno, 0);
 	if (error)
 		return error;
-	xfs_extent_busy_insert(sc->tp, sc->sa.pag, agbno, 1,
+	xfs_extent_busy_insert(sc->tp, pag_group(sc->sa.pag), agbno, 1,
 			XFS_EXTENT_BUSY_SKIP_DISCARD);
 
 	return 0;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 739ec69c4428..019371c865d2 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -117,10 +117,12 @@ xfs_discard_extents(
 
 	blk_start_plug(&plug);
 	list_for_each_entry(busyp, &extents->extent_list, list) {
-		trace_xfs_discard_extent(busyp->pag, busyp->bno, busyp->length);
+		struct xfs_perag	*pag = to_perag(busyp->group);
+
+		trace_xfs_discard_extent(pag, busyp->bno, busyp->length);
 
 		error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
-				xfs_agbno_to_daddr(busyp->pag, busyp->bno),
+				xfs_agbno_to_daddr(pag, busyp->bno),
 				XFS_FSB_TO_BB(mp, busyp->length),
 				GFP_KERNEL, &bio);
 		if (error && error != -EOPNOTSUPP) {
@@ -271,12 +273,12 @@ xfs_trim_gather_extents(
 		 * If any blocks in the range are still busy, skip the
 		 * discard and try again the next time.
 		 */
-		if (xfs_extent_busy_search(pag, fbno, flen)) {
+		if (xfs_extent_busy_search(pag_group(pag), fbno, flen)) {
 			trace_xfs_discard_busy(pag, fbno, flen);
 			goto next_extent;
 		}
 
-		xfs_extent_busy_insert_discard(pag, fbno, flen,
+		xfs_extent_busy_insert_discard(pag_group(pag), fbno, flen,
 				&extents->extent_list);
 next_extent:
 		if (tcur->by_bno)
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 9c5c6279ae21..457a27ab8375 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -19,14 +19,22 @@
 #include "xfs_log.h"
 #include "xfs_ag.h"
 
+struct xfs_extent_busy_tree {
+	spinlock_t		eb_lock;
+	struct rb_root		eb_tree;
+	unsigned int		eb_gen;
+	wait_queue_head_t	eb_wait;
+};
+
 static void
 xfs_extent_busy_insert_list(
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
 	unsigned int		flags,
 	struct list_head	*busy_list)
 {
+	struct xfs_extent_busy_tree *eb = xg->xg_busy_extents;
 	struct xfs_extent_busy	*new;
 	struct xfs_extent_busy	*busyp;
 	struct rb_node		**rbp;
@@ -34,17 +42,17 @@ xfs_extent_busy_insert_list(
 
 	new = kzalloc(sizeof(struct xfs_extent_busy),
 			GFP_KERNEL | __GFP_NOFAIL);
-	new->pag = xfs_perag_hold(pag);
+	new->group = xfs_group_hold(xg);
 	new->bno = bno;
 	new->length = len;
 	INIT_LIST_HEAD(&new->list);
 	new->flags = flags;
 
 	/* trace before insert to be able to see failed inserts */
-	trace_xfs_extent_busy(pag_group(pag), bno, len);
+	trace_xfs_extent_busy(xg, bno, len);
 
-	spin_lock(&pag->pagb_lock);
-	rbp = &pag->pagb_tree.rb_node;
+	spin_lock(&eb->eb_lock);
+	rbp = &eb->eb_tree.rb_node;
 	while (*rbp) {
 		parent = *rbp;
 		busyp = rb_entry(parent, struct xfs_extent_busy, rb_node);
@@ -61,32 +69,32 @@ xfs_extent_busy_insert_list(
 	}
 
 	rb_link_node(&new->rb_node, parent, rbp);
-	rb_insert_color(&new->rb_node, &pag->pagb_tree);
+	rb_insert_color(&new->rb_node, &eb->eb_tree);
 
 	/* always process discard lists in fifo order */
 	list_add_tail(&new->list, busy_list);
-	spin_unlock(&pag->pagb_lock);
+	spin_unlock(&eb->eb_lock);
 }
 
 void
 xfs_extent_busy_insert(
 	struct xfs_trans	*tp,
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
 	unsigned int		flags)
 {
-	xfs_extent_busy_insert_list(pag, bno, len, flags, &tp->t_busy);
+	xfs_extent_busy_insert_list(xg, bno, len, flags, &tp->t_busy);
 }
 
 void
 xfs_extent_busy_insert_discard(
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
 	struct list_head	*busy_list)
 {
-	xfs_extent_busy_insert_list(pag, bno, len, XFS_EXTENT_BUSY_DISCARDED,
+	xfs_extent_busy_insert_list(xg, bno, len, XFS_EXTENT_BUSY_DISCARDED,
 			busy_list);
 }
 
@@ -101,17 +109,18 @@ xfs_extent_busy_insert_discard(
  */
 int
 xfs_extent_busy_search(
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len)
 {
+	struct xfs_extent_busy_tree *eb = xg->xg_busy_extents;
 	struct rb_node		*rbp;
 	struct xfs_extent_busy	*busyp;
 	int			match = 0;
 
 	/* find closest start bno overlap */
-	spin_lock(&pag->pagb_lock);
-	rbp = pag->pagb_tree.rb_node;
+	spin_lock(&eb->eb_lock);
+	rbp = eb->eb_tree.rb_node;
 	while (rbp) {
 		busyp = rb_entry(rbp, struct xfs_extent_busy, rb_node);
 		if (bno < busyp->bno) {
@@ -130,7 +139,7 @@ xfs_extent_busy_search(
 			break;
 		}
 	}
-	spin_unlock(&pag->pagb_lock);
+	spin_unlock(&eb->eb_lock);
 	return match;
 }
 
@@ -147,13 +156,15 @@ xfs_extent_busy_search(
  */
 STATIC bool
 xfs_extent_busy_update_extent(
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	struct xfs_extent_busy	*busyp,
 	xfs_agblock_t		fbno,
 	xfs_extlen_t		flen,
-	bool			userdata) __releases(&pag->pagb_lock)
-					  __acquires(&pag->pagb_lock)
+	bool			userdata)
+		__releases(&eb->eb_lock)
+		__acquires(&eb->eb_lock)
 {
+	struct xfs_extent_busy_tree *eb = xg->xg_busy_extents;
 	xfs_agblock_t		fend = fbno + flen;
 	xfs_agblock_t		bbno = busyp->bno;
 	xfs_agblock_t		bend = bbno + busyp->length;
@@ -164,9 +175,9 @@ xfs_extent_busy_update_extent(
 	 * and retry.
 	 */
 	if (busyp->flags & XFS_EXTENT_BUSY_DISCARDED) {
-		spin_unlock(&pag->pagb_lock);
+		spin_unlock(&eb->eb_lock);
 		delay(1);
-		spin_lock(&pag->pagb_lock);
+		spin_lock(&eb->eb_lock);
 		return false;
 	}
 
@@ -239,7 +250,7 @@ xfs_extent_busy_update_extent(
 		 * tree root, because erasing the node can rearrange the
 		 * tree topology.
 		 */
-		rb_erase(&busyp->rb_node, &pag->pagb_tree);
+		rb_erase(&busyp->rb_node, &eb->eb_tree);
 		busyp->length = 0;
 		return false;
 	} else if (fend < bend) {
@@ -278,14 +289,14 @@ xfs_extent_busy_update_extent(
 		ASSERT(0);
 	}
 
-	trace_xfs_extent_busy_reuse(pag_group(pag), fbno, flen);
+	trace_xfs_extent_busy_reuse(xg, fbno, flen);
 	return true;
 
 out_force_log:
-	spin_unlock(&pag->pagb_lock);
-	xfs_log_force(pag_mount(pag), XFS_LOG_SYNC);
-	trace_xfs_extent_busy_force(pag_group(pag), fbno, flen);
-	spin_lock(&pag->pagb_lock);
+	spin_unlock(&eb->eb_lock);
+	xfs_log_force(xg->xg_mount, XFS_LOG_SYNC);
+	trace_xfs_extent_busy_force(xg, fbno, flen);
+	spin_lock(&eb->eb_lock);
 	return false;
 }
 
@@ -294,17 +305,18 @@ xfs_extent_busy_update_extent(
  */
 void
 xfs_extent_busy_reuse(
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	xfs_agblock_t		fbno,
 	xfs_extlen_t		flen,
 	bool			userdata)
 {
+	struct xfs_extent_busy_tree *eb = xg->xg_busy_extents;
 	struct rb_node		*rbp;
 
 	ASSERT(flen > 0);
-	spin_lock(&pag->pagb_lock);
+	spin_lock(&eb->eb_lock);
 restart:
-	rbp = pag->pagb_tree.rb_node;
+	rbp = eb->eb_tree.rb_node;
 	while (rbp) {
 		struct xfs_extent_busy *busyp =
 			rb_entry(rbp, struct xfs_extent_busy, rb_node);
@@ -319,11 +331,11 @@ xfs_extent_busy_reuse(
 			continue;
 		}
 
-		if (!xfs_extent_busy_update_extent(pag, busyp, fbno, flen,
+		if (!xfs_extent_busy_update_extent(xg, busyp, fbno, flen,
 						  userdata))
 			goto restart;
 	}
-	spin_unlock(&pag->pagb_lock);
+	spin_unlock(&eb->eb_lock);
 }
 
 /*
@@ -332,7 +344,7 @@ xfs_extent_busy_reuse(
  * args->minlen no suitable extent could be found, and the higher level
  * code needs to force out the log and retry the allocation.
  *
- * Return the current busy generation for the AG if the extent is busy. This
+ * Return the current busy generation for the group if the extent is busy. This
  * value can be used to wait for at least one of the currently busy extents
  * to be cleared. Note that the busy list is not guaranteed to be empty after
  * the gen is woken. The state of a specific extent must always be confirmed
@@ -340,11 +352,14 @@ xfs_extent_busy_reuse(
  */
 bool
 xfs_extent_busy_trim(
-	struct xfs_alloc_arg	*args,
+	struct xfs_group	*xg,
+	xfs_extlen_t		minlen,
+	xfs_extlen_t		maxlen,
 	xfs_agblock_t		*bno,
 	xfs_extlen_t		*len,
 	unsigned		*busy_gen)
 {
+	struct xfs_extent_busy_tree *eb = xg->xg_busy_extents;
 	xfs_agblock_t		fbno;
 	xfs_extlen_t		flen;
 	struct rb_node		*rbp;
@@ -352,11 +367,11 @@ xfs_extent_busy_trim(
 
 	ASSERT(*len > 0);
 
