[PATCH 02/21] xfs: create incore realtime group structures

[PATCH 02/21] xfs: create incore realtime group structures

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create an incore object that will contain information about a realtime
allocation group.  This will eventually enable us to shard the realtime
section in a similar manner to how we shard the data section, but for
now just a single object for the entire RT subvolume is created.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/Makefile             |    1 
 fs/xfs/libxfs/xfs_format.h  |    3 +
 fs/xfs/libxfs/xfs_group.c   |    8 ++
 fs/xfs/libxfs/xfs_rtgroup.c |  129 +++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_rtgroup.h |  208 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_sb.c      |    7 +
 fs/xfs/libxfs/xfs_types.h   |    8 +-
 fs/xfs/xfs_bmap_util.c      |    3 -
 fs/xfs/xfs_fsmap.c          |    5 +
 fs/xfs/xfs_log_recover.c    |   15 +++
 fs/xfs/xfs_mount.c          |   13 ++-
 fs/xfs/xfs_mount.h          |   13 +++
 fs/xfs/xfs_rtalloc.c        |    5 +
 fs/xfs/xfs_super.c          |    1 
 fs/xfs/xfs_trace.c          |    1 
 fs/xfs/xfs_trace.h          |    1 
 16 files changed, 416 insertions(+), 5 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_rtgroup.c
 create mode 100644 fs/xfs/libxfs/xfs_rtgroup.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index d80c2817eb4892..6814debac29929 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -61,6 +61,7 @@ xfs-y				+= $(addprefix libxfs/, \
 # xfs_rtbitmap is shared with libxfs
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix libxfs/, \
 				   xfs_rtbitmap.o \
+				   xfs_rtgroup.o \
 				   )
 
 # highlevel code
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index c035d8a45d6ffc..495eeaef0b5c71 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -185,6 +185,9 @@ typedef struct xfs_sb {
 
 	xfs_ino_t	sb_metadirino;	/* metadata directory tree root */
 
+	xfs_rgnumber_t	sb_rgcount;	/* number of realtime groups */
+	xfs_rtxlen_t	sb_rgextents;	/* size of a realtime group in rtx */
+
 	/* must be padded to 64 bit alignment */
 } xfs_sb_t;
 
diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c
index 07b96de47e2b56..cf6427cf350bb8 100644
--- a/fs/xfs/libxfs/xfs_group.c
+++ b/fs/xfs/libxfs/xfs_group.c
@@ -13,6 +13,7 @@
 #include "xfs_extent_busy.h"
 #include "xfs_group.h"
 #include "xfs_ag.h"
+#include "xfs_rtgroup.h"
 
 /*
  * Groups can have passive and active references.
@@ -221,6 +222,8 @@ xfs_gbno_to_fsb(
 	struct xfs_group	*xg,
 	xfs_agblock_t		gbno)
 {
+	if (xg->xg_type == XG_TYPE_RTG)
+		return xfs_rgbno_to_rtb(to_rtg(xg), gbno);
 	return xfs_agbno_to_fsb(to_perag(xg), gbno);
 }
 
@@ -229,6 +232,9 @@ xfs_gbno_to_daddr(
 	struct xfs_group	*xg,
 	xfs_agblock_t		gbno)
 {
+	if (xg->xg_type == XG_TYPE_RTG)
+		return xfs_rtb_to_daddr(xg->xg_mount,
+			xfs_rgbno_to_rtb(to_rtg(xg), gbno));
 	return xfs_agbno_to_daddr(to_perag(xg), gbno);
 }
 
@@ -238,6 +244,8 @@ xfs_fsb_to_gno(
 	xfs_fsblock_t		fsbno,
 	enum xfs_group_type	type)
 {
+	if (type == XG_TYPE_RTG)
+		return xfs_rtb_to_rgno(mp, fsbno);
 	return XFS_FSB_TO_AGNO(mp, fsbno);
 }
 
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
new file mode 100644
index 00000000000000..37c0330ca379d9
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_ag.h"
+#include "xfs_ag_resv.h"
+#include "xfs_health.h"
+#include "xfs_error.h"
+#include "xfs_bmap.h"
+#include "xfs_defer.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_trace.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtbitmap.h"
+
+int
+xfs_rtgroup_alloc(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgnumber_t		rgcount,
+	xfs_rtbxlen_t		rextents)
+{
+	struct xfs_rtgroup	*rtg;
+	int			error;
+
+	rtg = kzalloc(sizeof(struct xfs_rtgroup), GFP_KERNEL);
+	if (!rtg)
+		return -ENOMEM;
+
+	error = xfs_group_insert(mp, &rtg->rtg_group, rgno, XG_TYPE_RTG);
+	if (error)
+		goto out_free_rtg;
+	return 0;
+
+out_free_rtg:
+	kfree(rtg);
+	return error;
+}
+
+void
+xfs_rtgroup_free(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	xfs_group_free(mp, rgno, XG_TYPE_RTG, NULL);
+}
+
+/* Free a range of incore rtgroup objects. */
+void
+xfs_free_rtgroups(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		first_rgno,
+	xfs_rgnumber_t		end_rgno)
+{
+	xfs_rgnumber_t		rgno;
+
+	for (rgno = first_rgno; rgno < end_rgno; rgno++)
+		xfs_rtgroup_free(mp, rgno);
+}
+
+/* Initialize some range of incore rtgroup objects. */
+int
+xfs_initialize_rtgroups(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		first_rgno,
+	xfs_rgnumber_t		end_rgno,
+	xfs_rtbxlen_t		rextents)
+{
+	xfs_rgnumber_t		index;
+	int			error;
+
+	if (first_rgno >= end_rgno)
+		return 0;
+
+	for (index = first_rgno; index < end_rgno; index++) {
+		error = xfs_rtgroup_alloc(mp, index, end_rgno, rextents);
+		if (error)
+			goto out_unwind_new_rtgs;
+	}
+
+	return 0;
+
+out_unwind_new_rtgs:
+	xfs_free_rtgroups(mp, first_rgno, index);
+	return error;
+}
+
+/* Compute the number of rt extents in this realtime group. */
+xfs_rtxnum_t
+__xfs_rtgroup_extents(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgnumber_t		rgcount,
+	xfs_rtbxlen_t		rextents)
+{
+	ASSERT(rgno < rgcount);
+	if (rgno == rgcount - 1)
+		return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents);
+
+	ASSERT(xfs_has_rtgroups(mp));
+	return mp->m_sb.sb_rgextents;
+}
+
+xfs_rtxnum_t
+xfs_rtgroup_extents(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount,
+			mp->m_sb.sb_rextents);
+}
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
new file mode 100644
index 00000000000000..a9462aefefd77c
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -0,0 +1,208 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __LIBXFS_RTGROUP_H
+#define __LIBXFS_RTGROUP_H 1
+
+#include "xfs_group.h"
+
+struct xfs_mount;
+struct xfs_trans;
+
+/*
+ * Realtime group incore structure, similar to the per-AG structure.
+ */
+struct xfs_rtgroup {
+	struct xfs_group	rtg_group;
+
+	/* Number of blocks in this group */
+	xfs_rtxnum_t		rtg_extents;
+};
+
+static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg)
+{
+	return container_of(xg, struct xfs_rtgroup, rtg_group);
+}
+
+static inline struct xfs_mount *rtg_mount(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_mount;
+}
+
+static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_index;
+}
+
+/* Passive rtgroup references */
+static inline struct xfs_rtgroup *
+xfs_rtgroup_get(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return to_rtg(xfs_group_get(mp, rgno, XG_TYPE_RTG));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_hold(
+	struct xfs_rtgroup	*rtg)
+{
+	return to_rtg(xfs_group_hold(&rtg->rtg_group));
+}
+
+static inline void
+xfs_rtgroup_put(
+	struct xfs_rtgroup	*rtg)
+{
+	xfs_group_put(&rtg->rtg_group);
+}
+
+/* Active rtgroup references */
+static inline struct xfs_rtgroup *
+xfs_rtgroup_grab(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return to_rtg(xfs_group_grab(mp, rgno, XG_TYPE_RTG));
+}
+
+static inline void
+xfs_rtgroup_rele(
+	struct xfs_rtgroup	*rtg)
+{
+	xfs_group_rele(&rtg->rtg_group);
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_next_range(
+	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgnumber_t		start_rgno,
+	xfs_rgnumber_t		end_rgno)
+{
+	return to_rtg(xfs_group_next_range(mp, rtg ? &rtg->rtg_group : NULL,
+			start_rgno, end_rgno, XG_TYPE_RTG));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_next(
+	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg)
+{
+	return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1);
+}
+
+static inline xfs_rtblock_t
+xfs_rgno_start_rtb(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	if (mp->m_rgblklog >= 0)
+		return ((xfs_rtblock_t)rgno << mp->m_rgblklog);
+	return ((xfs_rtblock_t)rgno * mp->m_rgblocks);
+}
+
+static inline xfs_rtblock_t
+__xfs_rgbno_to_rtb(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgblock_t		rgbno)
+{
+	return xfs_rgno_start_rtb(mp, rgno) + rgbno;
+}
+
+static inline xfs_rtblock_t
+xfs_rgbno_to_rtb(
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		rgbno)
+{
+	return __xfs_rgbno_to_rtb(rtg_mount(rtg), rtg_rgno(rtg), rgbno);
+}
+
+static inline xfs_rgnumber_t
+xfs_rtb_to_rgno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	if (!xfs_has_rtgroups(mp))
+		return 0;
+
+	if (mp->m_rgblklog >= 0)
+		return rtbno >> mp->m_rgblklog;
+
+	return div_u64(rtbno, mp->m_rgblocks);
+}
+
+static inline uint64_t
+__xfs_rtb_to_rgbno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	uint32_t		rem;
+
+	if (!xfs_has_rtgroups(mp))
+		return rtbno;
+
+	if (mp->m_rgblklog >= 0)
+		return rtbno & mp->m_rgblkmask;
+
+	div_u64_rem(rtbno, mp->m_rgblocks, &rem);
+	return rem;
+}
+
+static inline xfs_rgblock_t
+xfs_rtb_to_rgbno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return __xfs_rtb_to_rgbno(mp, rtbno);
+}
+
+static inline xfs_daddr_t
+xfs_rtb_to_daddr(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return rtbno << mp->m_blkbb_log;
+}
+
+static inline xfs_rtblock_t
+xfs_daddr_to_rtb(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		daddr)
+{
+	return daddr >> mp->m_blkbb_log;
+}
+
+#ifdef CONFIG_XFS_RT
+int xfs_rtgroup_alloc(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
+void xfs_rtgroup_free(struct xfs_mount *mp, xfs_rgnumber_t rgno);
+
+void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
+		xfs_rgnumber_t end_rgno);
+int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
+		xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents);
+
+xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
+xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno);
+#else
+static inline void xfs_free_rtgroups(struct xfs_mount *mp,
+		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno)
+{
+}
+
+static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
+		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno,
+		xfs_rtbxlen_t rextents)
+{
+	return 0;
+}
+
+# define xfs_rtgroup_extents(mp, rgno)		(0)
+#endif /* CONFIG_XFS_RT */
+
+#endif /* __LIBXFS_RTGROUP_H */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 5fbf8d18417880..8fbdad6cc88724 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -707,6 +707,9 @@ __xfs_sb_from_disk(
 		to->sb_metadirino = NULLFSINO;
 		to->sb_bad_features2 = be32_to_cpu(from->sb_bad_features2);
 	}
+
+	to->sb_rgcount = 1;
+	to->sb_rgextents = 0;
 }
 
 void
@@ -997,6 +1000,10 @@ xfs_mount_sb_set_rextsize(
 {
 	mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize);
 	mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize);
+
+	mp->m_rgblocks = 0;
+	mp->m_rgblklog = 0;
+	mp->m_rgblkmask = 0;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index d3cb6ff3b91301..b7ff777ebacb8a 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -9,10 +9,12 @@
 typedef uint32_t	prid_t;		/* project ID */
 
 typedef uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
+typedef uint32_t	xfs_rgblock_t;	/* blockno in realtime group */
 typedef uint32_t	xfs_agino_t;	/* inode # within allocation grp */
 typedef uint32_t	xfs_extlen_t;	/* extent length in blocks */
 typedef uint32_t	xfs_rtxlen_t;	/* file extent length in rtextents */
 typedef uint32_t	xfs_agnumber_t;	/* allocation group number */
+typedef uint32_t	xfs_rgnumber_t;	/* realtime group number */
 typedef uint64_t	xfs_extnum_t;	/* # of extents in a file */
 typedef uint32_t	xfs_aextnum_t;	/* # extents in an attribute fork */
 typedef int64_t		xfs_fsize_t;	/* bytes in a file */
@@ -53,7 +55,9 @@ typedef void *		xfs_failaddr_t;
 #define	NULLFILEOFF	((xfs_fileoff_t)-1)
 
 #define	NULLAGBLOCK	((xfs_agblock_t)-1)
+#define NULLRGBLOCK	((xfs_rgblock_t)-1)
 #define	NULLAGNUMBER	((xfs_agnumber_t)-1)
+#define	NULLRGNUMBER	((xfs_rgnumber_t)-1)
 
 #define NULLCOMMITLSN	((xfs_lsn_t)-1)
 
@@ -214,11 +218,13 @@ enum xbtree_recpacking {
 
 enum xfs_group_type {
 	XG_TYPE_AG,
+	XG_TYPE_RTG,
 	XG_TYPE_MAX,
 } __packed;
 
 #define XG_TYPE_STRINGS \
-	{ XG_TYPE_AG,	"ag" }
+	{ XG_TYPE_AG,	"ag" }, \
+	{ XG_TYPE_RTG,	"rtg" }
 
 /*
  * Type verifier functions
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index d283e076a58d3d..9d654664a00dbd 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -29,6 +29,7 @@
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
 
 /* Kernel only BMAP related definitions and functions */
 
@@ -41,7 +42,7 @@ xfs_daddr_t
 xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
 {
 	if (XFS_IS_REALTIME_INODE(ip))
-		return XFS_FSB_TO_BB(ip->i_mount, fsb);
+		return xfs_rtb_to_daddr(ip->i_mount, fsb);
 	return XFS_FSB_TO_DADDR(ip->i_mount, fsb);
 }
 
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index db46fc3da48928..a31c748c85b0d8 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -25,6 +25,7 @@
 #include "xfs_alloc_btree.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_ag.h"
+#include "xfs_rtgroup.h"
 
 /* Convert an xfs_fsmap to an fsmap. */
 static void
@@ -735,7 +736,7 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
 		frec.start_daddr = info->end_daddr;
 	} else {
 		rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
-		frec.start_daddr = XFS_FSB_TO_BB(mp, rtbno);
+		frec.start_daddr = xfs_rtb_to_daddr(mp, rtbno);
 	}
 
 	rtbno = xfs_rtx_to_rtb(mp, rec->ar_extcount);
@@ -770,7 +771,7 @@ xfs_getfsmap_rtdev_rtbitmap(
 
 	/* Adjust the low key if we are continuing from where we left off. */
 	if (keys[0].fmr_length > 0) {
-		info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb);
+		info->low_daddr = xfs_rtb_to_daddr(mp, start_rtb);
 		if (info->low_daddr >= eofs)
 			return 0;
 	}
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 0856080f87d3e6..a6abc09864edd0 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -28,6 +28,7 @@
 #include "xfs_ag.h"
 #include "xfs_quota.h"
 #include "xfs_reflink.h"
+#include "xfs_rtgroup.h"
 
 #define BLK_AVG(blk1, blk2)	((blk1+blk2) >> 1)
 
@@ -3345,6 +3346,7 @@ xlog_do_recover(
 	struct xfs_buf		*bp = mp->m_sb_bp;
 	struct xfs_sb		*sbp = &mp->m_sb;
 	xfs_agnumber_t		old_agcount = sbp->sb_agcount;
+	xfs_rgnumber_t		old_rgcount = sbp->sb_rgcount;
 	int			error;
 
 	trace_xfs_log_recover(log, head_blk, tail_blk);
@@ -3398,6 +3400,19 @@ xlog_do_recover(
 		xfs_warn(mp, "Failed post-recovery per-ag init: %d", error);
 		return error;
 	}
+
+	if (sbp->sb_rgcount < old_rgcount) {
+		xfs_warn(mp, "rgcount shrink not supported");
+		return -EINVAL;
+	}
+
+	error = xfs_initialize_rtgroups(mp, old_rgcount, sbp->sb_rgcount,
+			sbp->sb_rextents);
+	if (error) {
+		xfs_warn(mp, "Failed post-recovery rtgroup init: %d", error);
+		return error;
+	}
+
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
 
 	/* Normal transactions can now occur */
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 2dd2606fc7e3e4..9464eddf9212e9 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -36,6 +36,7 @@
 #include "xfs_ag.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
 #include "scrub/stats.h"
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
@@ -834,10 +835,17 @@ xfs_mountfs(
 		goto out_free_dir;
 	}
 
+	error = xfs_initialize_rtgroups(mp, 0, sbp->sb_rgcount,
+			mp->m_sb.sb_rextents);
+	if (error) {
+		xfs_warn(mp, "Failed rtgroup init: %d", error);
+		goto out_free_perag;
+	}
+
 	if (XFS_IS_CORRUPT(mp, !sbp->sb_logblocks)) {
 		xfs_warn(mp, "no log defined");
 		error = -EFSCORRUPTED;
-		goto out_free_perag;
+		goto out_free_rtgroup;
 	}
 
 	error = xfs_inodegc_register_shrinker(mp);
@@ -1072,6 +1080,8 @@ xfs_mountfs(
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_buftarg_drain(mp->m_logdev_targp);
 	xfs_buftarg_drain(mp->m_ddev_targp);
+ out_free_rtgroup:
+	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
  out_free_perag:
 	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
  out_free_dir:
@@ -1156,6 +1166,7 @@ xfs_unmountfs(
 	xfs_errortag_clearall(mp);
 #endif
 	shrinker_free(mp->m_inodegc_shrinker);
+	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
 	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
 	xfs_errortag_del(mp);
 	xfs_error_sysfs_del(mp);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 92f376d5c2a863..02e5eab959d015 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -125,6 +125,7 @@ typedef struct xfs_mount {
 	uint8_t			m_agno_log;	/* log #ag's */
 	uint8_t			m_sectbb_log;	/* sectlog - BBSHIFT */
 	int8_t			m_rtxblklog;	/* log2 of rextsize, if possible */
+	int8_t			m_rgblklog;	/* log2 of rt group sz if possible */
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
 	uint			m_blockwmask;	/* blockwsize-1 */
@@ -153,12 +154,14 @@ typedef struct xfs_mount {
 	int			m_logbsize;	/* size of each log buffer */
 	uint			m_rsumlevels;	/* rt summary levels */
 	xfs_filblks_t		m_rsumblocks;	/* size of rt summary, FSBs */
+	uint32_t		m_rgblocks;	/* size of rtgroup in rtblocks */
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_qflags;	/* quota status flags */
 	uint64_t		m_features;	/* active filesystem features */
 	uint64_t		m_low_space[XFS_LOWSP_MAX];
 	uint64_t		m_low_rtexts[XFS_LOWSP_MAX];
 	uint64_t		m_rtxblkmask;	/* rt extent block mask */
+	uint64_t		m_rgblkmask;	/* rt group block mask */
 	struct xfs_ino_geometry	m_ino_geo;	/* inode geometry */
 	struct xfs_trans_resv	m_resv;		/* precomputed res values */
 						/* low free space thresholds */
@@ -361,6 +364,16 @@ __XFS_HAS_FEAT(large_extent_counts, NREXT64)
 __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE)
 __XFS_HAS_FEAT(metadir, METADIR)
 
+static inline bool xfs_has_rtgroups(struct xfs_mount *mp)
+{
+	return false;
+}
+
+static inline bool xfs_has_rtsb(struct xfs_mount *mp)
+{
+	return false;
+}
+
 /*
  * Some features are always on for v5 file systems, allow the compiler to
  * eliminiate dead code when building without v4 support.
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 46a920b192d191..917c1a5e8f3180 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -27,6 +27,7 @@
 #include "xfs_health.h"
 #include "xfs_da_format.h"
 #include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
 
 /*
  * Return whether there are any free extents in the size range given
@@ -1136,6 +1137,7 @@ xfs_rtmount_inodes(
 {
 	struct xfs_trans	*tp;
 	struct xfs_sb		*sbp = &mp->m_sb;
+	struct xfs_rtgroup	*rtg = NULL;
 	int			error;
 
 	error = xfs_trans_alloc_empty(mp, &tp);
@@ -1166,6 +1168,9 @@ xfs_rtmount_inodes(
 	if (error)
 		goto out_rele_summary;
 
+	while ((rtg = xfs_rtgroup_next(mp, rtg)))
+		rtg->rtg_extents = xfs_rtgroup_extents(mp, rtg_rgno(rtg));
+
 	error = xfs_alloc_rsum_cache(mp, sbp->sb_rbmblocks);
 	if (error)
 		goto out_rele_summary;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 59953278964de9..b2c12fd5ee41a3 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2027,6 +2027,7 @@ xfs_init_fs_context(
 		return -ENOMEM;
 
 	spin_lock_init(&mp->m_sb_lock);
+
 	for (i = 0; i < XG_TYPE_MAX; i++)
 		xa_init(&mp->m_groups[i].xa);
 	mutex_init(&mp->m_growlock);
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 061a3c43cd1d36..aaa0ea06910d88 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -48,6 +48,7 @@
 #include "xfs_refcount.h"
 #include "xfs_metafile.h"
 #include "xfs_metadir.h"
+#include "xfs_rtgroup.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index cb747da43c9c6c..31e3a941445211 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -219,6 +219,7 @@ DEFINE_PERAG_REF_EVENT(xfs_perag_clear_inode_tag);
 DEFINE_PERAG_REF_EVENT(xfs_reclaim_inodes_count);
 
 TRACE_DEFINE_ENUM(XG_TYPE_AG);
+TRACE_DEFINE_ENUM(XG_TYPE_RTG);
 
 DECLARE_EVENT_CLASS(xfs_group_class,
 	TP_PROTO(struct xfs_group *xg, unsigned long caller_ip),

[PATCH 02/21] xfs: create incore realtime group structures

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create an incore object that will contain information about a realtime
allocation group.  This will eventually enable us to shard the realtime
section in a similar manner to how we shard the data section, but for
now just a single object for the entire RT subvolume is created.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/Makefile               |    1 
 fs/xfs/libxfs/xfs_format.h    |    3 +
 fs/xfs/libxfs/xfs_rtgroup.c   |  152 +++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_rtgroup.h   |  217 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_sb.c        |   13 ++
 fs/xfs/libxfs/xfs_types.h     |    8 +-
 fs/xfs/xfs_bmap_util.c        |    3 -
 fs/xfs/xfs_buf_item_recover.c |   25 +++++
 fs/xfs/xfs_fsmap.c            |    5 +
 fs/xfs/xfs_mount.c            |   13 ++
 fs/xfs/xfs_mount.h            |   13 ++
 fs/xfs/xfs_rtalloc.c          |    5 +
 fs/xfs/xfs_trace.c            |    1 
 fs/xfs/xfs_trace.h            |    1 
 14 files changed, 455 insertions(+), 5 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_rtgroup.c
 create mode 100644 fs/xfs/libxfs/xfs_rtgroup.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index d80c2817eb4892..6814debac29929 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -61,6 +61,7 @@ xfs-y				+= $(addprefix libxfs/, \
 # xfs_rtbitmap is shared with libxfs
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix libxfs/, \
 				   xfs_rtbitmap.o \
+				   xfs_rtgroup.o \
 				   )
 
 # highlevel code
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 616f81045921b7..867060d60e8583 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -176,6 +176,9 @@ typedef struct xfs_sb {
 
 	xfs_ino_t	sb_metadirino;	/* metadata directory tree root */
 
+	xfs_rgnumber_t	sb_rgcount;	/* number of realtime groups */
+	xfs_rtxlen_t	sb_rgextents;	/* size of a realtime group in rtx */
+
 	/* must be padded to 64 bit alignment */
 } xfs_sb_t;
 
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
new file mode 100644
index 00000000000000..d91b6a3b091c9a
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_ag.h"
+#include "xfs_ag_resv.h"
+#include "xfs_health.h"
+#include "xfs_error.h"
+#include "xfs_bmap.h"
+#include "xfs_defer.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_trace.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtbitmap.h"
+
+int
+xfs_rtgroup_alloc(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgnumber_t		rgcount,
+	xfs_rtbxlen_t		rextents)
+{
+	struct xfs_rtgroup	*rtg;
+	int			error;
+
+	rtg = kzalloc(sizeof(struct xfs_rtgroup), GFP_KERNEL);
+	if (!rtg)
+		return -ENOMEM;
+
+	error = xfs_group_insert(mp, rtg_group(rtg), rgno, XG_TYPE_RTG);
+	if (error)
+		goto out_free_rtg;
+	return 0;
+
+out_free_rtg:
+	kfree(rtg);
+	return error;
+}
+
+void
+xfs_rtgroup_free(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	xfs_group_free(mp, rgno, XG_TYPE_RTG, NULL);
+}
+
+/* Free a range of incore rtgroup objects. */
+void
+xfs_free_rtgroups(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		first_rgno,
+	xfs_rgnumber_t		end_rgno)
+{
+	xfs_rgnumber_t		rgno;
+
+	for (rgno = first_rgno; rgno < end_rgno; rgno++)
+		xfs_rtgroup_free(mp, rgno);
+}
+
+/* Initialize some range of incore rtgroup objects. */
+int
+xfs_initialize_rtgroups(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		first_rgno,
+	xfs_rgnumber_t		end_rgno,
+	xfs_rtbxlen_t		rextents)
+{
+	xfs_rgnumber_t		index;
+	int			error;
+
+	if (first_rgno >= end_rgno)
+		return 0;
+
+	for (index = first_rgno; index < end_rgno; index++) {
+		error = xfs_rtgroup_alloc(mp, index, end_rgno, rextents);
+		if (error)
+			goto out_unwind_new_rtgs;
+	}
+
+	return 0;
+
+out_unwind_new_rtgs:
+	xfs_free_rtgroups(mp, first_rgno, index);
+	return error;
+}
+
+/* Compute the number of rt extents in this realtime group. */
+xfs_rtxnum_t
+__xfs_rtgroup_extents(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgnumber_t		rgcount,
+	xfs_rtbxlen_t		rextents)
+{
+	ASSERT(rgno < rgcount);
+	if (rgno == rgcount - 1)
+		return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents);
+
+	ASSERT(xfs_has_rtgroups(mp));
+	return mp->m_sb.sb_rgextents;
+}
+
+xfs_rtxnum_t
+xfs_rtgroup_extents(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount,
+			mp->m_sb.sb_rextents);
+}
+
+/*
+ * Update the rt extent count of the previous tail rtgroup if it changed during
+ * recovery (i.e. recovery of a growfs).
+ */
+int
+xfs_update_last_rtgroup_size(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		prev_rgcount)
+{
+	struct xfs_rtgroup	*rtg;
+
+	ASSERT(prev_rgcount > 0);
+
+	rtg = xfs_rtgroup_grab(mp, prev_rgcount - 1);
+	if (!rtg)
+		return -EFSCORRUPTED;
+	rtg->rtg_extents = __xfs_rtgroup_extents(mp, prev_rgcount - 1,
+			mp->m_sb.sb_rgcount, mp->m_sb.sb_rextents);
+	xfs_rtgroup_rele(rtg);
+	return 0;
+}
+
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
new file mode 100644
index 00000000000000..8872c27a9585fd
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __LIBXFS_RTGROUP_H
+#define __LIBXFS_RTGROUP_H 1
+
+#include "xfs_group.h"
+
+struct xfs_mount;
+struct xfs_trans;
+
+/*
+ * Realtime group incore structure, similar to the per-AG structure.
+ */
+struct xfs_rtgroup {
+	struct xfs_group	rtg_group;
+
+	/* Number of blocks in this group */
+	xfs_rtxnum_t		rtg_extents;
+};
+
+static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg)
+{
+	return container_of(xg, struct xfs_rtgroup, rtg_group);
+}
+
+static inline struct xfs_group *rtg_group(struct xfs_rtgroup *rtg)
+{
+	return &rtg->rtg_group;
+}
+
+static inline struct xfs_mount *rtg_mount(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_mount;
+}
+
+static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_gno;
+}
+
+/* Passive rtgroup references */
+static inline struct xfs_rtgroup *
+xfs_rtgroup_get(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return to_rtg(xfs_group_get(mp, rgno, XG_TYPE_RTG));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_hold(
+	struct xfs_rtgroup	*rtg)
+{
+	return to_rtg(xfs_group_hold(rtg_group(rtg)));
+}
+
+static inline void
+xfs_rtgroup_put(
+	struct xfs_rtgroup	*rtg)
+{
+	xfs_group_put(rtg_group(rtg));
+}
+
+/* Active rtgroup references */
+static inline struct xfs_rtgroup *
+xfs_rtgroup_grab(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return to_rtg(xfs_group_grab(mp, rgno, XG_TYPE_RTG));
+}
+
+static inline void
+xfs_rtgroup_rele(
+	struct xfs_rtgroup	*rtg)
+{
+	xfs_group_rele(rtg_group(rtg));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_next_range(
+	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgnumber_t		start_rgno,
+	xfs_rgnumber_t		end_rgno)
+{
+	return to_rtg(xfs_group_next_range(mp, rtg ? rtg_group(rtg) : NULL,
+			start_rgno, end_rgno, XG_TYPE_RTG));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_next(
+	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg)
+{
+	return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1);
+}
+
+static inline xfs_rtblock_t
+xfs_rgno_start_rtb(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	if (mp->m_rgblklog >= 0)
+		return ((xfs_rtblock_t)rgno << mp->m_rgblklog);
+	return ((xfs_rtblock_t)rgno * mp->m_rgblocks);
+}
+
+static inline xfs_rtblock_t
+__xfs_rgbno_to_rtb(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgblock_t		rgbno)
+{
+	return xfs_rgno_start_rtb(mp, rgno) + rgbno;
+}
+
+static inline xfs_rtblock_t
+xfs_rgbno_to_rtb(
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		rgbno)
+{
+	return __xfs_rgbno_to_rtb(rtg_mount(rtg), rtg_rgno(rtg), rgbno);
+}
+
+static inline xfs_rgnumber_t
+xfs_rtb_to_rgno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	if (!xfs_has_rtgroups(mp))
+		return 0;
+
+	if (mp->m_rgblklog >= 0)
+		return rtbno >> mp->m_rgblklog;
+
+	return div_u64(rtbno, mp->m_rgblocks);
+}
+
+static inline uint64_t
+__xfs_rtb_to_rgbno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	uint32_t		rem;
+
+	if (!xfs_has_rtgroups(mp))
+		return rtbno;
+
+	if (mp->m_rgblklog >= 0)
+		return rtbno & mp->m_rgblkmask;
+
+	div_u64_rem(rtbno, mp->m_rgblocks, &rem);
+	return rem;
+}
+
+static inline xfs_rgblock_t
+xfs_rtb_to_rgbno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return __xfs_rtb_to_rgbno(mp, rtbno);
+}
+
+static inline xfs_daddr_t
+xfs_rtb_to_daddr(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return rtbno << mp->m_blkbb_log;
+}
+
+static inline xfs_rtblock_t
+xfs_daddr_to_rtb(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		daddr)
+{
+	return daddr >> mp->m_blkbb_log;
+}
+
+#ifdef CONFIG_XFS_RT
+int xfs_rtgroup_alloc(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
+void xfs_rtgroup_free(struct xfs_mount *mp, xfs_rgnumber_t rgno);
+
+void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
+		xfs_rgnumber_t end_rgno);
+int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
+		xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents);
+
+xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
+xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno);
+
+int xfs_update_last_rtgroup_size(struct xfs_mount *mp,
+		xfs_rgnumber_t prev_rgcount);
+#else
+static inline void xfs_free_rtgroups(struct xfs_mount *mp,
+		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno)
+{
+}
+
+static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
+		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno,
+		xfs_rtbxlen_t rextents)
+{
+	return 0;
+}
+
+# define xfs_rtgroup_extents(mp, rgno)		(0)
+# define xfs_update_last_rtgroup_size(mp, rgno)	(-EOPNOTSUPP)
+#endif /* CONFIG_XFS_RT */
+
+#endif /* __LIBXFS_RTGROUP_H */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 4516824e3b9994..21891aa10ada02 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -696,6 +696,9 @@ __xfs_sb_from_disk(
 		to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
 	else
 		to->sb_metadirino = NULLFSINO;
+
+	to->sb_rgcount = 1;
+	to->sb_rgextents = 0;
 }
 
 void
@@ -980,8 +983,18 @@ xfs_mount_sb_set_rextsize(
 	struct xfs_mount	*mp,
 	struct xfs_sb		*sbp)
 {
+	struct xfs_groups	*rgs = &mp->m_groups[XG_TYPE_RTG];
+
 	mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize);
 	mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize);
+
+	mp->m_rgblocks = 0;
+	mp->m_rgblklog = 0;
+	mp->m_rgblkmask = (uint64_t)-1;
+
+	rgs->blocks = 0;
+	rgs->blklog = 0;
+	rgs->blkmask = (uint64_t)-1;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 25053a66c225ed..bf33c2b1e43e5f 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -9,10 +9,12 @@
 typedef uint32_t	prid_t;		/* project ID */
 
 typedef uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
+typedef uint32_t	xfs_rgblock_t;	/* blockno in realtime group */
 typedef uint32_t	xfs_agino_t;	/* inode # within allocation grp */
 typedef uint32_t	xfs_extlen_t;	/* extent length in blocks */
 typedef uint32_t	xfs_rtxlen_t;	/* file extent length in rtextents */
 typedef uint32_t	xfs_agnumber_t;	/* allocation group number */
+typedef uint32_t	xfs_rgnumber_t;	/* realtime group number */
 typedef uint64_t	xfs_extnum_t;	/* # of extents in a file */
 typedef uint32_t	xfs_aextnum_t;	/* # extents in an attribute fork */
 typedef int64_t		xfs_fsize_t;	/* bytes in a file */
@@ -53,7 +55,9 @@ typedef void *		xfs_failaddr_t;
 #define	NULLFILEOFF	((xfs_fileoff_t)-1)
 
 #define	NULLAGBLOCK	((xfs_agblock_t)-1)
+#define NULLRGBLOCK	((xfs_rgblock_t)-1)
 #define	NULLAGNUMBER	((xfs_agnumber_t)-1)
+#define	NULLRGNUMBER	((xfs_rgnumber_t)-1)
 
 #define NULLCOMMITLSN	((xfs_lsn_t)-1)
 
@@ -214,11 +218,13 @@ enum xbtree_recpacking {
 
 enum xfs_group_type {
 	XG_TYPE_AG,
+	XG_TYPE_RTG,
 	XG_TYPE_MAX,
 } __packed;
 
 #define XG_TYPE_STRINGS \
-	{ XG_TYPE_AG,	"ag" }
+	{ XG_TYPE_AG,	"ag" }, \
+	{ XG_TYPE_RTG,	"rtg" }
 
 /*
  * Type verifier functions
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index d283e076a58d3d..9d654664a00dbd 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -29,6 +29,7 @@
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
 
 /* Kernel only BMAP related definitions and functions */
 
@@ -41,7 +42,7 @@ xfs_daddr_t
 xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
 {
 	if (XFS_IS_REALTIME_INODE(ip))
-		return XFS_FSB_TO_BB(ip->i_mount, fsb);
+		return xfs_rtb_to_daddr(ip->i_mount, fsb);
 	return XFS_FSB_TO_DADDR(ip->i_mount, fsb);
 }
 
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index c627ad3a3bbbfd..c8259ee482fd86 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -25,6 +25,7 @@
 #include "xfs_alloc.h"
 #include "xfs_ag.h"
 #include "xfs_sb.h"
+#include "xfs_rtgroup.h"
 
 /*
  * This is the number of entries in the l_buf_cancel_table used during
@@ -704,6 +705,7 @@ xlog_recover_do_primary_sb_buffer(
 {
 	struct xfs_dsb			*dsb = bp->b_addr;
 	xfs_agnumber_t			orig_agcount = mp->m_sb.sb_agcount;
+	xfs_rgnumber_t			orig_rgcount = mp->m_sb.sb_rgcount;
 	int				error;
 
 	xlog_recover_do_reg_buffer(mp, item, bp, buf_f, current_lsn);
@@ -722,6 +724,11 @@ xlog_recover_do_primary_sb_buffer(
 		xfs_alert(mp, "Shrinking AG count in log recovery not supported");
 		return -EFSCORRUPTED;
 	}
+	if (mp->m_sb.sb_rgcount < orig_rgcount) {
+		xfs_warn(mp,
+ "Shrinking rtgroup count in log recovery not supported");
+		return -EFSCORRUPTED;
+	}
 
 	/*
 	 * If the last AG was grown or shrunk, we also need to update the
@@ -731,6 +738,17 @@ xlog_recover_do_primary_sb_buffer(
 	if (error)
 		return error;
 
+	/*
+	 * If the last rtgroup was grown or shrunk, we also need to update the
+	 * length in the in-core rtgroup structure and values depending on it.
+	 * Ignore this on any filesystem with zero rtgroups.
+	 */
+	if (orig_rgcount > 0) {
+		error = xfs_update_last_rtgroup_size(mp, orig_rgcount);
+		if (error)
+			return error;
+	}
+
 	/*
 	 * Initialize the new perags, and also update various block and inode
 	 * allocator setting based off the number of AGs or total blocks.
@@ -744,6 +762,13 @@ xlog_recover_do_primary_sb_buffer(
 		return error;
 	}
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
+
+	error = xfs_initialize_rtgroups(mp, orig_rgcount, mp->m_sb.sb_rgcount,
+			mp->m_sb.sb_rextents);
+	if (error) {
+		xfs_warn(mp, "Failed recovery rtgroup init: %d", error);
+		return error;
+	}
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 6cf4f00636a2d6..40beb8d75f26b1 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -25,6 +25,7 @@
 #include "xfs_alloc_btree.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_ag.h"
+#include "xfs_rtgroup.h"
 