-	spin_lock(&args->pag->pagb_lock);
+	spin_lock(&eb->eb_lock);
 	fbno = *bno;
 	flen = *len;
-	rbp = args->pag->pagb_tree.rb_node;
-	while (rbp && flen >= args->minlen) {
+	rbp = eb->eb_tree.rb_node;
+	while (rbp && flen >= minlen) {
 		struct xfs_extent_busy *busyp =
 			rb_entry(rbp, struct xfs_extent_busy, rb_node);
 		xfs_agblock_t	fend = fbno + flen;
@@ -477,13 +492,13 @@ xfs_extent_busy_trim(
 			 * good chance subsequent allocations will be
 			 * contiguous.
 			 */
-			if (bbno - fbno >= args->maxlen) {
+			if (bbno - fbno >= maxlen) {
 				/* left candidate fits perfect */
 				fend = bbno;
-			} else if (fend - bend >= args->maxlen * 4) {
+			} else if (fend - bend >= maxlen * 4) {
 				/* right candidate has enough free space */
 				fbno = bend;
-			} else if (bbno - fbno >= args->minlen) {
+			} else if (bbno - fbno >= minlen) {
 				/* left candidate fits minimum requirement */
 				fend = bbno;
 			} else {
@@ -496,14 +511,13 @@ xfs_extent_busy_trim(
 out:
 
 	if (fbno != *bno || flen != *len) {
-		trace_xfs_extent_busy_trim(pag_group(args->pag), *bno, *len,
-					   fbno, flen);
+		trace_xfs_extent_busy_trim(xg, *bno, *len, fbno, flen);
 		*bno = fbno;
 		*len = flen;
-		*busy_gen = args->pag->pagb_gen;
+		*busy_gen = eb->eb_gen;
 		ret = true;
 	}
-	spin_unlock(&args->pag->pagb_lock);
+	spin_unlock(&eb->eb_lock);
 	return ret;
 fail:
 	/*
@@ -516,23 +530,24 @@ xfs_extent_busy_trim(
 
 static bool
 xfs_extent_busy_clear_one(
-	struct xfs_perag	*pag,
 	struct xfs_extent_busy	*busyp,
 	bool			do_discard)
 {
+	struct xfs_extent_busy_tree *eb = busyp->group->xg_busy_extents;
+
 	if (busyp->length) {
 		if (do_discard &&
 		    !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD)) {
 			busyp->flags = XFS_EXTENT_BUSY_DISCARDED;
 			return false;
 		}
-		trace_xfs_extent_busy_clear(pag_group(pag), busyp->bno,
+		trace_xfs_extent_busy_clear(busyp->group, busyp->bno,
 				busyp->length);
-		rb_erase(&busyp->rb_node, &pag->pagb_tree);
+		rb_erase(&busyp->rb_node, &eb->eb_tree);
 	}
 
 	list_del_init(&busyp->list);
-	xfs_perag_put(busyp->pag);
+	xfs_group_put(busyp->group);
 	kfree(busyp);
 	return true;
 }
@@ -554,29 +569,30 @@ xfs_extent_busy_clear(
 		return;
 
 	do {
-		struct xfs_perag	*pag = xfs_perag_hold(busyp->pag);
+		struct xfs_group	*xg = xfs_group_hold(busyp->group);
+		struct xfs_extent_busy_tree *eb = xg->xg_busy_extents;
 		bool			wakeup = false;
 
-		spin_lock(&pag->pagb_lock);
+		spin_lock(&eb->eb_lock);
 		do {
 			next = list_next_entry(busyp, list);
-			if (xfs_extent_busy_clear_one(pag, busyp, do_discard))
+			if (xfs_extent_busy_clear_one(busyp, do_discard))
 				wakeup = true;
 			busyp = next;
 		} while (!list_entry_is_head(busyp, list, list) &&
-			 busyp->pag == pag);
+			 busyp->group == xg);
 
 		if (wakeup) {
-			pag->pagb_gen++;
-			wake_up_all(&pag->pagb_wait);
+			eb->eb_gen++;
+			wake_up_all(&eb->eb_wait);
 		}
-		spin_unlock(&pag->pagb_lock);
-		xfs_perag_put(pag);
+		spin_unlock(&eb->eb_lock);
+		xfs_group_put(xg);
 	} while (!list_entry_is_head(busyp, list, list));
 }
 
 /*
- * Flush out all busy extents for this AG.
+ * Flush out all busy extents for this group.
  *
  * If the current transaction is holding busy extents, the caller may not want
  * to wait for committed busy extents to resolve. If we are being told just to
@@ -592,10 +608,11 @@ xfs_extent_busy_clear(
 int
 xfs_extent_busy_flush(
 	struct xfs_trans	*tp,
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	unsigned		busy_gen,
 	uint32_t		alloc_flags)
 {
+	struct xfs_extent_busy_tree *eb = xg->xg_busy_extents;
 	DEFINE_WAIT		(wait);
 	int			error;
 
@@ -608,7 +625,7 @@ xfs_extent_busy_flush(
 		if (alloc_flags & XFS_ALLOC_FLAG_TRYFLUSH)
 			return 0;
 
-		if (busy_gen != READ_ONCE(pag->pagb_gen))
+		if (busy_gen != READ_ONCE(eb->eb_gen))
 			return 0;
 
 		if (alloc_flags & XFS_ALLOC_FLAG_FREEING)
@@ -617,36 +634,44 @@ xfs_extent_busy_flush(
 
 	/* Wait for committed busy extents to resolve. */
 	do {
-		prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
-		if  (busy_gen != READ_ONCE(pag->pagb_gen))
+		prepare_to_wait(&eb->eb_wait, &wait, TASK_KILLABLE);
+		if  (busy_gen != READ_ONCE(eb->eb_gen))
 			break;
 		schedule();
 	} while (1);
 
-	finish_wait(&pag->pagb_wait, &wait);
+	finish_wait(&eb->eb_wait, &wait);
 	return 0;
 }
 
+static void
+xfs_extent_busy_wait_group(
+	struct xfs_group	*xg)
+{
+	DEFINE_WAIT		(wait);
+	struct xfs_extent_busy_tree *eb = xg->xg_busy_extents;
+
+	do {
+		prepare_to_wait(&eb->eb_wait, &wait, TASK_KILLABLE);
+		if  (RB_EMPTY_ROOT(&eb->eb_tree))
+			break;
+		schedule();
+	} while (1);
+	finish_wait(&eb->eb_wait, &wait);
+}
+
 void
 xfs_extent_busy_wait_all(
 	struct xfs_mount	*mp)
 {
 	struct xfs_perag	*pag = NULL;
-	DEFINE_WAIT		(wait);
 
-	while ((pag = xfs_perag_next(mp, pag))) {
-		do {
-			prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
-			if  (RB_EMPTY_ROOT(&pag->pagb_tree))
-				break;
-			schedule();
-		} while (1);
-		finish_wait(&pag->pagb_wait, &wait);
-	}
+	while ((pag = xfs_perag_next(mp, pag)))
+		xfs_extent_busy_wait_group(pag_group(pag));
 }
 
 /*
- * Callback for list_sort to sort busy extents by the AG they reside in.
+ * Callback for list_sort to sort busy extents by the group they reside in.
  */
 int
 xfs_extent_busy_ag_cmp(
@@ -660,23 +685,38 @@ xfs_extent_busy_ag_cmp(
 		container_of(l2, struct xfs_extent_busy, list);
 	s32 diff;
 
-	diff = pag_agno(b1->pag) - pag_agno(b2->pag);
+	diff = b1->group->xg_gno - b2->group->xg_gno;
 	if (!diff)
 		diff = b1->bno - b2->bno;
 	return diff;
 }
 
-/* Are there any busy extents in this AG? */
+/* Are there any busy extents in this group? */
 bool
 xfs_extent_busy_list_empty(
-	struct xfs_perag	*pag,
+	struct xfs_group	*xg,
 	unsigned		*busy_gen)
 {
+	struct xfs_extent_busy_tree *eb = xg->xg_busy_extents;
 	bool			res;
 
-	spin_lock(&pag->pagb_lock);
-	res = RB_EMPTY_ROOT(&pag->pagb_tree);
-	*busy_gen = READ_ONCE(pag->pagb_gen);
-	spin_unlock(&pag->pagb_lock);
+	spin_lock(&eb->eb_lock);
+	res = RB_EMPTY_ROOT(&eb->eb_tree);
+	*busy_gen = READ_ONCE(eb->eb_gen);
+	spin_unlock(&eb->eb_lock);
 	return res;
 }
+
+struct xfs_extent_busy_tree *
+xfs_extent_busy_alloc(void)
+{
+	struct xfs_extent_busy_tree *eb;
+
+	eb = kzalloc(sizeof(*eb), GFP_KERNEL);
+	if (!eb)
+		return NULL;
+	spin_lock_init(&eb->eb_lock);
+	init_waitqueue_head(&eb->eb_wait);
+	eb->eb_tree = RB_ROOT;
+	return eb;
+}
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index c803dcd124a6..f069b04e8ea1 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -8,19 +8,18 @@
 #ifndef __XFS_EXTENT_BUSY_H__
 #define	__XFS_EXTENT_BUSY_H__
 
+struct xfs_group;
 struct xfs_mount;
-struct xfs_perag;
 struct xfs_trans;
-struct xfs_alloc_arg;
 
 /*
- * Busy block/extent entry.  Indexed by a rbtree in perag to mark blocks that
- * have been freed but whose transactions aren't committed to disk yet.
+ * Busy block/extent entry.  Indexed by a rbtree in the group to mark blocks
+ * that have been freed but whose transactions aren't committed to disk yet.
  */
 struct xfs_extent_busy {
-	struct rb_node	rb_node;	/* ag by-bno indexed search tree */
+	struct rb_node	rb_node;	/* group by-bno indexed search tree */
 	struct list_head list;		/* transaction busy extent list */
-	struct xfs_perag *pag;
+	struct xfs_group *group;
 	xfs_agblock_t	bno;
 	xfs_extlen_t	length;
 	unsigned int	flags;
@@ -44,45 +43,29 @@ struct xfs_busy_extents {
 	void			*owner;
 };
 
-void
-xfs_extent_busy_insert(struct xfs_trans *tp, struct xfs_perag *pag,
-	xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags);
-
-void
-xfs_extent_busy_insert_discard(struct xfs_perag *pag, xfs_agblock_t bno,
-	xfs_extlen_t len, struct list_head *busy_list);
-
-void
-xfs_extent_busy_clear(struct list_head *list, bool do_discard);
-
-int
-xfs_extent_busy_search(struct xfs_perag *pag, xfs_agblock_t bno,
+void xfs_extent_busy_insert(struct xfs_trans *tp, struct xfs_group *xg,
+		xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags);
+void xfs_extent_busy_insert_discard(struct xfs_group *xg, xfs_agblock_t bno,
+		xfs_extlen_t len, struct list_head *busy_list);
+void xfs_extent_busy_clear(struct list_head *list, bool do_discard);
+int xfs_extent_busy_search(struct xfs_group *xg, xfs_agblock_t bno,
 		xfs_extlen_t len);
-
-void
-xfs_extent_busy_reuse(struct xfs_perag *pag, xfs_agblock_t fbno,
+void xfs_extent_busy_reuse(struct xfs_group *xg, xfs_agblock_t fbno,
 		xfs_extlen_t flen, bool userdata);
-
-bool
-xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno,
-		xfs_extlen_t *len, unsigned *busy_gen);
-
-int
-xfs_extent_busy_flush(struct xfs_trans *tp, struct xfs_perag *pag,
+bool xfs_extent_busy_trim(struct xfs_group *xg, xfs_extlen_t minlen,
+		xfs_extlen_t maxlen, xfs_agblock_t *bno, xfs_extlen_t *len,
+		unsigned *busy_gen);
+int xfs_extent_busy_flush(struct xfs_trans *tp, struct xfs_group *xg,
 		unsigned busy_gen, uint32_t alloc_flags);
+void xfs_extent_busy_wait_all(struct xfs_mount *mp);
+bool xfs_extent_busy_list_empty(struct xfs_group *xg, unsigned int *busy_gen);
+struct xfs_extent_busy_tree *xfs_extent_busy_alloc(void);
 
-void
-xfs_extent_busy_wait_all(struct xfs_mount *mp);
-
-int
-xfs_extent_busy_ag_cmp(void *priv, const struct list_head *a,
-	const struct list_head *b);
-
+int xfs_extent_busy_ag_cmp(void *priv, const struct list_head *a,
+		const struct list_head *b);
 static inline void xfs_extent_busy_sort(struct list_head *list)
 {
 	list_sort(NULL, list, xfs_extent_busy_ag_cmp);
 }
 
-bool xfs_extent_busy_list_empty(struct xfs_perag *pag, unsigned int *busy_gen);
-
 #endif /* __XFS_EXTENT_BUSY_H__ */

From 77a530e6c49d22bd4a221d2f059db24fc30094db Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:44 -0800
Subject: [PATCH 12/16] xfs: add a generic group pointer to the btree cursor

Replace the pag pointers in the type specific union with a generic
xfs_group pointer.  This prepares for adding realtime group support.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc.c          |  8 +++----
 fs/xfs/libxfs/xfs_alloc_btree.c    | 28 ++++++++++++------------
 fs/xfs/libxfs/xfs_btree.c          | 35 ++++++++++--------------------
 fs/xfs/libxfs/xfs_btree.h          |  3 +--
 fs/xfs/libxfs/xfs_btree_mem.c      |  6 ++---
 fs/xfs/libxfs/xfs_ialloc.c         | 12 +++++-----
 fs/xfs/libxfs/xfs_ialloc_btree.c   | 15 +++++++------
 fs/xfs/libxfs/xfs_refcount.c       | 17 ++++++++-------
 fs/xfs/libxfs/xfs_refcount_btree.c | 10 ++++-----
 fs/xfs/libxfs/xfs_rmap.c           |  8 +++----
 fs/xfs/libxfs/xfs_rmap_btree.c     | 19 ++++++++--------
 fs/xfs/scrub/alloc.c               |  2 +-
 fs/xfs/scrub/bmap.c                |  3 ++-
 fs/xfs/scrub/bmap_repair.c         |  4 ++--
 fs/xfs/scrub/cow_repair.c          |  9 +++++---
 fs/xfs/scrub/health.c              |  2 +-
 fs/xfs/scrub/ialloc.c              | 14 ++++++------
 fs/xfs/scrub/refcount.c            |  3 ++-
 fs/xfs/scrub/rmap.c                |  2 +-
 fs/xfs/scrub/rmap_repair.c         |  2 +-
 fs/xfs/xfs_fsmap.c                 |  6 +++--
 fs/xfs/xfs_health.c                | 23 +++++---------------
 fs/xfs/xfs_trace.h                 | 28 ++++++++++++------------
 23 files changed, 122 insertions(+), 137 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 4ddd05c97a29..d33c2fdaf4f2 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -275,7 +275,7 @@ xfs_alloc_complain_bad_rec(
 
 	xfs_warn(mp,
 		"%sbt record corruption in AG %d detected at %pS!",
-		cur->bc_ops->name, pag_agno(cur->bc_ag.pag), fa);
+		cur->bc_ops->name, cur->bc_group->xg_gno, fa);
 	xfs_warn(mp,
 		"start block 0x%x block count 0x%x", irec->ar_startblock,
 		irec->ar_blockcount);
@@ -303,7 +303,7 @@ xfs_alloc_get_rec(
 		return error;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
+	fa = xfs_alloc_check_irec(to_perag(cur->bc_group), &irec);
 	if (fa)
 		return xfs_alloc_complain_bad_rec(cur, fa, &irec);
 
@@ -540,7 +540,7 @@ static int
 xfs_alloc_fixup_longest(
 	struct xfs_btree_cur	*cnt_cur)
 {
-	struct xfs_perag	*pag = cnt_cur->bc_ag.pag;
+	struct xfs_perag	*pag = to_perag(cnt_cur->bc_group);
 	struct xfs_buf		*bp = cnt_cur->bc_ag.agbp;
 	struct xfs_agf		*agf = bp->b_addr;
 	xfs_extlen_t		longest = 0;
@@ -4044,7 +4044,7 @@ xfs_alloc_query_range_helper(
 	xfs_failaddr_t				fa;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
+	fa = xfs_alloc_check_irec(to_perag(cur->bc_group), &irec);
 	if (fa)
 		return xfs_alloc_complain_bad_rec(cur, fa, &irec);
 
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index e69a1bb13f7f..a4ac37ba5d51 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -28,7 +28,7 @@ xfs_bnobt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_bnobt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ag.agbp,
-			cur->bc_ag.pag);
+			to_perag(cur->bc_group));
 }
 
 STATIC struct xfs_btree_cur *
@@ -36,29 +36,29 @@ xfs_cntbt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_cntbt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ag.agbp,
-			cur->bc_ag.pag);
+			to_perag(cur->bc_group));
 }
 
-
 STATIC void
 xfs_allocbt_set_root(
 	struct xfs_btree_cur		*cur,
 	const union xfs_btree_ptr	*ptr,
 	int				inc)
 {
-	struct xfs_buf		*agbp = cur->bc_ag.agbp;
-	struct xfs_agf		*agf = agbp->b_addr;
+	struct xfs_perag		*pag = to_perag(cur->bc_group);
+	struct xfs_buf			*agbp = cur->bc_ag.agbp;
+	struct xfs_agf			*agf = agbp->b_addr;
 
 	ASSERT(ptr->s != 0);
 
 	if (xfs_btree_is_bno(cur->bc_ops)) {
 		agf->agf_bno_root = ptr->s;
 		be32_add_cpu(&agf->agf_bno_level, inc);
-		cur->bc_ag.pag->pagf_bno_level += inc;
+		pag->pagf_bno_level += inc;
 	} else {
 		agf->agf_cnt_root = ptr->s;
 		be32_add_cpu(&agf->agf_cnt_level, inc);
-		cur->bc_ag.pag->pagf_cnt_level += inc;
+		pag->pagf_cnt_level += inc;
 	}
 
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
@@ -75,7 +75,7 @@ xfs_allocbt_alloc_block(
 	xfs_agblock_t		bno;
 
 	/* Allocate the new block from the freelist. If we can't, give up.  */
-	error = xfs_alloc_get_freelist(cur->bc_ag.pag, cur->bc_tp,
+	error = xfs_alloc_get_freelist(to_perag(cur->bc_group), cur->bc_tp,
 			cur->bc_ag.agbp, &bno, 1);
 	if (error)
 		return error;
@@ -86,7 +86,7 @@ xfs_allocbt_alloc_block(
 	}
 
 	atomic64_inc(&cur->bc_mp->m_allocbt_blks);
-	xfs_extent_busy_reuse(pag_group(cur->bc_ag.pag), bno, 1, false);
+	xfs_extent_busy_reuse(cur->bc_group, bno, 1, false);
 
 	new->s = cpu_to_be32(bno);
 
@@ -104,8 +104,8 @@ xfs_allocbt_free_block(
 	int			error;
 
 	bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp));
-	error = xfs_alloc_put_freelist(cur->bc_ag.pag, cur->bc_tp, agbp, NULL,
-			bno, 1);
+	error = xfs_alloc_put_freelist(to_perag(cur->bc_group), cur->bc_tp,
+			agbp, NULL, bno, 1);
 	if (error)
 		return error;
 
@@ -178,7 +178,7 @@ xfs_allocbt_init_ptr_from_cur(
 {
 	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agf->agf_seqno));
+	ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno));
 
 	if (xfs_btree_is_bno(cur->bc_ops))
 		ptr->s = agf->agf_bno_root;
@@ -492,7 +492,7 @@ xfs_bnobt_init_cursor(
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_bnobt_ops,
 			mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
-	cur->bc_ag.pag = xfs_perag_hold(pag);
+	cur->bc_group = xfs_group_hold(pag_group(pag));
 	cur->bc_ag.agbp = agbp;
 	if (agbp) {
 		struct xfs_agf		*agf = agbp->b_addr;
@@ -518,7 +518,7 @@ xfs_cntbt_init_cursor(
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_cntbt_ops,
 			mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
-	cur->bc_ag.pag = xfs_perag_hold(pag);
+	cur->bc_group = xfs_group_hold(pag_group(pag));
 	cur->bc_ag.agbp = agbp;
 	if (agbp) {
 		struct xfs_agf		*agf = agbp->b_addr;
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 9a13dbf5f54a..2b5fc5fd1643 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -225,7 +225,7 @@ __xfs_btree_check_agblock(
 	struct xfs_buf		*bp)
 {
 	struct xfs_mount	*mp = cur->bc_mp;
-	struct xfs_perag	*pag = cur->bc_ag.pag;
+	struct xfs_perag	*pag = to_perag(cur->bc_group);
 	xfs_failaddr_t		fa;
 	xfs_agblock_t		agbno;
 
@@ -331,7 +331,7 @@ __xfs_btree_check_ptr(
 			return -EFSCORRUPTED;
 		break;
 	case XFS_BTREE_TYPE_AG:
-		if (!xfs_verify_agbno(cur->bc_ag.pag,
+		if (!xfs_verify_agbno(to_perag(cur->bc_group),
 				be32_to_cpu((&ptr->s)[index])))
 			return -EFSCORRUPTED;
 		break;
@@ -372,7 +372,7 @@ xfs_btree_check_ptr(
 		case XFS_BTREE_TYPE_AG:
 			xfs_err(cur->bc_mp,
 "AG %u: Corrupt %sbt pointer at level %d index %d.",
-				pag_agno(cur->bc_ag.pag), cur->bc_ops->name,
+				cur->bc_group->xg_gno, cur->bc_ops->name,
 				level, index);
 			break;
 		}
@@ -523,20 +523,8 @@ xfs_btree_del_cursor(
 	ASSERT(!xfs_btree_is_bmap(cur->bc_ops) || cur->bc_bmap.allocated == 0 ||
 	       xfs_is_shutdown(cur->bc_mp) || error != 0);
 
-	switch (cur->bc_ops->type) {
-	case XFS_BTREE_TYPE_AG:
-		if (cur->bc_ag.pag)
-			xfs_perag_put(cur->bc_ag.pag);
-		break;
-	case XFS_BTREE_TYPE_INODE:
-		/* nothing to do */
-		break;
-	case XFS_BTREE_TYPE_MEM:
-		if (cur->bc_mem.pag)
-			xfs_perag_put(cur->bc_mem.pag);
-		break;
-	}
-
+	if (cur->bc_group)
+		xfs_group_put(cur->bc_group);
 	kmem_cache_free(cur->bc_cache, cur);
 }
 
@@ -1017,21 +1005,22 @@ xfs_btree_readahead_agblock(
 	struct xfs_btree_block	*block)
 {
 	struct xfs_mount	*mp = cur->bc_mp;
+	struct xfs_perag	*pag = to_perag(cur->bc_group);
 	xfs_agblock_t		left = be32_to_cpu(block->bb_u.s.bb_leftsib);
 	xfs_agblock_t		right = be32_to_cpu(block->bb_u.s.bb_rightsib);
 	int			rval = 0;
 
 	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) {
 		xfs_buf_readahead(mp->m_ddev_targp,
-				xfs_agbno_to_daddr(cur->bc_ag.pag, left),
-				mp->m_bsize, cur->bc_ops->buf_ops);
+				xfs_agbno_to_daddr(pag, left), mp->m_bsize,
+				cur->bc_ops->buf_ops);
 		rval++;
 	}
 
 	if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLAGBLOCK) {
 		xfs_buf_readahead(mp->m_ddev_targp,
-				xfs_agbno_to_daddr(cur->bc_ag.pag, right),
-				mp->m_bsize, cur->bc_ops->buf_ops);
+				xfs_agbno_to_daddr(pag, right), mp->m_bsize,
+				cur->bc_ops->buf_ops);
 		rval++;
 	}
 
@@ -1090,7 +1079,7 @@ xfs_btree_ptr_to_daddr(
 
 	switch (cur->bc_ops->type) {
 	case XFS_BTREE_TYPE_AG:
-		*daddr = xfs_agbno_to_daddr(cur->bc_ag.pag,
+		*daddr = xfs_agbno_to_daddr(to_perag(cur->bc_group),
 				be32_to_cpu(ptr->s));
 		break;
 	case XFS_BTREE_TYPE_INODE:
@@ -1312,7 +1301,7 @@ xfs_btree_owner(
 	case XFS_BTREE_TYPE_INODE:
 		return cur->bc_ino.ip->i_ino;
 	case XFS_BTREE_TYPE_AG:
-		return pag_agno(cur->bc_ag.pag);
+		return cur->bc_group->xg_gno;
 	default:
 		ASSERT(0);
 		return 0;
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 10b7ddc3b2b3..3b739459ebb0 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -254,6 +254,7 @@ struct xfs_btree_cur
 	union xfs_btree_irec	bc_rec;	/* current insert/search record value */
 	uint8_t			bc_nlevels; /* number of levels in the tree */
 	uint8_t			bc_maxlevels; /* maximum levels for this btree type */
+	struct xfs_group	*bc_group;
 