 /* Convert an xfs_fsmap to an fsmap. */
 static void
@@ -735,7 +736,7 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
 		frec.start_daddr = info->end_daddr;
 	} else {
 		rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
-		frec.start_daddr = XFS_FSB_TO_BB(mp, rtbno);
+		frec.start_daddr = xfs_rtb_to_daddr(mp, rtbno);
 	}
 
 	rtbno = xfs_rtx_to_rtb(mp, rec->ar_extcount);
@@ -770,7 +771,7 @@ xfs_getfsmap_rtdev_rtbitmap(
 
 	/* Adjust the low key if we are continuing from where we left off. */
 	if (keys[0].fmr_length > 0) {
-		info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb);
+		info->low_daddr = xfs_rtb_to_daddr(mp, start_rtb);
 		if (info->low_daddr >= eofs)
 			return 0;
 	}
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 2dd2606fc7e3e4..9464eddf9212e9 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -36,6 +36,7 @@
 #include "xfs_ag.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
 #include "scrub/stats.h"
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
@@ -834,10 +835,17 @@ xfs_mountfs(
 		goto out_free_dir;
 	}
 
+	error = xfs_initialize_rtgroups(mp, 0, sbp->sb_rgcount,
+			mp->m_sb.sb_rextents);
+	if (error) {
+		xfs_warn(mp, "Failed rtgroup init: %d", error);
+		goto out_free_perag;
+	}
+
 	if (XFS_IS_CORRUPT(mp, !sbp->sb_logblocks)) {
 		xfs_warn(mp, "no log defined");
 		error = -EFSCORRUPTED;
-		goto out_free_perag;
+		goto out_free_rtgroup;
 	}
 
 	error = xfs_inodegc_register_shrinker(mp);
@@ -1072,6 +1080,8 @@ xfs_mountfs(
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_buftarg_drain(mp->m_logdev_targp);
 	xfs_buftarg_drain(mp->m_ddev_targp);
+ out_free_rtgroup:
+	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
  out_free_perag:
 	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
  out_free_dir:
@@ -1156,6 +1166,7 @@ xfs_unmountfs(
 	xfs_errortag_clearall(mp);
 #endif
 	shrinker_free(mp->m_inodegc_shrinker);
+	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
 	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
 	xfs_errortag_del(mp);
 	xfs_error_sysfs_del(mp);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 1da0e10a9e2e6b..abc7c303f69e5f 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -155,6 +155,7 @@ typedef struct xfs_mount {
 	uint8_t			m_agno_log;	/* log #ag's */
 	uint8_t			m_sectbb_log;	/* sectlog - BBSHIFT */
 	int8_t			m_rtxblklog;	/* log2 of rextsize, if possible */
+	int8_t			m_rgblklog;	/* log2 of rt group sz if possible */
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
 	uint			m_blockwmask;	/* blockwsize-1 */
@@ -183,12 +184,14 @@ typedef struct xfs_mount {
 	int			m_logbsize;	/* size of each log buffer */
 	uint			m_rsumlevels;	/* rt summary levels */
 	xfs_filblks_t		m_rsumblocks;	/* size of rt summary, FSBs */
+	uint32_t		m_rgblocks;	/* size of rtgroup in rtblocks */
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_qflags;	/* quota status flags */
 	uint64_t		m_features;	/* active filesystem features */
 	uint64_t		m_low_space[XFS_LOWSP_MAX];
 	uint64_t		m_low_rtexts[XFS_LOWSP_MAX];
 	uint64_t		m_rtxblkmask;	/* rt extent block mask */
+	uint64_t		m_rgblkmask;	/* rt group block mask */
 	struct xfs_ino_geometry	m_ino_geo;	/* inode geometry */
 	struct xfs_trans_resv	m_resv;		/* precomputed res values */
 						/* low free space thresholds */
@@ -391,6 +394,16 @@ __XFS_HAS_FEAT(large_extent_counts, NREXT64)
 __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE)
 __XFS_HAS_FEAT(metadir, METADIR)
 
+static inline bool xfs_has_rtgroups(struct xfs_mount *mp)
+{
+	return false;
+}
+
+static inline bool xfs_has_rtsb(struct xfs_mount *mp)
+{
+	return false;
+}
+
 /*
  * Some features are always on for v5 file systems, allow the compiler to
  * eliminiate dead code when building without v4 support.
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 46a920b192d191..917c1a5e8f3180 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -27,6 +27,7 @@
 #include "xfs_health.h"
 #include "xfs_da_format.h"
 #include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
 
 /*
  * Return whether there are any free extents in the size range given
@@ -1136,6 +1137,7 @@ xfs_rtmount_inodes(
 {
 	struct xfs_trans	*tp;
 	struct xfs_sb		*sbp = &mp->m_sb;
+	struct xfs_rtgroup	*rtg = NULL;
 	int			error;
 
 	error = xfs_trans_alloc_empty(mp, &tp);
@@ -1166,6 +1168,9 @@ xfs_rtmount_inodes(
 	if (error)
 		goto out_rele_summary;
 
+	while ((rtg = xfs_rtgroup_next(mp, rtg)))
+		rtg->rtg_extents = xfs_rtgroup_extents(mp, rtg_rgno(rtg));
+
 	error = xfs_alloc_rsum_cache(mp, sbp->sb_rbmblocks);
 	if (error)
 		goto out_rele_summary;
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 1b9d75a54c5ea2..8f530e69c18ae7 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -48,6 +48,7 @@
 #include "xfs_refcount.h"
 #include "xfs_metafile.h"
 #include "xfs_metadir.h"
+#include "xfs_rtgroup.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index ba917c153aaf5d..818e9992ce5692 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -219,6 +219,7 @@ DEFINE_PERAG_REF_EVENT(xfs_perag_clear_inode_tag);
 DEFINE_PERAG_REF_EVENT(xfs_reclaim_inodes_count);
 
 TRACE_DEFINE_ENUM(XG_TYPE_AG);
+TRACE_DEFINE_ENUM(XG_TYPE_RTG);
 
 DECLARE_EVENT_CLASS(xfs_group_class,
 	TP_PROTO(struct xfs_group *xg, unsigned long caller_ip),

[PATCHBOMB 6.13 v5.5] xfs: metadata directories and realtime groups

[Darrick J. Wong]

Hi everyone,

Christoph and I have been working on getting the long-delayed metadata
directory tree patchset into mergeable shape, and now that it's fully
reviewed, I want to push it for 6.13.  Changes since 17 Oct include
dealing with merge conflicts, adding some more tags, using the new
experimental warning code for pnfs, fixing a refcounting bug, fixing
some quota flag handling bugs, and porting xfs/122 to the kernel.

I am sending the kernel patches one more time for posterity; pull
requests will follow immediately after.

--

The metadata directory tree sets us up for much more flexible metadata
within an XFS filesystem.  Instead of rooting inodes in the superblock
which has very limited space, we instead create a directory tree that
can contain arbitrary numbers of metadata files.

Having done that, we can now shard the realtime volume into multiple
allocation groups, much as we do with AGs for the data device.  However,
the realtime volume has a fun twist -- each rtgroup gets its own space
metadata files, and for that we need a metadata directory tree.
Note that we also implement busy free(d) extent tracking, which means
that we can do discards asynchronously.

Metadata directory trees and realtime groups also enable us to complete
the realtime modernization project, which will add reverse mapping
btrees, reflink, quota support, and zoned storage support for rt
volumes.

Finally, quota inodes now live in the metadata directory tree, which is
a pretty simple conversion.  However, we added yet another new feature,
which is that xfs will now remember the quota accounting and enforcement
state across unmounts.  You can still tweak them via mount options, but
not specifying any is no longer interpreted the same as 'noquota'.
Quotas for the realtime are now supported.

Please have a look at the git tree links for code changes:

https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux.git/tag/?h=metadir_2024-11-05
https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfsprogs-dev.git/tag/?h=metadir_2024-11-05
https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfstests-dev.git/tag/?h=realtime-quotas_2024-11-05

--D

[PATCHSET v5.5 01/10] xfs: convert perag to use xarrays

[Darrick J. Wong]

Hi all,

Convert the xfs_mount perag tree to use an xarray instead of a radix
tree.  There should be no functional changes here.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=perag-xarray-6.13
---
Commits in this patchset:
 * xfs: fix simplify extent lookup in xfs_can_free_eofblocks
 * xfs: fix superfluous clearing of info->low in __xfs_getfsmap_datadev
 * xfs: remove the unused pagb_count field in struct xfs_perag
 * xfs: remove the unused pag_active_wq field in struct xfs_perag
 * xfs: pass a pag to xfs_difree_inode_chunk
 * xfs: remove the agno argument to xfs_free_ag_extent
 * xfs: add xfs_agbno_to_fsb and xfs_agbno_to_daddr helpers
 * xfs: add a xfs_agino_to_ino helper
 * xfs: pass a pag to xfs_extent_busy_{search,reuse}
 * xfs: keep a reference to the pag for busy extents
 * xfs: remove the mount field from struct xfs_busy_extents
 * xfs: remove the unused trace_xfs_iwalk_ag trace point
 * xfs: remove the unused xrep_bmap_walk_rmap trace point
 * xfs: constify pag arguments to trace points
 * xfs: pass a perag structure to the xfs_ag_resv_init_error trace point
 * xfs: pass objects to the xfs_irec_merge_{pre,post} trace points
 * xfs: pass the iunlink item to the xfs_iunlink_update_dinode trace point
 * xfs: pass objects to the xrep_ibt_walk_rmap tracepoint
 * xfs: pass the pag to the trace_xrep_calc_ag_resblks{,_btsize} trace points
 * xfs: pass the pag to the xrep_newbt_extent_class tracepoints
 * xfs: convert remaining trace points to pass pag structures
 * xfs: split xfs_initialize_perag
 * xfs: insert the pag structures into the xarray later
---
 fs/xfs/libxfs/xfs_ag.c             |  135 ++++++++++++++-----------
 fs/xfs/libxfs/xfs_ag.h             |   30 +++++-
 fs/xfs/libxfs/xfs_ag_resv.c        |    3 -
 fs/xfs/libxfs/xfs_alloc.c          |   32 +++---
 fs/xfs/libxfs/xfs_alloc.h          |    5 -
 fs/xfs/libxfs/xfs_alloc_btree.c    |    2 
 fs/xfs/libxfs/xfs_btree.c          |    7 +
 fs/xfs/libxfs/xfs_ialloc.c         |   67 ++++++-------
 fs/xfs/libxfs/xfs_ialloc_btree.c   |    2 
 fs/xfs/libxfs/xfs_inode_util.c     |    4 -
 fs/xfs/libxfs/xfs_refcount.c       |   11 +-
 fs/xfs/libxfs/xfs_refcount_btree.c |    3 -
 fs/xfs/libxfs/xfs_rmap_btree.c     |    2 
 fs/xfs/scrub/agheader_repair.c     |   16 +--
 fs/xfs/scrub/alloc_repair.c        |   10 +-
 fs/xfs/scrub/bmap.c                |    5 -
 fs/xfs/scrub/bmap_repair.c         |    4 -
 fs/xfs/scrub/common.c              |    2 
 fs/xfs/scrub/cow_repair.c          |   18 +--
 fs/xfs/scrub/ialloc.c              |    8 +-
 fs/xfs/scrub/ialloc_repair.c       |   25 ++---
 fs/xfs/scrub/newbt.c               |   46 ++++-----
 fs/xfs/scrub/reap.c                |    8 +-
 fs/xfs/scrub/refcount_repair.c     |    5 -
 fs/xfs/scrub/repair.c              |   13 +-
 fs/xfs/scrub/rmap_repair.c         |    9 +-
 fs/xfs/scrub/trace.h               |  161 ++++++++++++++----------------
 fs/xfs/xfs_bmap_util.c             |    8 +-
 fs/xfs/xfs_buf_item_recover.c      |    5 -
 fs/xfs/xfs_discard.c               |   20 ++--
 fs/xfs/xfs_extent_busy.c           |   31 ++----
 fs/xfs/xfs_extent_busy.h           |   14 +--
 fs/xfs/xfs_extfree_item.c          |    4 -
 fs/xfs/xfs_filestream.c            |    5 -
 fs/xfs/xfs_fsmap.c                 |   25 ++---
 fs/xfs/xfs_health.c                |    8 +-
 fs/xfs/xfs_inode.c                 |    5 -
 fs/xfs/xfs_iunlink_item.c          |   13 +-
 fs/xfs/xfs_iwalk.c                 |   17 ++-
 fs/xfs/xfs_log_cil.c               |    3 -
 fs/xfs/xfs_log_recover.c           |    5 -
 fs/xfs/xfs_trace.c                 |    1 
 fs/xfs/xfs_trace.h                 |  191 +++++++++++++++---------------------
 fs/xfs/xfs_trans.c                 |    2 
 44 files changed, 459 insertions(+), 531 deletions(-)

[PATCHSET v5.5 02/10] xfs: create a generic allocation group structure

[Darrick J. Wong]

Hi all,

Soon we'll be sharding the realtime volume into separate allocation
groups.  These rt groups will /mostly/ behave the same as the ones on
the data device, but since rt groups don't have quite the same set of
struct fields as perags, let's hoist the parts that will be shared by
both into a common xfs_group object.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=generic-groups-6.13
---
Commits in this patchset:
 * xfs: factor out a xfs_iwalk_args helper
 * xfs: factor out a generic xfs_group structure
 * xfs: add a xfs_group_next_range helper
 * xfs: switch perag iteration from the for_each macros to a while based iterator
 * xfs: move metadata health tracking to the generic group structure
 * xfs: mark xfs_perag_intent_{hold,rele} static
 * xfs: move draining of deferred operations to the generic group structure
 * xfs: move the online repair rmap hooks to the generic group structure
 * xfs: return the busy generation from xfs_extent_busy_list_empty
 * xfs: convert extent busy tracepoints to the generic group structure
 * xfs: convert busy extent tracking to the generic group structure
 * xfs: add a generic group pointer to the btree cursor
 * xfs: store a generic xfs_group pointer in xfs_getfsmap_info
 * xfs: add group based bno conversion helpers
 * xfs: remove xfs_group_intent_hold and xfs_group_intent_rele
 * xfs: store a generic group structure in the intents
---
 fs/xfs/Makefile                    |    1 
 fs/xfs/libxfs/xfs_ag.c             |  149 ++++-------------------
 fs/xfs/libxfs/xfs_ag.h             |  165 ++++++++++++++-----------
 fs/xfs/libxfs/xfs_ag_resv.c        |   19 ++-
 fs/xfs/libxfs/xfs_alloc.c          |   74 ++++++-----
 fs/xfs/libxfs/xfs_alloc.h          |    2 
 fs/xfs/libxfs/xfs_alloc_btree.c    |   30 ++---
 fs/xfs/libxfs/xfs_bmap.c           |    2 
 fs/xfs/libxfs/xfs_bmap.h           |    2 
 fs/xfs/libxfs/xfs_btree.c          |   37 ++----
 fs/xfs/libxfs/xfs_btree.h          |    3 
 fs/xfs/libxfs/xfs_btree_mem.c      |    6 -
 fs/xfs/libxfs/xfs_group.c          |  225 ++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_group.h          |  131 ++++++++++++++++++++
 fs/xfs/libxfs/xfs_health.h         |   45 +++----
 fs/xfs/libxfs/xfs_ialloc.c         |   50 ++++----
 fs/xfs/libxfs/xfs_ialloc_btree.c   |   27 ++--
 fs/xfs/libxfs/xfs_refcount.c       |   26 ++--
 fs/xfs/libxfs/xfs_refcount.h       |    2 
 fs/xfs/libxfs/xfs_refcount_btree.c |   14 +-
 fs/xfs/libxfs/xfs_rmap.c           |   42 +++---
 fs/xfs/libxfs/xfs_rmap.h           |    6 -
 fs/xfs/libxfs/xfs_rmap_btree.c     |   28 ++--
 fs/xfs/libxfs/xfs_sb.c             |   28 ++--
 fs/xfs/libxfs/xfs_types.c          |    5 -
 fs/xfs/libxfs/xfs_types.h          |    8 +
 fs/xfs/scrub/agheader_repair.c     |   22 ++-
 fs/xfs/scrub/alloc.c               |    2 
 fs/xfs/scrub/alloc_repair.c        |   12 +-
 fs/xfs/scrub/bmap.c                |    8 +
 fs/xfs/scrub/bmap_repair.c         |    9 +
 fs/xfs/scrub/common.c              |    4 -
 fs/xfs/scrub/common.h              |    3 
 fs/xfs/scrub/cow_repair.c          |    9 +
 fs/xfs/scrub/fscounters.c          |   10 +-
 fs/xfs/scrub/health.c              |   21 +--
 fs/xfs/scrub/ialloc.c              |   14 +-
 fs/xfs/scrub/ialloc_repair.c       |    2 
 fs/xfs/scrub/inode_repair.c        |    5 -
 fs/xfs/scrub/iscan.c               |    4 -
 fs/xfs/scrub/newbt.c               |    8 +
 fs/xfs/scrub/reap.c                |    2 
 fs/xfs/scrub/refcount.c            |    3 
 fs/xfs/scrub/repair.c              |    4 -
 fs/xfs/scrub/rmap.c                |    4 -
 fs/xfs/scrub/rmap_repair.c         |   16 +-
 fs/xfs/scrub/trace.h               |   82 ++++++------
 fs/xfs/xfs_bmap_item.c             |    5 -
 fs/xfs/xfs_discard.c               |   20 ++-
 fs/xfs/xfs_drain.c                 |   78 +++++-------
 fs/xfs/xfs_drain.h                 |   22 +--
 fs/xfs/xfs_extent_busy.c           |  201 ++++++++++++++++++------------
 fs/xfs/xfs_extent_busy.h           |   59 +++------
 fs/xfs/xfs_extfree_item.c          |   14 +-
 fs/xfs/xfs_filestream.c            |    8 +
 fs/xfs/xfs_fsmap.c                 |   49 ++++---
 fs/xfs/xfs_fsops.c                 |   10 +-
 fs/xfs/xfs_health.c                |   99 +++++++--------
 fs/xfs/xfs_icache.c                |   60 +++------
 fs/xfs/xfs_inode.c                 |    6 -
 fs/xfs/xfs_iwalk.c                 |   99 ++++++---------
 fs/xfs/xfs_iwalk.h                 |    7 -
 fs/xfs/xfs_log_recover.c           |   11 +-
 fs/xfs/xfs_mount.h                 |   36 +++++
 fs/xfs/xfs_refcount_item.c         |    9 +
 fs/xfs/xfs_reflink.c               |    7 -
 fs/xfs/xfs_rmap_item.c             |    9 +
 fs/xfs/xfs_super.c                 |   11 +-
 fs/xfs/xfs_trace.c                 |    1 
 fs/xfs/xfs_trace.h                 |  238 ++++++++++++++++++++++--------------
 70 files changed, 1380 insertions(+), 1050 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_group.c
 create mode 100644 fs/xfs/libxfs/xfs_group.h

[PATCHSET v5.5 03/10] xfs: metadata inode directory trees

[Darrick J. Wong]

Hi all,

This series delivers a new feature -- metadata inode directories.  This
is a separate directory tree (rooted in the superblock) that contains
only inodes that contain filesystem metadata.  Different metadata
objects can be looked up with regular paths.

Start by creating xfs_imeta{dir,file}* functions to mediate access to
the metadata directory tree.  By the end of this mega series, all
existing metadata inodes (rt+quota) will use this directory tree instead
of the superblock.

Next, define the metadir on-disk format, which consists of marking
inodes with a new iflag that says they're metadata.  This prevents
bulkstat and friends from ever getting their hands on fs metadata files.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=metadata-directory-tree-6.13
---
Commits in this patchset:
 * xfs: constify the xfs_sb predicates
 * xfs: constify the xfs_inode predicates
 * xfs: rename metadata inode predicates
 * xfs: standardize EXPERIMENTAL warning generation
 * xfs: define the on-disk format for the metadir feature
 * xfs: iget for metadata inodes
 * xfs: load metadata directory root at mount time
 * xfs: enforce metadata inode flag
 * xfs: read and write metadata inode directory tree
 * xfs: disable the agi rotor for metadata inodes
 * xfs: hide metadata inodes from everyone because they are special
 * xfs: advertise metadata directory feature
 * xfs: allow bulkstat to return metadata directories
 * xfs: don't count metadata directory files to quota
 * xfs: mark quota inodes as metadata files
 * xfs: adjust xfs_bmap_add_attrfork for metadir
 * xfs: record health problems with the metadata directory
 * xfs: refactor directory tree root predicates
 * xfs: do not count metadata directory files when doing online quotacheck
 * xfs: metadata files can have xattrs if metadir is enabled
 * xfs: adjust parent pointer scrubber for sb-rooted metadata files
 * xfs: fix di_metatype field of inodes that won't load
 * xfs: scrub metadata directories
 * xfs: check the metadata directory inumber in superblocks
 * xfs: move repair temporary files to the metadata directory tree
 * xfs: check metadata directory file path connectivity
 * xfs: confirm dotdot target before replacing it during a repair
 * xfs: repair metadata directory file path connectivity
---
 fs/xfs/Makefile                 |    5 
 fs/xfs/libxfs/xfs_attr.c        |    5 
 fs/xfs/libxfs/xfs_bmap.c        |    5 
 fs/xfs/libxfs/xfs_format.h      |  121 +++++++--
 fs/xfs/libxfs/xfs_fs.h          |   25 ++
 fs/xfs/libxfs/xfs_health.h      |    6 
 fs/xfs/libxfs/xfs_ialloc.c      |   58 +++-
 fs/xfs/libxfs/xfs_inode_buf.c   |   90 ++++++-
 fs/xfs/libxfs/xfs_inode_buf.h   |    3 
 fs/xfs/libxfs/xfs_inode_util.c  |    2 
 fs/xfs/libxfs/xfs_log_format.h  |    2 
 fs/xfs/libxfs/xfs_metadir.c     |  481 ++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_metadir.h     |   47 ++++
 fs/xfs/libxfs/xfs_metafile.c    |   52 ++++
 fs/xfs/libxfs/xfs_metafile.h    |   31 ++
 fs/xfs/libxfs/xfs_ondisk.h      |    2 
 fs/xfs/libxfs/xfs_sb.c          |   12 +
 fs/xfs/libxfs/xfs_types.c       |    4 
 fs/xfs/libxfs/xfs_types.h       |    2 
 fs/xfs/scrub/agheader.c         |    5 
 fs/xfs/scrub/common.c           |   65 ++++-
 fs/xfs/scrub/common.h           |    5 
 fs/xfs/scrub/dir.c              |   10 +
 fs/xfs/scrub/dir_repair.c       |   20 +
 fs/xfs/scrub/dirtree.c          |   32 ++
 fs/xfs/scrub/dirtree.h          |   12 -
 fs/xfs/scrub/findparent.c       |   28 ++
 fs/xfs/scrub/health.c           |    1 
 fs/xfs/scrub/inode.c            |   35 ++-
 fs/xfs/scrub/inode_repair.c     |   34 ++-
 fs/xfs/scrub/metapath.c         |  521 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/nlinks.c           |    4 
 fs/xfs/scrub/nlinks_repair.c    |    4 
 fs/xfs/scrub/orphanage.c        |    4 
 fs/xfs/scrub/parent.c           |   39 ++-
 fs/xfs/scrub/parent_repair.c    |   37 ++-
 fs/xfs/scrub/quotacheck.c       |    7 -
 fs/xfs/scrub/refcount_repair.c  |    2 
 fs/xfs/scrub/repair.c           |   14 +
 fs/xfs/scrub/repair.h           |    3 
 fs/xfs/scrub/scrub.c            |   12 +
 fs/xfs/scrub/scrub.h            |    2 
 fs/xfs/scrub/stats.c            |    1 
 fs/xfs/scrub/tempfile.c         |  105 ++++++++
 fs/xfs/scrub/tempfile.h         |    3 
 fs/xfs/scrub/trace.c            |    1 
 fs/xfs/scrub/trace.h            |   42 +++
 fs/xfs/xfs_dquot.c              |    1 
 fs/xfs/xfs_fsops.c              |    4 
 fs/xfs/xfs_health.c             |    2 
 fs/xfs/xfs_icache.c             |   74 ++++++
 fs/xfs/xfs_inode.c              |   19 +
 fs/xfs/xfs_inode.h              |   36 ++-
 fs/xfs/xfs_inode_item.c         |    7 -
 fs/xfs/xfs_inode_item_recover.c |    2 
 fs/xfs/xfs_ioctl.c              |    7 +
 fs/xfs/xfs_iops.c               |   15 +
 fs/xfs/xfs_itable.c             |   33 ++
 fs/xfs/xfs_itable.h             |    3 
 fs/xfs/xfs_message.c            |   51 ++++
 fs/xfs/xfs_message.h            |   20 +
 fs/xfs/xfs_mount.c              |   31 ++
 fs/xfs/xfs_mount.h              |   25 +-
 fs/xfs/xfs_pnfs.c               |    3 
 fs/xfs/xfs_qm.c                 |   36 +++
 fs/xfs/xfs_quota.h              |    5 
 fs/xfs/xfs_rtalloc.c            |   38 ++-
 fs/xfs/xfs_super.c              |   13 -
 fs/xfs/xfs_trace.c              |    2 
 fs/xfs/xfs_trace.h              |  102 ++++++++
 fs/xfs/xfs_trans_dquot.c        |    6 
 fs/xfs/xfs_xattr.c              |    3 
 72 files changed, 2333 insertions(+), 206 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_metadir.c
 create mode 100644 fs/xfs/libxfs/xfs_metadir.h
 create mode 100644 fs/xfs/libxfs/xfs_metafile.c
 create mode 100644 fs/xfs/libxfs/xfs_metafile.h
 create mode 100644 fs/xfs/scrub/metapath.c

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

[Darrick J. Wong]

Hi all,

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

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=incore-rtgroups-6.13
---
Commits in this patchset:
 * xfs: clean up xfs_getfsmap_helper arguments
 * xfs: create incore realtime group structures
 * xfs: define locking primitives for realtime groups
 * xfs: add a lockdep class key for rtgroup inodes
 * xfs: support caching rtgroup metadata inodes
 * xfs: add rtgroup-based realtime scrubbing context management
 * xfs: add a xfs_bmap_free_rtblocks helper
 * xfs: add a xfs_qm_unmount_rt helper
 * xfs: factor out a xfs_growfs_rt_alloc_blocks helper
 * xfs: cleanup xfs_getfsmap_rtdev_rtbitmap
 * xfs: split xfs_trim_rtdev_extents
 * xfs: move RT bitmap and summary information to the rtgroup
 * xfs: support creating per-RTG files in growfs
 * xfs: remove XFS_ILOCK_RT*
 * xfs: calculate RT bitmap and summary blocks based on sb_rextents
 * xfs: factor out a xfs_growfs_rt_alloc_fake_mount helper
 * xfs: use xfs_growfs_rt_alloc_fake_mount in xfs_growfs_rt_alloc_blocks
 * xfs: factor out a xfs_growfs_check_rtgeom helper
 * xfs: refactor xfs_rtbitmap_blockcount
 * xfs: refactor xfs_rtsummary_blockcount
 * xfs: make RT extent numbers relative to the rtgroup
---
 fs/xfs/Makefile                 |    1 
 fs/xfs/libxfs/xfs_bmap.c        |   46 ++-
 fs/xfs/libxfs/xfs_format.h      |    3 
 fs/xfs/libxfs/xfs_rtbitmap.c    |  199 ++++++++-------
 fs/xfs/libxfs/xfs_rtbitmap.h    |  147 ++++++-----
 fs/xfs/libxfs/xfs_rtgroup.c     |  484 ++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_rtgroup.h     |  274 +++++++++++++++++++++
 fs/xfs/libxfs/xfs_sb.c          |   13 +
 fs/xfs/libxfs/xfs_trans_resv.c  |    2 
 fs/xfs/libxfs/xfs_types.h       |    8 +
 fs/xfs/scrub/bmap.c             |   13 +
 fs/xfs/scrub/common.c           |   78 ++++++
 fs/xfs/scrub/common.h           |   30 ++
 fs/xfs/scrub/fscounters.c       |   25 +-
 fs/xfs/scrub/repair.c           |   24 ++
 fs/xfs/scrub/repair.h           |    7 +
 fs/xfs/scrub/rtbitmap.c         |   54 ++--
 fs/xfs/scrub/rtsummary.c        |  111 ++++----
 fs/xfs/scrub/rtsummary_repair.c |    7 -
 fs/xfs/scrub/scrub.c            |   33 ++
 fs/xfs/scrub/scrub.h            |   13 +
 fs/xfs/xfs_bmap_util.c          |    3 
 fs/xfs/xfs_buf_item_recover.c   |   25 ++
 fs/xfs/xfs_discard.c            |  100 +++++---
 fs/xfs/xfs_fsmap.c              |  329 ++++++++++++++-----------
 fs/xfs/xfs_fsmap.h              |   15 +
 fs/xfs/xfs_inode.c              |    3 
 fs/xfs/xfs_inode.h              |   13 -
 fs/xfs/xfs_iomap.c              |    4 
 fs/xfs/xfs_mount.c              |   15 +
 fs/xfs/xfs_mount.h              |   26 +-
 fs/xfs/xfs_qm.c                 |   27 ++
 fs/xfs/xfs_rtalloc.c            |  520 ++++++++++++++++++++++++---------------
 fs/xfs/xfs_super.c              |    3 
 fs/xfs/xfs_trace.c              |    1 
 fs/xfs/xfs_trace.h              |   74 ++++--
 36 files changed, 2020 insertions(+), 710 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_rtgroup.c
 create mode 100644 fs/xfs/libxfs/xfs_rtgroup.h

[PATCHSET v5.5 05/10] xfs: preparation for realtime allocation groups

[Darrick J. Wong]

Hi all,

Prepare for realtime groups by adding a few bug fixes and generic code
that will be necessary.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=rtgroups-prep-6.13
---
Commits in this patchset:
 * xfs: fix rt device offset calculations for FITRIM
 * iomap: add a merge boundary flag
---
 fs/iomap/buffered-io.c |    6 ++++++
 fs/xfs/xfs_discard.c   |   19 +++++++++++--------
 include/linux/iomap.h  |    4 ++++
 3 files changed, 21 insertions(+), 8 deletions(-)

[PATCHSET v5.5 06/10] xfs: shard the realtime section

[Darrick J. Wong]

Hi all,

Right now, the realtime section uses a single pair of metadata inodes to
store the free space information.  This presents a scalability problem
since every thread trying to allocate or free rt extents have to lock
these files.  Solve this problem by sharding the realtime section into
separate realtime allocation groups.

While we're at it, define a superblock to be stamped into the start of
the rt section.  This enables utilities such as blkid to identify block
devices containing realtime sections, and avoids the situation where
anything written into block 0 of the realtime extent can be
misinterpreted as file data.

The best advantage for rtgroups will become evident later when we get to
adding rmap and reflink to the realtime volume, since the geometry
constraints are the same for rt groups and AGs.  Hence we can reuse all
that code directly.

This is a very large patchset, but it catches us up with 20 years of
technical debt that have accumulated.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=realtime-groups-6.13
---
Commits in this patchset:
 * xfs: define the format of rt groups
 * xfs: check the realtime superblock at mount time
 * xfs: update realtime super every time we update the primary fs super
 * xfs: export realtime group geometry via XFS_FSOP_GEOM
 * xfs: check that rtblock extents do not break rtsupers or rtgroups
 * xfs: add a helper to prevent bmap merges across rtgroup boundaries
 * xfs: add frextents to the lazysbcounters when rtgroups enabled
 * xfs: convert sick_map loops to use ARRAY_SIZE
 * xfs: record rt group metadata errors in the health system
 * xfs: export the geometry of realtime groups to userspace
 * xfs: add block headers to realtime bitmap and summary blocks
 * xfs: encode the rtbitmap in big endian format
 * xfs: encode the rtsummary in big endian format
 * xfs: grow the realtime section when realtime groups are enabled
 * xfs: store rtgroup information with a bmap intent
 * xfs: force swapext to a realtime file to use the file content exchange ioctl
 * xfs: support logging EFIs for realtime extents
 * xfs: support error injection when freeing rt extents
 * xfs: use realtime EFI to free extents when rtgroups are enabled
 * xfs: don't merge ioends across RTGs
 * xfs: make the RT allocator rtgroup aware
 * xfs: don't coalesce file mappings that cross rtgroup boundaries in scrub
 * xfs: scrub the realtime group superblock
 * xfs: repair realtime group superblock
 * xfs: scrub metadir paths for rtgroup metadata
 * xfs: mask off the rtbitmap and summary inodes when metadir in use
 * xfs: create helpers to deal with rounding xfs_fileoff_t to rtx boundaries
 * xfs: create helpers to deal with rounding xfs_filblks_t to rtx boundaries
 * xfs: make xfs_rtblock_t a segmented address like xfs_fsblock_t
 * xfs: adjust min_block usage in xfs_verify_agbno
 * xfs: move the min and max group block numbers to xfs_group
 * xfs: port the perag discard code to handle generic groups
 * xfs: implement busy extent tracking for rtgroups
 * xfs: use rtgroup busy extent list for FITRIM
---
 fs/xfs/Makefile                  |    1 
 fs/xfs/libxfs/xfs_ag.c           |   22 +
 fs/xfs/libxfs/xfs_ag.h           |   16 -
 fs/xfs/libxfs/xfs_alloc.c        |   15 +
 fs/xfs/libxfs/xfs_alloc.h        |   12 +
 fs/xfs/libxfs/xfs_bmap.c         |   84 +++++-
 fs/xfs/libxfs/xfs_defer.c        |    6 
 fs/xfs/libxfs/xfs_defer.h        |    1 
 fs/xfs/libxfs/xfs_format.h       |   74 +++++
 fs/xfs/libxfs/xfs_fs.h           |   28 ++
 fs/xfs/libxfs/xfs_group.h        |   33 ++
 fs/xfs/libxfs/xfs_health.h       |   42 ++-
 fs/xfs/libxfs/xfs_ialloc_btree.c |    2 
 fs/xfs/libxfs/xfs_log_format.h   |    6 
 fs/xfs/libxfs/xfs_log_recover.h  |    2 
 fs/xfs/libxfs/xfs_ondisk.h       |    4 
 fs/xfs/libxfs/xfs_rtbitmap.c     |  225 ++++++++++++---
 fs/xfs/libxfs/xfs_rtbitmap.h     |  114 ++++++--
 fs/xfs/libxfs/xfs_rtgroup.c      |  223 ++++++++++++++-
 fs/xfs/libxfs/xfs_rtgroup.h      |  104 ++++---
 fs/xfs/libxfs/xfs_sb.c           |  232 ++++++++++++++-
 fs/xfs/libxfs/xfs_sb.h           |    6 
 fs/xfs/libxfs/xfs_shared.h       |    4 
 fs/xfs/libxfs/xfs_types.c        |   35 ++
 fs/xfs/scrub/agheader.c          |   15 +
 fs/xfs/scrub/agheader_repair.c   |    4 
 fs/xfs/scrub/bmap.c              |   16 +
 fs/xfs/scrub/common.h            |    2 
 fs/xfs/scrub/fscounters_repair.c |    9 -
 fs/xfs/scrub/health.c            |   32 +-
 fs/xfs/scrub/metapath.c          |   92 ++++++
 fs/xfs/scrub/repair.c            |    6 
 fs/xfs/scrub/repair.h            |    3 
 fs/xfs/scrub/rgsuper.c           |   84 ++++++
 fs/xfs/scrub/rtsummary.c         |    5 
 fs/xfs/scrub/rtsummary_repair.c  |   15 +
 fs/xfs/scrub/scrub.c             |    7 
 fs/xfs/scrub/scrub.h             |    2 
 fs/xfs/scrub/stats.c             |    1 
 fs/xfs/scrub/trace.h             |    4 
 fs/xfs/xfs_bmap_item.c           |   25 +-
 fs/xfs/xfs_bmap_util.c           |   18 +
 fs/xfs/xfs_buf_item_recover.c    |   37 ++
 fs/xfs/xfs_discard.c             |  187 +++++++++++-
 fs/xfs/xfs_exchrange.c           |    2 
 fs/xfs/xfs_extent_busy.c         |    6 
 fs/xfs/xfs_extfree_item.c        |  270 ++++++++++++++++--
 fs/xfs/xfs_health.c              |  183 ++++++------
 fs/xfs/xfs_ioctl.c               |   39 +++
 fs/xfs/xfs_iomap.c               |   13 +
 fs/xfs/xfs_log_recover.c         |    2 
 fs/xfs/xfs_mount.h               |   15 +
 fs/xfs/xfs_rtalloc.c             |  577 ++++++++++++++++++++++++++++++++++----
 fs/xfs/xfs_rtalloc.h             |    6 
 fs/xfs/xfs_super.c               |   12 +
 fs/xfs/xfs_trace.h               |  150 ++++++++--
 fs/xfs/xfs_trans.c               |   64 +++-
 fs/xfs/xfs_trans.h               |    2 
 fs/xfs/xfs_trans_buf.c           |   25 +-
 59 files changed, 2704 insertions(+), 517 deletions(-)
 create mode 100644 fs/xfs/scrub/rgsuper.c

[PATCHSET v5.5 07/10] xfs: persist quota options with metadir

[Darrick J. Wong]

Hi all,

Store the quota files in the metadata directory tree instead of the
superblock.  Since we're introducing a new incompat feature flag, let's
also make the mount process bring up quotas in whatever state they were
when the filesystem was last unmounted, instead of requiring sysadmins
to remember that themselves.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=metadir-quotas-6.13
---
Commits in this patchset:
 * xfs: refactor xfs_qm_destroy_quotainos
 * xfs: use metadir for quota inodes
 * xfs: scrub quota file metapaths
 * xfs: persist quota flags with metadir
---
 fs/xfs/libxfs/xfs_dquot_buf.c  |  190 ++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_fs.h         |    6 +
 fs/xfs/libxfs/xfs_quota_defs.h |   43 +++++++
 fs/xfs/libxfs/xfs_sb.c         |    1 
 fs/xfs/scrub/metapath.c        |   76 ++++++++++++
 fs/xfs/xfs_mount.c             |   15 ++
 fs/xfs/xfs_mount.h             |   21 +++
 fs/xfs/xfs_qm.c                |  250 +++++++++++++++++++++++++++++++---------
 fs/xfs/xfs_qm_bhv.c            |   18 +++
 fs/xfs/xfs_quota.h             |    2 
 fs/xfs/xfs_super.c             |   25 ++++
 11 files changed, 586 insertions(+), 61 deletions(-)

[PATCHSET v5.5 08/10] xfs: enable quota for realtime volumes

[Darrick J. Wong]

Hi all,

At some point, I realized that I've refactored enough of the quota code
in XFS that I should evaluate whether or not quota actually works on
realtime volumes.  It turns out that it nearly works: the only broken
pieces are chown and delayed allocation, and reporting of project
quotas in the statvfs output for projinherit+rtinherit directories.

Fix these things and we can have realtime quotas again after 20 years.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=realtime-quotas-6.13
---
Commits in this patchset:
 * xfs: fix chown with rt quota
 * xfs: advertise realtime quota support in the xqm stat files
 * xfs: report realtime block quota limits on realtime directories
 * xfs: create quota preallocation watermarks for realtime quota
 * xfs: reserve quota for realtime files correctly
 * xfs: enable realtime quota again
---
 fs/xfs/xfs_dquot.c       |   37 +++++++++++++-----------
 fs/xfs/xfs_dquot.h       |   18 +++++++++---
 fs/xfs/xfs_iomap.c       |   37 +++++++++++++++++++-----
 fs/xfs/xfs_qm.c          |   72 ++++++++++++++++++++++++++++++----------------
 fs/xfs/xfs_qm_bhv.c      |   18 ++++++++----
 fs/xfs/xfs_quota.h       |   12 ++++----
 fs/xfs/xfs_rtalloc.c     |    4 ++-
 fs/xfs/xfs_stats.c       |    7 +++-
 fs/xfs/xfs_super.c       |   11 +++----
 fs/xfs/xfs_trans.c       |   31 +++++++++++++++++++-
 fs/xfs/xfs_trans_dquot.c |   11 +++++++
 11 files changed, 182 insertions(+), 76 deletions(-)

[PATCHSET v5.5 09/10] xfs: enable metadir

[Darrick J. Wong]

Hi all,

Actually enable this very large feature, which adds metadata directory
trees, allocation groups on the realtime volume, persistent quota
options, and quota for realtime files.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=metadir-6.13
---
Commits in this patchset:
 * xfs: update sb field checks when metadir is turned on
 * xfs: enable metadata directory feature
---
 fs/xfs/libxfs/xfs_format.h |    3 ++-
 fs/xfs/scrub/agheader.c    |   36 ++++++++++++++++++++++++------------
 2 files changed, 26 insertions(+), 13 deletions(-)

[PATCHSET v5.5 10/10] xfs: improve ondisk structure checks

[Darrick J. Wong]

Hi all,

Reorganize xfs_ondisk.h to group the build checks by type, then add a
bunch of missing checks that were in xfs/122 but not the build system.
With this, we can get rid of xfs/122.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

With a bit of luck, this should all go splendidly.
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=better-ondisk-6.13
---
Commits in this patchset:
 * xfs: convert struct typedefs in xfs_ondisk.h
 * xfs: separate space btree structures in xfs_ondisk.h
 * xfs: port ondisk structure checks from xfs/122 to the kernel
---
 fs/xfs/libxfs/xfs_ondisk.h |  186 ++++++++++++++++++++++++++++++++------------
 1 file changed, 137 insertions(+), 49 deletions(-)

[PATCH 01/23] xfs: fix simplify extent lookup in xfs_can_free_eofblocks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

In commit 11f4c3a53adde, we tried to simplify the extent lookup in
xfs_can_free_eofblocks so that it doesn't incur the overhead of all the
extra stuff that xfs_bmapi_read does around the iext lookup.

Unfortunately, this causes regressions on generic/603, xfs/108,
generic/219, xfs/173, generic/694, xfs/052, generic/230, and xfs/441
when always_cow is turned on.  In all cases, the regressions take the
form of alwayscow files consuming rather more space than the golden
output is expecting.  I observed that in all these cases, the cause of
the excess space usage was due to CoW fork delalloc reservations that go
beyond EOF.

For alwayscow files we allow posteof delalloc CoW reservations because
all writes go through the CoW fork.  Recall that all extents in the CoW
fork are accounted for via i_delayed_blks, which means that prior to
this patch, we'd invoke xfs_free_eofblocks on first close if anything
was in the CoW fork.  Now we don't do that.

Fix the problem by reverting the removal of the i_delayed_blks check.

Cc: <stable@vger.kernel.org> # v6.12-rc1
Fixes: 11f4c3a53adde ("xfs: simplify extent lookup in xfs_can_free_eofblocks")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_bmap_util.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 4719ec90029cb7..edaf193dbd5ccc 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -546,10 +546,14 @@ xfs_can_free_eofblocks(
 		return false;
 
 	/*
-	 * Check if there is an post-EOF extent to free.
+	 * Check if there is an post-EOF extent to free.  If there are any
+	 * delalloc blocks attached to the inode (data fork delalloc
+	 * reservations or CoW extents of any kind), we need to free them so
+	 * that inactivation doesn't fail to erase them.
 	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (xfs_iext_lookup_extent(ip, &ip->i_df, end_fsb, &icur, &imap))
+	if (ip->i_delayed_blks ||
+	    xfs_iext_lookup_extent(ip, &ip->i_df, end_fsb, &icur, &imap))
 		found_blocks = true;
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 	return found_blocks;

[PATCH 02/23] xfs: fix superfluous clearing of info->low in __xfs_getfsmap_datadev

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

The for_each_perag helpers update the agno passed in for each iteration,
and thus the "if (pag->pag_agno == start_ag)" check will always be true.

Add another variable for the loop iterator so that the field is only
cleared after the first iteration.

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 |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index ae18ab86e608b5..67140ef8c3232c 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -471,8 +471,7 @@ __xfs_getfsmap_datadev(
 	struct xfs_btree_cur		*bt_cur = NULL;
 	xfs_fsblock_t			start_fsb;
 	xfs_fsblock_t			end_fsb;
-	xfs_agnumber_t			start_ag;
-	xfs_agnumber_t			end_ag;
+	xfs_agnumber_t			start_ag, end_ag, ag;
 	uint64_t			eofs;
 	int				error = 0;
 
@@ -520,7 +519,8 @@ __xfs_getfsmap_datadev(
 	start_ag = XFS_FSB_TO_AGNO(mp, start_fsb);
 	end_ag = XFS_FSB_TO_AGNO(mp, end_fsb);
 
-	for_each_perag_range(mp, start_ag, end_ag, pag) {
+	ag = start_ag;
+	for_each_perag_range(mp, ag, end_ag, pag) {
 		/*
 		 * Set the AG high key from the fsmap high key if this
 		 * is the last AG that we're querying.

[PATCH 03/23] xfs: remove the unused pagb_count field in struct xfs_perag

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 |    1 -
 2 files changed, 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 5ca8d01068273d..1b6027ad9ce5f6 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -327,7 +327,6 @@ xfs_initialize_perag(
 		xfs_defer_drain_init(&pag->pag_intents_drain);
 		init_waitqueue_head(&pag->pagb_wait);
 		init_waitqueue_head(&pag->pag_active_wq);
-		pag->pagb_count = 0;
 		pag->pagb_tree = RB_ROOT;
 		xfs_hooks_init(&pag->pag_rmap_update_hooks);
 #endif /* __KERNEL__ */
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 9edfe0e9643964..79149a5ec44e9a 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -55,7 +55,6 @@ struct xfs_perag {
 	xfs_agino_t	pagl_leftrec;
 	xfs_agino_t	pagl_rightrec;
 
-	int		pagb_count;	/* pagb slots in use */
 	uint8_t		pagf_refcount_level; /* recount btree height */
 
 	/* Blocks reserved for all kinds of metadata. */

[PATCH 04/23] xfs: remove the unused pag_active_wq field in struct xfs_perag

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

pag_active_wq is only woken, but never waited for.

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 |    4 +---
 fs/xfs/libxfs/xfs_ag.h |    1 -
 2 files changed, 1 insertion(+), 4 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 1b6027ad9ce5f6..b9677abee70fd6 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -107,8 +107,7 @@ xfs_perag_rele(
 	struct xfs_perag	*pag)
 {
 	trace_xfs_perag_rele(pag, _RET_IP_);
-	if (atomic_dec_and_test(&pag->pag_active_ref))
-		wake_up(&pag->pag_active_wq);
+	atomic_dec(&pag->pag_active_ref);
 }
 
 /*
@@ -326,7 +325,6 @@ xfs_initialize_perag(
 		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
 		xfs_defer_drain_init(&pag->pag_intents_drain);
 		init_waitqueue_head(&pag->pagb_wait);
-		init_waitqueue_head(&pag->pag_active_wq);
 		pag->pagb_tree = RB_ROOT;
 		xfs_hooks_init(&pag->pag_rmap_update_hooks);
 #endif /* __KERNEL__ */
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 79149a5ec44e9a..958ca82524292f 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -34,7 +34,6 @@ struct xfs_perag {
 	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 */
-	wait_queue_head_t pag_active_wq;/* woken active_ref falls to zero */
 	unsigned long	pag_opstate;
 	uint8_t		pagf_bno_level;	/* # of levels in bno btree */
 	uint8_t		pagf_cnt_level;	/* # of levels in cnt btree */

[PATCH 05/23] xfs: pass a pag to xfs_difree_inode_chunk

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

We'll want to use more than just the agno field in a bit.

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_ialloc.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 271855227514cb..a58a66a77155c6 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1974,10 +1974,11 @@ xfs_dialloc(
 static int
 xfs_difree_inode_chunk(
 	struct xfs_trans		*tp,
-	xfs_agnumber_t			agno,
+	struct xfs_perag		*pag,
 	struct xfs_inobt_rec_incore	*rec)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_agnumber_t			agno = pag->pag_agno;
 	xfs_agblock_t			sagbno = XFS_AGINO_TO_AGBNO(mp,
 							rec->ir_startino);
 	int				startidx, endidx;
@@ -2148,7 +2149,7 @@ xfs_difree_inobt(
 			goto error0;
 		}
 
-		error = xfs_difree_inode_chunk(tp, pag->pag_agno, &rec);
+		error = xfs_difree_inode_chunk(tp, pag, &rec);
 		if (error)
 			goto error0;
 	} else {

[PATCH 06/23] xfs: remove the agno argument to xfs_free_ag_extent

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

xfs_free_ag_extent already has a pointer to the pag structure through
the agf buffer.  Use that instead of passing the redundant argument,
and do the same for the tracepoint.

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 |   10 ++++------
 fs/xfs/libxfs/xfs_alloc.h |    5 ++---
 fs/xfs/xfs_extfree_item.c |    4 ++--
 fs/xfs/xfs_trace.h        |   11 +++++------
 4 files changed, 13 insertions(+), 17 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 22bdbb3e9980c4..59a240b9462844 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2037,7 +2037,6 @@ int
 xfs_free_ag_extent(
 	struct xfs_trans		*tp,
 	struct xfs_buf			*agbp,
-	xfs_agnumber_t			agno,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	const struct xfs_owner_info	*oinfo,
@@ -2358,19 +2357,19 @@ xfs_free_ag_extent(
 	 * Update the freespace totals in the ag and superblock.
 	 */
 	error = xfs_alloc_update_counters(tp, agbp, len);
-	xfs_ag_resv_free_extent(agbp->b_pag, type, tp, len);
+	xfs_ag_resv_free_extent(pag, type, tp, len);
 	if (error)
 		goto error0;
 
 	XFS_STATS_INC(mp, xs_freex);
 	XFS_STATS_ADD(mp, xs_freeb, len);
 
-	trace_xfs_free_extent(mp, agno, bno, len, type, haveleft, haveright);
+	trace_xfs_free_extent(pag, bno, len, type, haveleft, haveright);
 
 	return 0;
 
  error0:
-	trace_xfs_free_extent(mp, agno, bno, len, type, -1, -1);
+	trace_xfs_free_extent(pag, bno, len, type, -1, -1);
 	if (bno_cur)
 		xfs_btree_del_cursor(bno_cur, XFS_BTREE_ERROR);
 	if (cnt_cur)
@@ -4012,8 +4011,7 @@ __xfs_free_extent(
 		goto err_release;
 	}
 
-	error = xfs_free_ag_extent(tp, agbp, pag->pag_agno, agbno, len, oinfo,
-			type);
+	error = xfs_free_ag_extent(tp, agbp, agbno, len, oinfo, type);
 	if (error)
 		goto err_release;
 
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 0165452e7cd055..88fbce5001185f 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -79,9 +79,8 @@ int xfs_alloc_put_freelist(struct xfs_perag *pag, struct xfs_trans *tp,
 		struct xfs_buf *agfbp, struct xfs_buf *agflbp,
 		xfs_agblock_t bno, int btreeblk);
 int xfs_free_ag_extent(struct xfs_trans *tp, struct xfs_buf *agbp,
-		xfs_agnumber_t agno, xfs_agblock_t bno,
-		xfs_extlen_t len, const struct xfs_owner_info *oinfo,
-		enum xfs_ag_resv_type type);
+		xfs_agblock_t bno, xfs_extlen_t len,
+		const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
 
 /*
  * Compute and fill in value of m_alloc_maxlevels.
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index abffc74a924f77..7f1be08dbc1123 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -547,8 +547,8 @@ xfs_agfl_free_finish_item(
 
 	error = xfs_alloc_read_agf(xefi->xefi_pag, tp, 0, &agbp);
 	if (!error)
-		error = xfs_free_ag_extent(tp, agbp, xefi->xefi_pag->pag_agno,
-				agbno, 1, &oinfo, XFS_AG_RESV_AGFL);
+		error = xfs_free_ag_extent(tp, agbp, agbno, 1, &oinfo,
+				XFS_AG_RESV_AGFL);
 
 	xfs_efd_add_extent(efdp, xefi);
 	xfs_extent_free_cancel_item(&xefi->xefi_list);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index fcb2bad4f76e4b..b9baafba031b25 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1758,10 +1758,9 @@ DEFINE_AGF_EVENT(xfs_agf);
 DEFINE_AGF_EVENT(xfs_agfl_reset);
 
 TRACE_EVENT(xfs_free_extent,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
-		 xfs_extlen_t len, enum xfs_ag_resv_type resv, int haveleft,
-		 int haveright),
-	TP_ARGS(mp, agno, agbno, len, resv, haveleft, haveright),
+	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len,
+		 enum xfs_ag_resv_type resv, int haveleft, int haveright),
+	TP_ARGS(pag, agbno, len, resv, haveleft, haveright),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -1772,8 +1771,8 @@ TRACE_EVENT(xfs_free_extent,
 		__field(int, haveright)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->resv = resv;

[PATCH 07/23] xfs: add xfs_agbno_to_fsb and xfs_agbno_to_daddr helpers

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Add helpers to convert an agbno to a daddr or fsbno based on a pag
structure.

This provides a simpler conversion and better type safety compared to the
existing code that passes the mount structure and the agno separately.

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             |    2 +-
 fs/xfs/libxfs/xfs_ag.h             |   16 ++++++++++++++++
 fs/xfs/libxfs/xfs_alloc.c          |   14 ++++++--------
 fs/xfs/libxfs/xfs_btree.c          |    7 +++----
 fs/xfs/libxfs/xfs_ialloc.c         |   29 +++++++++++++----------------
 fs/xfs/libxfs/xfs_ialloc_btree.c   |    2 +-
 fs/xfs/libxfs/xfs_refcount.c       |   11 ++++-------
 fs/xfs/libxfs/xfs_refcount_btree.c |    3 +--
 fs/xfs/scrub/bmap.c                |    5 ++---
 fs/xfs/scrub/bmap_repair.c         |    4 +---
 fs/xfs/scrub/cow_repair.c          |   18 +++++++-----------
 fs/xfs/scrub/ialloc.c              |    2 +-
 fs/xfs/scrub/ialloc_repair.c       |   13 +++++--------
 fs/xfs/scrub/newbt.c               |   17 +++++++----------
 fs/xfs/scrub/reap.c                |    8 +++-----
 fs/xfs/scrub/refcount_repair.c     |    5 ++---
 fs/xfs/scrub/repair.c              |    2 +-
 fs/xfs/scrub/rmap_repair.c         |    5 ++---
 fs/xfs/xfs_filestream.c            |    5 ++---
 fs/xfs/xfs_fsmap.c                 |   19 ++++++-------------
 fs/xfs/xfs_iwalk.c                 |    3 +--
 21 files changed, 85 insertions(+), 105 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index b9677abee70fd6..9de48f3c71235d 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -869,7 +869,7 @@ xfs_ag_shrink_space(
 
 	/* internal log shouldn't also show up in the free space btrees */
 	error = xfs_alloc_vextent_exact_bno(&args,
-			XFS_AGB_TO_FSB(mp, pag->pag_agno, aglen - delta));
+			xfs_agbno_to_fsb(pag, aglen - delta));
 	if (!error && args.agbno == NULLAGBLOCK)
 		error = -ENOSPC;
 
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 958ca82524292f..c0a30141ddc330 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -330,4 +330,20 @@ int xfs_ag_extend_space(struct xfs_perag *pag, struct xfs_trans *tp,
 			xfs_extlen_t len);
 int xfs_ag_get_geometry(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
 
+static inline xfs_fsblock_t
+xfs_agbno_to_fsb(
+	struct xfs_perag	*pag,
+	xfs_agblock_t		agbno)
+{
+	return XFS_AGB_TO_FSB(pag->pag_mount, pag->pag_agno, agbno);
+}
+
+static inline xfs_daddr_t
+xfs_agbno_to_daddr(
+	struct xfs_perag	*pag,
+	xfs_agblock_t		agbno)
+{
+	return XFS_AGB_TO_DADDR(pag->pag_mount, pag->pag_agno, agbno);
+}
+
 #endif /* __LIBXFS_AG_H */
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 59a240b9462844..847a028a6206fc 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1259,7 +1259,7 @@ xfs_alloc_ag_vextent_small(
 		struct xfs_buf	*bp;
 
 		error = xfs_trans_get_buf(args->tp, args->mp->m_ddev_targp,
-				XFS_AGB_TO_DADDR(args->mp, args->agno, fbno),
+				xfs_agbno_to_daddr(args->pag, fbno),
 				args->mp->m_bsize, 0, &bp);
 		if (error)
 			goto error;
@@ -2933,9 +2933,8 @@ xfs_alloc_fix_freelist(
 		 * Deferring the free disconnects freeing up the AGFL slot from
 		 * freeing the block.
 		 */
-		error = xfs_free_extent_later(tp,
-				XFS_AGB_TO_FSB(mp, args->agno, bno), 1,
-				&targs.oinfo, XFS_AG_RESV_AGFL, 0);
+		error = xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, bno),
+				1, &targs.oinfo, XFS_AG_RESV_AGFL, 0);
 		if (error)
 			goto out_agbp_relse;
 	}
@@ -3596,7 +3595,7 @@ xfs_alloc_vextent_finish(
 		goto out_drop_perag;
 	}
 
-	args->fsbno = XFS_AGB_TO_FSB(mp, args->agno, args->agbno);
+	args->fsbno = xfs_agbno_to_fsb(args->pag, args->agbno);
 
 	ASSERT(args->len >= args->minlen);
 	ASSERT(args->len <= args->maxlen);
@@ -3648,7 +3647,6 @@ xfs_alloc_vextent_this_ag(
 	struct xfs_alloc_arg	*args,
 	xfs_agnumber_t		agno)
 {
-	struct xfs_mount	*mp = args->mp;
 	xfs_agnumber_t		minimum_agno;
 	uint32_t		alloc_flags = 0;
 	int			error;
@@ -3661,8 +3659,8 @@ xfs_alloc_vextent_this_ag(
 
 	trace_xfs_alloc_vextent_this_ag(args);
 
-	error = xfs_alloc_vextent_check_args(args, XFS_AGB_TO_FSB(mp, agno, 0),
-			&minimum_agno);
+	error = xfs_alloc_vextent_check_args(args,
+			xfs_agbno_to_fsb(args->pag, 0), &minimum_agno);
 	if (error) {
 		if (error == -ENOSPC)
 			return 0;
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index a5c4af148853f8..804a1c96941127 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1017,21 +1017,20 @@ xfs_btree_readahead_agblock(
 	struct xfs_btree_block	*block)
 {
 	struct xfs_mount	*mp = cur->bc_mp;
-	xfs_agnumber_t		agno = cur->bc_ag.pag->pag_agno;
 	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_AGB_TO_DADDR(mp, agno, left),
+				xfs_agbno_to_daddr(cur->bc_ag.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_AGB_TO_DADDR(mp, agno, right),
+				xfs_agbno_to_daddr(cur->bc_ag.pag, right),
 				mp->m_bsize, cur->bc_ops->buf_ops);
 		rval++;
 	}
@@ -1091,7 +1090,7 @@ xfs_btree_ptr_to_daddr(
 
 	switch (cur->bc_ops->type) {
 	case XFS_BTREE_TYPE_AG:
-		*daddr = XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+		*daddr = xfs_agbno_to_daddr(cur->bc_ag.pag,
 				be32_to_cpu(ptr->s));
 		break;
 	case XFS_BTREE_TYPE_INODE:
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index a58a66a77155c6..6deb8346d1c34b 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -768,8 +768,7 @@ xfs_ialloc_ag_alloc(
 		/* Allow space for the inode btree to split. */
 		args.minleft = igeo->inobt_maxlevels;
 		error = xfs_alloc_vextent_exact_bno(&args,
-				XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
-						args.agbno));
+				xfs_agbno_to_fsb(pag, args.agbno));
 		if (error)
 			return error;
 
@@ -811,8 +810,8 @@ xfs_ialloc_ag_alloc(
 		 */
 		args.minleft = igeo->inobt_maxlevels;
 		error = xfs_alloc_vextent_near_bno(&args,
-				XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
-						be32_to_cpu(agi->agi_root)));
+				xfs_agbno_to_fsb(pag,
+					be32_to_cpu(agi->agi_root)));
 		if (error)
 			return error;
 	}
@@ -824,8 +823,8 @@ xfs_ialloc_ag_alloc(
 	if (isaligned && args.fsbno == NULLFSBLOCK) {
 		args.alignment = igeo->cluster_align;
 		error = xfs_alloc_vextent_near_bno(&args,
-				XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
-						be32_to_cpu(agi->agi_root)));
+				xfs_agbno_to_fsb(pag,
+					be32_to_cpu(agi->agi_root)));
 		if (error)
 			return error;
 	}
@@ -860,8 +859,8 @@ xfs_ialloc_ag_alloc(
 				 igeo->ialloc_blks;
 
 		error = xfs_alloc_vextent_near_bno(&args,
-				XFS_AGB_TO_FSB(args.mp, pag->pag_agno,
-						be32_to_cpu(agi->agi_root)));
+				xfs_agbno_to_fsb(pag,
+					be32_to_cpu(agi->agi_root)));
 		if (error)
 			return error;
 
@@ -1978,7 +1977,6 @@ xfs_difree_inode_chunk(
 	struct xfs_inobt_rec_incore	*rec)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
-	xfs_agnumber_t			agno = pag->pag_agno;
 	xfs_agblock_t			sagbno = XFS_AGINO_TO_AGBNO(mp,
 							rec->ir_startino);
 	int				startidx, endidx;
@@ -1989,8 +1987,7 @@ xfs_difree_inode_chunk(
 
 	if (!xfs_inobt_issparse(rec->ir_holemask)) {
 		/* not sparse, calculate extent info directly */
-		return xfs_free_extent_later(tp,
-				XFS_AGB_TO_FSB(mp, agno, sagbno),
+		return xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, sagbno),
 				M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES,
 				XFS_AG_RESV_NONE, 0);
 	}
@@ -2036,9 +2033,9 @@ xfs_difree_inode_chunk(
 
 		ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
-		error = xfs_free_extent_later(tp,
-				XFS_AGB_TO_FSB(mp, agno, agbno), contigblk,
-				&XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE, 0);
+		error = xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, agbno),
+				contigblk, &XFS_RMAP_OINFO_INODES,
+				XFS_AG_RESV_NONE, 0);
 		if (error)
 			return error;
 
@@ -2508,7 +2505,7 @@ xfs_imap(
 		offset = XFS_INO_TO_OFFSET(mp, ino);
 		ASSERT(offset < mp->m_sb.sb_inopblock);
 
-		imap->im_blkno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, agbno);
+		imap->im_blkno = xfs_agbno_to_daddr(pag, agbno);
 		imap->im_len = XFS_FSB_TO_BB(mp, 1);
 		imap->im_boffset = (unsigned short)(offset <<
 							mp->m_sb.sb_inodelog);
@@ -2538,7 +2535,7 @@ xfs_imap(
 	offset = ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock) +
 		XFS_INO_TO_OFFSET(mp, ino);
 
-	imap->im_blkno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, cluster_agbno);
+	imap->im_blkno = xfs_agbno_to_daddr(pag, cluster_agbno);
 	imap->im_len = XFS_FSB_TO_BB(mp, M_IGEO(mp)->blocks_per_cluster);
 	imap->im_boffset = (unsigned short)(offset << mp->m_sb.sb_inodelog);
 
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 401b42d52af686..3291541ae9665a 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -120,7 +120,7 @@ __xfs_inobt_alloc_block(
 	args.resv = resv;
 
 	error = xfs_alloc_vextent_near_bno(&args,
-			XFS_AGB_TO_FSB(args.mp, args.pag->pag_agno, sbno));
+			xfs_agbno_to_fsb(args.pag, sbno));
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 198b84117df138..5e166553a7a6e9 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1154,8 +1154,7 @@ xfs_refcount_adjust_extents(
 					goto out_error;
 				}
 			} else {
-				fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
-						cur->bc_ag.pag->pag_agno,
+				fsbno = xfs_agbno_to_fsb(cur->bc_ag.pag,
 						tmp.rc_startblock);
 				error = xfs_free_extent_later(cur->bc_tp, fsbno,
 						  tmp.rc_blockcount, NULL,
@@ -1217,8 +1216,7 @@ xfs_refcount_adjust_extents(
 			}
 			goto advloop;
 		} else {
-			fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
-					cur->bc_ag.pag->pag_agno,
+			fsbno = xfs_agbno_to_fsb(cur->bc_ag.pag,
 					ext.rc_startblock);
 			error = xfs_free_extent_later(cur->bc_tp, fsbno,
 					ext.rc_blockcount, NULL,
@@ -1320,7 +1318,7 @@ xfs_refcount_continue_op(
 		return -EFSCORRUPTED;
 	}
 
-	ri->ri_startblock = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+	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));
@@ -1956,8 +1954,7 @@ xfs_refcount_recover_cow_leftovers(
 			goto out_free;
 
 		/* Free the orphan record */
-		fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno,
-				rr->rr_rrec.rc_startblock);
+		fsb = xfs_agbno_to_fsb(pag, rr->rr_rrec.rc_startblock);
 		xfs_refcount_free_cow_extent(tp, fsb,
 				rr->rr_rrec.rc_blockcount);
 
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 795928d1a66d88..c4b10fbf8892a1 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -74,8 +74,7 @@ xfs_refcountbt_alloc_block(
 	args.resv = XFS_AG_RESV_METADATA;
 
 	error = xfs_alloc_vextent_near_bno(&args,
-			XFS_AGB_TO_FSB(args.mp, args.pag->pag_agno,
-					xfs_refc_block(args.mp)));
+			xfs_agbno_to_fsb(args.pag, xfs_refc_block(args.mp)));
 	if (error)
 		goto out_error;
 	if (args.fsbno == NULLFSBLOCK) {
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 5ab2ac53c92002..a43912227dd478 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -600,9 +600,8 @@ xchk_bmap_check_rmap(
 		if (irec.br_startoff != check_rec.rm_offset)
 			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					check_rec.rm_offset);
-		if (irec.br_startblock != XFS_AGB_TO_FSB(sc->mp,
-				cur->bc_ag.pag->pag_agno,
-				check_rec.rm_startblock))
+		if (irec.br_startblock !=
+		    xfs_agbno_to_fsb(cur->bc_ag.pag, 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 4505f4829d53f1..dc8fdd2da174ed 100644
--- a/fs/xfs/scrub/bmap_repair.c
+++ b/fs/xfs/scrub/bmap_repair.c
@@ -237,7 +237,6 @@ xrep_bmap_walk_rmap(
 	void				*priv)
 {
 	struct xrep_bmap		*rb = priv;
-	struct xfs_mount		*mp = cur->bc_mp;
 	xfs_fsblock_t			fsbno;
 	int				error = 0;
 
@@ -269,8 +268,7 @@ xrep_bmap_walk_rmap(
 	if ((rec->rm_flags & XFS_RMAP_UNWRITTEN) && !rb->allow_unwritten)
 		return -EFSCORRUPTED;
 
-	fsbno = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno,
-			rec->rm_startblock);
+	fsbno = xfs_agbno_to_fsb(cur->bc_ag.pag, 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 4de3f0f40f486c..19bded43c4fe1e 100644
--- a/fs/xfs/scrub/cow_repair.c
+++ b/fs/xfs/scrub/cow_repair.c
@@ -137,7 +137,6 @@ xrep_cow_mark_shared_staging(
 {
 	struct xrep_cow			*xc = priv;
 	struct xfs_refcount_irec	rrec;
-	xfs_fsblock_t			fsbno;
 
 	if (!xfs_refcount_check_domain(rec) ||
 	    rec->rc_domain != XFS_REFC_DOMAIN_SHARED)
@@ -145,9 +144,9 @@ xrep_cow_mark_shared_staging(
 
 	xrep_cow_trim_refcount(xc, &rrec, rec);
 
-	fsbno = XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno,
-			rrec.rc_startblock);
-	return xrep_cow_mark_file_range(xc, fsbno, rrec.rc_blockcount);
+	return xrep_cow_mark_file_range(xc,
+			xfs_agbno_to_fsb(cur->bc_ag.pag, rrec.rc_startblock),
+			rrec.rc_blockcount);
 }
 
 /*
@@ -178,8 +177,7 @@ xrep_cow_mark_missing_staging(
 		goto next;
 
 	error = xrep_cow_mark_file_range(xc,
-			XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno,
-				       xc->next_bno),
+			xfs_agbno_to_fsb(cur->bc_ag.pag, xc->next_bno),
 			rrec.rc_startblock - xc->next_bno);
 	if (error)
 		return error;
@@ -200,7 +198,6 @@ xrep_cow_mark_missing_staging_rmap(
 	void				*priv)
 {
 	struct xrep_cow			*xc = priv;
-	xfs_fsblock_t			fsbno;
 	xfs_agblock_t			rec_bno;
 	xfs_extlen_t			rec_len;
 	unsigned int			adj;
@@ -222,8 +219,8 @@ xrep_cow_mark_missing_staging_rmap(
 		rec_len -= adj;
 	}
 
-	fsbno = XFS_AGB_TO_FSB(xc->sc->mp, cur->bc_ag.pag->pag_agno, rec_bno);
-	return xrep_cow_mark_file_range(xc, fsbno, rec_len);
+	return xrep_cow_mark_file_range(xc,
+			xfs_agbno_to_fsb(cur->bc_ag.pag, rec_bno), rec_len);
 }
 
 /*
@@ -275,8 +272,7 @@ xrep_cow_find_bad(
 
 	if (xc->next_bno < xc->irec_startbno + xc->irec.br_blockcount) {
 		error = xrep_cow_mark_file_range(xc,
-				XFS_AGB_TO_FSB(sc->mp, pag->pag_agno,
-					       xc->next_bno),
+				xfs_agbno_to_fsb(pag, xc->next_bno),
 				xc->irec_startbno + xc->irec.br_blockcount -
 				xc->next_bno);
 		if (error)
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 750d7b0cd25a78..26938b90d22efc 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -396,7 +396,7 @@ 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_AGB_TO_DADDR(mp, agno, agbno);
+	imap.im_blkno = xfs_agbno_to_daddr(bs->cur->bc_ag.pag, 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;
diff --git a/fs/xfs/scrub/ialloc_repair.c b/fs/xfs/scrub/ialloc_repair.c
index c8d2196a04e15b..ff1a5952a9e7d0 100644
--- a/fs/xfs/scrub/ialloc_repair.c
+++ b/fs/xfs/scrub/ialloc_repair.c
@@ -307,7 +307,7 @@ xrep_ibt_process_cluster(
 	 * inobt because imap_to_bp directly maps the buffer without touching
 	 * either inode btree.
 	 */
-	imap.im_blkno = XFS_AGB_TO_DADDR(mp, sc->sa.pag->pag_agno, cluster_bno);
+	imap.im_blkno = xfs_agbno_to_daddr(sc->sa.pag, cluster_bno);
 	imap.im_len = XFS_FSB_TO_BB(mp, igeo->blocks_per_cluster);
 	imap.im_boffset = 0;
 	error = xfs_imap_to_bp(mp, sc->tp, &imap, &cluster_bp);
@@ -634,7 +634,6 @@ xrep_ibt_build_new_trees(
 	struct xfs_scrub	*sc = ri->sc;
 	struct xfs_btree_cur	*ino_cur;
 	struct xfs_btree_cur	*fino_cur = NULL;
-	xfs_fsblock_t		fsbno;
 	bool			need_finobt;
 	int			error;
 
@@ -656,9 +655,8 @@ xrep_ibt_build_new_trees(
 	 *
 	 * Start by setting up the inobt staging cursor.
 	 */
-	fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
-			XFS_IBT_BLOCK(sc->mp));
-	xrep_newbt_init_ag(&ri->new_inobt, sc, &XFS_RMAP_OINFO_INOBT, fsbno,
+	xrep_newbt_init_ag(&ri->new_inobt, sc, &XFS_RMAP_OINFO_INOBT,
+			xfs_agbno_to_fsb(sc->sa.pag, XFS_IBT_BLOCK(sc->mp)),
 			XFS_AG_RESV_NONE);
 	ri->new_inobt.bload.claim_block = xrep_ibt_claim_block;
 	ri->new_inobt.bload.get_records = xrep_ibt_get_records;
@@ -677,10 +675,9 @@ xrep_ibt_build_new_trees(
 		if (sc->mp->m_finobt_nores)
 			resv = XFS_AG_RESV_NONE;
 
-		fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
-				XFS_FIBT_BLOCK(sc->mp));
 		xrep_newbt_init_ag(&ri->new_finobt, sc, &XFS_RMAP_OINFO_INOBT,
-				fsbno, resv);
+				xfs_agbno_to_fsb(sc->sa.pag, XFS_FIBT_BLOCK(sc->mp)),
+				resv);
 		ri->new_finobt.bload.claim_block = xrep_fibt_claim_block;
 		ri->new_finobt.bload.get_records = xrep_fibt_get_records;
 
diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c
index 2aa14b7ab63060..baa00e1cf81ab2 100644
--- a/fs/xfs/scrub/newbt.c
+++ b/fs/xfs/scrub/newbt.c
@@ -186,11 +186,10 @@ xrep_newbt_add_extent(
 	xfs_agblock_t		agbno,
 	xfs_extlen_t		len)
 {
-	struct xfs_mount	*mp = xnr->sc->mp;
 	struct xfs_alloc_arg	args = {
 		.tp		= NULL, /* no autoreap */
 		.oinfo		= xnr->oinfo,
-		.fsbno		= XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno),
+		.fsbno		= xfs_agbno_to_fsb(pag, agbno),
 		.len		= len,
 		.resv		= xnr->resv,
 	};
@@ -210,8 +209,8 @@ xrep_newbt_validate_ag_alloc_hint(
 	    xfs_verify_fsbno(sc->mp, xnr->alloc_hint))
 		return;
 
-	xnr->alloc_hint = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
-					 XFS_AGFL_BLOCK(sc->mp) + 1);
+	xnr->alloc_hint =
+		xfs_agbno_to_fsb(sc->sa.pag, XFS_AGFL_BLOCK(sc->mp) + 1);
 }
 
 /* Allocate disk space for a new per-AG btree. */
@@ -376,7 +375,6 @@ xrep_newbt_free_extent(
 	struct xfs_scrub	*sc = xnr->sc;
 	xfs_agblock_t		free_agbno = resv->agbno;
 	xfs_extlen_t		free_aglen = resv->len;
-	xfs_fsblock_t		fsbno;
 	int			error;
 
 	if (!btree_committed || resv->used == 0) {
@@ -413,9 +411,9 @@ xrep_newbt_free_extent(
 	 * Use EFIs to free the reservations.  This reduces the chance
 	 * that we leak blocks if the system goes down.
 	 */
-	fsbno = XFS_AGB_TO_FSB(sc->mp, resv->pag->pag_agno, free_agbno);
-	error = xfs_free_extent_later(sc->tp, fsbno, free_aglen, &xnr->oinfo,
-			xnr->resv, XFS_FREE_EXTENT_SKIP_DISCARD);
+	error = xfs_free_extent_later(sc->tp,
+			xfs_agbno_to_fsb(resv->pag, free_agbno), free_aglen,
+			&xnr->oinfo, xnr->resv, XFS_FREE_EXTENT_SKIP_DISCARD);
 	if (error)
 		return error;
 
@@ -545,8 +543,7 @@ xrep_newbt_claim_block(
 			xnr->oinfo.oi_owner);
 
 	if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
-		ptr->l = cpu_to_be64(XFS_AGB_TO_FSB(mp, resv->pag->pag_agno,
-								agbno));
+		ptr->l = cpu_to_be64(xfs_agbno_to_fsb(resv->pag, agbno));
 	else
 		ptr->s = cpu_to_be32(agbno);
 
diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c
index 53697f3c5e1b0b..d65ad6aa856f4d 100644
--- a/fs/xfs/scrub/reap.c
+++ b/fs/xfs/scrub/reap.c
@@ -263,7 +263,6 @@ xreap_agextent_binval(
 	struct xfs_scrub	*sc = rs->sc;
 	struct xfs_perag	*pag = sc->sa.pag;
 	struct xfs_mount	*mp = sc->mp;
-	xfs_agnumber_t		agno = sc->sa.pag->pag_agno;
 	xfs_agblock_t		agbno_next = agbno + *aglenp;
 	xfs_agblock_t		bno = agbno;
 