 	/* per-type information */
 	union {
@@ -264,13 +265,11 @@ struct xfs_btree_cur
 			struct xbtree_ifakeroot	*ifake;	/* for staging cursor */
 		} bc_ino;
 		struct {
-			struct xfs_perag	*pag;
 			struct xfs_buf		*agbp;
 			struct xbtree_afakeroot	*afake;	/* for staging cursor */
 		} bc_ag;
 		struct {
 			struct xfbtree		*xfbtree;
-			struct xfs_perag	*pag;
 		} bc_mem;
 	};
 
diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c
index 036061fe32cc..df3d613675a1 100644
--- a/fs/xfs/libxfs/xfs_btree_mem.c
+++ b/fs/xfs/libxfs/xfs_btree_mem.c
@@ -57,10 +57,8 @@ xfbtree_dup_cursor(
 	ncur->bc_flags = cur->bc_flags;
 	ncur->bc_nlevels = cur->bc_nlevels;
 	ncur->bc_mem.xfbtree = cur->bc_mem.xfbtree;
-
-	if (cur->bc_mem.pag)
-		ncur->bc_mem.pag = xfs_perag_hold(cur->bc_mem.pag);
-
+	if (cur->bc_group)
+		ncur->bc_group = xfs_group_hold(cur->bc_group);
 	return ncur;
 }
 
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 78e1920c1ff9..f0261c4d9106 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -142,7 +142,7 @@ xfs_inobt_complain_bad_rec(
 
 	xfs_warn(mp,
 		"%sbt record corruption in AG %d detected at %pS!",
-		cur->bc_ops->name, pag_agno(cur->bc_ag.pag), fa);
+		cur->bc_ops->name, cur->bc_group->xg_gno, fa);
 	xfs_warn(mp,
 "start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
 		irec->ir_startino, irec->ir_count, irec->ir_freecount,
@@ -170,7 +170,7 @@ xfs_inobt_get_rec(
 		return error;
 
 	xfs_inobt_btrec_to_irec(mp, rec, irec);
-	fa = xfs_inobt_check_irec(cur->bc_ag.pag, irec);
+	fa = xfs_inobt_check_irec(to_perag(cur->bc_group), irec);
 	if (fa)
 		return xfs_inobt_complain_bad_rec(cur, fa, irec);
 
@@ -275,8 +275,10 @@ xfs_check_agi_freecount(
 			}
 		} while (i == 1);
 
-		if (!xfs_is_shutdown(cur->bc_mp))
-			ASSERT(freecount == cur->bc_ag.pag->pagi_freecount);
+		if (!xfs_is_shutdown(cur->bc_mp)) {
+			ASSERT(freecount ==
+				to_perag(cur->bc_group)->pagi_freecount);
+		}
 	}
 	return 0;
 }
@@ -2880,7 +2882,7 @@ xfs_ialloc_count_inodes_rec(
 	xfs_failaddr_t			fa;
 
 	xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec);
-	fa = xfs_inobt_check_irec(cur->bc_ag.pag, &irec);
+	fa = xfs_inobt_check_irec(to_perag(cur->bc_group), &irec);
 	if (fa)
 		return xfs_inobt_complain_bad_rec(cur, fa, &irec);
 
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 91d44be2ce48..4c28deb3e988 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -37,7 +37,7 @@ STATIC struct xfs_btree_cur *
 xfs_inobt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
-	return xfs_inobt_init_cursor(cur->bc_ag.pag, cur->bc_tp,
+	return xfs_inobt_init_cursor(to_perag(cur->bc_group), cur->bc_tp,
 			cur->bc_ag.agbp);
 }
 
@@ -45,7 +45,7 @@ STATIC struct xfs_btree_cur *
 xfs_finobt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
-	return xfs_finobt_init_cursor(cur->bc_ag.pag, cur->bc_tp,
+	return xfs_finobt_init_cursor(to_perag(cur->bc_group), cur->bc_tp,
 			cur->bc_ag.agbp);
 }
 
@@ -112,7 +112,7 @@ __xfs_inobt_alloc_block(
 	memset(&args, 0, sizeof(args));
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
-	args.pag = cur->bc_ag.pag;
+	args.pag = to_perag(cur->bc_group);
 	args.oinfo = XFS_RMAP_OINFO_INOBT;
 	args.minlen = 1;
 	args.maxlen = 1;
@@ -248,7 +248,7 @@ xfs_inobt_init_ptr_from_cur(
 {
 	struct xfs_agi		*agi = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agi->agi_seqno));
+	ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agi->agi_seqno));
 
 	ptr->s = agi->agi_root;
 }
@@ -260,7 +260,8 @@ xfs_finobt_init_ptr_from_cur(
 {
 	struct xfs_agi		*agi = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agi->agi_seqno));
+	ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agi->agi_seqno));
+
 	ptr->s = agi->agi_free_root;
 }
 
@@ -483,7 +484,7 @@ xfs_inobt_init_cursor(
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_inobt_ops,
 			M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache);
-	cur->bc_ag.pag = xfs_perag_hold(pag);
+	cur->bc_group = xfs_group_hold(pag_group(pag));
 	cur->bc_ag.agbp = agbp;
 	if (agbp) {
 		struct xfs_agi		*agi = agbp->b_addr;
@@ -509,7 +510,7 @@ xfs_finobt_init_cursor(
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_finobt_ops,
 			M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache);
-	cur->bc_ag.pag = xfs_perag_hold(pag);
+	cur->bc_group = xfs_group_hold(pag_group(pag));
 	cur->bc_ag.agbp = agbp;
 	if (agbp) {
 		struct xfs_agi		*agi = agbp->b_addr;
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index b8789c42c230..ed943f6e616d 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -154,7 +154,7 @@ xfs_refcount_complain_bad_rec(
 
 	xfs_warn(mp,
  "Refcount BTree record corruption in AG %d detected at %pS!",
-				pag_agno(cur->bc_ag.pag), fa);
+				cur->bc_group->xg_gno, fa);
 	xfs_warn(mp,
 		"Start block 0x%x, block count 0x%x, references 0x%x",
 		irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
@@ -180,7 +180,7 @@ xfs_refcount_get_rec(
 		return error;
 
 	xfs_refcount_btrec_to_irec(rec, irec);
-	fa = xfs_refcount_check_irec(cur->bc_ag.pag, irec);
+	fa = xfs_refcount_check_irec(to_perag(cur->bc_group), irec);
 	if (fa)
 		return xfs_refcount_complain_bad_rec(cur, fa, irec);
 
@@ -1154,7 +1154,7 @@ xfs_refcount_adjust_extents(
 					goto out_error;
 				}
 			} else {
-				fsbno = xfs_agbno_to_fsb(cur->bc_ag.pag,
+				fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group),
 						tmp.rc_startblock);
 				error = xfs_free_extent_later(cur->bc_tp, fsbno,
 						  tmp.rc_blockcount, NULL,
@@ -1216,7 +1216,7 @@ xfs_refcount_adjust_extents(
 			}
 			goto advloop;
 		} else {
-			fsbno = xfs_agbno_to_fsb(cur->bc_ag.pag,
+			fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group),
 					ext.rc_startblock);
 			error = xfs_free_extent_later(cur->bc_tp, fsbno,
 					ext.rc_blockcount, NULL,
@@ -1310,7 +1310,7 @@ xfs_refcount_continue_op(
 	xfs_agblock_t			new_agbno)
 {
 	struct xfs_mount		*mp = cur->bc_mp;
-	struct xfs_perag		*pag = cur->bc_ag.pag;
+	struct xfs_perag		*pag = to_perag(cur->bc_group);
 
 	if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno,
 					ri->ri_blockcount))) {
@@ -1358,7 +1358,7 @@ xfs_refcount_finish_one(
 	 * If we haven't gotten a cursor or the cursor AG doesn't match
 	 * the startblock, get one now.
 	 */
-	if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) {
+	if (rcur != NULL && to_perag(rcur->bc_group) != ri->ri_pag) {
 		nr_ops = rcur->bc_refc.nr_ops;
 		shape_changes = rcur->bc_refc.shape_changes;
 		xfs_btree_del_cursor(rcur, 0);
@@ -1878,7 +1878,8 @@ xfs_refcount_recover_extent(
 	INIT_LIST_HEAD(&rr->rr_list);
 	xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
 
-	if (xfs_refcount_check_irec(cur->bc_ag.pag, &rr->rr_rrec) != NULL ||
+	if (xfs_refcount_check_irec(to_perag(cur->bc_group), &rr->rr_rrec) !=
+			NULL ||
 	    XFS_IS_CORRUPT(cur->bc_mp,
 			   rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
 		xfs_btree_mark_sick(cur);
@@ -2026,7 +2027,7 @@ xfs_refcount_query_range_helper(
 	xfs_failaddr_t			fa;
 
 	xfs_refcount_btrec_to_irec(rec, &irec);
-	fa = xfs_refcount_check_irec(cur->bc_ag.pag, &irec);
+	fa = xfs_refcount_check_irec(to_perag(cur->bc_group), &irec);
 	if (fa)
 		return xfs_refcount_complain_bad_rec(cur, fa, &irec);
 
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index db389fdbd929..54505fee1852 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -30,7 +30,7 @@ xfs_refcountbt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_refcountbt_init_cursor(cur->bc_mp, cur->bc_tp,
-			cur->bc_ag.agbp, cur->bc_ag.pag);
+			cur->bc_ag.agbp, to_perag(cur->bc_group));
 }
 
 STATIC void
@@ -68,7 +68,7 @@ xfs_refcountbt_alloc_block(
 	memset(&args, 0, sizeof(args));
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
-	args.pag = cur->bc_ag.pag;
+	args.pag = to_perag(cur->bc_group);
 	args.oinfo = XFS_RMAP_OINFO_REFC;
 	args.minlen = args.maxlen = args.prod = 1;
 	args.resv = XFS_AG_RESV_METADATA;
@@ -81,7 +81,7 @@ xfs_refcountbt_alloc_block(
 		*stat = 0;
 		return 0;
 	}
-	ASSERT(args.agno == pag_agno(cur->bc_ag.pag));
+	ASSERT(args.agno == cur->bc_group->xg_gno);
 	ASSERT(args.len == 1);
 
 	new->s = cpu_to_be32(args.agbno);
@@ -169,7 +169,7 @@ xfs_refcountbt_init_ptr_from_cur(
 {
 	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agf->agf_seqno));
+	ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno));
 
 	ptr->s = agf->agf_refcount_root;
 }
@@ -365,7 +365,7 @@ xfs_refcountbt_init_cursor(
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_refcountbt_ops,
 			mp->m_refc_maxlevels, xfs_refcountbt_cur_cache);
-	cur->bc_ag.pag = xfs_perag_hold(pag);
+	cur->bc_group = xfs_group_hold(pag_group(pag));
 	cur->bc_refc.nr_ops = 0;
 	cur->bc_refc.shape_changes = 0;
 	cur->bc_ag.agbp = agbp;
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 984120b128fb..0c4046259861 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -269,9 +269,7 @@ xfs_rmap_check_btrec(
 	struct xfs_btree_cur		*cur,
 	const struct xfs_rmap_irec	*irec)
 {
-	if (xfs_btree_is_mem_rmap(cur->bc_ops))
-		return xfs_rmap_check_irec(cur->bc_mem.pag, irec);
-	return xfs_rmap_check_irec(cur->bc_ag.pag, irec);
+	return xfs_rmap_check_irec(to_perag(cur->bc_group), irec);
 }
 
 static inline int
@@ -288,7 +286,7 @@ xfs_rmap_complain_bad_rec(
 	else
 		xfs_warn(mp,
  "Reverse Mapping BTree record corruption in AG %d detected at %pS!",
-			pag_agno(cur->bc_ag.pag), fa);
+			cur->bc_group->xg_gno, fa);
 	xfs_warn(mp,
 		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
 		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
@@ -2588,7 +2586,7 @@ xfs_rmap_finish_one(
 	 * If we haven't gotten a cursor or the cursor AG doesn't match
 	 * the startblock, get one now.
 	 */
-	if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) {
+	if (rcur != NULL && to_perag(rcur->bc_group) != ri->ri_pag) {
 		xfs_btree_del_cursor(rcur, 0);
 		rcur = NULL;
 		*pcur = NULL;
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index b37eaf37c7fd..2cab694ac58a 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -57,7 +57,7 @@ xfs_rmapbt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_rmapbt_init_cursor(cur->bc_mp, cur->bc_tp,
-				cur->bc_ag.agbp, cur->bc_ag.pag);
+				cur->bc_ag.agbp, to_perag(cur->bc_group));
 }
 
 STATIC void
@@ -66,14 +66,15 @@ xfs_rmapbt_set_root(
 	const union xfs_btree_ptr	*ptr,
 	int				inc)
 {
-	struct xfs_buf		*agbp = cur->bc_ag.agbp;
-	struct xfs_agf		*agf = agbp->b_addr;
+	struct xfs_buf			*agbp = cur->bc_ag.agbp;
+	struct xfs_agf			*agf = agbp->b_addr;
+	struct xfs_perag		*pag = to_perag(cur->bc_group);
 
 	ASSERT(ptr->s != 0);
 
 	agf->agf_rmap_root = ptr->s;
 	be32_add_cpu(&agf->agf_rmap_level, inc);
-	cur->bc_ag.pag->pagf_rmap_level += inc;
+	pag->pagf_rmap_level += inc;
 
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
 }
@@ -87,7 +88,7 @@ xfs_rmapbt_alloc_block(
 {
 	struct xfs_buf		*agbp = cur->bc_ag.agbp;
 	struct xfs_agf		*agf = agbp->b_addr;
-	struct xfs_perag	*pag = cur->bc_ag.pag;
+	struct xfs_perag	*pag = to_perag(cur->bc_group);
 	struct xfs_alloc_arg    args = { .len = 1 };
 	int			error;
 	xfs_agblock_t		bno;
@@ -125,7 +126,7 @@ xfs_rmapbt_free_block(
 {
 	struct xfs_buf		*agbp = cur->bc_ag.agbp;
 	struct xfs_agf		*agf = agbp->b_addr;
-	struct xfs_perag	*pag = cur->bc_ag.pag;
+	struct xfs_perag	*pag = to_perag(cur->bc_group);
 	xfs_agblock_t		bno;
 	int			error;
 
@@ -227,7 +228,7 @@ xfs_rmapbt_init_ptr_from_cur(
 {
 	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(pag_agno(cur->bc_ag.pag) == be32_to_cpu(agf->agf_seqno));
+	ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno));
 
 	ptr->s = agf->agf_rmap_root;
 }
@@ -538,7 +539,7 @@ xfs_rmapbt_init_cursor(
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rmapbt_ops,
 			mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
-	cur->bc_ag.pag = xfs_perag_hold(pag);
+	cur->bc_group = xfs_group_hold(pag_group(pag));
 	cur->bc_ag.agbp = agbp;
 	if (agbp) {
 		struct xfs_agf		*agf = agbp->b_addr;
@@ -653,7 +654,7 @@ xfs_rmapbt_mem_cursor(
 	cur->bc_mem.xfbtree = xfbt;
 	cur->bc_nlevels = xfbt->nlevels;
 
-	cur->bc_mem.pag = xfs_perag_hold(pag);
+	cur->bc_group = xfs_group_hold(pag_group(pag));
 	return cur;
 }
 
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index d1b8a4997dd2..8b282138097f 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -139,7 +139,7 @@ xchk_allocbt_rec(
 	struct xchk_alloc	*ca = bs->private;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	if (xfs_alloc_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
+	if (xfs_alloc_check_irec(to_perag(bs->cur->bc_group), &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index fb022b403716..64168f2e4222 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -601,7 +601,8 @@ xchk_bmap_check_rmap(
 			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					check_rec.rm_offset);
 		if (irec.br_startblock !=
-		    xfs_agbno_to_fsb(cur->bc_ag.pag, check_rec.rm_startblock))
+		    xfs_agbno_to_fsb(to_perag(cur->bc_group),
+				check_rec.rm_startblock))
 			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					check_rec.rm_offset);
 		if (irec.br_blockcount > check_rec.rm_blockcount)
diff --git a/fs/xfs/scrub/bmap_repair.c b/fs/xfs/scrub/bmap_repair.c
index be408e50484b..7c4955482641 100644
--- a/fs/xfs/scrub/bmap_repair.c
+++ b/fs/xfs/scrub/bmap_repair.c
@@ -196,7 +196,7 @@ xrep_bmap_check_fork_rmap(
 		return -EFSCORRUPTED;
 
 	/* Check that this is within the AG. */
-	if (!xfs_verify_agbext(cur->bc_ag.pag, rec->rm_startblock,
+	if (!xfs_verify_agbext(to_perag(cur->bc_group), rec->rm_startblock,
 				rec->rm_blockcount))
 		return -EFSCORRUPTED;
 
@@ -268,7 +268,7 @@ xrep_bmap_walk_rmap(
 	if ((rec->rm_flags & XFS_RMAP_UNWRITTEN) && !rb->allow_unwritten)
 		return -EFSCORRUPTED;
 
-	fsbno = xfs_agbno_to_fsb(cur->bc_ag.pag, rec->rm_startblock);
+	fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group), rec->rm_startblock);
 
 	if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK) {
 		rb->old_bmbt_block_count += rec->rm_blockcount;
diff --git a/fs/xfs/scrub/cow_repair.c b/fs/xfs/scrub/cow_repair.c
index 19bded43c4fe..5b6194cef3e5 100644
--- a/fs/xfs/scrub/cow_repair.c
+++ b/fs/xfs/scrub/cow_repair.c
@@ -145,7 +145,8 @@ xrep_cow_mark_shared_staging(
 	xrep_cow_trim_refcount(xc, &rrec, rec);
 
 	return xrep_cow_mark_file_range(xc,
-			xfs_agbno_to_fsb(cur->bc_ag.pag, rrec.rc_startblock),
+			xfs_agbno_to_fsb(to_perag(cur->bc_group),
+				rrec.rc_startblock),
 			rrec.rc_blockcount);
 }
 
@@ -176,8 +177,9 @@ xrep_cow_mark_missing_staging(
 	if (xc->next_bno >= rrec.rc_startblock)
 		goto next;
 
+
 	error = xrep_cow_mark_file_range(xc,
-			xfs_agbno_to_fsb(cur->bc_ag.pag, xc->next_bno),
+			xfs_agbno_to_fsb(to_perag(cur->bc_group), xc->next_bno),
 			rrec.rc_startblock - xc->next_bno);
 	if (error)
 		return error;
@@ -220,7 +222,8 @@ xrep_cow_mark_missing_staging_rmap(
 	}
 
 	return xrep_cow_mark_file_range(xc,
-			xfs_agbno_to_fsb(cur->bc_ag.pag, rec_bno), rec_len);
+			xfs_agbno_to_fsb(to_perag(cur->bc_group), rec_bno),
+			rec_len);
 }
 
 /*
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index fce04444c37c..6ceef3749e3b 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -276,7 +276,7 @@ xchk_ag_btree_del_cursor_if_sick(
 	    type_to_health_flag[sc->sm->sm_type].group == XHG_AG)
 		mask &= ~sc->sick_mask;
 
-	if (xfs_ag_has_sickness((*curp)->bc_ag.pag, mask)) {
+	if (xfs_group_has_sickness((*curp)->bc_group, mask)) {
 		sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XFAIL;
 		xfs_btree_del_cursor(*curp, XFS_BTREE_NOERROR);
 		*curp = NULL;
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index ee71cf2050b7..abad54c3621d 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -258,7 +258,7 @@ xchk_iallocbt_chunk(
 {
 	struct xfs_scrub		*sc = bs->sc;
 	struct xfs_mount		*mp = bs->cur->bc_mp;
-	struct xfs_perag		*pag = bs->cur->bc_ag.pag;
+	struct xfs_perag		*pag = to_perag(bs->cur->bc_group);
 	xfs_agblock_t			agbno;
 	xfs_extlen_t			len;
 
@@ -318,7 +318,7 @@ xchk_iallocbt_check_cluster_ifree(
 	 * the record, compute which fs inode we're talking about.
 	 */
 	agino = irec->ir_startino + irec_ino;
-	fsino = xfs_agino_to_ino(bs->cur->bc_ag.pag, agino);
+	fsino = xfs_agino_to_ino(to_perag(bs->cur->bc_group), agino);
 	irec_free = (irec->ir_free & XFS_INOBT_MASK(irec_ino));
 
 	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
@@ -394,7 +394,7 @@ xchk_iallocbt_check_cluster(
 	 * ir_startino can be large enough to make im_boffset nonzero.
 	 */
 	ir_holemask = (irec->ir_holemask & cluster_mask);
-	imap.im_blkno = xfs_agbno_to_daddr(bs->cur->bc_ag.pag, agbno);
+	imap.im_blkno = xfs_agbno_to_daddr(to_perag(bs->cur->bc_group), agbno);
 	imap.im_len = XFS_FSB_TO_BB(mp, M_IGEO(mp)->blocks_per_cluster);
 	imap.im_boffset = XFS_INO_TO_OFFSET(mp, irec->ir_startino) <<
 			mp->m_sb.sb_inodelog;
@@ -405,9 +405,9 @@ xchk_iallocbt_check_cluster(
 		return 0;
 	}
 
-	trace_xchk_iallocbt_check_cluster(bs->cur->bc_ag.pag, irec->ir_startino,
-			imap.im_blkno, imap.im_len, cluster_base, nr_inodes,
-			cluster_mask, ir_holemask,
+	trace_xchk_iallocbt_check_cluster(to_perag(bs->cur->bc_group),
+			irec->ir_startino, imap.im_blkno, imap.im_len,
+			cluster_base, nr_inodes, cluster_mask, ir_holemask,
 			XFS_INO_TO_OFFSET(mp, irec->ir_startino +
 					  cluster_base));
 
@@ -583,7 +583,7 @@ xchk_iallocbt_rec(
 	uint16_t			holemask;
 
 	xfs_inobt_btrec_to_irec(mp, rec, &irec);
-	if (xfs_inobt_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
+	if (xfs_inobt_check_irec(to_perag(bs->cur->bc_group), &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index d0c7d4a29c0f..2b6be75e9424 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -453,7 +453,8 @@ xchk_refcountbt_rec(
 	struct xchk_refcbt_records *rrc = bs->private;
 
 	xfs_refcount_btrec_to_irec(rec, &irec);
-	if (xfs_refcount_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
+	if (xfs_refcount_check_irec(to_perag(bs->cur->bc_group), &irec) !=
+			NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 26b5c90b3f6a..39e9ad7cd8ae 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -358,7 +358,7 @@ xchk_rmapbt_rec(
 	struct xfs_rmap_irec	irec;
 
 	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL ||
-	    xfs_rmap_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
+	    xfs_rmap_check_irec(to_perag(bs->cur->bc_group), &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index 6c420ec7dacd..a0a227d183d2 100644
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -622,7 +622,7 @@ xrep_rmap_walk_inobt(
 		return error;
 
 	xfs_inobt_btrec_to_irec(mp, rec, &irec);
-	if (xfs_inobt_check_irec(cur->bc_ag.pag, &irec) != NULL)
+	if (xfs_inobt_check_irec(to_perag(cur->bc_group), &irec) != NULL)
 		return -EFSCORRUPTED;
 
 	agino = irec.ir_startino;
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index a26fb054346b..5d5e54a16f23 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -394,7 +394,8 @@ xfs_getfsmap_datadev_helper(
 	struct xfs_getfsmap_info	*info = priv;
 
 	return xfs_getfsmap_helper(cur->bc_tp, info, rec,
-			xfs_agbno_to_daddr(cur->bc_ag.pag, rec->rm_startblock),
+			xfs_agbno_to_daddr(to_perag(cur->bc_group),
+				rec->rm_startblock),
 			0);
 }
 