@@ -284,7 +283,7 @@ xreap_agextent_binval(
 	 */
 	while (bno < agbno_next) {
 		struct xrep_bufscan	scan = {
-			.daddr		= XFS_AGB_TO_DADDR(mp, agno, bno),
+			.daddr		= xfs_agbno_to_daddr(pag, bno),
 			.max_sectors	= xrep_bufscan_max_sectors(mp,
 							agbno_next - bno),
 			.daddr_step	= XFS_FSB_TO_BB(mp, 1),
@@ -391,7 +390,7 @@ xreap_agextent_iter(
 	xfs_fsblock_t		fsbno;
 	int			error = 0;
 
-	fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno, agbno);
+	fsbno = xfs_agbno_to_fsb(sc->sa.pag, agbno);
 
 	/*
 	 * If there are other rmappings, this block is cross linked and must
@@ -780,7 +779,6 @@ xreap_bmapi_binval(
 	xfs_fileoff_t		off;
 	xfs_fileoff_t		max_off;
 	xfs_extlen_t		scan_blocks;
-	xfs_agnumber_t		agno = sc->sa.pag->pag_agno;
 	xfs_agblock_t		bno;
 	xfs_agblock_t		agbno;
 	xfs_agblock_t		agbno_next;
@@ -837,7 +835,7 @@ xreap_bmapi_binval(
 	 */
 	while (bno < agbno_next) {
 		struct xrep_bufscan	scan = {
-			.daddr		= XFS_AGB_TO_DADDR(mp, agno, bno),
+			.daddr		= xfs_agbno_to_daddr(pag, bno),
 			.max_sectors	= xrep_bufscan_max_sectors(mp,
 								scan_blocks),
 			.daddr_step	= XFS_FSB_TO_BB(mp, 1),
diff --git a/fs/xfs/scrub/refcount_repair.c b/fs/xfs/scrub/refcount_repair.c
index a00d7ce7ae5b87..4240fff459cb1d 100644
--- a/fs/xfs/scrub/refcount_repair.c
+++ b/fs/xfs/scrub/refcount_repair.c
@@ -590,7 +590,6 @@ xrep_refc_build_new_tree(
 	struct xfs_scrub	*sc = rr->sc;
 	struct xfs_btree_cur	*refc_cur;
 	struct xfs_perag	*pag = sc->sa.pag;
-	xfs_fsblock_t		fsbno;
 	int			error;
 
 	error = xrep_refc_sort_records(rr);
@@ -603,8 +602,8 @@ xrep_refc_build_new_tree(
 	 * to root the new btree while it's under construction and before we
 	 * attach it to the AG header.
 	 */
-	fsbno = XFS_AGB_TO_FSB(sc->mp, pag->pag_agno, xfs_refc_block(sc->mp));
-	xrep_newbt_init_ag(&rr->new_btree, sc, &XFS_RMAP_OINFO_REFC, fsbno,
+	xrep_newbt_init_ag(&rr->new_btree, sc, &XFS_RMAP_OINFO_REFC,
+			xfs_agbno_to_fsb(pag, xfs_refc_block(sc->mp)),
 			XFS_AG_RESV_METADATA);
 	rr->new_btree.bload.get_records = xrep_refc_get_records;
 	rr->new_btree.bload.claim_block = xrep_refc_claim_block;
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 155bbaaa496e44..382092a6ea6410 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -483,7 +483,7 @@ xrep_findroot_block(
 	int				block_level;
 	int				error = 0;
 
-	daddr = XFS_AGB_TO_DADDR(mp, ri->sc->sa.pag->pag_agno, agbno);
+	daddr = xfs_agbno_to_daddr(ri->sc->sa.pag, agbno);
 
 	/*
 	 * Blocks in the AGFL have stale contents that might just happen to
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index e8080eba37d29b..f99849ae8f67e2 100644
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -1272,7 +1272,6 @@ xrep_rmap_build_new_tree(
 	struct xfs_perag	*pag = sc->sa.pag;
 	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
 	struct xfs_btree_cur	*rmap_cur;
-	xfs_fsblock_t		fsbno;
 	int			error;
 
 	/*
@@ -1290,9 +1289,9 @@ xrep_rmap_build_new_tree(
 	 * rmapbt per-AG reservation, which we will adjust further after
 	 * committing the new btree.
 	 */
-	fsbno = XFS_AGB_TO_FSB(sc->mp, pag->pag_agno, XFS_RMAP_BLOCK(sc->mp));
 	xrep_newbt_init_ag(&rr->new_btree, sc, &XFS_RMAP_OINFO_SKIP_UPDATE,
-			fsbno, XFS_AG_RESV_RMAPBT);
+			xfs_agbno_to_fsb(pag, XFS_RMAP_BLOCK(sc->mp)),
+			XFS_AG_RESV_RMAPBT);
 	rr->new_btree.bload.get_records = xrep_rmap_get_records;
 	rr->new_btree.bload.claim_block = xrep_rmap_claim_block;
 	rr->new_btree.alloc_vextent = xrep_rmap_alloc_vextent;
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 290ba8887d29e9..f2caebb78dd25d 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -227,7 +227,7 @@ xfs_filestream_lookup_association(
 
 	trace_xfs_filestream_lookup(pag, ap->ip->i_ino);
 
-	ap->blkno = XFS_AGB_TO_FSB(args->mp, pag->pag_agno, 0);
+	ap->blkno = xfs_agbno_to_fsb(pag, 0);
 	xfs_bmap_adjacent(ap);
 
 	/*
@@ -344,7 +344,6 @@ xfs_filestream_select_ag(
 	struct xfs_alloc_arg	*args,
 	xfs_extlen_t		*longest)
 {
-	struct xfs_mount	*mp = args->mp;
 	struct xfs_inode	*pip;
 	xfs_ino_t		ino = 0;
 	int			error = 0;
@@ -370,7 +369,7 @@ xfs_filestream_select_ag(
 		return error;
 
 out_select:
-	ap->blkno = XFS_AGB_TO_FSB(mp, args->pag->pag_agno, 0);
+	ap->blkno = xfs_agbno_to_fsb(args->pag, 0);
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 67140ef8c3232c..eff198ae1ce33a 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -391,15 +391,11 @@ xfs_getfsmap_datadev_helper(
 	const struct xfs_rmap_irec	*rec,
 	void				*priv)
 {
-	struct xfs_mount		*mp = cur->bc_mp;
 	struct xfs_getfsmap_info	*info = priv;
-	xfs_fsblock_t			fsb;
-	xfs_daddr_t			rec_daddr;
 
-	fsb = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno, rec->rm_startblock);
-	rec_daddr = XFS_FSB_TO_DADDR(mp, fsb);
-
-	return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr, 0);
+	return xfs_getfsmap_helper(cur->bc_tp, info, rec,
+			xfs_agbno_to_daddr(cur->bc_ag.pag, rec->rm_startblock),
+			0);
 }
 
 /* Transform a bnobt irec into a fsmap */
@@ -409,13 +405,8 @@ xfs_getfsmap_datadev_bnobt_helper(
 	const struct xfs_alloc_rec_incore *rec,
 	void				*priv)
 {
-	struct xfs_mount		*mp = cur->bc_mp;
 	struct xfs_getfsmap_info	*info = priv;
 	struct xfs_rmap_irec		irec;
-	xfs_daddr_t			rec_daddr;
-
-	rec_daddr = XFS_AGB_TO_DADDR(mp, cur->bc_ag.pag->pag_agno,
-			rec->ar_startblock);
 
 	irec.rm_startblock = rec->ar_startblock;
 	irec.rm_blockcount = rec->ar_blockcount;
@@ -423,7 +414,9 @@ xfs_getfsmap_datadev_bnobt_helper(
 	irec.rm_offset = 0;
 	irec.rm_flags = 0;
 
-	return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr, 0);
+	return xfs_getfsmap_helper(cur->bc_tp, info, &irec,
+			xfs_agbno_to_daddr(cur->bc_ag.pag, rec->ar_startblock),
+			0);
 }
 
 /* Set rmap flags based on the getfsmap flags */
diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index 86f14ec7c31fed..894318886a5670 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -100,7 +100,6 @@ xfs_iwalk_ichunk_ra(
 	struct xfs_inobt_rec_incore	*irec)
 {
 	struct xfs_ino_geometry		*igeo = M_IGEO(mp);
-	xfs_agnumber_t			agno = pag->pag_agno;
 	xfs_agblock_t			agbno;
 	struct blk_plug			plug;
 	int				i;	/* inode chunk index */
@@ -114,7 +113,7 @@ xfs_iwalk_ichunk_ra(
 		imask = xfs_inobt_maskn(i, igeo->inodes_per_cluster);
 		if (imask & ~irec->ir_free) {
 			xfs_buf_readahead(mp->m_ddev_targp,
-					XFS_AGB_TO_DADDR(mp, agno, agbno),
+					xfs_agbno_to_daddr(pag, agbno),
 					igeo->blocks_per_cluster * mp->m_bsize,
 					&xfs_inode_buf_ops);
 		}

[PATCH 08/23] xfs: add a xfs_agino_to_ino helper

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Add a helpers to convert an agino to an ino based on a pag structure.

This provides a simpler conversion and better type safety compared to the
existing code that passes the mount structure and the agno separately.

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         |    8 ++++++++
 fs/xfs/libxfs/xfs_ialloc.c     |   24 +++++++++++-------------
 fs/xfs/scrub/agheader_repair.c |   16 ++++------------
 fs/xfs/scrub/common.c          |    2 +-
 fs/xfs/scrub/ialloc.c          |    3 +--
 fs/xfs/scrub/ialloc_repair.c   |    6 ++----
 fs/xfs/xfs_inode.c             |    5 ++---
 fs/xfs/xfs_iwalk.c             |   12 ++++++------
 fs/xfs/xfs_log_recover.c       |    5 ++---
 9 files changed, 37 insertions(+), 44 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index c0a30141ddc330..e0f567d90debee 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -346,4 +346,12 @@ xfs_agbno_to_daddr(
 	return XFS_AGB_TO_DADDR(pag->pag_mount, pag->pag_agno, agbno);
 }
 
+static inline xfs_ino_t
+xfs_agino_to_ino(
+	struct xfs_perag	*pag,
+	xfs_agino_t		agino)
+{
+	return XFS_AGINO_TO_INO(pag->pag_mount, pag->pag_agno, agino);
+}
+
 #endif /* __LIBXFS_AG_H */
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 6deb8346d1c34b..c072317a0fe514 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -914,8 +914,7 @@ xfs_ialloc_ag_alloc(
 		if (error == -EFSCORRUPTED) {
 			xfs_alert(args.mp,
 	"invalid sparse inode record: ino 0x%llx holemask 0x%x count %u",
-				  XFS_AGINO_TO_INO(args.mp, pag->pag_agno,
-						   rec.ir_startino),
+				  xfs_agino_to_ino(pag, rec.ir_startino),
 				  rec.ir_holemask, rec.ir_count);
 			xfs_force_shutdown(args.mp, SHUTDOWN_CORRUPT_INCORE);
 		}
@@ -1334,7 +1333,7 @@ xfs_dialloc_ag_inobt(
 	ASSERT(offset < XFS_INODES_PER_CHUNK);
 	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
 				   XFS_INODES_PER_CHUNK) == 0);
-	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
+	ino = xfs_agino_to_ino(pag, rec.ir_startino + offset);
 
 	if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
 		error = xfs_dialloc_check_ino(pag, tp, ino);
@@ -1615,7 +1614,7 @@ xfs_dialloc_ag(
 	ASSERT(offset < XFS_INODES_PER_CHUNK);
 	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
 				   XFS_INODES_PER_CHUNK) == 0);
-	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
+	ino = xfs_agino_to_ino(pag, rec.ir_startino + offset);
 
 	if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
 		error = xfs_dialloc_check_ino(pag, tp, ino);
@@ -2122,8 +2121,7 @@ xfs_difree_inobt(
 	if (!xfs_has_ikeep(mp) && rec.ir_free == XFS_INOBT_ALL_FREE &&
 	    mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) {
 		xic->deleted = true;
-		xic->first_ino = XFS_AGINO_TO_INO(mp, pag->pag_agno,
-				rec.ir_startino);
+		xic->first_ino = xfs_agino_to_ino(pag, rec.ir_startino);
 		xic->alloc = xfs_inobt_irec_to_allocmask(&rec);
 
 		/*
@@ -2322,10 +2320,10 @@ xfs_difree(
 		return -EINVAL;
 	}
 	agino = XFS_INO_TO_AGINO(mp, inode);
-	if (inode != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino))  {
-		xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
+	if (inode != xfs_agino_to_ino(pag, agino))  {
+		xfs_warn(mp, "%s: inode != xfs_agino_to_ino() (%llu != %llu).",
 			__func__, (unsigned long long)inode,
-			(unsigned long long)XFS_AGINO_TO_INO(mp, pag->pag_agno, agino));
+			(unsigned long long)xfs_agino_to_ino(pag, agino));
 		ASSERT(0);
 		return -EINVAL;
 	}
@@ -2456,7 +2454,7 @@ xfs_imap(
 	agino = XFS_INO_TO_AGINO(mp, ino);
 	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
 	if (agbno >= mp->m_sb.sb_agblocks ||
-	    ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
+	    ino != xfs_agino_to_ino(pag, agino)) {
 		error = -EINVAL;
 #ifdef DEBUG
 		/*
@@ -2471,11 +2469,11 @@ xfs_imap(
 				__func__, (unsigned long long)agbno,
 				(unsigned long)mp->m_sb.sb_agblocks);
 		}
-		if (ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
+		if (ino != xfs_agino_to_ino(pag, agino)) {
 			xfs_alert(mp,
-		"%s: ino (0x%llx) != XFS_AGINO_TO_INO() (0x%llx)",
+		"%s: ino (0x%llx) != xfs_agino_to_ino() (0x%llx)",
 				__func__, ino,
-				XFS_AGINO_TO_INO(mp, pag->pag_agno, agino));
+				xfs_agino_to_ino(pag, agino));
 		}
 		xfs_stack_trace();
 #endif /* DEBUG */
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 2f98d90d7fd66d..82a850eba6c88c 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -1038,12 +1038,10 @@ xrep_iunlink_reload_next(
 {
 	struct xfs_scrub	*sc = ragi->sc;
 	struct xfs_inode	*ip;
-	xfs_ino_t		ino;
 	xfs_agino_t		ret = NULLAGINO;
 	int			error;
 
-	ino = XFS_AGINO_TO_INO(sc->mp, sc->sa.pag->pag_agno, agino);
-	error = xchk_iget(ragi->sc, ino, &ip);
+	error = xchk_iget(ragi->sc, xfs_agino_to_ino(sc->sa.pag, agino), &ip);
 	if (error)
 		return ret;
 
@@ -1278,9 +1276,7 @@ xrep_iunlink_mark_ondisk_rec(
 		 * on because we haven't actually scrubbed the inobt or the
 		 * inodes yet.
 		 */
-		error = xchk_iget(ragi->sc,
-				XFS_AGINO_TO_INO(mp, sc->sa.pag->pag_agno,
-						 agino),
+		error = xchk_iget(ragi->sc, xfs_agino_to_ino(sc->sa.pag, agino),
 				&ip);
 		if (error)
 			continue;
@@ -1539,15 +1535,13 @@ xrep_iunlink_relink_next(
 
 	ip = xfs_iunlink_lookup(pag, agino);
 	if (!ip) {
-		xfs_ino_t	ino;
 		xfs_agino_t	prev_agino;
 
 		/*
 		 * No inode exists in cache.  Load it off the disk so that we
 		 * can reinsert it into the incore unlinked list.
 		 */
-		ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
-		error = xchk_iget(sc, ino, &ip);
+		error = xchk_iget(sc, xfs_agino_to_ino(pag, agino), &ip);
 		if (error)
 			return -EFSCORRUPTED;
 
@@ -1601,15 +1595,13 @@ xrep_iunlink_relink_prev(
 
 	ip = xfs_iunlink_lookup(pag, agino);
 	if (!ip) {
-		xfs_ino_t	ino;
 		xfs_agino_t	next_agino;
 
 		/*
 		 * No inode exists in cache.  Load it off the disk so that we
 		 * can reinsert it into the incore unlinked list.
 		 */
-		ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
-		error = xchk_iget(sc, ino, &ip);
+		error = xchk_iget(sc, xfs_agino_to_ino(pag, agino), &ip);
 		if (error)
 			return -EFSCORRUPTED;
 
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 22f5f1a9d3f09b..28095ed490fbf6 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -1336,7 +1336,7 @@ xchk_inode_is_allocated(
 	}
 
 	/* reject inode numbers outside existing AGs */
-	ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
+	ino = xfs_agino_to_ino(pag, agino);
 	if (!xfs_verify_ino(mp, ino))
 		return -EINVAL;
 
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 26938b90d22efc..c1c798076d66ab 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -303,7 +303,6 @@ xchk_iallocbt_check_cluster_ifree(
 	unsigned int			irec_ino,
 	struct xfs_dinode		*dip)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
 	xfs_ino_t			fsino;
 	xfs_agino_t			agino;
 	bool				irec_free;
@@ -319,7 +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(mp, bs->cur->bc_ag.pag->pag_agno, agino);
+	fsino = xfs_agino_to_ino(bs->cur->bc_ag.pag, agino);
 	irec_free = (irec->ir_free & XFS_INOBT_MASK(irec_ino));
 
 	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
diff --git a/fs/xfs/scrub/ialloc_repair.c b/fs/xfs/scrub/ialloc_repair.c
index ff1a5952a9e7d0..eac5c6f75a35ef 100644
--- a/fs/xfs/scrub/ialloc_repair.c
+++ b/fs/xfs/scrub/ialloc_repair.c
@@ -146,15 +146,12 @@ xrep_ibt_check_ifree(
 	struct xfs_scrub	*sc = ri->sc;
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_dinode	*dip;
-	xfs_ino_t		fsino;
 	xfs_agino_t		agino;
-	xfs_agnumber_t		agno = ri->sc->sa.pag->pag_agno;
 	unsigned int		cluster_buf_base;
 	unsigned int		offset;
 	int			error;
 
 	agino = cluster_ag_base + cluster_index;
-	fsino = XFS_AGINO_TO_INO(mp, agno, agino);
 
 	/* Inode uncached or half assembled, read disk buffer */
 	cluster_buf_base = XFS_INO_TO_OFFSET(mp, cluster_ag_base);
@@ -165,7 +162,8 @@ xrep_ibt_check_ifree(
 	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC)
 		return -EFSCORRUPTED;
 
-	if (dip->di_version >= 3 && be64_to_cpu(dip->di_ino) != fsino)
+	if (dip->di_version >= 3 &&
+	    be64_to_cpu(dip->di_ino) != xfs_agino_to_ino(ri->sc->sa.pag, agino))
 		return -EFSCORRUPTED;
 
 	/* Will the in-core inode tell us if it's in use? */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 19dcb569a3e7f8..5529ff39b64001 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1516,7 +1516,6 @@ xfs_iunlink_reload_next(
 	struct xfs_perag	*pag = agibp->b_pag;
 	struct xfs_mount	*mp = pag->pag_mount;
 	struct xfs_inode	*next_ip = NULL;
-	xfs_ino_t		ino;
 	int			error;
 
 	ASSERT(next_agino != NULLAGINO);
@@ -1538,8 +1537,8 @@ xfs_iunlink_reload_next(
 	 * but we'd rather shut down now since we're already running in a weird
 	 * situation.
 	 */
-	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, next_agino);
-	error = xfs_iget(mp, tp, ino, XFS_IGET_UNTRUSTED, 0, &next_ip);
+	error = xfs_iget(mp, tp, xfs_agino_to_ino(pag, next_agino),
+			XFS_IGET_UNTRUSTED, 0, &next_ip);
 	if (error) {
 		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		return error;
diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index 894318886a5670..ab5252f19509a6 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -176,7 +176,6 @@ xfs_iwalk_ag_recs(
 	struct xfs_mount	*mp = iwag->mp;
 	struct xfs_trans	*tp = iwag->tp;
 	struct xfs_perag	*pag = iwag->pag;
-	xfs_ino_t		ino;
 	unsigned int		i, j;
 	int			error;
 
@@ -207,9 +206,10 @@ xfs_iwalk_ag_recs(
 				continue;
 
 			/* Otherwise call our function. */
-			ino = XFS_AGINO_TO_INO(mp, pag->pag_agno,
-						irec->ir_startino + j);
-			error = iwag->iwalk_fn(mp, tp, ino, iwag->data);
+			error = iwag->iwalk_fn(mp, tp,
+					xfs_agino_to_ino(pag,
+						irec->ir_startino + j),
+					iwag->data);
 			if (error)
 				return error;
 		}
@@ -304,7 +304,7 @@ xfs_iwalk_ag_start(
 		return -EFSCORRUPTED;
 	}
 
-	iwag->lastino = XFS_AGINO_TO_INO(mp, pag->pag_agno,
+	iwag->lastino = xfs_agino_to_ino(pag,
 				irec->ir_startino + XFS_INODES_PER_CHUNK - 1);
 
 	/*
@@ -424,7 +424,7 @@ xfs_iwalk_ag(
 			break;
 
 		/* Make sure that we always move forward. */
-		rec_fsino = XFS_AGINO_TO_INO(mp, pag->pag_agno, irec->ir_startino);
+		rec_fsino = xfs_agino_to_ino(pag, irec->ir_startino);
 		if (iwag->lastino != NULLFSINO &&
 		    XFS_IS_CORRUPT(mp, iwag->lastino >= rec_fsino)) {
 			xfs_btree_mark_sick(cur);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 704aaadb61cf29..56772bbd38cdea 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2726,9 +2726,8 @@ xlog_recover_iunlink_bucket(
 
 	agino = be32_to_cpu(agi->agi_unlinked[bucket]);
 	while (agino != NULLAGINO) {
-		error = xfs_iget(mp, NULL,
-				XFS_AGINO_TO_INO(mp, pag->pag_agno, agino),
-				0, 0, &ip);
+		error = xfs_iget(mp, NULL, xfs_agino_to_ino(pag, agino), 0, 0,
+				&ip);
 		if (error)
 			break;
 

[PATCH 09/23] xfs: pass a pag to xfs_extent_busy_{search,reuse}

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Replace the [mp,agno] tuple with the perag structure, which will become
more useful later.

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       |    4 ++--
 fs/xfs/libxfs/xfs_alloc_btree.c |    2 +-
 fs/xfs/libxfs/xfs_rmap_btree.c  |    2 +-
 fs/xfs/xfs_discard.c            |    2 +-
 fs/xfs/xfs_extent_busy.c        |   12 ++++--------
 fs/xfs/xfs_extent_busy.h        |    8 ++++----
 6 files changed, 13 insertions(+), 17 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 847a028a6206fc..6970a47bea1bd2 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1252,7 +1252,7 @@ xfs_alloc_ag_vextent_small(
 	if (fbno == NULLAGBLOCK)
 		goto out;
 
-	xfs_extent_busy_reuse(args->mp, args->pag, fbno, 1,
+	xfs_extent_busy_reuse(args->pag, fbno, 1,
 			      (args->datatype & XFS_ALLOC_NOBUSY));
 
 	if (args->datatype & XFS_ALLOC_USERDATA) {
@@ -3616,7 +3616,7 @@ xfs_alloc_vextent_finish(
 		if (error)
 			goto out_drop_perag;
 
-		ASSERT(!xfs_extent_busy_search(mp, args->pag, args->agbno,
+		ASSERT(!xfs_extent_busy_search(args->pag, args->agbno,
 				args->len));
 	}
 
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index aada676eee519c..5175d0b4d32e48 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_mp, cur->bc_ag.pag, bno, 1, false);
+	xfs_extent_busy_reuse(cur->bc_ag.pag, bno, 1, false);
 
 	new->s = cpu_to_be32(bno);
 
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index ac2f1f499b76f6..b49006c1ca7eee 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(cur->bc_mp, pag, bno, 1, false);
+	xfs_extent_busy_reuse(pag, bno, 1, false);
 
 	new->s = cpu_to_be32(bno);
 	be32_add_cpu(&agf->agf_rmap_blocks, 1);
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index d8c4a5dcca7aea..1a91e97d25ffba 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -272,7 +272,7 @@ 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(mp, pag, fbno, flen)) {
+		if (xfs_extent_busy_search(pag, fbno, flen)) {
 			trace_xfs_discard_busy(mp, pag->pag_agno, fbno, flen);
 			goto next_extent;
 		}
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index a73e7c73b664c6..22c16fa56bcc44 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -101,7 +101,6 @@ xfs_extent_busy_insert_discard(
  */
 int
 xfs_extent_busy_search(
-	struct xfs_mount	*mp,
 	struct xfs_perag	*pag,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len)
@@ -148,7 +147,6 @@ xfs_extent_busy_search(
  */
 STATIC bool
 xfs_extent_busy_update_extent(
-	struct xfs_mount	*mp,
 	struct xfs_perag	*pag,
 	struct xfs_extent_busy	*busyp,
 	xfs_agblock_t		fbno,
@@ -280,24 +278,22 @@ xfs_extent_busy_update_extent(
 		ASSERT(0);
 	}
 
-	trace_xfs_extent_busy_reuse(mp, pag->pag_agno, fbno, flen);
+	trace_xfs_extent_busy_reuse(pag->pag_mount, pag->pag_agno, fbno, flen);
 	return true;
 
 out_force_log:
 	spin_unlock(&pag->pagb_lock);
-	xfs_log_force(mp, XFS_LOG_SYNC);
-	trace_xfs_extent_busy_force(mp, pag->pag_agno, fbno, flen);
+	xfs_log_force(pag->pag_mount, XFS_LOG_SYNC);
+	trace_xfs_extent_busy_force(pag->pag_mount, pag->pag_agno, fbno, flen);
 	spin_lock(&pag->pagb_lock);
 	return false;
 }
 
-
 /*
  * For a given extent [fbno, flen], make sure we can reuse it safely.
  */
 void
 xfs_extent_busy_reuse(
-	struct xfs_mount	*mp,
 	struct xfs_perag	*pag,
 	xfs_agblock_t		fbno,
 	xfs_extlen_t		flen,
@@ -323,7 +319,7 @@ xfs_extent_busy_reuse(
 			continue;
 		}
 
-		if (!xfs_extent_busy_update_extent(mp, pag, busyp, fbno, flen,
+		if (!xfs_extent_busy_update_extent(pag, busyp, fbno, flen,
 						  userdata))
 			goto restart;
 	}
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index 470032de31391b..847c904a19386c 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -58,12 +58,12 @@ xfs_extent_busy_clear(struct xfs_mount *mp, struct list_head *list,
 	bool do_discard);
 
 int
-xfs_extent_busy_search(struct xfs_mount *mp, struct xfs_perag *pag,
-	xfs_agblock_t bno, xfs_extlen_t len);
+xfs_extent_busy_search(struct xfs_perag *pag, xfs_agblock_t bno,
+		xfs_extlen_t len);
 
 void
-xfs_extent_busy_reuse(struct xfs_mount *mp, struct xfs_perag *pag,
-	xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata);
+xfs_extent_busy_reuse(struct xfs_perag *pag, xfs_agblock_t fbno,
+		xfs_extlen_t flen, bool userdata);
 
 bool
 xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno,

[PATCH 10/23] xfs: keep a reference to the pag for busy extents

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Processing of busy extents requires the perag structure, so keep the
reference while they are in flight.

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_discard.c     |    4 ++--
 fs/xfs/xfs_extent_busy.c |   15 ++++++++-------
 fs/xfs/xfs_extent_busy.h |    2 +-
 3 files changed, 11 insertions(+), 10 deletions(-)


diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 1a91e97d25ffba..5c00904e439305 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -117,11 +117,11 @@ xfs_discard_extents(
 
 	blk_start_plug(&plug);
 	list_for_each_entry(busyp, &extents->extent_list, list) {
-		trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
+		trace_xfs_discard_extent(mp, busyp->pag->pag_agno, busyp->bno,
 					 busyp->length);
 
 		error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
-				XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
+				xfs_agbno_to_daddr(busyp->pag, busyp->bno),
 				XFS_FSB_TO_BB(mp, busyp->length),
 				GFP_KERNEL, &bio);
 		if (error && error != -EOPNOTSUPP) {
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 22c16fa56bcc44..7c0595db29857f 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -34,7 +34,7 @@ xfs_extent_busy_insert_list(
 
 	new = kzalloc(sizeof(struct xfs_extent_busy),
 			GFP_KERNEL | __GFP_NOFAIL);
-	new->agno = pag->pag_agno;
+	new->pag = xfs_perag_hold(pag);
 	new->bno = bno;
 	new->length = len;
 	INIT_LIST_HEAD(&new->list);
@@ -526,12 +526,14 @@ xfs_extent_busy_clear_one(
 			busyp->flags = XFS_EXTENT_BUSY_DISCARDED;
 			return false;
 		}
-		trace_xfs_extent_busy_clear(pag->pag_mount, busyp->agno,
-				busyp->bno, busyp->length);
+		trace_xfs_extent_busy_clear(pag->pag_mount,
+				busyp->pag->pag_agno, busyp->bno,
+				busyp->length);
 		rb_erase(&busyp->rb_node, &pag->pagb_tree);
 	}
 
 	list_del_init(&busyp->list);
+	xfs_perag_put(busyp->pag);
 	kfree(busyp);
 	return true;
 }
@@ -554,10 +556,9 @@ xfs_extent_busy_clear(
 		return;
 
 	do {
+		struct xfs_perag	*pag = xfs_perag_hold(busyp->pag);
 		bool			wakeup = false;
-		struct xfs_perag	*pag;
 
-		pag = xfs_perag_get(mp, busyp->agno);
 		spin_lock(&pag->pagb_lock);
 		do {
 			next = list_next_entry(busyp, list);
@@ -565,7 +566,7 @@ xfs_extent_busy_clear(
 				wakeup = true;
 			busyp = next;
 		} while (!list_entry_is_head(busyp, list, list) &&
-			 busyp->agno == pag->pag_agno);
+			 busyp->pag == pag);
 
 		if (wakeup) {
 			pag->pagb_gen++;
@@ -662,7 +663,7 @@ xfs_extent_busy_ag_cmp(
 		container_of(l2, struct xfs_extent_busy, list);
 	s32 diff;
 
-	diff = b1->agno - b2->agno;
+	diff = b1->pag->pag_agno - b2->pag->pag_agno;
 	if (!diff)
 		diff = b1->bno - b2->bno;
 	return diff;
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index 847c904a19386c..72be61912c005f 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -20,7 +20,7 @@ struct xfs_alloc_arg;
 struct xfs_extent_busy {
 	struct rb_node	rb_node;	/* ag by-bno indexed search tree */
 	struct list_head list;		/* transaction busy extent list */
-	xfs_agnumber_t	agno;
+	struct xfs_perag *pag;
 	xfs_agblock_t	bno;
 	xfs_extlen_t	length;
 	unsigned int	flags;

[PATCH 11/23] xfs: remove the mount field from struct xfs_busy_extents

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

The mount field is only passed to xfs_extent_busy_clear, which never uses
it.

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_discard.c     |    5 ++---
 fs/xfs/xfs_extent_busy.c |    1 -
 fs/xfs/xfs_extent_busy.h |    4 +---
 fs/xfs/xfs_log_cil.c     |    3 +--
 fs/xfs/xfs_trans.c       |    2 +-
 5 files changed, 5 insertions(+), 10 deletions(-)


diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 5c00904e439305..e1b4a8c59d0cc8 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -81,7 +81,7 @@ xfs_discard_endio_work(
 	struct xfs_busy_extents	*extents =
 		container_of(work, struct xfs_busy_extents, endio_work);
 
-	xfs_extent_busy_clear(extents->mount, &extents->extent_list, false);
+	xfs_extent_busy_clear(&extents->extent_list, false);
 	kfree(extents->owner);
 }
 
@@ -301,7 +301,7 @@ xfs_trim_gather_extents(
 	 * we aren't going to issue a discard on them any more.
 	 */
 	if (error)
-		xfs_extent_busy_clear(mp, &extents->extent_list, false);
+		xfs_extent_busy_clear(&extents->extent_list, false);
 out_del_cursor:
 	xfs_btree_del_cursor(cur, error);
 out_trans_cancel:
@@ -347,7 +347,6 @@ xfs_trim_perag_extents(
 			break;
 		}
 
-		extents->mount = pag->pag_mount;
 		extents->owner = extents;
 		INIT_LIST_HEAD(&extents->extent_list);
 
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 7c0595db29857f..7353f9844684b0 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -545,7 +545,6 @@ xfs_extent_busy_clear_one(
  */
 void
 xfs_extent_busy_clear(
-	struct xfs_mount	*mp,
 	struct list_head	*list,
 	bool			do_discard)
 {
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index 72be61912c005f..7241035ce4ef9d 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -33,7 +33,6 @@ struct xfs_extent_busy {
  * to discard completion.
  */
 struct xfs_busy_extents {
-	struct xfs_mount	*mount;
 	struct list_head	extent_list;
 	struct work_struct	endio_work;
 
@@ -54,8 +53,7 @@ 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 xfs_mount *mp, struct list_head *list,
-	bool do_discard);
+xfs_extent_busy_clear(struct list_head *list, bool do_discard);
 
 int
 xfs_extent_busy_search(struct xfs_perag *pag, xfs_agblock_t bno,
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 80da0cf87d7a45..2e9157b650e647 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -907,7 +907,7 @@ xlog_cil_committed(
 	xlog_cil_ail_insert(ctx, abort);
 
 	xfs_extent_busy_sort(&ctx->busy_extents.extent_list);
-	xfs_extent_busy_clear(mp, &ctx->busy_extents.extent_list,
+	xfs_extent_busy_clear(&ctx->busy_extents.extent_list,
 			      xfs_has_discard(mp) && !abort);
 
 	spin_lock(&ctx->cil->xc_push_lock);
@@ -917,7 +917,6 @@ xlog_cil_committed(
 	xlog_cil_free_logvec(&ctx->lv_chain);
 
 	if (!list_empty(&ctx->busy_extents.extent_list)) {
-		ctx->busy_extents.mount = mp;
 		ctx->busy_extents.owner = ctx;
 		xfs_discard_extents(mp, &ctx->busy_extents);
 		return;
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index bdf3704dc30118..cee7f0564409bd 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -67,7 +67,7 @@ xfs_trans_free(
 	struct xfs_trans	*tp)
 {
 	xfs_extent_busy_sort(&tp->t_busy);
-	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
+	xfs_extent_busy_clear(&tp->t_busy, false);
 
 	trace_xfs_trans_free(tp, _RET_IP_);
 	xfs_trans_clear_context(tp);

[PATCH 12/23] xfs: remove the unused trace_xfs_iwalk_ag trace point

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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_trace.h |   19 -------------------
 1 file changed, 19 deletions(-)


diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index b9baafba031b25..35b07af3b71d51 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -4237,25 +4237,6 @@ DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_corrupt);
 DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_healthy);
 DEFINE_INODE_CORRUPT_EVENT(xfs_inode_unfixed_corruption);
 
-TRACE_EVENT(xfs_iwalk_ag,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agino_t startino),
-	TP_ARGS(mp, agno, startino),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_agnumber_t, agno)
-		__field(xfs_agino_t, startino)
-	),
-	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->startino = startino;
-	),
-	TP_printk("dev %d:%d agno 0x%x startino 0x%x",
-		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno,
-		  __entry->startino)
-)
-
 TRACE_EVENT(xfs_iwalk_ag_rec,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 struct xfs_inobt_rec_incore *irec),

[PATCH 13/23] xfs: remove the unused xrep_bmap_walk_rmap trace point

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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/trace.h |    1 -
 1 file changed, 1 deletion(-)


diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index c886d5d0eb021a..5eff6186724d4a 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2020,7 +2020,6 @@ DEFINE_EVENT(xrep_rmap_class, name, \
 		 uint64_t owner, uint64_t offset, unsigned int flags), \
 	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
 DEFINE_REPAIR_RMAP_EVENT(xrep_ibt_walk_rmap);
-DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_walk_rmap);
 
 TRACE_EVENT(xrep_abt_found,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,

[PATCH 14/23] xfs: constify pag arguments to trace points

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Trace points never modify their arguments.  Mark all the pag objects
passed to trace points.  The exception is the xfs_ag_resv_class, which
uses the xfs_perag_resv helper that can't be marked const due to
other users modifying the returned 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/scrub/trace.h |   34 +++++++++++++++++++---------------
 fs/xfs/xfs_trace.h   |   19 ++++++++++---------
 2 files changed, 29 insertions(+), 24 deletions(-)


diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 5eff6186724d4a..ae8b850fdd85ae 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -922,7 +922,8 @@ DEFINE_XCHK_FSFREEZE_EVENT(xchk_fsfreeze);
 DEFINE_XCHK_FSFREEZE_EVENT(xchk_fsthaw);
 
 TRACE_EVENT(xchk_refcount_incorrect,
-	TP_PROTO(struct xfs_perag *pag, const struct xfs_refcount_irec *irec,
+	TP_PROTO(const struct xfs_perag *pag,
+		 const struct xfs_refcount_irec *irec,
 		 xfs_nlink_t seen),
 	TP_ARGS(pag, irec, seen),
 	TP_STRUCT__entry(
@@ -1918,7 +1919,8 @@ TRACE_EVENT(xchk_dirtree_live_update,
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 
 DECLARE_EVENT_CLASS(xrep_extent_class,
-	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len),
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
+		 xfs_extlen_t len),
 	TP_ARGS(pag, agbno, len),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -1940,7 +1942,8 @@ DECLARE_EVENT_CLASS(xrep_extent_class,
 );
 #define DEFINE_REPAIR_EXTENT_EVENT(name) \
 DEFINE_EVENT(xrep_extent_class, name, \
-	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len), \
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \
+		 xfs_extlen_t len), \
 	TP_ARGS(pag, agbno, len))
 DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_unmap_extent);
 DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_free_extent);
@@ -1949,8 +1952,8 @@ DEFINE_REPAIR_EXTENT_EVENT(xreap_bmapi_binval);
 DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert);
 
 DECLARE_EVENT_CLASS(xrep_reap_find_class,
-	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len,
-		bool crosslinked),
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
+		 xfs_extlen_t len, bool crosslinked),
 	TP_ARGS(pag, agbno, len, crosslinked),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -1975,8 +1978,8 @@ DECLARE_EVENT_CLASS(xrep_reap_find_class,
 );
 #define DEFINE_REPAIR_REAP_FIND_EVENT(name) \
 DEFINE_EVENT(xrep_reap_find_class, name, \
-	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len, \
-		 bool crosslinked), \
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \
+		 xfs_extlen_t len, bool crosslinked), \
 	TP_ARGS(pag, agbno, len, crosslinked))
 DEFINE_REPAIR_REAP_FIND_EVENT(xreap_agextent_select);
 DEFINE_REPAIR_REAP_FIND_EVENT(xreap_bmapi_select);
@@ -2077,7 +2080,8 @@ TRACE_EVENT(xrep_ibt_found,
 )
 
 TRACE_EVENT(xrep_refc_found,
-	TP_PROTO(struct xfs_perag *pag, const struct xfs_refcount_irec *rec),
+	TP_PROTO(const struct xfs_perag *pag,
+		 const struct xfs_refcount_irec *rec),
 	TP_ARGS(pag, rec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -2595,7 +2599,7 @@ TRACE_EVENT(xrep_cow_replace_mapping,
 );
 
 TRACE_EVENT(xrep_cow_free_staging,
-	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno,
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
 		 xfs_extlen_t blockcount),
 	TP_ARGS(pag, agbno, blockcount),
 	TP_STRUCT__entry(
@@ -3312,7 +3316,7 @@ DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_rebuild);
 DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_reset_fork);
 
 TRACE_EVENT(xrep_iunlink_visit,
-	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+	TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
 		 xfs_agino_t bucket_agino, struct xfs_inode *ip),
 	TP_ARGS(pag, bucket, bucket_agino, ip),
 	TP_STRUCT__entry(
@@ -3402,7 +3406,7 @@ TRACE_EVENT(xrep_iunlink_reload_ondisk,
 );
 
 TRACE_EVENT(xrep_iunlink_walk_ondisk_bucket,
-	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+	TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
 		 xfs_agino_t prev_agino, xfs_agino_t next_agino),
 	TP_ARGS(pag, bucket, prev_agino, next_agino),
 	TP_STRUCT__entry(
@@ -3428,7 +3432,7 @@ TRACE_EVENT(xrep_iunlink_walk_ondisk_bucket,
 );
 
 DECLARE_EVENT_CLASS(xrep_iunlink_resolve_class,
-	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+	TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
 		 xfs_agino_t prev_agino, xfs_agino_t next_agino),
 	TP_ARGS(pag, bucket, prev_agino, next_agino),
 	TP_STRUCT__entry(
@@ -3454,7 +3458,7 @@ DECLARE_EVENT_CLASS(xrep_iunlink_resolve_class,
 );
 #define DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(name) \
 DEFINE_EVENT(xrep_iunlink_resolve_class, name, \
-	TP_PROTO(struct xfs_perag *pag, unsigned int bucket, \
+	TP_PROTO(const struct xfs_perag *pag, unsigned int bucket, \
 		 xfs_agino_t prev_agino, xfs_agino_t next_agino), \
 	TP_ARGS(pag, bucket, prev_agino, next_agino))
 DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_uncached);
@@ -3515,7 +3519,7 @@ TRACE_EVENT(xrep_iunlink_relink_prev,
 );
 
 TRACE_EVENT(xrep_iunlink_add_to_bucket,
-	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+	TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
 		 xfs_agino_t agino, xfs_agino_t curr_head),
 	TP_ARGS(pag, bucket, agino, curr_head),
 	TP_STRUCT__entry(
@@ -3541,7 +3545,7 @@ TRACE_EVENT(xrep_iunlink_add_to_bucket,
 );
 
 TRACE_EVENT(xrep_iunlink_commit_bucket,
-	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+	TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
 		 xfs_agino_t old_agino, xfs_agino_t agino),
 	TP_ARGS(pag, bucket, old_agino, agino),
 	TP_STRUCT__entry(
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 35b07af3b71d51..c5128b151dbfce 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -181,7 +181,7 @@ TRACE_EVENT(xlog_intent_recovery_failed,
 );
 
 DECLARE_EVENT_CLASS(xfs_perag_class,
-	TP_PROTO(struct xfs_perag *pag, unsigned long caller_ip),
+	TP_PROTO(const struct xfs_perag *pag, unsigned long caller_ip),
 	TP_ARGS(pag, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -207,7 +207,7 @@ DECLARE_EVENT_CLASS(xfs_perag_class,
 
 #define DEFINE_PERAG_REF_EVENT(name)	\
 DEFINE_EVENT(xfs_perag_class, name,	\
-	TP_PROTO(struct xfs_perag *pag, unsigned long caller_ip), \
+	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);
@@ -662,7 +662,7 @@ DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold_release);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_binval);
 
 DECLARE_EVENT_CLASS(xfs_filestream_class,
-	TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino),
+	TP_PROTO(const struct xfs_perag *pag, xfs_ino_t ino),
 	TP_ARGS(pag, ino),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -684,14 +684,14 @@ DECLARE_EVENT_CLASS(xfs_filestream_class,
 )
 #define DEFINE_FILESTREAM_EVENT(name) \
 DEFINE_EVENT(xfs_filestream_class, name, \
-	TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino), \
+	TP_PROTO(const struct xfs_perag *pag, xfs_ino_t ino), \
 	TP_ARGS(pag, ino))
 DEFINE_FILESTREAM_EVENT(xfs_filestream_free);
 DEFINE_FILESTREAM_EVENT(xfs_filestream_lookup);
 DEFINE_FILESTREAM_EVENT(xfs_filestream_scan);
 
 TRACE_EVENT(xfs_filestream_pick,
-	TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino),
+	TP_PROTO(const struct xfs_perag *pag, xfs_ino_t ino),
 	TP_ARGS(pag, ino),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -1758,8 +1758,9 @@ DEFINE_AGF_EVENT(xfs_agf);
 DEFINE_AGF_EVENT(xfs_agfl_reset);
 
 TRACE_EVENT(xfs_free_extent,
-	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len,
-		 enum xfs_ag_resv_type resv, int haveleft, int haveright),
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
+		 xfs_extlen_t len, enum xfs_ag_resv_type resv, int haveleft,
+		 int haveright),
 	TP_ARGS(pag, agbno, len, resv, haveleft, haveright),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -4652,7 +4653,7 @@ TRACE_EVENT(xfs_force_shutdown,
 
 #ifdef CONFIG_XFS_DRAIN_INTENTS
 DECLARE_EVENT_CLASS(xfs_perag_intents_class,
-	TP_PROTO(struct xfs_perag *pag, void *caller_ip),
+	TP_PROTO(const struct xfs_perag *pag, void *caller_ip),
 	TP_ARGS(pag, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -4675,7 +4676,7 @@ DECLARE_EVENT_CLASS(xfs_perag_intents_class,
 
 #define DEFINE_PERAG_INTENTS_EVENT(name)	\
 DEFINE_EVENT(xfs_perag_intents_class, name,					\
-	TP_PROTO(struct xfs_perag *pag, void *caller_ip), \
+	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);

[PATCH 15/23] xfs: pass a perag structure to the xfs_ag_resv_init_error trace point

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

And remove the single instance class indirection for it.

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_resv.c |    3 +--
 fs/xfs/xfs_trace.h          |   18 +++++-------------
 2 files changed, 6 insertions(+), 15 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 216423df939e5c..4b1bd7cc7ba28c 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -206,8 +206,7 @@ __xfs_ag_resv_init(
 	else
 		error = xfs_dec_fdblocks(mp, hidden_space, true);
 	if (error) {
-		trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
-				error, _RET_IP_);
+		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);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index c5128b151dbfce..14fb86daea61bf 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3139,11 +3139,10 @@ DEFINE_AG_RESV_EVENT(xfs_ag_resv_free_extent);
 DEFINE_AG_RESV_EVENT(xfs_ag_resv_critical);
 DEFINE_AG_RESV_EVENT(xfs_ag_resv_needed);
 
-/* simple AG-based error/%ip tracepoint class */
-DECLARE_EVENT_CLASS(xfs_ag_error_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, int error,
+TRACE_EVENT(xfs_ag_resv_init_error,
+	TP_PROTO(const struct xfs_perag *pag, int error,
 		 unsigned long caller_ip),
-	TP_ARGS(mp, agno, error, caller_ip),
+	TP_ARGS(pag, error, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -3151,8 +3150,8 @@ DECLARE_EVENT_CLASS(xfs_ag_error_class,
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->error = error;
 		__entry->caller_ip = caller_ip;
 	),
@@ -3163,13 +3162,6 @@ DECLARE_EVENT_CLASS(xfs_ag_error_class,
 		  (char *)__entry->caller_ip)
 );
 
-#define DEFINE_AG_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_ag_error_class, name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, int error, \
-		 unsigned long caller_ip), \
-	TP_ARGS(mp, agno, error, caller_ip))
-DEFINE_AG_ERROR_EVENT(xfs_ag_resv_init_error);
-
 /* refcount tracepoint classes */
 
 DECLARE_EVENT_CLASS(xfs_refcount_class,

[PATCH 16/23] xfs: pass objects to the xfs_irec_merge_{pre,post} trace points

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Pass the perag structure and the irec to these tracepoints so that the
decoding is only done when tracing is actually enabled and the call sites
look a lot neater.

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_ialloc.c |    7 ++-----
 fs/xfs/xfs_trace.h         |   33 +++++++++++++++++----------------
 2 files changed, 19 insertions(+), 21 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index c072317a0fe514..085032443f1267 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -606,15 +606,12 @@ xfs_inobt_insert_sprec(
 		goto error;
 	}
 
-	trace_xfs_irec_merge_pre(mp, pag->pag_agno, rec.ir_startino,
-				 rec.ir_holemask, nrec->ir_startino,
-				 nrec->ir_holemask);
+	trace_xfs_irec_merge_pre(pag, &rec, nrec);
 
 	/* merge to nrec to output the updated record */
 	__xfs_inobt_rec_merge(nrec, &rec);
 
-	trace_xfs_irec_merge_post(mp, pag->pag_agno, nrec->ir_startino,
-				  nrec->ir_holemask);
+	trace_xfs_irec_merge_post(pag, nrec);
 
 	error = xfs_inobt_rec_check_count(mp, nrec);
 	if (error)
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 14fb86daea61bf..efd89d79dff2b6 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -894,9 +894,10 @@ TRACE_EVENT(xfs_iomap_prealloc_size,
 )
 
 TRACE_EVENT(xfs_irec_merge_pre,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agino_t agino,
-		 uint16_t holemask, xfs_agino_t nagino, uint16_t nholemask),
-	TP_ARGS(mp, agno, agino, holemask, nagino, nholemask),
+	TP_PROTO(const struct xfs_perag *pag,
+		 const struct xfs_inobt_rec_incore *rec,
+		 const struct xfs_inobt_rec_incore *nrec),
+	TP_ARGS(pag, rec, nrec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -906,12 +907,12 @@ TRACE_EVENT(xfs_irec_merge_pre,
 		__field(uint16_t, nholemask)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->agino = agino;
-		__entry->holemask = holemask;
-		__entry->nagino = nagino;
-		__entry->nholemask = holemask;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->agino = rec->ir_startino;
+		__entry->holemask = rec->ir_holemask;
+		__entry->nagino = nrec->ir_startino;
+		__entry->nholemask = nrec->ir_holemask;
 	),
 	TP_printk("dev %d:%d agno 0x%x agino 0x%x holemask 0x%x new_agino 0x%x new_holemask 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -923,9 +924,9 @@ TRACE_EVENT(xfs_irec_merge_pre,
 )
 
 TRACE_EVENT(xfs_irec_merge_post,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agino_t agino,
-		 uint16_t holemask),
-	TP_ARGS(mp, agno, agino, holemask),
+	TP_PROTO(const struct xfs_perag *pag,
+		 const struct xfs_inobt_rec_incore *nrec),
+	TP_ARGS(pag, nrec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -933,10 +934,10 @@ TRACE_EVENT(xfs_irec_merge_post,
 		__field(uint16_t, holemask)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->agino = agino;
-		__entry->holemask = holemask;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->agino = nrec->ir_startino;
+		__entry->holemask = nrec->ir_holemask;
 	),
 	TP_printk("dev %d:%d agno 0x%x agino 0x%x holemask 0x%x",
 		  MAJOR(__entry->dev),

[PATCH 17/23] xfs: pass the iunlink item to the xfs_iunlink_update_dinode trace point

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

So that decoding is only done when tracing is actually enabled and the
call site look a lot neater.

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_iunlink_item.c |   13 ++++++-------
 fs/xfs/xfs_trace.c        |    1 +
 fs/xfs/xfs_trace.h        |   15 ++++++++-------
 3 files changed, 15 insertions(+), 14 deletions(-)


diff --git a/fs/xfs/xfs_iunlink_item.c b/fs/xfs/xfs_iunlink_item.c
index 2ddccb172fa013..1fd70a7aed6347 100644
--- a/fs/xfs/xfs_iunlink_item.c
+++ b/fs/xfs/xfs_iunlink_item.c
@@ -52,14 +52,14 @@ xfs_iunlink_log_dinode(
 	struct xfs_trans	*tp,
 	struct xfs_iunlink_item	*iup)
 {
-	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_inode	*ip = iup->ip;
 	struct xfs_dinode	*dip;
 	struct xfs_buf		*ibp;
+	xfs_agino_t		old_ptr;
 	int			offset;
 	int			error;
 
-	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &ibp);
+	error = xfs_imap_to_bp(tp->t_mountp, tp, &ip->i_imap, &ibp);
 	if (error)
 		return error;
 	/*
@@ -73,22 +73,21 @@ xfs_iunlink_log_dinode(
 	dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset);
 
 	/* Make sure the old pointer isn't garbage. */
-	if (be32_to_cpu(dip->di_next_unlinked) != iup->old_agino) {
+	old_ptr = be32_to_cpu(dip->di_next_unlinked);
+	if (old_ptr != iup->old_agino) {
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
 				sizeof(*dip), __this_address);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
 
-	trace_xfs_iunlink_update_dinode(mp, iup->pag->pag_agno,
-			XFS_INO_TO_AGINO(mp, ip->i_ino),
-			be32_to_cpu(dip->di_next_unlinked), iup->next_agino);
+	trace_xfs_iunlink_update_dinode(iup, old_ptr);
 
 	dip->di_next_unlinked = cpu_to_be32(iup->next_agino);
 	offset = ip->i_imap.im_boffset +
 			offsetof(struct xfs_dinode, di_next_unlinked);
 
-	xfs_dinode_calc_crc(mp, dip);
+	xfs_dinode_calc_crc(tp->t_mountp, dip);
 	xfs_trans_inode_buf(tp, ibp);
 	xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1);
 	return 0;
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 2af9f274e8724e..7ef50107224647 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -32,6 +32,7 @@
 #include "xfs_fsmap.h"
 #include "xfs_btree_staging.h"
 #include "xfs_icache.h"
+#include "xfs_iunlink_item.h"
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
 #include "xfs_error.h"
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index efd89d79dff2b6..7b1fbcf970655a 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -74,6 +74,7 @@ struct xfs_refcount_irec;
 struct xfs_fsmap;
 struct xfs_rmap_irec;
 struct xfs_icreate_log;
+struct xfs_iunlink_item;
 struct xfs_owner_info;
 struct xfs_trans_res;
 struct xfs_inobt_rec_incore;
@@ -4055,9 +4056,8 @@ TRACE_EVENT(xfs_iunlink_update_bucket,
 );
 
 TRACE_EVENT(xfs_iunlink_update_dinode,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agino_t agino,
-		 xfs_agino_t old_ptr, xfs_agino_t new_ptr),
-	TP_ARGS(mp, agno, agino, old_ptr, new_ptr),
+	TP_PROTO(const struct xfs_iunlink_item *iup, xfs_agino_t old_ptr),
+	TP_ARGS(iup, old_ptr),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -4066,11 +4066,12 @@ TRACE_EVENT(xfs_iunlink_update_dinode,
 		__field(xfs_agino_t, new_ptr)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->agino = agino;
+		__entry->dev = iup->pag->pag_mount->m_super->s_dev;
+		__entry->agno = iup->pag->pag_agno;
+		__entry->agino =
+			XFS_INO_TO_AGINO(iup->ip->i_mount, iup->ip->i_ino);
 		__entry->old_ptr = old_ptr;
-		__entry->new_ptr = new_ptr;
+		__entry->new_ptr = iup->next_agino;
 	),
 	TP_printk("dev %d:%d agno 0x%x agino 0x%x old 0x%x new 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),

[PATCH 18/23] xfs: pass objects to the xrep_ibt_walk_rmap tracepoint

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Pass the perag structure and the irec so that the decoding is only done
when tracing is actually enabled and the call sites look a lot neater,
and remove the pointless class indirection.

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/ialloc_repair.c |    4 +---
 fs/xfs/scrub/trace.h         |   29 ++++++++++-------------------
 2 files changed, 11 insertions(+), 22 deletions(-)


diff --git a/fs/xfs/scrub/ialloc_repair.c b/fs/xfs/scrub/ialloc_repair.c
index eac5c6f75a35ef..f1c24f2da497ed 100644
--- a/fs/xfs/scrub/ialloc_repair.c
+++ b/fs/xfs/scrub/ialloc_repair.c
@@ -421,9 +421,7 @@ xrep_ibt_record_inode_blocks(
 	if (error)
 		return error;
 
-	trace_xrep_ibt_walk_rmap(mp, ri->sc->sa.pag->pag_agno,
-			rec->rm_startblock, rec->rm_blockcount, rec->rm_owner,
-			rec->rm_offset, rec->rm_flags);
+	trace_xrep_ibt_walk_rmap(ri->sc->sa.pag, rec);
 
 	/*
 	 * Record the free/hole masks for each inode cluster that could be
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index ae8b850fdd85ae..992f87f52b7656 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1984,11 +1984,9 @@ DEFINE_EVENT(xrep_reap_find_class, name, \
 DEFINE_REPAIR_REAP_FIND_EVENT(xreap_agextent_select);
 DEFINE_REPAIR_REAP_FIND_EVENT(xreap_bmapi_select);
 
-DECLARE_EVENT_CLASS(xrep_rmap_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agblock_t agbno, xfs_extlen_t len,
-		 uint64_t owner, uint64_t offset, unsigned int flags),
-	TP_ARGS(mp, agno, agbno, len, owner, offset, flags),
+TRACE_EVENT(xrep_ibt_walk_rmap,
+	TP_PROTO(const struct xfs_perag *pag, const struct xfs_rmap_irec *rec),
+	TP_ARGS(pag, rec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -1999,13 +1997,13 @@ DECLARE_EVENT_CLASS(xrep_rmap_class,
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->agbno = agbno;
-		__entry->len = len;
-		__entry->owner = owner;
-		__entry->offset = offset;
-		__entry->flags = flags;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->agbno = rec->rm_startblock;
+		__entry->len = rec->rm_blockcount;
+		__entry->owner = rec->rm_owner;
+		__entry->offset = rec->rm_offset;
+		__entry->flags = rec->rm_flags;
 	),
 	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -2016,13 +2014,6 @@ DECLARE_EVENT_CLASS(xrep_rmap_class,
 		  __entry->offset,
 		  __entry->flags)
 );
-#define DEFINE_REPAIR_RMAP_EVENT(name) \
-DEFINE_EVENT(xrep_rmap_class, name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
-		 xfs_agblock_t agbno, xfs_extlen_t len, \
-		 uint64_t owner, uint64_t offset, unsigned int flags), \
-	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
-DEFINE_REPAIR_RMAP_EVENT(xrep_ibt_walk_rmap);
 
 TRACE_EVENT(xrep_abt_found,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,

[PATCH 19/23] xfs: pass the pag to the trace_xrep_calc_ag_resblks{,_btsize} trace points

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

This requires holding the pag refcount a little longer, but allows for the
decoding to only happen when tracing is actually enabled, and cleans up the
callsites a bit.

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/repair.c |    9 ++++-----
 fs/xfs/scrub/trace.h  |   22 +++++++++++-----------
 2 files changed, 15 insertions(+), 16 deletions(-)


diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 382092a6ea6410..47f9b04e3798f1 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -331,10 +331,8 @@ xrep_calc_ag_resblks(
 		freelen = aglen;
 		usedlen = aglen;
 	}
-	xfs_perag_put(pag);
 
-	trace_xrep_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
-			freelen, usedlen);
+	trace_xrep_calc_ag_resblks(pag, icount, aglen, freelen, usedlen);
 
 	/*
 	 * Figure out how many blocks we'd need worst case to rebuild
@@ -372,8 +370,9 @@ xrep_calc_ag_resblks(
 		rmapbt_sz = 0;
 	}
 
-	trace_xrep_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
-			inobt_sz, rmapbt_sz, refcbt_sz);
+	trace_xrep_calc_ag_resblks_btsize(pag, bnobt_sz, inobt_sz, rmapbt_sz,
+			refcbt_sz);
+	xfs_perag_put(pag);
 
 	return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz));
 }
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 992f87f52b7656..0da641f046f3a7 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2189,10 +2189,10 @@ TRACE_EVENT(xrep_findroot_block,
 		  __entry->level)
 )
 TRACE_EVENT(xrep_calc_ag_resblks,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agino_t icount, xfs_agblock_t aglen, xfs_agblock_t freelen,
+	TP_PROTO(const struct xfs_perag *pag, xfs_agino_t icount,
+		 xfs_agblock_t aglen, xfs_agblock_t freelen,
 		 xfs_agblock_t usedlen),
-	TP_ARGS(mp, agno, icount, aglen, freelen, usedlen),
+	TP_ARGS(pag, icount, aglen, freelen, usedlen),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2202,8 +2202,8 @@ TRACE_EVENT(xrep_calc_ag_resblks,
 		__field(xfs_agblock_t, usedlen)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->icount = icount;
 		__entry->aglen = aglen;
 		__entry->freelen = freelen;
@@ -2218,10 +2218,10 @@ TRACE_EVENT(xrep_calc_ag_resblks,
 		  __entry->usedlen)
 )
 TRACE_EVENT(xrep_calc_ag_resblks_btsize,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agblock_t bnobt_sz, xfs_agblock_t inobt_sz,
-		 xfs_agblock_t rmapbt_sz, xfs_agblock_t refcbt_sz),
-	TP_ARGS(mp, agno, bnobt_sz, inobt_sz, rmapbt_sz, refcbt_sz),
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t bnobt_sz,
+		 xfs_agblock_t inobt_sz, xfs_agblock_t rmapbt_sz,
+		 xfs_agblock_t refcbt_sz),
+	TP_ARGS(pag, bnobt_sz, inobt_sz, rmapbt_sz, refcbt_sz),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2231,8 +2231,8 @@ TRACE_EVENT(xrep_calc_ag_resblks_btsize,
 		__field(xfs_agblock_t, refcbt_sz)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->bnobt_sz = bnobt_sz;
 		__entry->inobt_sz = inobt_sz;
 		__entry->rmapbt_sz = rmapbt_sz;

[PATCH 20/23] xfs: pass the pag to the xrep_newbt_extent_class tracepoints

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

This requires moving a few of the callsites a little bit to ensure that
we already have the reference, but allows for the decoding to only happen
when tracing is actually enabled, and cleans up the callsites a bit.

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 |    8 ++++----
 fs/xfs/scrub/newbt.c        |   29 +++++++++++++----------------
 fs/xfs/scrub/trace.h        |   16 +++++++---------
 3 files changed, 24 insertions(+), 29 deletions(-)


diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c
index 30295898cc8a63..6fd0e193f0b739 100644
--- a/fs/xfs/scrub/alloc_repair.c
+++ b/fs/xfs/scrub/alloc_repair.c
@@ -484,8 +484,8 @@ xrep_abt_reserve_space(
 		ASSERT(arec.ar_blockcount <= UINT_MAX);
 		len = min_t(unsigned int, arec.ar_blockcount, desired);
 
-		trace_xrep_newbt_alloc_ag_blocks(sc->mp, sc->sa.pag->pag_agno,
-				arec.ar_startblock, len, XFS_RMAP_OWN_AG);
+		trace_xrep_newbt_alloc_ag_blocks(sc->sa.pag, arec.ar_startblock,
+				len, XFS_RMAP_OWN_AG);
 
 		error = xrep_newbt_add_extent(&ra->new_bnobt, sc->sa.pag,
 				arec.ar_startblock, len);
@@ -554,8 +554,8 @@ xrep_abt_dispose_one(
 	if (free_aglen == 0)
 		return 0;
 
-	trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno, free_agbno,
-			free_aglen, ra->new_bnobt.oinfo.oi_owner);
+	trace_xrep_newbt_free_blocks(resv->pag, free_agbno, free_aglen,
+			ra->new_bnobt.oinfo.oi_owner);
 
 	error = __xfs_free_extent(sc->tp, resv->pag, free_agbno, free_aglen,
 			&ra->new_bnobt.oinfo, XFS_AG_RESV_IGNORE, true);
diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c
index baa00e1cf81ab2..81cad6c4fe6d9d 100644
--- a/fs/xfs/scrub/newbt.c
+++ b/fs/xfs/scrub/newbt.c
@@ -250,16 +250,15 @@ xrep_newbt_alloc_ag_blocks(
 			return -ENOSPC;
 
 		agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
-
-		trace_xrep_newbt_alloc_ag_blocks(mp, agno,
-				XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
-				xnr->oinfo.oi_owner);
-
 		if (agno != sc->sa.pag->pag_agno) {
 			ASSERT(agno == sc->sa.pag->pag_agno);
 			return -EFSCORRUPTED;
 		}
 
+		trace_xrep_newbt_alloc_ag_blocks(sc->sa.pag,
+				XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
+				xnr->oinfo.oi_owner);
+
 		error = xrep_newbt_add_blocks(xnr, sc->sa.pag, &args);
 		if (error)
 			return error;
@@ -325,16 +324,16 @@ xrep_newbt_alloc_file_blocks(
 
 		agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
 
-		trace_xrep_newbt_alloc_file_blocks(mp, agno,
-				XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
-				xnr->oinfo.oi_owner);
-
 		pag = xfs_perag_get(mp, agno);
 		if (!pag) {
 			ASSERT(0);
 			return -EFSCORRUPTED;
 		}
 
+		trace_xrep_newbt_alloc_file_blocks(pag,
+				XFS_FSB_TO_AGBNO(mp, args.fsbno), args.len,
+				xnr->oinfo.oi_owner);
+
 		error = xrep_newbt_add_blocks(xnr, pag, &args);
 		xfs_perag_put(pag);
 		if (error)
@@ -383,8 +382,8 @@ xrep_newbt_free_extent(
 		 * space reservation, let the existing EFI free the entire
 		 * space extent.
 		 */
-		trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno,
-				free_agbno, free_aglen, xnr->oinfo.oi_owner);
+		trace_xrep_newbt_free_blocks(resv->pag, free_agbno, free_aglen,
+				xnr->oinfo.oi_owner);
 		xfs_alloc_commit_autoreap(sc->tp, &resv->autoreap);
 		return 1;
 	}
@@ -401,8 +400,8 @@ xrep_newbt_free_extent(
 	if (free_aglen == 0)
 		return 0;
 
-	trace_xrep_newbt_free_blocks(sc->mp, resv->pag->pag_agno, free_agbno,
-			free_aglen, xnr->oinfo.oi_owner);
+	trace_xrep_newbt_free_blocks(resv->pag, free_agbno, free_aglen,
+			xnr->oinfo.oi_owner);
 
 	ASSERT(xnr->resv != XFS_AG_RESV_AGFL);
 	ASSERT(xnr->resv != XFS_AG_RESV_IGNORE);
@@ -514,7 +513,6 @@ xrep_newbt_claim_block(
 	union xfs_btree_ptr	*ptr)
 {
 	struct xrep_newbt_resv	*resv;
-	struct xfs_mount	*mp = cur->bc_mp;
 	xfs_agblock_t		agbno;
 
 	/*
@@ -539,8 +537,7 @@ xrep_newbt_claim_block(
 	if (resv->used == resv->len)
 		list_move_tail(&resv->list, &xnr->resv_list);
 
-	trace_xrep_newbt_claim_block(mp, resv->pag->pag_agno, agbno, 1,
-			xnr->oinfo.oi_owner);
+	trace_xrep_newbt_claim_block(resv->pag, agbno, 1, xnr->oinfo.oi_owner);
 
 	if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
 		ptr->l = cpu_to_be64(xfs_agbno_to_fsb(resv->pag, agbno));
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 0da641f046f3a7..16c275cb6520de 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2272,10 +2272,9 @@ TRACE_EVENT(xrep_reset_counters,
 )
 
 DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agblock_t agbno, xfs_extlen_t len,
-		 int64_t owner),
-	TP_ARGS(mp, agno, agbno, len, owner),
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
+		 xfs_extlen_t len, int64_t owner),
+	TP_ARGS(pag, agbno, len, owner),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2284,8 +2283,8 @@ DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
 		__field(int64_t, owner)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->owner = owner;
@@ -2299,10 +2298,9 @@ DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
 );
 #define DEFINE_NEWBT_EXTENT_EVENT(name) \
 DEFINE_EVENT(xrep_newbt_extent_class, name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
-		 xfs_agblock_t agbno, xfs_extlen_t len, \
+	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len, \
 		 int64_t owner), \
-	TP_ARGS(mp, agno, agbno, len, owner))
+	TP_ARGS(pag, agbno, len, owner))
 DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_ag_blocks);
 DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_file_blocks);
 DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_free_blocks);

[PATCH 21/23] xfs: convert remaining trace points to pass pag structures

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Convert all tracepoints that take [mp,agno] tuples to take a pag argument
instead so that decoding only happens when tracepoints are enabled and to
clean up the callers.

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      |    4 +-
 fs/xfs/libxfs/xfs_ialloc.c     |    4 +-
 fs/xfs/libxfs/xfs_inode_util.c |    4 +-
 fs/xfs/scrub/alloc_repair.c    |    2 -
 fs/xfs/scrub/ialloc.c          |    3 -
 fs/xfs/scrub/ialloc_repair.c   |    2 -
 fs/xfs/scrub/repair.c          |    2 -
 fs/xfs/scrub/rmap_repair.c     |    4 +-
 fs/xfs/scrub/trace.h           |   61 ++++++++++++++---------------
 fs/xfs/xfs_discard.c           |   11 ++---
 fs/xfs/xfs_extent_busy.c       |   13 ++----
 fs/xfs/xfs_health.c            |    8 ++--
 fs/xfs/xfs_iwalk.c             |    2 -
 fs/xfs/xfs_trace.h             |   84 ++++++++++++++++++++--------------------
 14 files changed, 98 insertions(+), 106 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 6970a47bea1bd2..cd5c44a75cd138 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -3360,7 +3360,7 @@ xfs_read_agf(
 	struct xfs_mount	*mp = pag->pag_mount;
 	int			error;
 
-	trace_xfs_read_agf(pag->pag_mount, pag->pag_agno);
+	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)),
@@ -3391,7 +3391,7 @@ xfs_alloc_read_agf(
 	int			error;
 	int			allocbt_blks;
 
-	trace_xfs_alloc_read_agf(pag->pag_mount, pag->pag_agno);
+	trace_xfs_alloc_read_agf(pag);
 
 	/* We don't support trylock when freeing. */
 	ASSERT((flags & (XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK)) !=
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 085032443f1267..f5167847f05119 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2729,7 +2729,7 @@ xfs_read_agi(
 	struct xfs_mount	*mp = pag->pag_mount;
 	int			error;
 
-	trace_xfs_read_agi(pag->pag_mount, pag->pag_agno);
+	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)),
@@ -2760,7 +2760,7 @@ xfs_ialloc_read_agi(
 	struct xfs_agi		*agi;
 	int			error;
 
-	trace_xfs_ialloc_read_agi(pag->pag_mount, pag->pag_agno);
+	trace_xfs_ialloc_read_agi(pag);
 
 	error = xfs_read_agi(pag, tp,
 			(flags & XFS_IALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0,
diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
index cc38e1c3c3e1d3..ec64eda3bbe2e1 100644
--- a/fs/xfs/libxfs/xfs_inode_util.c
+++ b/fs/xfs/libxfs/xfs_inode_util.c
@@ -442,8 +442,8 @@ xfs_iunlink_update_bucket(
 	ASSERT(xfs_verify_agino_or_null(pag, new_agino));
 
 	old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]);
-	trace_xfs_iunlink_update_bucket(tp->t_mountp, pag->pag_agno, bucket_index,
-			old_value, new_agino);
+	trace_xfs_iunlink_update_bucket(pag, bucket_index, old_value,
+			new_agino);
 
 	/*
 	 * We should never find the head of the list already set to the value
diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c
index 6fd0e193f0b739..1e0c2db6dcf7df 100644
--- a/fs/xfs/scrub/alloc_repair.c
+++ b/fs/xfs/scrub/alloc_repair.c
@@ -210,7 +210,7 @@ xrep_abt_stash(
 	if (error)
 		return error;
 
-	trace_xrep_abt_found(sc->mp, sc->sa.pag->pag_agno, &arec);
+	trace_xrep_abt_found(sc->sa.pag, &arec);
 
 	error = xfarray_append(ra->free_records, &arec);
 	if (error)
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index c1c798076d66ab..ee71cf2050b72e 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -367,7 +367,6 @@ xchk_iallocbt_check_cluster(
 	struct xfs_mount		*mp = bs->cur->bc_mp;
 	struct xfs_buf			*cluster_bp;
 	unsigned int			nr_inodes;
-	xfs_agnumber_t			agno = bs->cur->bc_ag.pag->pag_agno;
 	xfs_agblock_t			agbno;
 	unsigned int			cluster_index;
 	uint16_t			cluster_mask = 0;
@@ -406,7 +405,7 @@ xchk_iallocbt_check_cluster(
 		return 0;
 	}
 
-	trace_xchk_iallocbt_check_cluster(mp, agno, irec->ir_startino,
+	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,
 			XFS_INO_TO_OFFSET(mp, irec->ir_startino +
diff --git a/fs/xfs/scrub/ialloc_repair.c b/fs/xfs/scrub/ialloc_repair.c
index f1c24f2da497ed..ffa0d67508aa00 100644
--- a/fs/xfs/scrub/ialloc_repair.c
+++ b/fs/xfs/scrub/ialloc_repair.c
@@ -192,7 +192,7 @@ xrep_ibt_stash(
 	if (ri->rie.ir_freecount > 0)
 		ri->finobt_recs++;
 
-	trace_xrep_ibt_found(ri->sc->mp, ri->sc->sa.pag->pag_agno, &ri->rie);
+	trace_xrep_ibt_found(ri->sc->sa.pag, &ri->rie);
 
 	error = xfarray_append(ri->inode_records, &ri->rie);
 	if (error)
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 47f9b04e3798f1..707ca52650e130 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -611,7 +611,7 @@ xrep_findroot_block(
 	else
 		fab->root = NULLAGBLOCK;
 
-	trace_xrep_findroot_block(mp, ri->sc->sa.pag->pag_agno, agbno,
+	trace_xrep_findroot_block(ri->sc->sa.pag, agbno,
 			be32_to_cpu(btblock->bb_magic), fab->height - 1);
 out:
 	xfs_trans_brelse(ri->sc->tp, bp);
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index f99849ae8f67e2..57d445f7cb2a5d 100644
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -231,7 +231,7 @@ xrep_rmap_stash(
 	if (xchk_iscan_aborted(&rr->iscan))
 		return -EFSCORRUPTED;
 
-	trace_xrep_rmap_found(sc->mp, sc->sa.pag->pag_agno, &rmap);
+	trace_xrep_rmap_found(sc->sa.pag, &rmap);
 
 	mutex_lock(&rr->lock);
 	mcur = xfs_rmapbt_mem_cursor(sc->sa.pag, sc->tp, &rr->rmap_btree);
@@ -1552,7 +1552,7 @@ xrep_rmapbt_live_update(
 	if (!xrep_rmapbt_want_live_update(&rr->iscan, &p->oinfo))
 		goto out_unlock;
 
-	trace_xrep_rmap_live_update(mp, rr->sc->sa.pag->pag_agno, action, p);
+	trace_xrep_rmap_live_update(rr->sc->sa.pag, action, p);
 
 	error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp);
 	if (error)
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 16c275cb6520de..a1ec6445ae5fbf 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -772,12 +772,12 @@ TRACE_EVENT(xchk_xref_error,
 );
 
 TRACE_EVENT(xchk_iallocbt_check_cluster,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agino_t startino, xfs_daddr_t map_daddr,
-		 unsigned short map_len, unsigned int chunk_ino,
-		 unsigned int nr_inodes, uint16_t cluster_mask,
-		 uint16_t holemask, unsigned int cluster_ino),
-	TP_ARGS(mp, agno, startino, map_daddr, map_len, chunk_ino, nr_inodes,
+	TP_PROTO(const struct xfs_perag *pag, xfs_agino_t startino,
+		 xfs_daddr_t map_daddr,  unsigned short map_len,
+		 unsigned int chunk_ino,  unsigned int nr_inodes,
+		 uint16_t cluster_mask, uint16_t holemask,
+		 unsigned int cluster_ino),
+	TP_ARGS(pag, startino, map_daddr, map_len, chunk_ino, nr_inodes,
 		cluster_mask, holemask, cluster_ino),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -792,8 +792,8 @@ TRACE_EVENT(xchk_iallocbt_check_cluster,
 		__field(uint16_t, holemask)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->startino = startino;
 		__entry->map_daddr = map_daddr;
 		__entry->map_len = map_len;
@@ -2016,9 +2016,9 @@ TRACE_EVENT(xrep_ibt_walk_rmap,
 );
 
 TRACE_EVENT(xrep_abt_found,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+	TP_PROTO(const struct xfs_perag *pag,
 		 const struct xfs_alloc_rec_incore *rec),
-	TP_ARGS(mp, agno, rec),
+	TP_ARGS(pag, rec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2026,8 +2026,8 @@ TRACE_EVENT(xrep_abt_found,
 		__field(xfs_extlen_t, blockcount)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->startblock = rec->ar_startblock;
 		__entry->blockcount = rec->ar_blockcount;
 	),
@@ -2039,9 +2039,9 @@ TRACE_EVENT(xrep_abt_found,
 )
 