@@ -415,7 +416,8 @@ xfs_getfsmap_datadev_bnobt_helper(
 	irec.rm_flags = 0;
 
 	return xfs_getfsmap_helper(cur->bc_tp, info, &irec,
-			xfs_agbno_to_daddr(cur->bc_ag.pag, rec->ar_startblock),
+			xfs_agbno_to_daddr(to_perag(cur->bc_group),
+				rec->ar_startblock),
 			0);
 }
 
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 732246f46680..f45f125a669d 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -531,24 +531,13 @@ void
 xfs_btree_mark_sick(
 	struct xfs_btree_cur		*cur)
 {
-	switch (cur->bc_ops->type) {
-	case XFS_BTREE_TYPE_MEM:
-		/* no health state tracking for ephemeral btrees */
-		return;
-	case XFS_BTREE_TYPE_AG:
+	if (xfs_btree_is_bmap(cur->bc_ops)) {
+		xfs_bmap_mark_sick(cur->bc_ino.ip, cur->bc_ino.whichfork);
+	/* no health state tracking for ephemeral btrees */
+	} else if (cur->bc_ops->type != XFS_BTREE_TYPE_MEM) {
+		ASSERT(cur->bc_group);
 		ASSERT(cur->bc_ops->sick_mask);
-		xfs_ag_mark_sick(cur->bc_ag.pag, cur->bc_ops->sick_mask);
-		return;
-	case XFS_BTREE_TYPE_INODE:
-		if (xfs_btree_is_bmap(cur->bc_ops)) {
-			xfs_bmap_mark_sick(cur->bc_ino.ip,
-					   cur->bc_ino.whichfork);
-			return;
-		}
-		fallthrough;
-	default:
-		ASSERT(0);
-		return;
+		xfs_group_mark_sick(cur->bc_group, cur->bc_ops->sick_mask);
 	}
 }
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 562e0ad1c6cf..8aa6af5c9c01 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2588,7 +2588,7 @@ TRACE_EVENT(xfs_btree_alloc_block,
 			__entry->ino = cur->bc_ino.ip->i_ino;
 			break;
 		case XFS_BTREE_TYPE_AG:
-			__entry->agno = pag_agno(cur->bc_ag.pag);
+			__entry->agno = cur->bc_group->xg_gno;
 			__entry->ino = 0;
 			break;
 		case XFS_BTREE_TYPE_MEM:
@@ -2844,7 +2844,7 @@ DECLARE_EVENT_CLASS(xfs_rmap_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->owner = oinfo->oi_owner;
@@ -2889,7 +2889,7 @@ DECLARE_EVENT_CLASS(xfs_btree_error_class,
 			__entry->ino = cur->bc_ino.ip->i_ino;
 			break;
 		case XFS_BTREE_TYPE_AG:
-			__entry->agno = pag_agno(cur->bc_ag.pag);
+			__entry->agno = cur->bc_group->xg_gno;
 			__entry->ino = 0;
 			break;
 		case XFS_BTREE_TYPE_MEM:
@@ -2943,7 +2943,7 @@ TRACE_EVENT(xfs_rmap_convert_state,
 			__entry->ino = cur->bc_ino.ip->i_ino;
 			break;
 		case XFS_BTREE_TYPE_AG:
-			__entry->agno = pag_agno(cur->bc_ag.pag);
+			__entry->agno = cur->bc_group->xg_gno;
 			__entry->ino = 0;
 			break;
 		case XFS_BTREE_TYPE_MEM:
@@ -2978,7 +2978,7 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->owner = owner;
@@ -3222,7 +3222,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 	),
@@ -3253,7 +3253,7 @@ TRACE_EVENT(xfs_refcount_lookup,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->agbno = agbno;
 		__entry->dir = dir;
 	),
@@ -3279,7 +3279,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->domain = irec->rc_domain;
 		__entry->startblock = irec->rc_startblock;
 		__entry->blockcount = irec->rc_blockcount;
@@ -3315,7 +3315,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->domain = irec->rc_domain;
 		__entry->startblock = irec->rc_startblock;
 		__entry->blockcount = irec->rc_blockcount;
@@ -3357,7 +3357,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
@@ -3407,7 +3407,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
@@ -3462,7 +3462,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
@@ -4352,7 +4352,7 @@ TRACE_EVENT(xfs_btree_commit_afakeroot,
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
 		__assign_str(name);
-		__entry->agno = pag_agno(cur->bc_ag.pag);
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->agbno = cur->bc_ag.afake->af_root;
 		__entry->levels = cur->bc_ag.afake->af_levels;
 		__entry->blocks = cur->bc_ag.afake->af_blocks;
@@ -4467,7 +4467,7 @@ TRACE_EVENT(xfs_btree_bload_block,
 			__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsb);
 			__entry->agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsb);
 		} else {
-			__entry->agno = pag_agno(cur->bc_ag.pag);
+			__entry->agno = cur->bc_group->xg_gno;
 			__entry->agbno = be32_to_cpu(ptr->s);
 		}
 		__entry->nr_records = nr_records;

From 198febb9fe653503f94edc080529fa9e1e22d359 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:45 -0800
Subject: [PATCH 13/16] xfs: store a generic xfs_group pointer in
 xfs_getfsmap_info

Replace the pag and rtg pointers with a generic group pointer.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_fsmap.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 5d5e54a16f23..a91677ac54e7 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -158,7 +158,7 @@ struct xfs_getfsmap_info {
 	struct xfs_fsmap_head	*head;
 	struct fsmap		*fsmap_recs;	/* mapping records */
 	struct xfs_buf		*agf_bp;	/* AGF, for refcount queries */
-	struct xfs_perag	*pag;		/* AG info, if applicable */
+	struct xfs_group	*group;		/* group info, if applicable */
 	xfs_daddr_t		next_daddr;	/* next daddr we expect */
 	/* daddr of low fsmap key when we're using the rtbitmap */
 	xfs_daddr_t		low_daddr;
@@ -216,12 +216,13 @@ xfs_getfsmap_is_shared(
 	if (!xfs_has_reflink(mp))
 		return 0;
 	/* rt files will have no perag structure */
-	if (!info->pag)
+	if (!info->group)
 		return 0;
 
 	/* Are there any shared blocks here? */
 	flen = 0;
-	cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp, info->pag);
+	cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp,
+			to_perag(info->group));
 
 	error = xfs_refcount_find_shared(cur, rec->rm_startblock,
 			rec->rm_blockcount, &fbno, &flen, false);
@@ -353,7 +354,8 @@ xfs_getfsmap_helper(
 		return -ECANCELED;
 
 	trace_xfs_fsmap_mapping(mp, info->dev,
-			info->pag ? pag_agno(info->pag) : NULLAGNUMBER, rec);
+			info->group ? info->group->xg_gno : NULLAGNUMBER,
+			rec);
 
 	fmr.fmr_device = info->dev;
 	fmr.fmr_physical = rec_daddr;
@@ -519,7 +521,7 @@ __xfs_getfsmap_datadev(
 		 * Set the AG high key from the fsmap high key if this
 		 * is the last AG that we're querying.
 		 */
-		info->pag = pag;
+		info->group = pag_group(pag);
 		if (pag_agno(pag) == end_ag) {
 			info->high.rm_startblock = XFS_FSB_TO_AGBNO(mp,
 					end_fsb);
@@ -569,7 +571,7 @@ __xfs_getfsmap_datadev(
 			if (error)
 				break;
 		}
-		info->pag = NULL;
+		info->group = NULL;
 	}
 
 	if (bt_cur)
@@ -579,9 +581,9 @@ __xfs_getfsmap_datadev(
 		xfs_trans_brelse(tp, info->agf_bp);
 		info->agf_bp = NULL;
 	}
-	if (info->pag) {
-		xfs_perag_rele(info->pag);
-		info->pag = NULL;
+	if (info->group) {
+		xfs_perag_rele(pag);
+		info->group = NULL;
 	} else if (pag) {
 		/* loop termination case */
 		xfs_perag_rele(pag);
@@ -604,7 +606,7 @@ xfs_getfsmap_datadev_rmapbt_query(
 
 	/* Allocate cursor for this AG and query_range it. */
 	*curpp = xfs_rmapbt_init_cursor(tp->t_mountp, tp, info->agf_bp,
-			info->pag);
+			to_perag(info->group));
 	return xfs_rmap_query_range(*curpp, &info->low, &info->high,
 			xfs_getfsmap_datadev_helper, info);
 }
@@ -637,7 +639,7 @@ xfs_getfsmap_datadev_bnobt_query(
 
 	/* Allocate cursor for this AG and query_range it. */
 	*curpp = xfs_bnobt_init_cursor(tp->t_mountp, tp, info->agf_bp,
-			info->pag);
+			to_perag(info->group));
 	key->ar_startblock = info->low.rm_startblock;
 	key[1].ar_startblock = info->high.rm_startblock;
 	return xfs_alloc_query_range(*curpp, key, &key[1],
@@ -997,7 +999,7 @@ xfs_getfsmap(
 
 		info.dev = handlers[i].dev;
 		info.last = false;
-		info.pag = NULL;
+		info.group = NULL;
 		info.low_daddr = XFS_BUF_DADDR_NULL;
 		info.low.rm_blockcount = 0;
 		error = handlers[i].fn(tp, dkeys, &info);

From 759cc1989a53024066b0f2ea52c206b4ff8f522c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:45 -0800
Subject: [PATCH 14/16] xfs: add group based bno conversion helpers

Add/move the blocks, blklog and blkmask fields to the generic groups
structure so that code can work with AGs and RTGs by just using the
right index into the array.

Then, add convenience helpers to convert block numbers based on the
generic group.  This will allow writing code that doesn't care if it is
used on AGs or the upcoming realtime groups.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_group.c |  9 +++++++
 fs/xfs/libxfs/xfs_group.h | 56 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_sb.c    |  7 +++++
 fs/xfs/xfs_mount.h        | 30 +++++++++++++++++++++
 4 files changed, 102 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c
index 5c6fa5d76a91..e9d76bcdc820 100644
--- a/fs/xfs/libxfs/xfs_group.c
+++ b/fs/xfs/libxfs/xfs_group.c
@@ -214,3 +214,12 @@ xfs_group_insert(
 #endif
 	return error;
 }
+
+struct xfs_group *
+xfs_group_get_by_fsb(
+	struct xfs_mount	*mp,
+	xfs_fsblock_t		fsbno,
+	enum xfs_group_type	type)
+{
+	return xfs_group_get(mp, xfs_fsb_to_gno(mp, fsbno, type), type);
+}
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index 0ff6e1d5635c..5b7362277c3f 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -46,6 +46,8 @@ struct xfs_group {
 
 struct xfs_group *xfs_group_get(struct xfs_mount *mp, uint32_t index,
 		enum xfs_group_type type);
+struct xfs_group *xfs_group_get_by_fsb(struct xfs_mount *mp,
+		xfs_fsblock_t fsbno, enum xfs_group_type type);
 struct xfs_group *xfs_group_hold(struct xfs_group *xg);
 void xfs_group_put(struct xfs_group *xg);
 
@@ -72,4 +74,58 @@ int xfs_group_insert(struct xfs_mount *mp, struct xfs_group *xg,
 #define xfs_group_marked(_mp, _type, _mark) \
 	xa_marked(&(_mp)->m_groups[(_type)].xa, (_mark))
 