 TRACE_EVENT(xrep_ibt_found,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+	TP_PROTO(const struct xfs_perag *pag,
 		 const struct xfs_inobt_rec_incore *rec),
-	TP_ARGS(mp, agno, rec),
+	TP_ARGS(pag, rec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2052,8 +2052,8 @@ TRACE_EVENT(xrep_ibt_found,
 		__field(uint64_t, freemask)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->startino = rec->ir_startino;
 		__entry->holemask = rec->ir_holemask;
 		__entry->count = rec->ir_count;
@@ -2132,9 +2132,8 @@ TRACE_EVENT(xrep_bmap_found,
 );
 
 TRACE_EVENT(xrep_rmap_found,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 const struct xfs_rmap_irec *rec),
-	TP_ARGS(mp, agno, rec),
+	TP_PROTO(const struct xfs_perag *pag, const struct xfs_rmap_irec *rec),
+	TP_ARGS(pag, rec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2145,8 +2144,8 @@ TRACE_EVENT(xrep_rmap_found,
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->agbno = rec->rm_startblock;
 		__entry->len = rec->rm_blockcount;
 		__entry->owner = rec->rm_owner;
@@ -2164,9 +2163,9 @@ TRACE_EVENT(xrep_rmap_found,
 );
 
 TRACE_EVENT(xrep_findroot_block,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
 		 uint32_t magic, uint16_t level),
-	TP_ARGS(mp, agno, agbno, magic, level),
+	TP_ARGS(pag, agbno, magic, level),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2175,8 +2174,8 @@ TRACE_EVENT(xrep_findroot_block,
 		__field(uint16_t, level)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->agbno = agbno;
 		__entry->magic = magic;
 		__entry->level = level;
@@ -2298,8 +2297,8 @@ DECLARE_EVENT_CLASS(xrep_newbt_extent_class,
 );
 #define DEFINE_NEWBT_EXTENT_EVENT(name) \
 DEFINE_EVENT(xrep_newbt_extent_class, name, \
-	TP_PROTO(struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len, \
-		 int64_t owner), \
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \
+		 xfs_extlen_t len, int64_t owner), \
 	TP_ARGS(pag, agbno, len, owner))
 DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_ag_blocks);
 DEFINE_NEWBT_EXTENT_EVENT(xrep_newbt_alloc_file_blocks);
@@ -2644,9 +2643,9 @@ DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_update_inode);
 DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_unfixable_inode);
 
 TRACE_EVENT(xrep_rmap_live_update,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, unsigned int op,
+	TP_PROTO(const struct xfs_perag *pag, unsigned int op,
 		 const struct xfs_rmap_update_params *p),
-	TP_ARGS(mp, agno, op, p),
+	TP_ARGS(pag, op, p),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2658,8 +2657,8 @@ TRACE_EVENT(xrep_rmap_live_update,
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->op = op;
 		__entry->agbno = p->startblock;
 		__entry->len = p->blockcount;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index e1b4a8c59d0cc8..79648f8c6b270b 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -117,8 +117,7 @@ xfs_discard_extents(
 
 	blk_start_plug(&plug);
 	list_for_each_entry(busyp, &extents->extent_list, list) {
-		trace_xfs_discard_extent(mp, busyp->pag->pag_agno, busyp->bno,
-					 busyp->length);
+		trace_xfs_discard_extent(busyp->pag, busyp->bno, busyp->length);
 
 		error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
 				xfs_agbno_to_daddr(busyp->pag, busyp->bno),
@@ -239,11 +238,11 @@ xfs_trim_gather_extents(
 		 * overlapping ranges for now.
 		 */
 		if (fbno + flen < tcur->start) {
-			trace_xfs_discard_exclude(mp, pag->pag_agno, fbno, flen);
+			trace_xfs_discard_exclude(pag, fbno, flen);
 			goto next_extent;
 		}
 		if (fbno > tcur->end) {
-			trace_xfs_discard_exclude(mp, pag->pag_agno, fbno, flen);
+			trace_xfs_discard_exclude(pag, fbno, flen);
 			if (tcur->by_bno) {
 				tcur->count = 0;
 				break;
@@ -261,7 +260,7 @@ xfs_trim_gather_extents(
 
 		/* Too small?  Give up. */
 		if (flen < tcur->minlen) {
-			trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen);
+			trace_xfs_discard_toosmall(pag, fbno, flen);
 			if (tcur->by_bno)
 				goto next_extent;
 			tcur->count = 0;
@@ -273,7 +272,7 @@ xfs_trim_gather_extents(
 		 * discard and try again the next time.
 		 */
 		if (xfs_extent_busy_search(pag, fbno, flen)) {
-			trace_xfs_discard_busy(mp, pag->pag_agno, fbno, flen);
+			trace_xfs_discard_busy(pag, fbno, flen);
 			goto next_extent;
 		}
 
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 7353f9844684b0..81099400a171dc 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->pag_mount, pag->pag_agno, bno, len);
+	trace_xfs_extent_busy(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->pag_mount, pag->pag_agno, fbno, flen);
+	trace_xfs_extent_busy_reuse(pag, fbno, flen);
 	return true;
 
 out_force_log:
 	spin_unlock(&pag->pagb_lock);
 	xfs_log_force(pag->pag_mount, XFS_LOG_SYNC);
-	trace_xfs_extent_busy_force(pag->pag_mount, pag->pag_agno, fbno, flen);
+	trace_xfs_extent_busy_force(pag, fbno, flen);
 	spin_lock(&pag->pagb_lock);
 	return false;
 }
@@ -496,8 +496,7 @@ xfs_extent_busy_trim(
 out:
 
 	if (fbno != *bno || flen != *len) {
-		trace_xfs_extent_busy_trim(args->mp, args->agno, *bno, *len,
-					  fbno, flen);
+		trace_xfs_extent_busy_trim(args->pag, *bno, *len, fbno, flen);
 		*bno = fbno;
 		*len = flen;
 		*busy_gen = args->pag->pagb_gen;
@@ -526,9 +525,7 @@ xfs_extent_busy_clear_one(
 			busyp->flags = XFS_EXTENT_BUSY_DISCARDED;
 			return false;
 		}
-		trace_xfs_extent_busy_clear(pag->pag_mount,
-				busyp->pag->pag_agno, busyp->bno,
-				busyp->length);
+		trace_xfs_extent_busy_clear(pag, busyp->bno, busyp->length);
 		rb_erase(&busyp->rb_node, &pag->pagb_tree);
 	}
 
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 10f116d093a225..d6492128582a3e 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -41,7 +41,7 @@ xfs_health_unmount(
 	for_each_perag(mp, agno, pag) {
 		xfs_ag_measure_sickness(pag, &sick, &checked);
 		if (sick) {
-			trace_xfs_ag_unfixed_corruption(mp, agno, sick);
+			trace_xfs_ag_unfixed_corruption(pag, sick);
 			warn = true;
 		}
 	}
@@ -233,7 +233,7 @@ xfs_ag_mark_sick(
 	unsigned int		mask)
 {
 	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
-	trace_xfs_ag_mark_sick(pag->pag_mount, pag->pag_agno, mask);
+	trace_xfs_ag_mark_sick(pag, mask);
 
 	spin_lock(&pag->pag_state_lock);
 	pag->pag_sick |= mask;
@@ -247,7 +247,7 @@ xfs_ag_mark_corrupt(
 	unsigned int		mask)
 {
 	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
-	trace_xfs_ag_mark_corrupt(pag->pag_mount, pag->pag_agno, mask);
+	trace_xfs_ag_mark_corrupt(pag, mask);
 
 	spin_lock(&pag->pag_state_lock);
 	pag->pag_sick |= mask;
@@ -262,7 +262,7 @@ xfs_ag_mark_healthy(
 	unsigned int		mask)
 {
 	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
-	trace_xfs_ag_mark_healthy(pag->pag_mount, pag->pag_agno, mask);
+	trace_xfs_ag_mark_healthy(pag, mask);
 
 	spin_lock(&pag->pag_state_lock);
 	pag->pag_sick &= ~mask;
diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index ab5252f19509a6..d4ef7485e8f740 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -182,7 +182,7 @@ xfs_iwalk_ag_recs(
 	for (i = 0; i < iwag->nr_recs; i++) {
 		struct xfs_inobt_rec_incore	*irec = &iwag->recs[i];
 
-		trace_xfs_iwalk_ag_rec(mp, pag->pag_agno, irec);
+		trace_xfs_iwalk_ag_rec(pag, irec);
 
 		if (xfs_pwork_want_abort(&iwag->pwork))
 			return 0;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 7b1fbcf970655a..dcd0452fc7e438 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -300,15 +300,15 @@ TRACE_EVENT(xfs_inodegc_shrinker_scan,
 );
 
 DECLARE_EVENT_CLASS(xfs_ag_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno),
-	TP_ARGS(mp, agno),
+	TP_PROTO(const struct xfs_perag *pag),
+	TP_ARGS(pag),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 	),
 	TP_printk("dev %d:%d agno 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -316,8 +316,8 @@ DECLARE_EVENT_CLASS(xfs_ag_class,
 );
 #define DEFINE_AG_EVENT(name)	\
 DEFINE_EVENT(xfs_ag_class, name,	\
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno),	\
-	TP_ARGS(mp, agno))
+	TP_PROTO(const struct xfs_perag *pag),	\
+	TP_ARGS(pag))
 
 DEFINE_AG_EVENT(xfs_read_agf);
 DEFINE_AG_EVENT(xfs_alloc_read_agf);
@@ -1636,9 +1636,9 @@ TRACE_EVENT(xfs_bunmap,
 );
 
 DECLARE_EVENT_CLASS(xfs_extent_busy_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agblock_t agbno, xfs_extlen_t len),
-	TP_ARGS(mp, agno, agbno, len),
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
+		 xfs_extlen_t len),
+	TP_ARGS(pag, agbno, len),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -1646,8 +1646,8 @@ DECLARE_EVENT_CLASS(xfs_extent_busy_class,
 		__field(xfs_extlen_t, len)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 	),
@@ -1659,19 +1659,18 @@ DECLARE_EVENT_CLASS(xfs_extent_busy_class,
 );
 #define DEFINE_BUSY_EVENT(name) \
 DEFINE_EVENT(xfs_extent_busy_class, name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
-		 xfs_agblock_t agbno, xfs_extlen_t len), \
-	TP_ARGS(mp, agno, agbno, len))
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \
+			xfs_extlen_t len), \
+	TP_ARGS(pag, 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(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agblock_t agbno, xfs_extlen_t len,
-		 xfs_agblock_t tbno, xfs_extlen_t tlen),
-	TP_ARGS(mp, agno, agbno, len, tbno, tlen),
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
+		 xfs_extlen_t len, xfs_agblock_t tbno, xfs_extlen_t tlen),
+	TP_ARGS(pag, agbno, len, tbno, tlen),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -1681,8 +1680,8 @@ TRACE_EVENT(xfs_extent_busy_trim,
 		__field(xfs_extlen_t, tlen)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 		__entry->tbno = tbno;
@@ -2428,9 +2427,9 @@ DEFINE_LOG_RECOVER_ICREATE_ITEM(xfs_log_recover_icreate_cancel);
 DEFINE_LOG_RECOVER_ICREATE_ITEM(xfs_log_recover_icreate_recover);
 
 DECLARE_EVENT_CLASS(xfs_discard_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agblock_t agbno, xfs_extlen_t len),
-	TP_ARGS(mp, agno, agbno, len),
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno,
+		 xfs_extlen_t len),
+	TP_ARGS(pag, agbno, len),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2438,8 +2437,8 @@ DECLARE_EVENT_CLASS(xfs_discard_class,
 		__field(xfs_extlen_t, len)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->agbno = agbno;
 		__entry->len = len;
 	),
@@ -2452,9 +2451,9 @@ DECLARE_EVENT_CLASS(xfs_discard_class,
 
 #define DEFINE_DISCARD_EVENT(name) \
 DEFINE_EVENT(xfs_discard_class, name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
-		 xfs_agblock_t agbno, xfs_extlen_t len), \
-	TP_ARGS(mp, agno, agbno, len))
+	TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \
+		xfs_extlen_t len), \
+	TP_ARGS(pag, agbno, len))
 DEFINE_DISCARD_EVENT(xfs_discard_extent);
 DEFINE_DISCARD_EVENT(xfs_discard_toosmall);
 DEFINE_DISCARD_EVENT(xfs_discard_exclude);
@@ -4030,9 +4029,9 @@ DEFINE_TRANS_EVENT(xfs_trans_commit_items);
 DEFINE_TRANS_EVENT(xfs_trans_free_items);
 
 TRACE_EVENT(xfs_iunlink_update_bucket,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, unsigned int bucket,
+	TP_PROTO(const struct xfs_perag *pag, unsigned int bucket,
 		 xfs_agino_t old_ptr, xfs_agino_t new_ptr),
-	TP_ARGS(mp, agno, bucket, old_ptr, new_ptr),
+	TP_ARGS(pag, bucket, old_ptr, new_ptr),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -4041,8 +4040,8 @@ TRACE_EVENT(xfs_iunlink_update_bucket,
 		__field(xfs_agino_t, new_ptr)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->bucket = bucket;
 		__entry->old_ptr = old_ptr;
 		__entry->new_ptr = new_ptr;
@@ -4180,16 +4179,16 @@ 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(struct xfs_mount *mp, xfs_agnumber_t agno, unsigned int flags),
-	TP_ARGS(mp, agno, flags),
+	TP_PROTO(const struct xfs_perag *pag, unsigned int flags),
+	TP_ARGS(pag, flags),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
 		__field(unsigned int, flags)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->flags = flags;
 	),
 	TP_printk("dev %d:%d agno 0x%x flags 0x%x",
@@ -4198,9 +4197,8 @@ DECLARE_EVENT_CLASS(xfs_ag_corrupt_class,
 );
 #define DEFINE_AG_CORRUPT_EVENT(name)	\
 DEFINE_EVENT(xfs_ag_corrupt_class, name,	\
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
-		 unsigned int flags), \
-	TP_ARGS(mp, agno, flags))
+	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);
@@ -4233,9 +4231,9 @@ DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_healthy);
 DEFINE_INODE_CORRUPT_EVENT(xfs_inode_unfixed_corruption);
 
 TRACE_EVENT(xfs_iwalk_ag_rec,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+	TP_PROTO(const struct xfs_perag *pag, \
 		 struct xfs_inobt_rec_incore *irec),
-	TP_ARGS(mp, agno, irec),
+	TP_ARGS(pag, irec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -4243,8 +4241,8 @@ TRACE_EVENT(xfs_iwalk_ag_rec,
 		__field(uint64_t, freemask)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
 		__entry->startino = irec->ir_startino;
 		__entry->freemask = irec->ir_free;
 	),

[PATCH 22/23] xfs: split xfs_initialize_perag

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Factor out a xfs_perag_alloc helper that allocates a single perag
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        |  121 ++++++++++++++++++++++++-----------------
 fs/xfs/libxfs/xfs_ag.h        |    4 +
 fs/xfs/xfs_buf_item_recover.c |    5 +-
 3 files changed, 74 insertions(+), 56 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 9de48f3c71235d..3e232b3d4c4262 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -272,6 +272,10 @@ xfs_agino_range(
 	return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last);
 }
 
+/*
+ * Update the perag of the previous tail AG if it has been changed during
+ * recovery (i.e. recovery of a growfs).
+ */
 int
 xfs_update_last_ag_size(
 	struct xfs_mount	*mp,
@@ -289,69 +293,57 @@ xfs_update_last_ag_size(
 	return 0;
 }
 
-int
-xfs_initialize_perag(
+static int
+xfs_perag_alloc(
 	struct xfs_mount	*mp,
-	xfs_agnumber_t		old_agcount,
-	xfs_agnumber_t		new_agcount,
-	xfs_rfsblock_t		dblocks,
-	xfs_agnumber_t		*maxagi)
+	xfs_agnumber_t		index,
+	xfs_agnumber_t		agcount,
+	xfs_rfsblock_t		dblocks)
 {
 	struct xfs_perag	*pag;
-	xfs_agnumber_t		index;
 	int			error;
 
-	for (index = old_agcount; index < new_agcount; index++) {
-		pag = kzalloc(sizeof(*pag), GFP_KERNEL);
-		if (!pag) {
-			error = -ENOMEM;
-			goto out_unwind_new_pags;
-		}
-		pag->pag_agno = index;
-		pag->pag_mount = mp;
+	pag = kzalloc(sizeof(*pag), GFP_KERNEL);
+	if (!pag)
+		return -ENOMEM;
 
-		error = xa_insert(&mp->m_perags, index, pag, GFP_KERNEL);
-		if (error) {
-			WARN_ON_ONCE(error == -EBUSY);
-			goto out_free_pag;
-		}
+	pag->pag_agno = index;
+	pag->pag_mount = mp;
+
+	error = xa_insert(&mp->m_perags, index, pag, GFP_KERNEL);
+	if (error) {
+		WARN_ON_ONCE(error == -EBUSY);
+		goto out_free_pag;
+	}
 
 #ifdef __KERNEL__
-		/* 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);
-		init_waitqueue_head(&pag->pagb_wait);
-		pag->pagb_tree = RB_ROOT;
-		xfs_hooks_init(&pag->pag_rmap_update_hooks);
+	/* 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);
+	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);
-		if (error)
-			goto out_remove_pag;
+	error = xfs_buf_cache_init(&pag->pag_bcache);
+	if (error)
+		goto out_remove_pag;
 
-		/* Active ref owned by mount indicates AG is online. */
-		atomic_set(&pag->pag_active_ref, 1);
+	/* Active ref owned by mount indicates AG is online. */
+	atomic_set(&pag->pag_active_ref, 1);
 
-		/*
-		 * Pre-calculated geometry
-		 */
-		pag->block_count = __xfs_ag_block_count(mp, index, new_agcount,
-				dblocks);
-		pag->min_block = XFS_AGFL_BLOCK(mp);
-		__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
-				&pag->agino_max);
-	}
+	/*
+	 * Pre-calculated geometry
+	 */
+	pag->block_count = __xfs_ag_block_count(mp, index, agcount, dblocks);
+	pag->min_block = XFS_AGFL_BLOCK(mp);
+	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+			&pag->agino_max);
 
-	index = xfs_set_inode_alloc(mp, new_agcount);
-
-	if (maxagi)
-		*maxagi = index;
-
-	mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp);
 	return 0;
 
 out_remove_pag:
@@ -359,8 +351,35 @@ xfs_initialize_perag(
 	pag = xa_erase(&mp->m_perags, index);
 out_free_pag:
 	kfree(pag);
+	return error;
+}
+
+int
+xfs_initialize_perag(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		orig_agcount,
+	xfs_agnumber_t		new_agcount,
+	xfs_rfsblock_t		dblocks,
+	xfs_agnumber_t		*maxagi)
+{
+	xfs_agnumber_t		index;
+	int			error;
+
+	if (orig_agcount >= new_agcount)
+		return 0;
+
+	for (index = orig_agcount; index < new_agcount; index++) {
+		error = xfs_perag_alloc(mp, index, new_agcount, dblocks);
+		if (error)
+			goto out_unwind_new_pags;
+	}
+
+	*maxagi = xfs_set_inode_alloc(mp, new_agcount);
+	mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp);
+	return 0;
+
 out_unwind_new_pags:
-	xfs_free_perag_range(mp, old_agcount, index);
+	xfs_free_perag_range(mp, orig_agcount, index);
 	return error;
 }
 
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index e0f567d90debee..8787823ae37f9f 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -142,8 +142,8 @@ __XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA)
 __XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES)
 __XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET)
 
-int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t old_agcount,
-		xfs_agnumber_t agcount, xfs_rfsblock_t dcount,
+int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t orig_agcount,
+		xfs_agnumber_t new_agcount, xfs_rfsblock_t dcount,
 		xfs_agnumber_t *maxagi);
 void xfs_free_perag_range(struct xfs_mount *mp, xfs_agnumber_t first_agno,
 		xfs_agnumber_t end_agno);
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index 5180cbf5a90b4b..c627ad3a3bbbfd 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -724,9 +724,8 @@ xlog_recover_do_primary_sb_buffer(
 	}
 
 	/*
-	 * Growfs can also grow the last existing AG.  In this case we also need
-	 * to update the length in the in-core perag structure and values
-	 * depending on it.
+	 * If the last AG was grown or shrunk, we also need to update the
+	 * length in the in-core perag structure and values depending on it.
 	 */
 	error = xfs_update_last_ag_size(mp, orig_agcount);
 	if (error)

[PATCH 23/23] xfs: insert the pag structures into the xarray later

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Cleaning up is much easier if a structure can't be looked up yet, so only
insert the pag once it is fully set up.

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 |   31 +++++++++++++++----------------
 1 file changed, 15 insertions(+), 16 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 3e232b3d4c4262..d51e88a4e7e283 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -307,15 +307,6 @@ xfs_perag_alloc(
 	if (!pag)
 		return -ENOMEM;
 
-	pag->pag_agno = index;
-	pag->pag_mount = mp;
-
-	error = xa_insert(&mp->m_perags, index, pag, GFP_KERNEL);
-	if (error) {
-		WARN_ON_ONCE(error == -EBUSY);
-		goto out_free_pag;
-	}
-
 #ifdef __KERNEL__
 	/* Place kernel structure only init below this point. */
 	spin_lock_init(&pag->pag_ici_lock);
@@ -331,10 +322,7 @@ xfs_perag_alloc(
 
 	error = xfs_buf_cache_init(&pag->pag_bcache);
 	if (error)
-		goto out_remove_pag;
-
-	/* Active ref owned by mount indicates AG is online. */
-	atomic_set(&pag->pag_active_ref, 1);
+		goto out_defer_drain_free;
 
 	/*
 	 * Pre-calculated geometry
@@ -344,12 +332,23 @@ 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);
+		goto out_buf_cache_destroy;
+	}
+
 	return 0;
 
-out_remove_pag:
+out_buf_cache_destroy:
+	xfs_buf_cache_destroy(&pag->pag_bcache);
+out_defer_drain_free:
 	xfs_defer_drain_free(&pag->pag_intents_drain);
-	pag = xa_erase(&mp->m_perags, index);
-out_free_pag:
 	kfree(pag);
 	return error;
 }

[PATCH 01/16] xfs: factor out a xfs_iwalk_args helper

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 d4ef7485e8f740..a89ae2aef7c445 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 83699089755ebb..17a5a2c6debb15 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__ */

[PATCH 02/16] xfs: factor out a generic xfs_group structure

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 dd692619bed580..94cb8ca9f9da77 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 d51e88a4e7e283..9ea20e9cf0d4e5 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 8787823ae37f9f..69b934ad2c4aad 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 4b1bd7cc7ba28c..f5d853089019f0 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 cd5c44a75cd138..bfe7b4321c47ae 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 5175d0b4d32e48..88e1545ed4c9dc 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 36dd08d132931d..5eda036cf9bfa5 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 804a1c96941127..9a13dbf5f54a33 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 00000000000000..edf5907845f003
--- /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 00000000000000..e3b6be7ff9e802
--- /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 f5167847f05119..78e1920c1ff964 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 3291541ae9665a..91d44be2ce48bc 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 5e166553a7a6e9..b8789c42c230b4 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 c4b10fbf8892a1..db389fdbd929a4 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 6ef4687b3aba8f..b6764d6b3ab891 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 b49006c1ca7eee..6fd460fc7c9c1d 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 d95409f3cba667..d2012fbf07aa65 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 a8cd44d03ef648..d3cb6ff3b91301 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 82a850eba6c88c..0ea04d6e21cd83 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 1e0c2db6dcf7df..ab0084c4249657 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 47148cc4a833e5..f3db628b14e1b9 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 ffa0d67508aa00..14e48d3f1912bf 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 cf9d983667cec6..84f117667ca2bf 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 81cad6c4fe6d9d..70af27d987342f 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 707ca52650e130..646ac8ade88d0b 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 ba5bbc3fb754db..26b5c90b3f6aee 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 57d445f7cb2a5d..f88f58db909867 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 a1ec6445ae5fbf..58cc61f2ed5372 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 79648f8c6b270b..dfd6edcebb6ea4 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 81099400a171dc..79b0f833c511e3 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 7f1be08dbc1123..c198962edea163 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 f2caebb78dd25d..a961aa420c488b 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 eff198ae1ce33a..918e1c38a15592 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 6b119a7a324fa4..0a930fc116f575 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 5529ff39b64001..693770f9bb09f0 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 a89ae2aef7c445..ec2d56f1840fc6 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 56772bbd38cdea..a285d2d1f68c15 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 96496f39f551ae..530d7f025506ce 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 27398512b179b2..29f101005f3eda 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 5bf6682e701b5a..2e82b5b6ed52d2 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 88b5580e1e19f5..1b83d09351f028 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 fbb3a1594c0dcc..457c2d70968d9a 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 7ef50107224647..17164b2d0472d4 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 dcd0452fc7e438..14e7f6a26a2300 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;
 	),

[PATCH 03/16] xfs: add a xfs_group_next_range helper

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 edf5907845f003..59e08cfaf9bffd 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 e3b6be7ff9e802..dd7da90443054b 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);

[PATCH 04/16] xfs: switch perag iteration from the for_each macros to a while based iterator

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 69b934ad2c4aad..80969682dc4746 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 d2012fbf07aa65..061c8c961d5bc9 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 c299b16c9365fa..c91db4f5140743 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 a43912227dd478..fb022b403716b1 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 dc8fdd2da174ed..be408e50484b54 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 1d3e98346933e1..28db0c83819c20 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 b712a8bd34f543..112dd05e5551d3 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 3e45b9b72312ab..5da9e1a387a8bb 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 dfd6edcebb6ea4..739ec69c44281c 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 79b0f833c511e3..3d5a57d7ac5e14 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 918e1c38a15592..a26fb054346b68 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 b247d895c276d2..82812a458cf10f 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 d6492128582a3e..ff5aca875ab0d0 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 0a930fc116f575..383c245482027b 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 ec2d56f1840fc6..7db3ece370b100 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 a285d2d1f68c15..55e412a821483e 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 2e82b5b6ed52d2..b11769c009effc 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);

[PATCH 05/16] xfs: move metadata health tracking to the generic group structure

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 9ea20e9cf0d4e5..84bd3831297e07 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 80969682dc4746..8271cb72c88387 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 59e08cfaf9bffd..927e72c0882b88 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 dd7da90443054b..d2c61dd1f43e44 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 b0edb4288e5929..13301420a2f670 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 112dd05e5551d3..fce04444c37c2a 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 ff5aca875ab0d0..732246f46680d5 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 14e7f6a26a2300..fd597a410b0298 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),

[PATCH 06/16] xfs: mark xfs_perag_intent_{hold,rele} static

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 7bdb9688c0f5e3..3f280971b498b8 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 775164f54ea6de..f39c90946ab71f 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_ */

[PATCH 07/16] xfs: move draining of deferred operations to the generic group structure

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 84bd3831297e07..c2f1f830d299d3 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 8271cb72c88387..45f8de06cdbc8a 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 927e72c0882b88..6737f009dd38ca 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 d2c61dd1f43e44..ebefbba7d98cc2 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 28095ed490fbf6..e8b5e73bab60d3 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 3f280971b498b8..a72d08947d6d10 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 f39c90946ab71f..3e6143572e52d2 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 fd597a410b0298..29e8be9b6829d9 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 */
 

[PATCH 08/16] xfs: move the online repair rmap hooks to the generic group structure

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 c2f1f830d299d3..e60469fee87514 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 45f8de06cdbc8a..042ee0913fb9b9 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 6737f009dd38ca..8532dc2f8628c5 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 ebefbba7d98cc2..a87b9b80ef7516 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 b6764d6b3ab891..984120b128fb9c 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 b783dd4dd95d1a..d409b463bc6662 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 f88f58db909867..6c420ec7dacd1b 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);

[PATCH 09/16] xfs: return the busy generation from xfs_extent_busy_list_empty

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 ab0084c4249657..f07cd93012c675 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 3d5a57d7ac5e14..2806fc6ab4800d 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 7241035ce4ef9d..c803dcd124a628 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__ */

[PATCH 10/16] xfs: convert extent busy tracepoints to the generic group structure

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 2806fc6ab4800d..9c5c6279ae216e 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 29e8be9b6829d9..562e0ad1c6cf0d 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,

[PATCH 11/16] xfs: convert busy extent tracking to the generic group structure

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 e60469fee87514..47e90dbb852bba 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 042ee0913fb9b9..7290148fa6e6aa 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 bfe7b4321c47ae..4ddd05c97a2928 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 88e1545ed4c9dc..e69a1bb13f7f86 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 8532dc2f8628c5..5c6fa5d76a91b1 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 a87b9b80ef7516..0ff6e1d5635cb1 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 6fd460fc7c9c1d..b37eaf37c7fd2d 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 f07cd93012c675..0433363a90b616 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 d65ad6aa856f4d..08230952053b7d 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 739ec69c44281c..019371c865d22a 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 9c5c6279ae216e..457a27ab837599 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 c803dcd124a628..f069b04e8ea184 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__ */

[PATCH 12/16] xfs: add a generic group pointer to the btree cursor

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 4ddd05c97a2928..d33c2fdaf4f2c9 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 e69a1bb13f7f86..a4ac37ba5d510e 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 9a13dbf5f54a33..2b5fc5fd16435d 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 10b7ddc3b2b34e..3b739459ebb0f4 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 036061fe32cc90..df3d613675a15a 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 78e1920c1ff964..f0261c4d91061c 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 91d44be2ce48bc..4c28deb3e9881d 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 b8789c42c230b4..ed943f6e616d96 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 db389fdbd929a4..54505fee185289 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 984120b128fb9c..0c404625986163 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 b37eaf37c7fd2d..2cab694ac58a7a 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 d1b8a4997dd2ce..8b282138097fb8 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 fb022b403716b1..64168f2e42220a 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 be408e50484b54..7c4955482641f7 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 19bded43c4fe1e..5b6194cef3e5e3 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 fce04444c37c2a..6ceef3749e3b99 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 ee71cf2050b72e..abad54c3621d44 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 d0c7d4a29c0feb..2b6be75e942415 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 26b5c90b3f6aee..39e9ad7cd8aea5 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 6c420ec7dacd1b..a0a227d183d28d 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 a26fb054346b68..5d5e54a16f23c8 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 732246f46680d5..f45f125a669de7 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 562e0ad1c6cf0d..8aa6af5c9c0174 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;

[PATCH 13/16] xfs: store a generic xfs_group pointer in xfs_getfsmap_info

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 5d5e54a16f23c8..a91677ac54e7e3 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);

[PATCH 14/16] xfs: add group based bno conversion helpers

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 5c6fa5d76a91b1..e9d76bcdc820dd 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 0ff6e1d5635cb1..5b7362277c3f7a 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 061c8c961d5bc9..f7a07e61341ded 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 530d7f025506ce..1b698878f40cb1 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;
 };
 
 /*

[PATCH 15/16] xfs: remove xfs_group_intent_hold and xfs_group_intent_rele

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 a72d08947d6d10..7a728a04f7a6b1 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);
 }
 

[PATCH 16/16] xfs: store a generic group structure in the intents

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

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 88fbce5001185f..efbde04fbbb15f 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 7592d46e97c661..4b721d9359943b 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 ed943f6e616d96..2dbab68b4fe69f 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 68acb0b1b4a878..62d78afcf1f3ff 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 0c404625986163..d0df68dc313185 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 d409b463bc6662..96b4321d831007 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 35a8c1b8b3cb34..37dab184c2dfc2 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 7a728a04f7a6b1..5ede81fadbd8ca 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 3e6143572e52d2..efcf88df9a5e70 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 c198962edea163..e469510986e8d0 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 29f101005f3eda..bede1c96c33011 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 1b83d09351f028..76b3c0ed3b4f63 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);
 }

[PATCH 01/28] xfs: constify the xfs_sb predicates

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Change the xfs_sb predicates to take a const struct xfs_sb pointer
because they do not change the superblock.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_format.h |   24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index e1bfee0c3b1a8c..a24ab46aaebc7e 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -278,7 +278,7 @@ struct xfs_dsb {
 
 #define	XFS_SB_VERSION_NUM(sbp)	((sbp)->sb_versionnum & XFS_SB_VERSION_NUMBITS)
 
-static inline bool xfs_sb_is_v5(struct xfs_sb *sbp)
+static inline bool xfs_sb_is_v5(const struct xfs_sb *sbp)
 {
 	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5;
 }
@@ -287,12 +287,12 @@ static inline bool xfs_sb_is_v5(struct xfs_sb *sbp)
  * Detect a mismatched features2 field.  Older kernels read/wrote
  * this into the wrong slot, so to be safe we keep them in sync.
  */
-static inline bool xfs_sb_has_mismatched_features2(struct xfs_sb *sbp)
+static inline bool xfs_sb_has_mismatched_features2(const struct xfs_sb *sbp)
 {
 	return sbp->sb_bad_features2 != sbp->sb_features2;
 }
 
-static inline bool xfs_sb_version_hasmorebits(struct xfs_sb *sbp)
+static inline bool xfs_sb_version_hasmorebits(const struct xfs_sb *sbp)
 {
 	return xfs_sb_is_v5(sbp) ||
 	       (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT);
@@ -342,8 +342,8 @@ static inline void xfs_sb_version_addprojid32(struct xfs_sb *sbp)
 #define XFS_SB_FEAT_COMPAT_UNKNOWN	~XFS_SB_FEAT_COMPAT_ALL
 static inline bool
 xfs_sb_has_compat_feature(
-	struct xfs_sb	*sbp,
-	uint32_t	feature)
+	const struct xfs_sb	*sbp,
+	uint32_t		feature)
 {
 	return (sbp->sb_features_compat & feature) != 0;
 }
@@ -360,8 +360,8 @@ xfs_sb_has_compat_feature(
 #define XFS_SB_FEAT_RO_COMPAT_UNKNOWN	~XFS_SB_FEAT_RO_COMPAT_ALL
 static inline bool
 xfs_sb_has_ro_compat_feature(
-	struct xfs_sb	*sbp,
-	uint32_t	feature)
+	const struct xfs_sb	*sbp,
+	uint32_t		feature)
 {
 	return (sbp->sb_features_ro_compat & feature) != 0;
 }
@@ -387,8 +387,8 @@ xfs_sb_has_ro_compat_feature(
 #define XFS_SB_FEAT_INCOMPAT_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_ALL
 static inline bool
 xfs_sb_has_incompat_feature(
-	struct xfs_sb	*sbp,
-	uint32_t	feature)
+	const struct xfs_sb	*sbp,
+	uint32_t		feature)
 {
 	return (sbp->sb_features_incompat & feature) != 0;
 }
@@ -399,8 +399,8 @@ xfs_sb_has_incompat_feature(
 #define XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_LOG_ALL
 static inline bool
 xfs_sb_has_incompat_log_feature(
-	struct xfs_sb	*sbp,
-	uint32_t	feature)
+	const struct xfs_sb	*sbp,
+	uint32_t		feature)
 {
 	return (sbp->sb_features_log_incompat & feature) != 0;
 }
@@ -420,7 +420,7 @@ xfs_sb_add_incompat_log_features(
 	sbp->sb_features_log_incompat |= features;
 }
 
-static inline bool xfs_sb_version_haslogxattrs(struct xfs_sb *sbp)
+static inline bool xfs_sb_version_haslogxattrs(const struct xfs_sb *sbp)
 {
 	return xfs_sb_is_v5(sbp) && (sbp->sb_features_log_incompat &
 		 XFS_SB_FEAT_INCOMPAT_LOG_XATTRS);

[PATCH 02/28] xfs: constify the xfs_inode predicates

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Change the xfs_inode predicates to take a const struct xfs_inode pointer
because they do not change the inode.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_inode.c |    2 +-
 fs/xfs/xfs_inode.h |   20 ++++++++++----------
 2 files changed, 11 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 693770f9bb09f0..a8430f30d6df29 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3040,7 +3040,7 @@ xfs_inode_alloc_unitsize(
 /* Should we always be using copy on write for file writes? */
 bool
 xfs_is_always_cow_inode(
-	struct xfs_inode	*ip)
+	const struct xfs_inode	*ip)
 {
 	return ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount);
 }
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 03944b6c5fba1c..41444a557576c1 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -100,7 +100,7 @@ static inline bool xfs_inode_on_unlinked_list(const struct xfs_inode *ip)
 	return ip->i_prev_unlinked != 0;
 }
 
-static inline bool xfs_inode_has_attr_fork(struct xfs_inode *ip)
+static inline bool xfs_inode_has_attr_fork(const struct xfs_inode *ip)
 {
 	return ip->i_forkoff > 0;
 }
@@ -271,7 +271,7 @@ xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned long flags)
 	return ret;
 }
 
-static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
+static inline bool xfs_is_reflink_inode(const struct xfs_inode *ip)
 {
 	return ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
 }
@@ -285,9 +285,9 @@ static inline bool xfs_is_metadata_inode(const struct xfs_inode *ip)
 	       xfs_is_quota_inode(&mp->m_sb, ip->i_ino);
 }
 
-bool xfs_is_always_cow_inode(struct xfs_inode *ip);
+bool xfs_is_always_cow_inode(const struct xfs_inode *ip);
 
-static inline bool xfs_is_cow_inode(struct xfs_inode *ip)
+static inline bool xfs_is_cow_inode(const struct xfs_inode *ip)
 {
 	return xfs_is_reflink_inode(ip) || xfs_is_always_cow_inode(ip);
 }
@@ -301,17 +301,17 @@ static inline bool xfs_inode_has_filedata(const struct xfs_inode *ip)
  * Check if an inode has any data in the COW fork.  This might be often false
  * even for inodes with the reflink flag when there is no pending COW operation.
  */
-static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
+static inline bool xfs_inode_has_cow_data(const struct xfs_inode *ip)
 {
 	return ip->i_cowfp && ip->i_cowfp->if_bytes;
 }
 
-static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip)
+static inline bool xfs_inode_has_bigtime(const struct xfs_inode *ip)
 {
 	return ip->i_diflags2 & XFS_DIFLAG2_BIGTIME;
 }
 
-static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
+static inline bool xfs_inode_has_large_extent_counts(const struct xfs_inode *ip)
 {
 	return ip->i_diflags2 & XFS_DIFLAG2_NREXT64;
 }
@@ -320,7 +320,7 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
  * Decide if this file is a realtime file whose data allocation unit is larger
  * than a single filesystem block.
  */
-static inline bool xfs_inode_has_bigrtalloc(struct xfs_inode *ip)
+static inline bool xfs_inode_has_bigrtalloc(const struct xfs_inode *ip)
 {
 	return XFS_IS_REALTIME_INODE(ip) && ip->i_mount->m_sb.sb_rextsize > 1;
 }
@@ -625,9 +625,9 @@ void xfs_sort_inodes(struct xfs_inode **i_tab, unsigned int num_inodes);
 
 static inline bool
 xfs_inode_unlinked_incomplete(
-	struct xfs_inode	*ip)
+	const struct xfs_inode	*ip)
 {
-	return VFS_I(ip)->i_nlink == 0 && !xfs_inode_on_unlinked_list(ip);
+	return VFS_IC(ip)->i_nlink == 0 && !xfs_inode_on_unlinked_list(ip);
 }
 int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip);
 int xfs_inode_reload_unlinked(struct xfs_inode *ip);

[PATCH 03/28] xfs: rename metadata inode predicates

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The predicate xfs_internal_inum tells us if an inumber refers to one of
the inodes rooted in the superblock.  Soon we're going to have internal
inodes in a metadata directory tree, so this helper should be renamed
to capture its limited scope.