+static inline xfs_agblock_t
+xfs_group_max_blocks(
+	struct xfs_group	*xg)
+{
+	return xg->xg_mount->m_groups[xg->xg_type].blocks;
+}
+
+static inline xfs_fsblock_t
+xfs_group_start_fsb(
+	struct xfs_group	*xg)
+{
+	return ((xfs_fsblock_t)xg->xg_gno) <<
+		xg->xg_mount->m_groups[xg->xg_type].blklog;
+}
+
+static inline xfs_fsblock_t
+xfs_gbno_to_fsb(
+	struct xfs_group	*xg,
+	xfs_agblock_t		gbno)
+{
+	return xfs_group_start_fsb(xg) | gbno;
+}
+
+static inline xfs_daddr_t
+xfs_gbno_to_daddr(
+	struct xfs_group	*xg,
+	xfs_agblock_t		gbno)
+{
+	struct xfs_mount	*mp = xg->xg_mount;
+	uint32_t		blocks = mp->m_groups[xg->xg_type].blocks;
+
+	return XFS_FSB_TO_BB(mp, (xfs_fsblock_t)xg->xg_gno * blocks + gbno);
+}
+
+static inline uint32_t
+xfs_fsb_to_gno(
+	struct xfs_mount	*mp,
+	xfs_fsblock_t		fsbno,
+	enum xfs_group_type	type)
+{
+	if (!mp->m_groups[type].blklog)
+		return 0;
+	return fsbno >> mp->m_groups[type].blklog;
+}
+
+static inline xfs_agblock_t
+xfs_fsb_to_gbno(
+	struct xfs_mount	*mp,
+	xfs_fsblock_t		fsbno,
+	enum xfs_group_type	type)
+{
+	return fsbno & mp->m_groups[type].blkmask;
+}
+
 #endif /* __LIBXFS_GROUP_H */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 061c8c961d5b..f7a07e61341d 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -988,6 +988,8 @@ xfs_sb_mount_common(
 	struct xfs_mount	*mp,
 	struct xfs_sb		*sbp)
 {
+	struct xfs_groups	*ags = &mp->m_groups[XG_TYPE_AG];
+
 	mp->m_agfrotor = 0;
 	atomic_set(&mp->m_agirotor, 0);
 	mp->m_maxagi = mp->m_sb.sb_agcount;
@@ -998,6 +1000,11 @@ xfs_sb_mount_common(
 	mp->m_blockmask = sbp->sb_blocksize - 1;
 	mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
 	mp->m_blockwmask = mp->m_blockwsize - 1;
+
+	ags->blocks = mp->m_sb.sb_agblocks;
+	ags->blklog = mp->m_sb.sb_agblklog;
+	ags->blkmask = xfs_mask32lo(mp->m_sb.sb_agblklog);
+
 	xfs_mount_sb_set_rextsize(mp, sbp);
 
 	mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, true);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 530d7f025506..1b698878f40c 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -71,8 +71,38 @@ struct xfs_inodegc {
 	unsigned int		cpu;
 };
 
+/*
+ * Container for each type of groups, used to look up individual groups and
+ * describes the geometry.
+ */
 struct xfs_groups {
 	struct xarray		xa;
+
+	/*
+	 * Maximum capacity of the group in FSBs.
+	 *
+	 * Each group is laid out densely in the daddr space.  For the
+	 * degenerate case of a pre-rtgroups filesystem, the incore rtgroup
+	 * pretends to have a zero-block and zero-blklog rtgroup.
+	 */
+	uint32_t		blocks;
+
+	/*
+	 * Log(2) of the logical size of each group.
+	 *
+	 * Compared to the blocks field above this is rounded up to the next
+	 * power of two, and thus lays out the xfs_fsblock_t/xfs_rtblock_t
+	 * space sparsely with a hole from blocks to (1 << blklog) at the end
+	 * of each group.
+	 */
+	uint8_t			blklog;
+
+	/*
+	 * Mask to extract the group-relative block number from a FSB.
+	 * For a pre-rtgroups filesystem we pretend to have one very large
+	 * rtgroup, so this mask must be 64-bit.
+	 */
+	uint64_t		blkmask;
 };
 
 /*

From ba102a682d9336a9414968133695764a3d9352d1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:46 -0800
Subject: [PATCH 15/16] xfs: remove xfs_group_intent_hold and
 xfs_group_intent_rele

Each of them just has a single caller, so fold them.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_drain.c | 36 +++++++++---------------------------
 1 file changed, 9 insertions(+), 27 deletions(-)

diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c
index a72d08947d6d..7a728a04f7a6 100644
--- a/fs/xfs/xfs_drain.c
+++ b/fs/xfs/xfs_drain.c
@@ -94,31 +94,11 @@ static inline int xfs_defer_drain_wait(struct xfs_defer_drain *dr)
 }
 
 /*
- * Declare an intent to update group metadata.  Other threads that need
- * exclusive access can decide to back off if they see declared intentions.
- */
-static void
-xfs_group_intent_hold(
-	struct xfs_group	*xg)
-{
-	trace_xfs_group_intent_hold(xg, __return_address);
-	xfs_defer_drain_grab(&xg->xg_intents_drain);
-}
-
-/*
- * Release our intent to update this groups metadata.
- */
-static void
-xfs_group_intent_rele(
-	struct xfs_group	*xg)
-{
-	trace_xfs_group_intent_rele(xg, __return_address);
-	xfs_defer_drain_rele(&xg->xg_intents_drain);
-}
-
-/*
- * Get a passive reference to the AG that contains a fsbno and declare an intent
- * to update its metadata.
+ * Get a passive reference to the AG that contains a fsbno and declare an
+ * intent to update its metadata.
+ *
+ * Other threads that need exclusive access can decide to back off if they see
+ * declared intentions.
  */
 struct xfs_perag *
 xfs_perag_intent_get(
@@ -131,7 +111,8 @@ xfs_perag_intent_get(
 	if (!pag)
 		return NULL;
 
-	xfs_group_intent_hold(pag_group(pag));
+	trace_xfs_group_intent_hold(pag_group(pag), __return_address);
+	xfs_defer_drain_grab(pag_group(pag).xg_intents_drain);
 	return pag;
 }
 
@@ -143,7 +124,8 @@ void
 xfs_perag_intent_put(
 	struct xfs_perag	*pag)
 {
-	xfs_group_intent_rele(pag_group(pag));
+	trace_xfs_group_intent_rele(pag_group(pag), __return_address);
+	xfs_defer_drain_rele(pag_group(pag).xg_intents_drain);
 	xfs_perag_put(pag);
 }
 

From e5e5cae05b71aa5b5e291c0e74b4e4d98a0b05d4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Nov 2024 20:18:46 -0800
Subject: [PATCH 16/16] xfs: store a generic group structure in the intents

Replace the pag pointers in the extent free, bmap, rmap and refcount
intent structures with a pointer to the generic group to prepare
for adding intents for realtime groups.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc.h    |  2 +-
 fs/xfs/libxfs/xfs_bmap.h     |  2 +-
 fs/xfs/libxfs/xfs_refcount.c |  9 +++++----
 fs/xfs/libxfs/xfs_refcount.h |  2 +-
 fs/xfs/libxfs/xfs_rmap.c     | 16 +++++++++-------
 fs/xfs/libxfs/xfs_rmap.h     |  2 +-
 fs/xfs/xfs_bmap_item.c       |  5 +++--
 fs/xfs/xfs_drain.c           | 36 ++++++++++++++++++------------------
 fs/xfs/xfs_drain.h           | 12 ++++++------
 fs/xfs/xfs_extfree_item.c    | 14 ++++++++------
 fs/xfs/xfs_refcount_item.c   |  9 +++++----
 fs/xfs/xfs_rmap_item.c       |  9 +++++----
 12 files changed, 63 insertions(+), 55 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 88fbce500118..efbde04fbbb1 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -248,7 +248,7 @@ struct xfs_extent_free_item {
 	uint64_t		xefi_owner;
 	xfs_fsblock_t		xefi_startblock;/* starting fs block number */
 	xfs_extlen_t		xefi_blockcount;/* number of blocks in extent */
-	struct xfs_perag	*xefi_pag;
+	struct xfs_group	*xefi_group;
 	unsigned int		xefi_flags;
 	enum xfs_ag_resv_type	xefi_agresv;
 };
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 7592d46e97c6..4b721d935994 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -248,7 +248,7 @@ struct xfs_bmap_intent {
 	enum xfs_bmap_intent_type		bi_type;
 	int					bi_whichfork;
 	struct xfs_inode			*bi_owner;
-	struct xfs_perag			*bi_pag;
+	struct xfs_group			*bi_group;
 	struct xfs_bmbt_irec			bi_bmap;
 };
 
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index ed943f6e616d..2dbab68b4fe6 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1358,7 +1358,7 @@ xfs_refcount_finish_one(
 	 * If we haven't gotten a cursor or the cursor AG doesn't match
 	 * the startblock, get one now.
 	 */
-	if (rcur != NULL && to_perag(rcur->bc_group) != ri->ri_pag) {
+	if (rcur != NULL && rcur->bc_group != ri->ri_group) {
 		nr_ops = rcur->bc_refc.nr_ops;
 		shape_changes = rcur->bc_refc.shape_changes;
 		xfs_btree_del_cursor(rcur, 0);
@@ -1366,13 +1366,14 @@ xfs_refcount_finish_one(
 		*pcur = NULL;
 	}
 	if (rcur == NULL) {
-		error = xfs_alloc_read_agf(ri->ri_pag, tp,
+		struct xfs_perag	*pag = to_perag(ri->ri_group);
+
+		error = xfs_alloc_read_agf(pag, tp,
 				XFS_ALLOC_FLAG_FREEING, &agbp);
 		if (error)
 			return error;
 
-		*pcur = rcur = xfs_refcountbt_init_cursor(mp, tp, agbp,
-							  ri->ri_pag);
+		*pcur = rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag);
 		rcur->bc_refc.nr_ops = nr_ops;
 		rcur->bc_refc.shape_changes = shape_changes;
 	}
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 68acb0b1b4a8..62d78afcf1f3 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -56,7 +56,7 @@ enum xfs_refcount_intent_type {
 
 struct xfs_refcount_intent {
 	struct list_head			ri_list;
-	struct xfs_perag			*ri_pag;
+	struct xfs_group			*ri_group;
 	enum xfs_refcount_intent_type		ri_type;
 	xfs_extlen_t				ri_blockcount;
 	xfs_fsblock_t				ri_startblock;
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 0c4046259861..d0df68dc3131 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2586,28 +2586,30 @@ xfs_rmap_finish_one(
 	 * If we haven't gotten a cursor or the cursor AG doesn't match
 	 * the startblock, get one now.
 	 */
-	if (rcur != NULL && to_perag(rcur->bc_group) != ri->ri_pag) {
+	if (rcur != NULL && rcur->bc_group != ri->ri_group) {
 		xfs_btree_del_cursor(rcur, 0);
 		rcur = NULL;
 		*pcur = NULL;
 	}
 	if (rcur == NULL) {
+		struct xfs_perag	*pag = to_perag(ri->ri_group);
+
 		/*
 		 * Refresh the freelist before we start changing the
 		 * rmapbt, because a shape change could cause us to
 		 * allocate blocks.
 		 */
-		error = xfs_free_extent_fix_freelist(tp, ri->ri_pag, &agbp);
+		error = xfs_free_extent_fix_freelist(tp, pag, &agbp);
 		if (error) {
-			xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
+			xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
 			return error;
 		}
 		if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) {
-			xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
+			xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
 			return -EFSCORRUPTED;
 		}
 
-		*pcur = rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, ri->ri_pag);
+		*pcur = rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
 	}
 
 	xfs_rmap_ino_owner(&oinfo, ri->ri_owner, ri->ri_whichfork,
@@ -2620,8 +2622,8 @@ xfs_rmap_finish_one(
 	if (error)
 		return error;
 
-	xfs_rmap_update_hook(tp, pag_group(ri->ri_pag), ri->ri_type, bno,
-			     ri->ri_bmap.br_blockcount, unwritten, &oinfo);
+	xfs_rmap_update_hook(tp, ri->ri_group, ri->ri_type, bno,
+			ri->ri_bmap.br_blockcount, unwritten, &oinfo);
 	return 0;
 }
 
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index d409b463bc66..96b4321d8310 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -173,7 +173,7 @@ struct xfs_rmap_intent {
 	int					ri_whichfork;
 	uint64_t				ri_owner;
 	struct xfs_bmbt_irec			ri_bmap;
-	struct xfs_perag			*ri_pag;
+	struct xfs_group			*ri_group;
 };
 
 /* functions for updating the rmapbt based on bmbt map/unmap operations */
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 35a8c1b8b3cb..37dab184c2df 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -334,7 +334,8 @@ xfs_bmap_update_get_group(
 	 * intent drops the intent count, ensuring that the intent count
 	 * remains nonzero across the transaction roll.
 	 */
-	bi->bi_pag = xfs_perag_intent_get(mp, bi->bi_bmap.br_startblock);
+	bi->bi_group = xfs_group_intent_get(mp, bi->bi_bmap.br_startblock,
+			XG_TYPE_AG);
 }
 
 /* Add this deferred BUI to the transaction. */
@@ -368,7 +369,7 @@ xfs_bmap_update_put_group(
 	if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
 		return;
 
-	xfs_perag_intent_put(bi->bi_pag);
+	xfs_group_intent_put(bi->bi_group);
 }
 
 /* Cancel a deferred bmap update. */
diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c
index 7a728a04f7a6..5ede81fadbd8 100644
--- a/fs/xfs/xfs_drain.c
+++ b/fs/xfs/xfs_drain.c
@@ -94,39 +94,39 @@ static inline int xfs_defer_drain_wait(struct xfs_defer_drain *dr)
 }
 
 /*
- * Get a passive reference to the AG that contains a fsbno and declare an
+ * Get a passive reference to the group that contains a fsbno and declare an
  * intent to update its metadata.
  *
  * Other threads that need exclusive access can decide to back off if they see
  * declared intentions.
  */
-struct xfs_perag *
-xfs_perag_intent_get(
+struct xfs_group *
+xfs_group_intent_get(
 	struct xfs_mount	*mp,
-	xfs_fsblock_t		fsbno)
+	xfs_fsblock_t		fsbno,
+	enum xfs_group_type	type)
 {
-	struct xfs_perag	*pag;
+	struct xfs_group	*xg;
 
-	pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, fsbno));
-	if (!pag)
+	xg = xfs_group_get_by_fsb(mp, fsbno, type);
+	if (!xg)
 		return NULL;
-
-	trace_xfs_group_intent_hold(pag_group(pag), __return_address);
-	xfs_defer_drain_grab(pag_group(pag).xg_intents_drain);
-	return pag;
+	trace_xfs_group_intent_hold(xg, __return_address);
+	xfs_defer_drain_grab(&xg->xg_intents_drain);
+	return xg;
 }
 
 /*
- * Release our intent to update this AG's metadata, and then release our
- * passive ref to the AG.
+ * Release our intent to update this groups metadata, and then release our
+ * passive ref to it.
  */
 void
-xfs_perag_intent_put(
-	struct xfs_perag	*pag)
+xfs_group_intent_put(
+	struct xfs_group	*xg)
 {
-	trace_xfs_group_intent_rele(pag_group(pag), __return_address);
-	xfs_defer_drain_rele(pag_group(pag).xg_intents_drain);
-	xfs_perag_put(pag);
+	trace_xfs_group_intent_rele(xg, __return_address);
+	xfs_defer_drain_rele(&xg->xg_intents_drain);
+	xfs_group_put(xg);
 }
 
 /*
diff --git a/fs/xfs/xfs_drain.h b/fs/xfs/xfs_drain.h
index 3e6143572e52..efcf88df9a5e 100644
--- a/fs/xfs/xfs_drain.h
+++ b/fs/xfs/xfs_drain.h
@@ -62,9 +62,9 @@ void xfs_drain_wait_enable(void);
  * soon as the item is added to the transaction and cannot drop the counter
  * until the item is finished or cancelled.
  */
-struct xfs_perag *xfs_perag_intent_get(struct xfs_mount *mp,
-		xfs_fsblock_t fsbno);
-void xfs_perag_intent_put(struct xfs_perag *pag);
+struct xfs_group *xfs_group_intent_get(struct xfs_mount *mp,
+		xfs_fsblock_t fsbno, enum xfs_group_type type);
+void xfs_group_intent_put(struct xfs_group *rtg);
 
 int xfs_group_intent_drain(struct xfs_group *xg);
 bool xfs_group_intent_busy(struct xfs_group *xg);
@@ -75,9 +75,9 @@ struct xfs_defer_drain { /* empty */ };
 #define xfs_defer_drain_free(dr)		((void)0)
 #define xfs_defer_drain_init(dr)		((void)0)
 
-#define xfs_perag_intent_get(mp, fsbno) \
-	xfs_perag_get((mp), XFS_FSB_TO_AGNO(mp, fsbno))
-#define xfs_perag_intent_put(pag)		xfs_perag_put(pag)
+#define xfs_group_intent_get(_mp, _fsbno, _type) \
+	xfs_group_get_by_fsb((_mp), (_fsbno), (_type))
+#define xfs_group_intent_put(xg)		xfs_group_put(xg)
 
 #endif /* CONFIG_XFS_DRAIN_INTENTS */
 
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index c198962edea1..e469510986e8 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -362,7 +362,7 @@ xfs_extent_free_diff_items(
 	struct xfs_extent_free_item	*ra = xefi_entry(a);
 	struct xfs_extent_free_item	*rb = xefi_entry(b);
 
-	return pag_agno(ra->xefi_pag) - pag_agno(rb->xefi_pag);
+	return ra->xefi_group->xg_gno - rb->xefi_group->xg_gno;
 }
 
 /* Log a free extent to the intent item. */
@@ -447,7 +447,8 @@ xfs_extent_free_defer_add(
 
 	trace_xfs_extent_free_defer(mp, xefi);
 
-	xefi->xefi_pag = xfs_perag_intent_get(mp, xefi->xefi_startblock);
+	xefi->xefi_group = xfs_group_intent_get(mp, xefi->xefi_startblock,
+			XG_TYPE_AG);
 	if (xefi->xefi_agresv == XFS_AG_RESV_AGFL)
 		*dfpp = xfs_defer_add(tp, &xefi->xefi_list,
 				&xfs_agfl_free_defer_type);
@@ -463,7 +464,7 @@ xfs_extent_free_cancel_item(
 {
 	struct xfs_extent_free_item	*xefi = xefi_entry(item);
 
-	xfs_perag_intent_put(xefi->xefi_pag);
+	xfs_group_intent_put(xefi->xefi_group);
 	kmem_cache_free(xfs_extfree_item_cache, xefi);
 }
 
@@ -499,7 +500,7 @@ xfs_extent_free_finish_item(
 	 * in this EFI to the EFD so this works correctly.
 	 */
 	if (!(xefi->xefi_flags & XFS_EFI_CANCELLED))
-		error = __xfs_free_extent(tp, xefi->xefi_pag, agbno,
+		error = __xfs_free_extent(tp, to_perag(xefi->xefi_group), agbno,
 				xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv,
 				xefi->xefi_flags & XFS_EFI_SKIP_DISCARD);
 	if (error == -EAGAIN) {
@@ -545,7 +546,7 @@ xfs_agfl_free_finish_item(
 
 	trace_xfs_agfl_free_deferred(mp, xefi);
 
-	error = xfs_alloc_read_agf(xefi->xefi_pag, tp, 0, &agbp);
+	error = xfs_alloc_read_agf(to_perag(xefi->xefi_group), tp, 0, &agbp);
 	if (!error)
 		error = xfs_free_ag_extent(tp, agbp, agbno, 1, &oinfo,
 				XFS_AG_RESV_AGFL);
@@ -578,7 +579,8 @@ xfs_efi_recover_work(
 	xefi->xefi_blockcount = extp->ext_len;
 	xefi->xefi_agresv = XFS_AG_RESV_NONE;
 	xefi->xefi_owner = XFS_RMAP_OWN_UNKNOWN;
-	xefi->xefi_pag = xfs_perag_intent_get(mp, extp->ext_start);
+	xefi->xefi_group = xfs_group_intent_get(mp, extp->ext_start,
+			XG_TYPE_AG);
 
 	xfs_defer_add_item(dfp, &xefi->xefi_list);
 }
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 29f101005f3e..bede1c96c330 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -244,7 +244,7 @@ xfs_refcount_update_diff_items(
 	struct xfs_refcount_intent	*ra = ci_entry(a);
 	struct xfs_refcount_intent	*rb = ci_entry(b);
 
-	return pag_agno(ra->ri_pag) - pag_agno(rb->ri_pag);
+	return ra->ri_group->xg_gno - rb->ri_group->xg_gno;
 }
 
 /* Log refcount updates in the intent item. */
@@ -330,7 +330,7 @@ xfs_refcount_defer_add(
 
 	trace_xfs_refcount_defer(mp, ri);
 
-	ri->ri_pag = xfs_perag_intent_get(mp, ri->ri_startblock);
+	ri->ri_group = xfs_group_intent_get(mp, ri->ri_startblock, XG_TYPE_AG);
 	xfs_defer_add(tp, &ri->ri_list, &xfs_refcount_update_defer_type);
 }
 
@@ -341,7 +341,7 @@ xfs_refcount_update_cancel_item(
 {
 	struct xfs_refcount_intent	*ri = ci_entry(item);
 
-	xfs_perag_intent_put(ri->ri_pag);
+	xfs_group_intent_put(ri->ri_group);
 	kmem_cache_free(xfs_refcount_intent_cache, ri);
 }
 
@@ -431,7 +431,8 @@ xfs_cui_recover_work(
 	ri->ri_type = pmap->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK;
 	ri->ri_startblock = pmap->pe_startblock;
 	ri->ri_blockcount = pmap->pe_len;
-	ri->ri_pag = xfs_perag_intent_get(mp, pmap->pe_startblock);
+	ri->ri_group = xfs_group_intent_get(mp, pmap->pe_startblock,
+			XG_TYPE_AG);
 
 	xfs_defer_add_item(dfp, &ri->ri_list);
 }
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 1b83d09351f0..76b3c0ed3b4f 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -243,7 +243,7 @@ xfs_rmap_update_diff_items(
 	struct xfs_rmap_intent		*ra = ri_entry(a);
 	struct xfs_rmap_intent		*rb = ri_entry(b);
 
-	return pag_agno(ra->ri_pag) - pag_agno(rb->ri_pag);
+	return ra->ri_group->xg_gno - rb->ri_group->xg_gno;
 }
 
 /* Log rmap updates in the intent item. */
@@ -353,7 +353,8 @@ xfs_rmap_defer_add(
 
 	trace_xfs_rmap_defer(mp, ri);
 
-	ri->ri_pag = xfs_perag_intent_get(mp, ri->ri_bmap.br_startblock);
+	ri->ri_group = xfs_group_intent_get(mp, ri->ri_bmap.br_startblock,
+			XG_TYPE_AG);
 	xfs_defer_add(tp, &ri->ri_list, &xfs_rmap_update_defer_type);
 }
 
@@ -364,7 +365,7 @@ xfs_rmap_update_cancel_item(
 {
 	struct xfs_rmap_intent		*ri = ri_entry(item);
 
-	xfs_perag_intent_put(ri->ri_pag);
+	xfs_group_intent_put(ri->ri_group);
 	kmem_cache_free(xfs_rmap_intent_cache, ri);
 }
 
@@ -494,7 +495,7 @@ xfs_rui_recover_work(
 	ri->ri_bmap.br_blockcount = map->me_len;
 	ri->ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ?
 			XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
-	ri->ri_pag = xfs_perag_intent_get(mp, map->me_startblock);
+	ri->ri_group = xfs_group_intent_get(mp, map->me_startblock, XG_TYPE_AG);
 
 	xfs_defer_add_item(dfp, &ri->ri_list);
 }