Ondisk inodes will soon have a flag to indicate that they're metadata
inodes.  Head off some confusion by renaming the xfs_is_metadata_inode
predicate to xfs_is_internal_inode.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_types.c      |    4 ++--
 fs/xfs/libxfs/xfs_types.h      |    2 +-
 fs/xfs/scrub/common.c          |    2 +-
 fs/xfs/scrub/inode.c           |    2 +-
 fs/xfs/scrub/inode_repair.c    |    2 +-
 fs/xfs/scrub/orphanage.c       |    2 +-
 fs/xfs/scrub/parent.c          |    2 +-
 fs/xfs/scrub/refcount_repair.c |    2 +-
 fs/xfs/xfs_inode.c             |    4 ++--
 fs/xfs/xfs_inode.h             |    2 +-
 fs/xfs/xfs_itable.c            |    2 +-
 11 files changed, 13 insertions(+), 13 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index c91db4f5140743..1cbfe57e971d5c 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -111,7 +111,7 @@ xfs_verify_ino(
 
 /* Is this an internal inode number? */
 inline bool
-xfs_internal_inum(
+xfs_is_sb_inum(
 	struct xfs_mount	*mp,
 	xfs_ino_t		ino)
 {
@@ -129,7 +129,7 @@ xfs_verify_dir_ino(
 	struct xfs_mount	*mp,
 	xfs_ino_t		ino)
 {
-	if (xfs_internal_inum(mp, ino))
+	if (xfs_is_sb_inum(mp, ino))
 		return false;
 	return xfs_verify_ino(mp, ino);
 }
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index d3cb6ff3b91301..25053a66c225ed 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -230,7 +230,7 @@ bool xfs_verify_fsbext(struct xfs_mount *mp, xfs_fsblock_t fsbno,
 		xfs_fsblock_t len);
 
 bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino);
-bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
+bool xfs_is_sb_inum(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
 bool xfs_verify_rtbext(struct xfs_mount *mp, xfs_rtblock_t rtbno,
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index e8b5e73bab60d3..777959f8ec724b 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -948,7 +948,7 @@ xchk_iget_for_scrubbing(
 		return xchk_install_live_inode(sc, ip_in);
 
 	/* Reject internal metadata files and obviously bad inode numbers. */
-	if (xfs_internal_inum(mp, sc->sm->sm_ino))
+	if (xfs_is_sb_inum(mp, sc->sm->sm_ino))
 		return -ENOENT;
 	if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
 		return -ENOENT;
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index d32716fb2fecf7..4a8637afb0e29b 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -95,7 +95,7 @@ xchk_setup_inode(
 	}
 
 	/* Reject internal metadata files and obviously bad inode numbers. */
-	if (xfs_internal_inum(mp, sc->sm->sm_ino))
+	if (xfs_is_sb_inum(mp, sc->sm->sm_ino))
 		return -ENOENT;
 	if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
 		return -ENOENT;
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 5da9e1a387a8bb..9085d6d11aebcd 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -1762,7 +1762,7 @@ xrep_inode_pptr(
 	 * Metadata inodes are rooted in the superblock and do not have any
 	 * parents.
 	 */
-	if (xfs_is_metadata_inode(ip))
+	if (xfs_is_internal_inode(ip))
 		return 0;
 
 	/* Inode already has an attr fork; no further work possible here. */
diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c
index 7148d8362db833..5f0d4239260862 100644
--- a/fs/xfs/scrub/orphanage.c
+++ b/fs/xfs/scrub/orphanage.c
@@ -295,7 +295,7 @@ xrep_orphanage_can_adopt(
 		return false;
 	if (sc->ip == sc->orphanage)
 		return false;
-	if (xfs_internal_inum(sc->mp, sc->ip->i_ino))
+	if (xfs_is_sb_inum(sc->mp, sc->ip->i_ino))
 		return false;
 	return true;
 }
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 91e7b51ce0680b..20711a68a87482 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -910,7 +910,7 @@ xchk_pptr_looks_zapped(
 	 * any parents.  Hence the attr fork will not be initialized, but
 	 * there are no parent pointers that might have been zapped.
 	 */
-	if (xfs_is_metadata_inode(ip))
+	if (xfs_is_internal_inode(ip))
 		return false;
 
 	/*
diff --git a/fs/xfs/scrub/refcount_repair.c b/fs/xfs/scrub/refcount_repair.c
index 4240fff459cb1d..4e572b81c98669 100644
--- a/fs/xfs/scrub/refcount_repair.c
+++ b/fs/xfs/scrub/refcount_repair.c
@@ -215,7 +215,7 @@ xrep_refc_rmap_shareable(
 		return false;
 
 	/* Metadata in files are never shareable */
-	if (xfs_internal_inum(mp, rmap->rm_owner))
+	if (xfs_is_sb_inum(mp, rmap->rm_owner))
 		return false;
 
 	/* Metadata and unwritten file blocks are not shareable. */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a8430f30d6df29..0465546010554a 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1295,7 +1295,7 @@ xfs_inode_needs_inactive(
 		return false;
 
 	/* Metadata inodes require explicit resource cleanup. */
-	if (xfs_is_metadata_inode(ip))
+	if (xfs_is_internal_inode(ip))
 		return false;
 
 	/* Want to clean out the cow blocks if there are any. */
@@ -1388,7 +1388,7 @@ xfs_inactive(
 		goto out;
 
 	/* Metadata inodes require explicit resource cleanup. */
-	if (xfs_is_metadata_inode(ip))
+	if (xfs_is_internal_inode(ip))
 		goto out;
 
 	/* Try to clean out the cow blocks if there are any. */
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 41444a557576c1..df7262f4674f78 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -276,7 +276,7 @@ static inline bool xfs_is_reflink_inode(const struct xfs_inode *ip)
 	return ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
 }
 
-static inline bool xfs_is_metadata_inode(const struct xfs_inode *ip)
+static inline bool xfs_is_internal_inode(const struct xfs_inode *ip)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index c0757ab994957b..37c2b50d877e42 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -69,7 +69,7 @@ xfs_bulkstat_one_int(
 	vfsuid_t		vfsuid;
 	vfsgid_t		vfsgid;
 
-	if (xfs_internal_inum(mp, ino))
+	if (xfs_is_sb_inum(mp, ino))
 		goto out_advance;
 
 	error = xfs_iget(mp, tp, ino,

[PATCH 04/28] xfs: standardize EXPERIMENTAL warning generation

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Refactor the open-coded warnings about EXPERIMENTAL feature use into a
standard helper before we go adding more experimental features.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/scrub.c |    3 +--
 fs/xfs/xfs_fsops.c   |    4 +---
 fs/xfs/xfs_message.c |   47 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_message.h |   19 +++++++++++++------
 fs/xfs/xfs_mount.h   |   20 ++++++++++++++------
 fs/xfs/xfs_pnfs.c    |    3 +--
 fs/xfs/xfs_super.c   |   10 +++-------
 fs/xfs/xfs_xattr.c   |    3 +--
 8 files changed, 81 insertions(+), 28 deletions(-)


diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 4cbcf7a86dbec5..8a5c3af4cfda38 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -605,8 +605,7 @@ xfs_scrub_metadata(
 	if (error)
 		goto out;
 
-	xfs_warn_mount(mp, XFS_OPSTATE_WARNED_SCRUB,
- "EXPERIMENTAL online scrub feature in use. Use at your own risk!");
+	xfs_warn_experimental(mp, XFS_EXPERIMENTAL_SCRUB);
 
 	sc = kzalloc(sizeof(struct xfs_scrub), XCHK_GFP_FLAGS);
 	if (!sc) {
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 82812a458cf10f..28dde215c89953 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -162,9 +162,7 @@ xfs_growfs_data_private(
 		error = xfs_resizefs_init_new_ags(tp, &id, oagcount, nagcount,
 				delta, last_pag, &lastag_extended);
 	} else {
-		xfs_warn_mount(mp, XFS_OPSTATE_WARNED_SHRINK,
-	"EXPERIMENTAL online shrink feature in use. Use at your own risk!");
-
+		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_SHRINK);
 		error = xfs_ag_shrink_space(last_pag, &tp, -delta);
 	}
 	xfs_perag_put(last_pag);
diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c
index 8f495cc23903b2..c7aa16af6f0996 100644
--- a/fs/xfs/xfs_message.c
+++ b/fs/xfs/xfs_message.c
@@ -131,3 +131,50 @@ xfs_buf_alert_ratelimited(
 	__xfs_printk(KERN_ALERT, mp, &vaf);
 	va_end(args);
 }
+
+void
+xfs_warn_experimental(
+	struct xfs_mount		*mp,
+	enum xfs_experimental_feat	feat)
+{
+	static const struct {
+		const char		*name;
+		long			opstate;
+	} features[] = {
+		[XFS_EXPERIMENTAL_PNFS] = {
+			.opstate	= XFS_OPSTATE_WARNED_PNFS,
+			.name		= "pNFS",
+		},
+		[XFS_EXPERIMENTAL_SCRUB] = {
+			.opstate	= XFS_OPSTATE_WARNED_SCRUB,
+			.name		= "online scrub",
+		},
+		[XFS_EXPERIMENTAL_SHRINK] = {
+			.opstate	= XFS_OPSTATE_WARNED_SHRINK,
+			.name		= "online shrink",
+		},
+		[XFS_EXPERIMENTAL_LARP] = {
+			.opstate	= XFS_OPSTATE_WARNED_LARP,
+			.name		= "logged extended attributes",
+		},
+		[XFS_EXPERIMENTAL_LBS] = {
+			.opstate	= XFS_OPSTATE_WARNED_LBS,
+			.name		= "large block size",
+		},
+		[XFS_EXPERIMENTAL_EXCHRANGE] = {
+			.opstate	= XFS_OPSTATE_WARNED_EXCHRANGE,
+			.name		= "exchange range",
+		},
+		[XFS_EXPERIMENTAL_PPTR] = {
+			.opstate	= XFS_OPSTATE_WARNED_PPTR,
+			.name		= "parent pointer",
+		},
+	};
+	ASSERT(feat >= 0 && feat < XFS_EXPERIMENTAL_MAX);
+	BUILD_BUG_ON(ARRAY_SIZE(features) != XFS_EXPERIMENTAL_MAX);
+
+	if (xfs_should_warn(mp, features[feat].opstate))
+		xfs_warn(mp,
+ "EXPERIMENTAL %s feature enabled.  Use at your own risk!",
+				features[feat].name);
+}
diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h
index cc323775a12c31..5be8be72f225a6 100644
--- a/fs/xfs/xfs_message.h
+++ b/fs/xfs/xfs_message.h
@@ -75,12 +75,6 @@ do {									\
 #define xfs_debug_ratelimited(dev, fmt, ...)				\
 	xfs_printk_ratelimited(xfs_debug, dev, fmt, ##__VA_ARGS__)
 
-#define xfs_warn_mount(mp, warntag, fmt, ...)				\
-do {									\
-	if (xfs_should_warn((mp), (warntag)))				\
-		xfs_warn((mp), (fmt), ##__VA_ARGS__);			\
-} while (0)
-
 #define xfs_warn_once(dev, fmt, ...)				\
 	xfs_printk_once(xfs_warn, dev, fmt, ##__VA_ARGS__)
 #define xfs_notice_once(dev, fmt, ...)				\
@@ -96,4 +90,17 @@ extern void xfs_hex_dump(const void *p, int length);
 void xfs_buf_alert_ratelimited(struct xfs_buf *bp, const char *rlmsg,
 			       const char *fmt, ...);
 
+enum xfs_experimental_feat {
+	XFS_EXPERIMENTAL_PNFS,
+	XFS_EXPERIMENTAL_SCRUB,
+	XFS_EXPERIMENTAL_SHRINK,
+	XFS_EXPERIMENTAL_LARP,
+	XFS_EXPERIMENTAL_LBS,
+	XFS_EXPERIMENTAL_EXCHRANGE,
+	XFS_EXPERIMENTAL_PPTR,
+
+	XFS_EXPERIMENTAL_MAX,
+};
+void xfs_warn_experimental(struct xfs_mount *mp, enum xfs_experimental_feat f);
+
 #endif	/* __XFS_MESSAGE_H */
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 1b698878f40cb1..b82977f654a5e5 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -467,18 +467,26 @@ __XFS_HAS_FEAT(nouuid, NOUUID)
  */
 #define XFS_OPSTATE_BLOCKGC_ENABLED	6
 
+/* Kernel has logged a warning about pNFS being used on this fs. */
+#define XFS_OPSTATE_WARNED_PNFS		7
 /* Kernel has logged a warning about online fsck being used on this fs. */
-#define XFS_OPSTATE_WARNED_SCRUB	7
+#define XFS_OPSTATE_WARNED_SCRUB	8
 /* Kernel has logged a warning about shrink being used on this fs. */
-#define XFS_OPSTATE_WARNED_SHRINK	8
+#define XFS_OPSTATE_WARNED_SHRINK	9
 /* Kernel has logged a warning about logged xattr updates being used. */
-#define XFS_OPSTATE_WARNED_LARP		9
+#define XFS_OPSTATE_WARNED_LARP		10
 /* Mount time quotacheck is running */
-#define XFS_OPSTATE_QUOTACHECK_RUNNING	10
+#define XFS_OPSTATE_QUOTACHECK_RUNNING	11
 /* Do we want to clear log incompat flags? */
-#define XFS_OPSTATE_UNSET_LOG_INCOMPAT	11
+#define XFS_OPSTATE_UNSET_LOG_INCOMPAT	12
 /* Filesystem can use logged extended attributes */
-#define XFS_OPSTATE_USE_LARP		12
+#define XFS_OPSTATE_USE_LARP		13
+/* Kernel has logged a warning about blocksize > pagesize on this fs. */
+#define XFS_OPSTATE_WARNED_LBS		14
+/* Kernel has logged a warning about exchange-range being used on this fs. */
+#define XFS_OPSTATE_WARNED_EXCHRANGE	15
+/* Kernel has logged a warning about parent pointers being used on this fs. */
+#define XFS_OPSTATE_WARNED_PPTR		16
 
 #define __XFS_IS_OPSTATE(name, NAME) \
 static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 23d16186e1a34a..6f4479deac6d68 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -58,8 +58,7 @@ xfs_fs_get_uuid(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
-	xfs_notice_once(mp,
-"Using experimental pNFS feature, use at your own risk!");
+	xfs_warn_experimental(mp, XFS_EXPERIMENTAL_PNFS);
 
 	if (*len < sizeof(uuid_t))
 		return -EINVAL;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 457c2d70968d9a..b7091728791bf5 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1657,9 +1657,7 @@ xfs_fs_fill_super(
 			goto out_free_sb;
 		}
 
-		xfs_warn(mp,
-"EXPERIMENTAL: V5 Filesystem with Large Block Size (%d bytes) enabled.",
-			mp->m_sb.sb_blocksize);
+		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_LBS);
 	}
 
 	/* Ensure this filesystem fits in the page cache limits */
@@ -1755,12 +1753,10 @@ xfs_fs_fill_super(
 	}
 
 	if (xfs_has_exchange_range(mp))
-		xfs_warn(mp,
-	"EXPERIMENTAL exchange-range feature enabled. Use at your own risk!");
+		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_EXCHRANGE);
 
 	if (xfs_has_parent(mp))
-		xfs_warn(mp,
-	"EXPERIMENTAL parent pointer feature enabled. Use at your own risk!");
+		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_PPTR);
 
 	error = xfs_mountfs(mp);
 	if (error)
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index eaf849260bd672..0f641a9091ecbf 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -51,8 +51,7 @@ xfs_attr_grab_log_assist(
 		return error;
 	xfs_set_using_logged_xattrs(mp);
 
-	xfs_warn_mount(mp, XFS_OPSTATE_WARNED_LARP,
- "EXPERIMENTAL logged extended attributes feature in use. Use at your own risk!");
+	xfs_warn_experimental(mp, XFS_EXPERIMENTAL_LARP);
 
 	return 0;
 }

[PATCH 05/28] xfs: define the on-disk format for the metadir feature

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Define the on-disk layout and feature flags for the metadata inode
directory feature.  Add a xfs_sb_version_hasmetadir for benefit of
xfs_repair, which needs to know where the new end of the superblock
lies.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_format.h      |   97 ++++++++++++++++++++++++++++++++++-----
 fs/xfs/libxfs/xfs_inode_buf.c   |   20 ++++++--
 fs/xfs/libxfs/xfs_inode_util.c  |    2 +
 fs/xfs/libxfs/xfs_log_format.h  |    2 -
 fs/xfs/libxfs/xfs_ondisk.h      |    2 -
 fs/xfs/libxfs/xfs_sb.c          |   10 ++++
 fs/xfs/scrub/inode.c            |    2 -
 fs/xfs/scrub/inode_repair.c     |    9 ++--
 fs/xfs/xfs_inode.h              |   14 ++++++
 fs/xfs/xfs_inode_item.c         |    7 ++-
 fs/xfs/xfs_inode_item_recover.c |    2 -
 fs/xfs/xfs_message.c            |    4 ++
 fs/xfs/xfs_message.h            |    1 
 fs/xfs/xfs_mount.h              |    4 ++
 fs/xfs/xfs_super.c              |    3 +
 15 files changed, 153 insertions(+), 26 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index a24ab46aaebc7e..616f81045921b7 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -174,6 +174,8 @@ typedef struct xfs_sb {
 	xfs_lsn_t	sb_lsn;		/* last write sequence */
 	uuid_t		sb_meta_uuid;	/* metadata file system unique id */
 
+	xfs_ino_t	sb_metadirino;	/* metadata directory tree root */
+
 	/* must be padded to 64 bit alignment */
 } xfs_sb_t;
 
@@ -259,6 +261,8 @@ struct xfs_dsb {
 	__be64		sb_lsn;		/* last write sequence */
 	uuid_t		sb_meta_uuid;	/* metadata file system unique id */
 
+	__be64		sb_metadirino;	/* metadata directory tree root */
+
 	/* must be padded to 64 bit alignment */
 };
 
@@ -374,6 +378,7 @@ xfs_sb_has_ro_compat_feature(
 #define XFS_SB_FEAT_INCOMPAT_NREXT64	(1 << 5)  /* large extent counters */
 #define XFS_SB_FEAT_INCOMPAT_EXCHRANGE	(1 << 6)  /* exchangerange supported */
 #define XFS_SB_FEAT_INCOMPAT_PARENT	(1 << 7)  /* parent pointers */
+#define XFS_SB_FEAT_INCOMPAT_METADIR	(1 << 8)  /* metadata dir tree */
 #define XFS_SB_FEAT_INCOMPAT_ALL \
 		(XFS_SB_FEAT_INCOMPAT_FTYPE | \
 		 XFS_SB_FEAT_INCOMPAT_SPINODES | \
@@ -790,6 +795,27 @@ static inline time64_t xfs_bigtime_to_unix(uint64_t ondisk_seconds)
 	return (time64_t)ondisk_seconds - XFS_BIGTIME_EPOCH_OFFSET;
 }
 
+enum xfs_metafile_type {
+	XFS_METAFILE_UNKNOWN,		/* unknown */
+	XFS_METAFILE_DIR,		/* metadir directory */
+	XFS_METAFILE_USRQUOTA,		/* user quota */
+	XFS_METAFILE_GRPQUOTA,		/* group quota */
+	XFS_METAFILE_PRJQUOTA,		/* project quota */
+	XFS_METAFILE_RTBITMAP,		/* rt bitmap */
+	XFS_METAFILE_RTSUMMARY,		/* rt summary */
+
+	XFS_METAFILE_MAX
+} __packed;
+
+#define XFS_METAFILE_TYPE_STR \
+	{ XFS_METAFILE_UNKNOWN,		"unknown" }, \
+	{ XFS_METAFILE_DIR,		"dir" }, \
+	{ XFS_METAFILE_USRQUOTA,	"usrquota" }, \
+	{ XFS_METAFILE_GRPQUOTA,	"grpquota" }, \
+	{ XFS_METAFILE_PRJQUOTA,	"prjquota" }, \
+	{ XFS_METAFILE_RTBITMAP,	"rtbitmap" }, \
+	{ XFS_METAFILE_RTSUMMARY,	"rtsummary" }
+
 /*
  * On-disk inode structure.
  *
@@ -812,7 +838,7 @@ struct xfs_dinode {
 	__be16		di_mode;	/* mode and type of file */
 	__u8		di_version;	/* inode version */
 	__u8		di_format;	/* format of di_c data */
-	__be16		di_onlink;	/* old number of links to file */
+	__be16		di_metatype;	/* XFS_METAFILE_*; was di_onlink */
 	__be32		di_uid;		/* owner's user id */
 	__be32		di_gid;		/* owner's group id */
 	__be32		di_nlink;	/* number of links to file */
@@ -1088,21 +1114,60 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
  * Values for di_flags2 These start by being exposed to userspace in the upper
  * 16 bits of the XFS_XFLAG_s range.
  */
-#define XFS_DIFLAG2_DAX_BIT	0	/* use DAX for this inode */
-#define XFS_DIFLAG2_REFLINK_BIT	1	/* file's blocks may be shared */
-#define XFS_DIFLAG2_COWEXTSIZE_BIT   2  /* copy on write extent size hint */
-#define XFS_DIFLAG2_BIGTIME_BIT	3	/* big timestamps */
-#define XFS_DIFLAG2_NREXT64_BIT 4	/* large extent counters */
-
-#define XFS_DIFLAG2_DAX		(1 << XFS_DIFLAG2_DAX_BIT)
-#define XFS_DIFLAG2_REFLINK     (1 << XFS_DIFLAG2_REFLINK_BIT)
-#define XFS_DIFLAG2_COWEXTSIZE  (1 << XFS_DIFLAG2_COWEXTSIZE_BIT)
-#define XFS_DIFLAG2_BIGTIME	(1 << XFS_DIFLAG2_BIGTIME_BIT)
-#define XFS_DIFLAG2_NREXT64	(1 << XFS_DIFLAG2_NREXT64_BIT)
+/* use DAX for this inode */
+#define XFS_DIFLAG2_DAX_BIT		0
+
+/* file's blocks may be shared */
+#define XFS_DIFLAG2_REFLINK_BIT		1
+
+/* copy on write extent size hint */
+#define XFS_DIFLAG2_COWEXTSIZE_BIT	2
+
+/* big timestamps */
+#define XFS_DIFLAG2_BIGTIME_BIT		3
+
+/* large extent counters */
+#define XFS_DIFLAG2_NREXT64_BIT		4
+
+/*
+ * The inode contains filesystem metadata and can be found through the metadata
+ * directory tree.  Metadata inodes must satisfy the following constraints:
+ *
+ * - V5 filesystem (and ftype) are enabled;
+ * - The only valid modes are regular files and directories;
+ * - The access bits must be zero;
+ * - DMAPI event and state masks are zero;
+ * - The user and group IDs must be zero;
+ * - The project ID can be used as a u32 annotation;
+ * - The immutable, sync, noatime, nodump, nodefrag flags must be set.
+ * - The dax flag must not be set.
+ * - Directories must have nosymlinks set.
+ *
+ * These requirements are chosen defensively to minimize the ability of
+ * userspace to read or modify the contents, should a metadata file ever
+ * escape to userspace.
+ *
+ * There are further constraints on the directory tree itself:
+ *
+ * - Metadata inodes must never be resolvable through the root directory;
+ * - They must never be accessed by userspace;
+ * - Metadata directory entries must have correct ftype.
+ *
+ * Superblock-rooted metadata files must have the METADATA iflag set even
+ * though they do not have a parent directory.
+ */
+#define XFS_DIFLAG2_METADATA_BIT	5
+
+#define XFS_DIFLAG2_DAX		(1ULL << XFS_DIFLAG2_DAX_BIT)
+#define XFS_DIFLAG2_REFLINK	(1ULL << XFS_DIFLAG2_REFLINK_BIT)
+#define XFS_DIFLAG2_COWEXTSIZE	(1ULL << XFS_DIFLAG2_COWEXTSIZE_BIT)
+#define XFS_DIFLAG2_BIGTIME	(1ULL << XFS_DIFLAG2_BIGTIME_BIT)
+#define XFS_DIFLAG2_NREXT64	(1ULL << XFS_DIFLAG2_NREXT64_BIT)
+#define XFS_DIFLAG2_METADATA	(1ULL << XFS_DIFLAG2_METADATA_BIT)
 
 #define XFS_DIFLAG2_ANY \
 	(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \
-	 XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64)
+	 XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64 | XFS_DIFLAG2_METADATA)
 
 static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
 {
@@ -1117,6 +1182,12 @@ static inline bool xfs_dinode_has_large_extent_counts(
 	       (dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_NREXT64));
 }
 
+static inline bool xfs_dinode_is_metadir(const struct xfs_dinode *dip)
+{
+	return dip->di_version >= 3 &&
+	       (dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA));
+}
+
 /*
  * Inode number format:
  * low inopblog bits - offset in block
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 79babeac9d7546..78febaa0d6923b 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -209,12 +209,15 @@ xfs_inode_from_disk(
 	 * They will also be unconditionally written back to disk as v2 inodes.
 	 */
 	if (unlikely(from->di_version == 1)) {
-		set_nlink(inode, be16_to_cpu(from->di_onlink));
+		/* di_metatype used to be di_onlink */
+		set_nlink(inode, be16_to_cpu(from->di_metatype));
 		ip->i_projid = 0;
 	} else {
 		set_nlink(inode, be32_to_cpu(from->di_nlink));
 		ip->i_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 |
 					be16_to_cpu(from->di_projid_lo);
+		if (xfs_dinode_is_metadir(from))
+			ip->i_metatype = be16_to_cpu(from->di_metatype);
 	}
 
 	i_uid_write(inode, be32_to_cpu(from->di_uid));
@@ -315,7 +318,10 @@ xfs_inode_to_disk(
 	struct inode		*inode = VFS_I(ip);
 
 	to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
-	to->di_onlink = 0;
+	if (xfs_is_metadir_inode(ip))
+		to->di_metatype = cpu_to_be16(ip->i_metatype);
+	else
+		to->di_metatype = 0;
 
 	to->di_format = xfs_ifork_format(&ip->i_df);
 	to->di_uid = cpu_to_be32(i_uid_read(inode));
@@ -523,8 +529,11 @@ xfs_dinode_verify(
 	 * di_nlink==0 on a V1 inode.  V2/3 inodes would get written out with
 	 * di_onlink==0, so we can check that.
 	 */
-	if (dip->di_version >= 2) {
-		if (dip->di_onlink)
+	if (dip->di_version == 2) {
+		if (dip->di_metatype)
+			return __this_address;
+	} else if (dip->di_version >= 3) {
+		if (!xfs_dinode_is_metadir(dip) && dip->di_metatype)
 			return __this_address;
 	}
 
@@ -546,7 +555,8 @@ xfs_dinode_verify(
 			if (dip->di_nlink)
 				return __this_address;
 		} else {
-			if (dip->di_onlink)
+			/* di_metatype used to be di_onlink */
+			if (dip->di_metatype)
 				return __this_address;
 		}
 	}
diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
index ec64eda3bbe2e1..deb0b7c00a1ffa 100644
--- a/fs/xfs/libxfs/xfs_inode_util.c
+++ b/fs/xfs/libxfs/xfs_inode_util.c
@@ -224,6 +224,8 @@ xfs_inode_inherit_flags2(
 	}
 	if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
 		ip->i_diflags2 |= XFS_DIFLAG2_DAX;
+	if (xfs_is_metadir_inode(pip))
+		ip->i_diflags2 |= XFS_DIFLAG2_METADATA;
 
 	/* Don't let invalid cowextsize hints propagate. */
 	failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize,
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 3e6682ed656b30..ace7384a275bfb 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -404,7 +404,7 @@ struct xfs_log_dinode {
 	uint16_t	di_mode;	/* mode and type of file */
 	int8_t		di_version;	/* inode version */
 	int8_t		di_format;	/* format of di_c data */
-	uint8_t		di_pad3[2];	/* unused in v2/3 inodes */
+	uint16_t	di_metatype;	/* metadata type, if DIFLAG2_METADATA */
 	uint32_t	di_uid;		/* owner's user id */
 	uint32_t	di_gid;		/* owner's group id */
 	uint32_t	di_nlink;	/* number of links to file */
diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 23c133fd36f5bb..8bca86e350fdc1 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -37,7 +37,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dinode,		176);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot,		104);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk,			136);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			264);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			272);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr,		56);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key,		4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec,		16);
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index f7a07e61341ded..19fa999b4032c8 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -180,6 +180,8 @@ xfs_sb_version_to_features(
 		features |= XFS_FEAT_EXCHANGE_RANGE;
 	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_PARENT)
 		features |= XFS_FEAT_PARENT;
+	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
+		features |= XFS_FEAT_METADIR;
 
 	return features;
 }
@@ -689,6 +691,11 @@ __xfs_sb_from_disk(
 	/* Convert on-disk flags to in-memory flags? */
 	if (convert_xquota)
 		xfs_sb_quota_from_disk(to);
+
+	if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
+		to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
+	else
+		to->sb_metadirino = NULLFSINO;
 }
 
 void
@@ -836,6 +843,9 @@ xfs_sb_to_disk(
 	to->sb_lsn = cpu_to_be64(from->sb_lsn);
 	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID)
 		uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid);
+
+	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
+		to->sb_metadirino = cpu_to_be64(from->sb_metadirino);
 }
 
 /*
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 4a8637afb0e29b..a7ac7a4125ff12 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -421,7 +421,7 @@ xchk_dinode(
 		break;
 	case 2:
 	case 3:
-		if (dip->di_onlink != 0)
+		if (!xfs_dinode_is_metadir(dip) && dip->di_metatype)
 			xchk_ino_set_corrupt(sc, ino);
 
 		if (dip->di_mode == 0 && sc->ip)
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 9085d6d11aebcd..1eec5c6eb11071 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -521,10 +521,13 @@ STATIC void
 xrep_dinode_nlinks(
 	struct xfs_dinode	*dip)
 {
-	if (dip->di_version > 1)
-		dip->di_onlink = 0;
-	else
+	if (dip->di_version < 2) {
 		dip->di_nlink = 0;
+		return;
+	}
+
+	if (!xfs_dinode_is_metadir(dip))
+		dip->di_metatype = 0;
 }
 
 /* Fix any conflicting flags that the verifiers complain about. */
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index df7262f4674f78..b6e959563547fd 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -65,6 +65,7 @@ typedef struct xfs_inode {
 		uint16_t	i_flushiter;	/* incremented on flush */
 	};
 	uint8_t			i_forkoff;	/* attr fork offset >> 3 */
+	enum xfs_metafile_type	i_metatype;	/* XFS_METAFILE_* */
 	uint16_t		i_diflags;	/* XFS_DIFLAG_... */
 	uint64_t		i_diflags2;	/* XFS_DIFLAG2_... */
 	struct timespec64	i_crtime;	/* time created */
@@ -276,10 +277,23 @@ static inline bool xfs_is_reflink_inode(const struct xfs_inode *ip)
 	return ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
 }
 
+static inline bool xfs_is_metadir_inode(const struct xfs_inode *ip)
+{
+	return ip->i_diflags2 & XFS_DIFLAG2_METADATA;
+}
+
 static inline bool xfs_is_internal_inode(const struct xfs_inode *ip)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
+	/* Any file in the metadata directory tree is a metadata inode. */
+	if (xfs_has_metadir(mp))
+		return xfs_is_metadir_inode(ip);
+
+	/*
+	 * Before metadata directories, the only metadata inodes were the
+	 * three quota files, the realtime bitmap, and the realtime summary.
+	 */
 	return ip->i_ino == mp->m_sb.sb_rbmino ||
 	       ip->i_ino == mp->m_sb.sb_rsumino ||
 	       xfs_is_quota_inode(&mp->m_sb, ip->i_ino);
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index b509cbd191f4e6..912f0b1bc3cb70 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -556,7 +556,6 @@ xfs_inode_to_log_dinode(
 	to->di_projid_lo = ip->i_projid & 0xffff;
 	to->di_projid_hi = ip->i_projid >> 16;
 
-	memset(to->di_pad3, 0, sizeof(to->di_pad3));
 	to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode_get_atime(inode));
 	to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode_get_mtime(inode));
 	to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode_get_ctime(inode));
@@ -590,10 +589,16 @@ xfs_inode_to_log_dinode(
 
 		/* dummy value for initialisation */
 		to->di_crc = 0;
+
+		if (xfs_is_metadir_inode(ip))
+			to->di_metatype = ip->i_metatype;
+		else
+			to->di_metatype = 0;
 	} else {
 		to->di_version = 2;
 		to->di_flushiter = ip->i_flushiter;
 		memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad));
+		to->di_metatype = 0;
 	}
 
 	xfs_inode_to_log_dinode_iext_counters(ip, to);
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index dbdab4ce7c44c4..e70d2611456bc9 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -175,7 +175,7 @@ xfs_log_dinode_to_disk(
 	to->di_mode = cpu_to_be16(from->di_mode);
 	to->di_version = from->di_version;
 	to->di_format = from->di_format;
-	to->di_onlink = 0;
+	to->di_metatype = cpu_to_be16(from->di_metatype);
 	to->di_uid = cpu_to_be32(from->di_uid);
 	to->di_gid = cpu_to_be32(from->di_gid);
 	to->di_nlink = cpu_to_be32(from->di_nlink);
diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c
index c7aa16af6f0996..6ed485ff27568c 100644
--- a/fs/xfs/xfs_message.c
+++ b/fs/xfs/xfs_message.c
@@ -169,6 +169,10 @@ xfs_warn_experimental(
 			.opstate	= XFS_OPSTATE_WARNED_PPTR,
 			.name		= "parent pointer",
 		},
+		[XFS_EXPERIMENTAL_METADIR] = {
+			.opstate	= XFS_OPSTATE_WARNED_METADIR,
+			.name		= "metadata directory tree",
+		},
 	};
 	ASSERT(feat >= 0 && feat < XFS_EXPERIMENTAL_MAX);
 	BUILD_BUG_ON(ARRAY_SIZE(features) != XFS_EXPERIMENTAL_MAX);
diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h
index 5be8be72f225a6..7fb36ced9df747 100644
--- a/fs/xfs/xfs_message.h
+++ b/fs/xfs/xfs_message.h
@@ -98,6 +98,7 @@ enum xfs_experimental_feat {
 	XFS_EXPERIMENTAL_LBS,
 	XFS_EXPERIMENTAL_EXCHRANGE,
 	XFS_EXPERIMENTAL_PPTR,
+	XFS_EXPERIMENTAL_METADIR,
 
 	XFS_EXPERIMENTAL_MAX,
 };
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index b82977f654a5e5..6aaacfc0487e90 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -332,6 +332,7 @@ typedef struct xfs_mount {
 #define XFS_FEAT_NEEDSREPAIR	(1ULL << 25)	/* needs xfs_repair */
 #define XFS_FEAT_NREXT64	(1ULL << 26)	/* large extent counters */
 #define XFS_FEAT_EXCHANGE_RANGE	(1ULL << 27)	/* exchange range */
+#define XFS_FEAT_METADIR	(1ULL << 28)	/* metadata directory tree */
 
 /* Mount features */
 #define XFS_FEAT_NOATTR2	(1ULL << 48)	/* disable attr2 creation */
@@ -387,6 +388,7 @@ __XFS_HAS_FEAT(bigtime, BIGTIME)
 __XFS_HAS_FEAT(needsrepair, NEEDSREPAIR)
 __XFS_HAS_FEAT(large_extent_counts, NREXT64)
 __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE)
+__XFS_HAS_FEAT(metadir, METADIR)
 
 /*
  * Some features are always on for v5 file systems, allow the compiler to
@@ -487,6 +489,8 @@ __XFS_HAS_FEAT(nouuid, NOUUID)
 #define XFS_OPSTATE_WARNED_EXCHRANGE	15
 /* Kernel has logged a warning about parent pointers being used on this fs. */
 #define XFS_OPSTATE_WARNED_PPTR		16
+/* Kernel has logged a warning about metadata dirs being used on this fs. */
+#define XFS_OPSTATE_WARNED_METADIR	17
 
 #define __XFS_IS_OPSTATE(name, NAME) \
 static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index b7091728791bf5..be493d39296005 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1731,6 +1731,9 @@ xfs_fs_fill_super(
 		mp->m_features &= ~XFS_FEAT_DISCARD;
 	}
 
+	if (xfs_has_metadir(mp))
+		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_METADIR);
+
 	if (xfs_has_reflink(mp)) {
 		if (mp->m_sb.sb_rblocks) {
 			xfs_alert(mp,

[PATCH 06/28] xfs: iget for metadata inodes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a xfs_trans_metafile_iget function for metadata inodes to ensure
that when we try to iget a metadata file, the inode is allocated and its
file mode matches the metadata file type the caller expects.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_metafile.h |   16 ++++++++++
 fs/xfs/xfs_icache.c          |   65 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_inode.c           |    1 +
 fs/xfs/xfs_qm.c              |   23 ++++++++++++++-
 fs/xfs/xfs_rtalloc.c         |   38 ++++++++++++++-----------
 5 files changed, 125 insertions(+), 18 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_metafile.h


diff --git a/fs/xfs/libxfs/xfs_metafile.h b/fs/xfs/libxfs/xfs_metafile.h
new file mode 100644
index 00000000000000..60fe1890611277
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_metafile.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_METAFILE_H__
+#define __XFS_METAFILE_H__
+
+/* Code specific to kernel/userspace; must be provided externally. */
+
+int xfs_trans_metafile_iget(struct xfs_trans *tp, xfs_ino_t ino,
+		enum xfs_metafile_type metafile_type, struct xfs_inode **ipp);
+int xfs_metafile_iget(struct xfs_mount *mp, xfs_ino_t ino,
+		enum xfs_metafile_type metafile_type, struct xfs_inode **ipp);
+
+#endif /* __XFS_METAFILE_H__ */
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 383c245482027b..aa645e35781202 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -25,6 +25,9 @@
 #include "xfs_ag.h"
 #include "xfs_log_priv.h"
 #include "xfs_health.h"
+#include "xfs_da_format.h"
+#include "xfs_dir2.h"
+#include "xfs_metafile.h"
 
 #include <linux/iversion.h>
 
@@ -828,6 +831,68 @@ xfs_iget(
 	return error;
 }
 
+/*
+ * Get a metadata inode.
+ *
+ * The metafile type must match the file mode exactly.
+ */
+int
+xfs_trans_metafile_iget(
+	struct xfs_trans	*tp,
+	xfs_ino_t		ino,
+	enum xfs_metafile_type	metafile_type,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_inode	*ip;
+	umode_t			mode;
+	int			error;
+
+	error = xfs_iget(mp, tp, ino, 0, 0, &ip);
+	if (error == -EFSCORRUPTED)
+		goto whine;
+	if (error)
+		return error;
+
+	if (VFS_I(ip)->i_nlink == 0)
+		goto bad_rele;
+
+	if (metafile_type == XFS_METAFILE_DIR)
+		mode = S_IFDIR;
+	else
+		mode = S_IFREG;
+	if (inode_wrong_type(VFS_I(ip), mode))
+		goto bad_rele;
+
+	*ipp = ip;
+	return 0;
+bad_rele:
+	xfs_irele(ip);
+whine:
+	xfs_err(mp, "metadata inode 0x%llx is corrupt", ino);
+	return -EFSCORRUPTED;
+}
+
+/* Grab a metadata file if the caller doesn't already have a transaction. */
+int
+xfs_metafile_iget(
+	struct xfs_mount	*mp,
+	xfs_ino_t		ino,
+	enum xfs_metafile_type	metafile_type,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_trans	*tp;
+	int			error;
+
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	error = xfs_trans_metafile_iget(tp, ino, metafile_type, ipp);
+	xfs_trans_cancel(tp);
+	return error;
+}
+
 /*
  * Grab the inode for reclaim exclusively.
  *
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 0465546010554a..12c5ff151edf4c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -43,6 +43,7 @@
 #include "xfs_parent.h"
 #include "xfs_xattr.h"
 #include "xfs_inode_util.h"
+#include "xfs_metafile.h"
 
 struct kmem_cache *xfs_inode_cache;
 
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 7e2307921deb2f..d0674d84af3ec5 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -27,6 +27,8 @@
 #include "xfs_ialloc.h"
 #include "xfs_log_priv.h"
 #include "xfs_health.h"
+#include "xfs_da_format.h"
+#include "xfs_metafile.h"
 
 /*
  * The global quota manager. There is only one of these for the entire
@@ -733,6 +735,17 @@ xfs_qm_destroy_quotainfo(
 	mp->m_quotainfo = NULL;
 }
 
+static inline enum xfs_metafile_type
+xfs_qm_metafile_type(
+	unsigned int		flags)
+{
+	if (flags & XFS_QMOPT_UQUOTA)
+		return XFS_METAFILE_USRQUOTA;
+	else if (flags & XFS_QMOPT_GQUOTA)
+		return XFS_METAFILE_GRPQUOTA;
+	return XFS_METAFILE_PRJQUOTA;
+}
+
 /*
  * Create an inode and return with a reference already taken, but unlocked
  * This is how we create quota inodes
@@ -744,6 +757,7 @@ xfs_qm_qino_alloc(
 	unsigned int		flags)
 {
 	struct xfs_trans	*tp;
+	enum xfs_metafile_type	metafile_type = xfs_qm_metafile_type(flags);
 	int			error;
 	bool			need_alloc = true;
 
@@ -777,9 +791,10 @@ xfs_qm_qino_alloc(
 			}
 		}
 		if (ino != NULLFSINO) {
-			error = xfs_iget(mp, NULL, ino, 0, 0, ipp);
+			error = xfs_metafile_iget(mp, ino, metafile_type, ipp);
 			if (error)
 				return error;
+
 			mp->m_sb.sb_gquotino = NULLFSINO;
 			mp->m_sb.sb_pquotino = NULLFSINO;
 			need_alloc = false;
@@ -1553,16 +1568,20 @@ xfs_qm_qino_load(
 	struct xfs_inode	**ipp)
 {
 	xfs_ino_t		ino = NULLFSINO;
+	enum xfs_metafile_type	metafile_type = XFS_METAFILE_UNKNOWN;
 
 	switch (type) {
 	case XFS_DQTYPE_USER:
 		ino = mp->m_sb.sb_uquotino;
+		metafile_type = XFS_METAFILE_USRQUOTA;
 		break;
 	case XFS_DQTYPE_GROUP:
 		ino = mp->m_sb.sb_gquotino;
+		metafile_type = XFS_METAFILE_GRPQUOTA;
 		break;
 	case XFS_DQTYPE_PROJ:
 		ino = mp->m_sb.sb_pquotino;
+		metafile_type = XFS_METAFILE_PRJQUOTA;
 		break;
 	default:
 		ASSERT(0);
@@ -1572,7 +1591,7 @@ xfs_qm_qino_load(
 	if (ino == NULLFSINO)
 		return -ENOENT;
 
-	return xfs_iget(mp, NULL, ino, 0, 0, ipp);
+	return xfs_metafile_iget(mp, ino, metafile_type, ipp);
 }
 
 /*
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 3a2005a1e673dc..46a920b192d191 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -25,6 +25,8 @@
 #include "xfs_quota.h"
 #include "xfs_log_priv.h"
 #include "xfs_health.h"
+#include "xfs_da_format.h"
+#include "xfs_metafile.h"
 
 /*
  * Return whether there are any free extents in the size range given
@@ -1101,16 +1103,12 @@ xfs_rtalloc_reinit_frextents(
  */
 static inline int
 xfs_rtmount_iread_extents(
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	unsigned int		lock_class)
 {
-	struct xfs_trans	*tp;
 	int			error;
 
-	error = xfs_trans_alloc_empty(ip->i_mount, &tp);
-	if (error)
-		return error;
-
 	xfs_ilock(ip, XFS_ILOCK_EXCL | lock_class);
 
 	error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
@@ -1125,7 +1123,6 @@ xfs_rtmount_iread_extents(
 
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL | lock_class);
-	xfs_trans_cancel(tp);
 	return error;
 }
 
@@ -1133,45 +1130,54 @@ xfs_rtmount_iread_extents(
  * Get the bitmap and summary inodes and the summary cache into the mount
  * structure at mount time.
  */
-int					/* error */
+int
 xfs_rtmount_inodes(
-	xfs_mount_t	*mp)		/* file system mount structure */
+	struct xfs_mount	*mp)
 {
-	int		error;		/* error return value */
-	xfs_sb_t	*sbp;
+	struct xfs_trans	*tp;
+	struct xfs_sb		*sbp = &mp->m_sb;
+	int			error;
 
-	sbp = &mp->m_sb;
-	error = xfs_iget(mp, NULL, sbp->sb_rbmino, 0, 0, &mp->m_rbmip);
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	error = xfs_trans_metafile_iget(tp, mp->m_sb.sb_rbmino,
+			XFS_METAFILE_RTBITMAP, &mp->m_rbmip);
 	if (xfs_metadata_is_sick(error))
 		xfs_rt_mark_sick(mp, XFS_SICK_RT_BITMAP);
 	if (error)
-		return error;
+		goto out_trans;
 	ASSERT(mp->m_rbmip != NULL);
 
-	error = xfs_rtmount_iread_extents(mp->m_rbmip, XFS_ILOCK_RTBITMAP);
+	error = xfs_rtmount_iread_extents(tp, mp->m_rbmip, XFS_ILOCK_RTBITMAP);
 	if (error)
 		goto out_rele_bitmap;
 
-	error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip);
+	error = xfs_trans_metafile_iget(tp, mp->m_sb.sb_rsumino,
+			XFS_METAFILE_RTSUMMARY, &mp->m_rsumip);
 	if (xfs_metadata_is_sick(error))
 		xfs_rt_mark_sick(mp, XFS_SICK_RT_SUMMARY);
 	if (error)
 		goto out_rele_bitmap;
 	ASSERT(mp->m_rsumip != NULL);
 
-	error = xfs_rtmount_iread_extents(mp->m_rsumip, XFS_ILOCK_RTSUM);
+	error = xfs_rtmount_iread_extents(tp, mp->m_rsumip, XFS_ILOCK_RTSUM);
 	if (error)
 		goto out_rele_summary;
 
 	error = xfs_alloc_rsum_cache(mp, sbp->sb_rbmblocks);
 	if (error)
 		goto out_rele_summary;
+	xfs_trans_cancel(tp);
 	return 0;
 
 out_rele_summary:
 	xfs_irele(mp->m_rsumip);
 out_rele_bitmap:
 	xfs_irele(mp->m_rbmip);
+out_trans:
+	xfs_trans_cancel(tp);
 	return error;
 }
 

[PATCH 07/28] xfs: load metadata directory root at mount time

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Load the metadata directory root inode into memory at mount time and
release it at unmount time.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_mount.c |   31 +++++++++++++++++++++++++++++--
 fs/xfs/xfs_mount.h |    1 +
 2 files changed, 30 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 25bbcc3f4ee08b..2dd2606fc7e3e4 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -35,6 +35,7 @@
 #include "xfs_trace.h"
 #include "xfs_ag.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_metafile.h"
 #include "scrub/stats.h"
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
@@ -620,6 +621,22 @@ xfs_mount_setup_inode_geom(
 	xfs_ialloc_setup_geometry(mp);
 }
 
+/* Mount the metadata directory tree root. */
+STATIC int
+xfs_mount_setup_metadir(
+	struct xfs_mount	*mp)
+{
+	int			error;
+
+	/* Load the metadata directory root inode into memory. */
+	error = xfs_metafile_iget(mp, mp->m_sb.sb_metadirino, XFS_METAFILE_DIR,
+			&mp->m_metadirip);
+	if (error)
+		xfs_warn(mp, "Failed to load metadir root directory, error %d",
+				error);
+	return error;
+}
+
 /* Compute maximum possible height for per-AG btree types for this fs. */
 static inline void
 xfs_agbtree_compute_maxlevels(
@@ -866,6 +883,12 @@ xfs_mountfs(
 		mp->m_features |= XFS_FEAT_ATTR2;
 	}
 
+	if (xfs_has_metadir(mp)) {
+		error = xfs_mount_setup_metadir(mp);
+		if (error)
+			goto out_free_metadir;
+	}
+
 	/*
 	 * Get and sanity-check the root inode.
 	 * Save the pointer to it in the mount structure.
@@ -876,7 +899,7 @@ xfs_mountfs(
 		xfs_warn(mp,
 			"Failed to read root inode 0x%llx, error %d",
 			sbp->sb_rootino, -error);
-		goto out_log_dealloc;
+		goto out_free_metadir;
 	}
 
 	ASSERT(rip != NULL);
@@ -1018,6 +1041,9 @@ xfs_mountfs(
 	xfs_irele(rip);
 	/* Clean out dquots that might be in memory after quotacheck. */
 	xfs_qm_unmount(mp);
+ out_free_metadir:
+	if (mp->m_metadirip)
+		xfs_irele(mp->m_metadirip);
 
 	/*
 	 * Inactivate all inodes that might still be in memory after a log
@@ -1039,7 +1065,6 @@ xfs_mountfs(
 	 * quota inodes.
 	 */
 	xfs_unmount_flush_inodes(mp);
- out_log_dealloc:
 	xfs_log_mount_cancel(mp);
  out_inodegc_shrinker:
 	shrinker_free(mp->m_inodegc_shrinker);
@@ -1091,6 +1116,8 @@ xfs_unmountfs(
 	xfs_qm_unmount_quotas(mp);
 	xfs_rtunmount_inodes(mp);
 	xfs_irele(mp->m_rootip);
+	if (mp->m_metadirip)
+		xfs_irele(mp->m_metadirip);
 
 	xfs_unmount_flush_inodes(mp);
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 6aaacfc0487e90..71ed04ddd737de 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -127,6 +127,7 @@ typedef struct xfs_mount {
 	struct xfs_inode	*m_rbmip;	/* pointer to bitmap inode */
 	struct xfs_inode	*m_rsumip;	/* pointer to summary inode */
 	struct xfs_inode	*m_rootip;	/* pointer to root directory */
+	struct xfs_inode	*m_metadirip;	/* ptr to metadata directory */
 	struct xfs_quotainfo	*m_quotainfo;	/* disk quota information */
 	struct xfs_buftarg	*m_ddev_targp;	/* data device */
 	struct xfs_buftarg	*m_logdev_targp;/* log device */

[PATCH 08/28] xfs: enforce metadata inode flag

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add checks for the metadata inode flag so that we don't ever leak
metadata inodes out to userspace, and we don't ever try to read a
regular inode as metadata.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_inode_buf.c |   70 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_inode_buf.h |    3 ++
 fs/xfs/libxfs/xfs_metafile.h  |   11 ++++++
 fs/xfs/scrub/common.c         |   10 +++++-
 fs/xfs/scrub/inode.c          |   26 ++++++++++++++-
 fs/xfs/scrub/inode_repair.c   |   10 ++++++
 fs/xfs/xfs_icache.c           |   12 ++++++-
 fs/xfs/xfs_inode.c            |   11 ++++++
 8 files changed, 147 insertions(+), 6 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 78febaa0d6923b..424861fbf1bd49 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -19,6 +19,7 @@
 #include "xfs_ialloc.h"
 #include "xfs_dir2.h"
 #include "xfs_health.h"
+#include "xfs_metafile.h"
 
 #include <linux/iversion.h>
 
@@ -489,6 +490,69 @@ xfs_dinode_verify_nrext64(
 	return NULL;
 }
 
+/*
+ * Validate all the picky requirements we have for a file that claims to be
+ * filesystem metadata.
+ */
+xfs_failaddr_t
+xfs_dinode_verify_metadir(
+	struct xfs_mount	*mp,
+	struct xfs_dinode	*dip,
+	uint16_t		mode,
+	uint16_t		flags,
+	uint64_t		flags2)
+{
+	if (!xfs_has_metadir(mp))
+		return __this_address;
+
+	/* V5 filesystem only */
+	if (dip->di_version < 3)
+		return __this_address;
+
+	if (be16_to_cpu(dip->di_metatype) >= XFS_METAFILE_MAX)
+		return __this_address;
+
+	/* V3 inode fields that are always zero */
+	if ((flags2 & XFS_DIFLAG2_NREXT64) && dip->di_nrext64_pad)
+		return __this_address;
+	if (!(flags2 & XFS_DIFLAG2_NREXT64) && dip->di_flushiter)
+		return __this_address;
+
+	/* Metadata files can only be directories or regular files */
+	if (!S_ISDIR(mode) && !S_ISREG(mode))
+		return __this_address;
+
+	/* They must have zero access permissions */
+	if (mode & 0777)
+		return __this_address;
+
+	/* DMAPI event and state masks are zero */
+	if (dip->di_dmevmask || dip->di_dmstate)
+		return __this_address;
+
+	/*
+	 * User and group IDs must be zero.  The project ID is used for
+	 * grouping inodes.  Metadata inodes are never accounted to quotas.
+	 */
+	if (dip->di_uid || dip->di_gid)
+		return __this_address;
+
+	/* Mandatory inode flags must be set */
+	if (S_ISDIR(mode)) {
+		if ((flags & XFS_METADIR_DIFLAGS) != XFS_METADIR_DIFLAGS)
+			return __this_address;
+	} else {
+		if ((flags & XFS_METAFILE_DIFLAGS) != XFS_METAFILE_DIFLAGS)
+			return __this_address;
+	}
+
+	/* dax flags2 must not be set */
+	if (flags2 & XFS_DIFLAG2_DAX)
+		return __this_address;
+
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
@@ -673,6 +737,12 @@ xfs_dinode_verify(
 	    !xfs_has_bigtime(mp))
 		return __this_address;
 
+	if (flags2 & XFS_DIFLAG2_METADATA) {
+		fa = xfs_dinode_verify_metadir(mp, dip, mode, flags, flags2);
+		if (fa)
+			return fa;
+	}
+
 	return NULL;
 }
 
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 585ed5a110af4e..8d43d2641c7328 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -28,6 +28,9 @@ int	xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
 
 xfs_failaddr_t xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino,
 			   struct xfs_dinode *dip);
+xfs_failaddr_t xfs_dinode_verify_metadir(struct xfs_mount *mp,
+		struct xfs_dinode *dip, uint16_t mode, uint16_t flags,
+		uint64_t flags2);
 xfs_failaddr_t xfs_inode_validate_extsize(struct xfs_mount *mp,
 		uint32_t extsize, uint16_t mode, uint16_t flags);
 xfs_failaddr_t xfs_inode_validate_cowextsize(struct xfs_mount *mp,
diff --git a/fs/xfs/libxfs/xfs_metafile.h b/fs/xfs/libxfs/xfs_metafile.h
index 60fe1890611277..c66b0c51b461a8 100644
--- a/fs/xfs/libxfs/xfs_metafile.h
+++ b/fs/xfs/libxfs/xfs_metafile.h
@@ -6,6 +6,17 @@
 #ifndef __XFS_METAFILE_H__
 #define __XFS_METAFILE_H__
 
+/* All metadata files must have these flags set. */
+#define XFS_METAFILE_DIFLAGS	(XFS_DIFLAG_IMMUTABLE | \
+				 XFS_DIFLAG_SYNC | \
+				 XFS_DIFLAG_NOATIME | \
+				 XFS_DIFLAG_NODUMP | \
+				 XFS_DIFLAG_NODEFRAG)
+
+/* All metadata directories must have these flags set. */
+#define XFS_METADIR_DIFLAGS	(XFS_METAFILE_DIFLAGS | \
+				 XFS_DIFLAG_NOSYMLINKS)
+
 /* Code specific to kernel/userspace; must be provided externally. */
 
 int xfs_trans_metafile_iget(struct xfs_trans *tp, xfs_ino_t ino,
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 777959f8ec724b..001af49b298818 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -947,9 +947,15 @@ xchk_iget_for_scrubbing(
 	if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino)
 		return xchk_install_live_inode(sc, ip_in);
 
-	/* Reject internal metadata files and obviously bad inode numbers. */
-	if (xfs_is_sb_inum(mp, sc->sm->sm_ino))
+	/*
+	 * On pre-metadir filesystems, reject internal metadata files.  For
+	 * metadir filesystems, limited scrubbing of any file in the metadata
+	 * directory tree by handle is allowed, because that is the only way to
+	 * validate the lack of parent pointers in the sb-root metadata inodes.
+	 */
+	if (!xfs_has_metadir(mp) && xfs_is_sb_inum(mp, sc->sm->sm_ino))
 		return -ENOENT;
+	/* Reject obviously bad inode numbers. */
 	if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
 		return -ENOENT;
 
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index a7ac7a4125ff12..ac5c5641653392 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -60,6 +60,22 @@ xchk_install_handle_iscrub(
 	if (error)
 		return error;
 
+	/*
+	 * Don't allow scrubbing by handle of any non-directory inode records
+	 * in the metadata directory tree.  We don't know if any of the scans
+	 * launched by this scrubber will end up indirectly trying to lock this
+	 * file.
+	 *
+	 * Scrubbers of inode-rooted metadata files (e.g. quota files) will
+	 * attach all the resources needed to scrub the inode and call
+	 * xchk_inode directly.  Userspace cannot call this directly.
+	 */
+	if (xfs_is_metadir_inode(ip) && !S_ISDIR(VFS_I(ip)->i_mode)) {
+		xchk_irele(sc, ip);
+		sc->ip = NULL;
+		return -ENOENT;
+	}
+
 	return xchk_prepare_iscrub(sc);
 }
 
@@ -94,9 +110,15 @@ xchk_setup_inode(
 		return xchk_prepare_iscrub(sc);
 	}
 
-	/* Reject internal metadata files and obviously bad inode numbers. */
-	if (xfs_is_sb_inum(mp, sc->sm->sm_ino))
+	/*
+	 * On pre-metadir filesystems, reject internal metadata files.  For
+	 * metadir filesystems, limited scrubbing of any file in the metadata
+	 * directory tree by handle is allowed, because that is the only way to
+	 * validate the lack of parent pointers in the sb-root metadata inodes.
+	 */
+	if (!xfs_has_metadir(mp) && xfs_is_sb_inum(mp, sc->sm->sm_ino))
 		return -ENOENT;
+	/* Reject obviously bad inode numbers. */
 	if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
 		return -ENOENT;
 
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 1eec5c6eb11071..486cedbc40bb8e 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -568,6 +568,16 @@ xrep_dinode_flags(
 		dip->di_nrext64_pad = 0;
 	else if (dip->di_version >= 3)
 		dip->di_v3_pad = 0;
+
+	if (flags2 & XFS_DIFLAG2_METADATA) {
+		xfs_failaddr_t	fa;
+
+		fa = xfs_dinode_verify_metadir(sc->mp, dip, mode, flags,
+				flags2);
+		if (fa)
+			flags2 &= ~XFS_DIFLAG2_METADATA;
+	}
+
 	dip->di_flags = cpu_to_be16(flags);
 	dip->di_flags2 = cpu_to_be64(flags2);
 }
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index aa645e35781202..48543bf0f5ce83 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -834,7 +834,8 @@ xfs_iget(
 /*
  * Get a metadata inode.
  *
- * The metafile type must match the file mode exactly.
+ * The metafile type must match the file mode exactly, and for files in the
+ * metadata directory tree, it must match the inode's metatype exactly.
  */
 int
 xfs_trans_metafile_iget(
@@ -863,13 +864,20 @@ xfs_trans_metafile_iget(
 		mode = S_IFREG;
 	if (inode_wrong_type(VFS_I(ip), mode))
 		goto bad_rele;
+	if (xfs_has_metadir(mp)) {
+		if (!xfs_is_metadir_inode(ip))
+			goto bad_rele;
+		if (metafile_type != ip->i_metatype)
+			goto bad_rele;
+	}
 
 	*ipp = ip;
 	return 0;
 bad_rele:
 	xfs_irele(ip);
 whine:
-	xfs_err(mp, "metadata inode 0x%llx is corrupt", ino);
+	xfs_err(mp, "metadata inode 0x%llx type %u is corrupt", ino,
+			metafile_type);
 	return -EFSCORRUPTED;
 }
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 12c5ff151edf4c..ae94583ea3bbe7 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -555,8 +555,19 @@ xfs_lookup(
 	if (error)
 		goto out_free_name;
 
+	/*
+	 * Fail if a directory entry in the regular directory tree points to
+	 * a metadata file.
+	 */
+	if (XFS_IS_CORRUPT(dp->i_mount, xfs_is_metadir_inode(*ipp))) {
+		error = -EFSCORRUPTED;
+		goto out_irele;
+	}
+
 	return 0;
 
+out_irele:
+	xfs_irele(*ipp);
 out_free_name:
 	if (ci_name)
 		kfree(ci_name->name);

[PATCH 09/28] xfs: read and write metadata inode directory tree

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Plumb in the bits we need to load metadata inodes from a named entry in
a metadir directory, create (or hardlink) inodes into a metadir
directory, create metadir directories, and flag inodes as being metadata
files.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/Makefile              |    4 
 fs/xfs/libxfs/xfs_metadir.c  |  474 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_metadir.h  |   47 ++++
 fs/xfs/libxfs/xfs_metafile.c |   52 +++++
 fs/xfs/libxfs/xfs_metafile.h |    4 
 fs/xfs/xfs_icache.c          |    2 
 fs/xfs/xfs_trace.c           |    2 
 fs/xfs/xfs_trace.h           |  102 +++++++++
 8 files changed, 685 insertions(+), 2 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_metadir.c
 create mode 100644 fs/xfs/libxfs/xfs_metadir.h
 create mode 100644 fs/xfs/libxfs/xfs_metafile.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 94cb8ca9f9da77..ba418a40aeb528 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -16,6 +16,7 @@ xfs-y				+= xfs_trace.o
 xfs-y				+= $(addprefix libxfs/, \
 				   xfs_group.o \
 				   xfs_ag.o \
+				   xfs_ag_resv.o \
 				   xfs_alloc.o \
 				   xfs_alloc_btree.o \
 				   xfs_attr.o \
@@ -43,7 +44,8 @@ xfs-y				+= $(addprefix libxfs/, \
 				   xfs_inode_buf.o \
 				   xfs_inode_util.o \
 				   xfs_log_rlimit.o \
-				   xfs_ag_resv.o \
+				   xfs_metadir.o \
+				   xfs_metafile.o \
 				   xfs_parent.o \
 				   xfs_rmap.o \
 				   xfs_rmap_btree.o \
diff --git a/fs/xfs/libxfs/xfs_metadir.c b/fs/xfs/libxfs/xfs_metadir.c
new file mode 100644
index 00000000000000..0a61316b4f520f
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_metadir.c
@@ -0,0 +1,474 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_trans.h"
+#include "xfs_metafile.h"
+#include "xfs_metadir.h"
+#include "xfs_trace.h"
+#include "xfs_inode.h"
+#include "xfs_quota.h"
+#include "xfs_ialloc.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_ag.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_parent.h"
+
+/*
+ * Metadata Directory Tree
+ * =======================
+ *
+ * These functions provide an abstraction layer for looking up, creating, and
+ * deleting metadata inodes that live within a special metadata directory tree.
+ *
+ * This code does not manage the five existing metadata inodes: real time
+ * bitmap & summary; and the user, group, and quotas.  All other metadata
+ * inodes must use only the xfs_meta{dir,file}_* functions.
+ *
+ * Callers wishing to create or hardlink a metadata inode must create an
+ * xfs_metadir_update structure, call the appropriate xfs_metadir* function,
+ * and then call xfs_metadir_commit or xfs_metadir_cancel to commit or cancel
+ * the update.  Files in the metadata directory tree currently cannot be
+ * unlinked.
+ *
+ * When the metadir feature is enabled, all metadata inodes must have the
+ * "metadata" inode flag set to prevent them from being exposed to the outside
+ * world.
+ *
+ * Callers must take the ILOCK of any inode in the metadata directory tree to
+ * synchronize access to that inode.  It is never necessary to take the IOLOCK
+ * or the MMAPLOCK since metadata inodes must not be exposed to user space.
+ */
+
+static inline void
+xfs_metadir_set_xname(
+	struct xfs_name		*xname,
+	const char		*path,
+	unsigned char		ftype)
+{
+	xname->name = (const unsigned char *)path;
+	xname->len = strlen(path);
+	xname->type = ftype;
+}
+
+/*
+ * Given a parent directory @dp and a metadata inode path component @xname,
+ * Look up the inode number in the directory, returning it in @ino.
+ * @xname.type must match the directory entry's ftype.
+ *
+ * Caller must hold ILOCK_EXCL.
+ */
+static inline int
+xfs_metadir_lookup(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_name		*xname,
+	xfs_ino_t		*ino)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_da_args	args = {
+		.trans		= tp,
+		.dp		= dp,
+		.geo		= mp->m_dir_geo,
+		.name		= xname->name,
+		.namelen	= xname->len,
+		.hashval	= xfs_dir2_hashname(mp, xname),
+		.whichfork	= XFS_DATA_FORK,
+		.op_flags	= XFS_DA_OP_OKNOENT,
+		.owner		= dp->i_ino,
+	};
+	int			error;
+
+	if (!S_ISDIR(VFS_I(dp)->i_mode))
+		return -EFSCORRUPTED;
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+
+	error = xfs_dir_lookup_args(&args);
+	if (error)
+		return error;
+
+	if (!xfs_verify_ino(mp, args.inumber))
+		return -EFSCORRUPTED;
+	if (xname->type != XFS_DIR3_FT_UNKNOWN && xname->type != args.filetype)
+		return -EFSCORRUPTED;
+
+	trace_xfs_metadir_lookup(dp, xname, args.inumber);
+	*ino = args.inumber;
+	return 0;
+}
+
+/*
+ * Look up and read a metadata inode from the metadata directory.  If the path
+ * component doesn't exist, return -ENOENT.
+ */
+int
+xfs_metadir_load(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	const char		*path,
+	enum xfs_metafile_type	metafile_type,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_name		xname;
+	xfs_ino_t		ino;
+	int			error;
+
+	xfs_metadir_set_xname(&xname, path, XFS_DIR3_FT_UNKNOWN);
+
+	xfs_ilock(dp, XFS_ILOCK_EXCL);
+	error = xfs_metadir_lookup(tp, dp, &xname, &ino);
+	xfs_iunlock(dp, XFS_ILOCK_EXCL);
+	if (error)
+		return error;
+	return xfs_trans_metafile_iget(tp, ino, metafile_type, ipp);
+}
+
+/*
+ * Unlock and release resources after committing (or cancelling) a metadata
+ * directory tree operation.  The caller retains its reference to @upd->ip
+ * and must release it explicitly.
+ */
+static inline void
+xfs_metadir_teardown(
+	struct xfs_metadir_update	*upd,
+	int				error)
+{
+	trace_xfs_metadir_teardown(upd, error);
+
+	if (upd->ppargs) {
+		xfs_parent_finish(upd->dp->i_mount, upd->ppargs);
+		upd->ppargs = NULL;
+	}
+
+	if (upd->ip) {
+		if (upd->ip_locked)
+			xfs_iunlock(upd->ip, XFS_ILOCK_EXCL);
+		upd->ip_locked = false;
+	}
+
+	if (upd->dp_locked)
+		xfs_iunlock(upd->dp, XFS_ILOCK_EXCL);
+	upd->dp_locked = false;
+}
+
+/*
+ * Begin the process of creating a metadata file by allocating transactions
+ * and taking whatever resources we're going to need.
+ */
+int
+xfs_metadir_start_create(
+	struct xfs_metadir_update	*upd)
+{
+	struct xfs_mount		*mp = upd->dp->i_mount;
+	int				error;
+
+	ASSERT(upd->dp != NULL);
+	ASSERT(upd->ip == NULL);
+	ASSERT(xfs_has_metadir(mp));
+	ASSERT(upd->metafile_type != XFS_METAFILE_UNKNOWN);
+
+	error = xfs_parent_start(mp, &upd->ppargs);
+	if (error)
+		return error;
+
+	/*
+	 * If we ever need the ability to create rt metadata files on a
+	 * pre-metadir filesystem, we'll need to dqattach the parent here.
+	 * Currently we assume that mkfs will create the files and quotacheck
+	 * will account for them.
+	 */
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_create,
+			xfs_create_space_res(mp, MAXNAMELEN), 0, 0, &upd->tp);
+	if (error)
+		goto out_teardown;
+
+	/*
+	 * Lock the parent directory if there is one.  We can't ijoin it to
+	 * the transaction until after the child file has been created.
+	 */
+	xfs_ilock(upd->dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
+	upd->dp_locked = true;
+
+	trace_xfs_metadir_start_create(upd);
+	return 0;
+out_teardown:
+	xfs_metadir_teardown(upd, error);
+	return error;
+}
+
+/*
+ * Create a metadata inode with the given @mode, and insert it into the
+ * metadata directory tree at the given @upd->path.  The path up to the final
+ * component must already exist.  The final path component must not exist.
+ *
+ * The new metadata inode will be attached to the update structure @upd->ip,
+ * with the ILOCK held until the caller releases it.
+ *
+ * NOTE: This function may return a new inode to the caller even if it returns
+ * a negative error code.  If an inode is passed back, the caller must finish
+ * setting up the inode before releasing it.
+ */
+int
+xfs_metadir_create(
+	struct xfs_metadir_update	*upd,
+	umode_t				mode)
+{
+	struct xfs_icreate_args		args = {
+		.pip			= upd->dp,
+		.mode			= mode,
+	};
+	struct xfs_name			xname;
+	struct xfs_dir_update		du = {
+		.dp			= upd->dp,
+		.name			= &xname,
+		.ppargs			= upd->ppargs,
+	};
+	struct xfs_mount		*mp = upd->dp->i_mount;
+	xfs_ino_t			ino;
+	unsigned int			resblks;
+	int				error;
+
+	xfs_assert_ilocked(upd->dp, XFS_ILOCK_EXCL);
+
+	/* Check that the name does not already exist in the directory. */
+	xfs_metadir_set_xname(&xname, upd->path, XFS_DIR3_FT_UNKNOWN);
+	error = xfs_metadir_lookup(upd->tp, upd->dp, &xname, &ino);
+	switch (error) {
+	case -ENOENT:
+		break;
+	case 0:
+		error = -EEXIST;
+		fallthrough;
+	default:
+		return error;
+	}
+
+	/*
+	 * A newly created regular or special file just has one directory
+	 * entry pointing to them, but a directory also the "." entry
+	 * pointing to itself.
+	 */
+	error = xfs_dialloc(&upd->tp, &args, &ino);
+	if (error)
+		return error;
+	error = xfs_icreate(upd->tp, ino, &args, &upd->ip);
+	if (error)
+		return error;
+	du.ip = upd->ip;
+	xfs_metafile_set_iflag(upd->tp, upd->ip, upd->metafile_type);
+	upd->ip_locked = true;
+
+	/*
+	 * Join the directory inode to the transaction.  We do not do it
+	 * earlier because xfs_dialloc rolls the transaction.
+	 */
+	xfs_trans_ijoin(upd->tp, upd->dp, 0);
+
+	/* Create the entry. */
+	if (S_ISDIR(args.mode))
+		resblks = xfs_mkdir_space_res(mp, xname.len);
+	else
+		resblks = xfs_create_space_res(mp, xname.len);
+	xname.type = xfs_mode_to_ftype(args.mode);
+
+	trace_xfs_metadir_try_create(upd);
+
+	error = xfs_dir_create_child(upd->tp, resblks, &du);
+	if (error)
+		return error;
+
+	/* Metadir files are not accounted to quota. */
+
+	trace_xfs_metadir_create(upd);
+
+	return 0;
+}
+
+#ifndef __KERNEL__
+/*
+ * Begin the process of linking a metadata file by allocating transactions
+ * and locking whatever resources we're going to need.
+ */
+int
+xfs_metadir_start_link(
+	struct xfs_metadir_update	*upd)
+{
+	struct xfs_mount		*mp = upd->dp->i_mount;
+	unsigned int			resblks;
+	int				nospace_error = 0;
+	int				error;
+
+	ASSERT(upd->dp != NULL);
+	ASSERT(upd->ip != NULL);
+	ASSERT(xfs_has_metadir(mp));
+
+	error = xfs_parent_start(mp, &upd->ppargs);
+	if (error)
+		return error;
+
+	resblks = xfs_link_space_res(mp, MAXNAMELEN);
+	error = xfs_trans_alloc_dir(upd->dp, &M_RES(mp)->tr_link, upd->ip,
+			&resblks, &upd->tp, &nospace_error);
+	if (error)
+		goto out_teardown;
+	if (!resblks) {
+		/* We don't allow reservationless updates. */
+		xfs_trans_cancel(upd->tp);
+		upd->tp = NULL;
+		xfs_iunlock(upd->dp, XFS_ILOCK_EXCL);
+		xfs_iunlock(upd->ip, XFS_ILOCK_EXCL);
+		error = nospace_error;
+		goto out_teardown;
+	}
+
+	upd->dp_locked = true;
+	upd->ip_locked = true;
+
+	trace_xfs_metadir_start_link(upd);
+	return 0;
+out_teardown:
+	xfs_metadir_teardown(upd, error);
+	return error;
+}
+
+/*
+ * Link the metadata directory given by @path to the inode @upd->ip.
+ * The path (up to the final component) must already exist, but the final
+ * component must not already exist.
+ */
+int
+xfs_metadir_link(
+	struct xfs_metadir_update	*upd)
+{
+	struct xfs_name			xname;
+	struct xfs_dir_update		du = {
+		.dp			= upd->dp,
+		.name			= &xname,
+		.ip			= upd->ip,
+		.ppargs			= upd->ppargs,
+	};
+	struct xfs_mount		*mp = upd->dp->i_mount;
+	xfs_ino_t			ino;
+	unsigned int			resblks;
+	int				error;
+
+	xfs_assert_ilocked(upd->dp, XFS_ILOCK_EXCL);
+	xfs_assert_ilocked(upd->ip, XFS_ILOCK_EXCL);
+
+	/* Look up the name in the current directory. */
+	xfs_metadir_set_xname(&xname, upd->path,
+			xfs_mode_to_ftype(VFS_I(upd->ip)->i_mode));
+	error = xfs_metadir_lookup(upd->tp, upd->dp, &xname, &ino);
+	switch (error) {
+	case -ENOENT:
+		break;
+	case 0:
+		error = -EEXIST;
+		fallthrough;
+	default:
+		return error;
+	}
+
+	resblks = xfs_link_space_res(mp, xname.len);
+	error = xfs_dir_add_child(upd->tp, resblks, &du);
+	if (error)
+		return error;
+
+	trace_xfs_metadir_link(upd);
+
+	return 0;
+}
+#endif /* ! __KERNEL__ */
+
+/* Commit a metadir update and unlock/drop all resources. */
+int
+xfs_metadir_commit(
+	struct xfs_metadir_update	*upd)
+{
+	int				error;
+
+	trace_xfs_metadir_commit(upd);
+
+	error = xfs_trans_commit(upd->tp);
+	upd->tp = NULL;
+
+	xfs_metadir_teardown(upd, error);
+	return error;
+}
+
+/* Cancel a metadir update and unlock/drop all resources. */
+void
+xfs_metadir_cancel(
+	struct xfs_metadir_update	*upd,
+	int				error)
+{
+	trace_xfs_metadir_cancel(upd);
+
+	xfs_trans_cancel(upd->tp);
+	upd->tp = NULL;
+
+	xfs_metadir_teardown(upd, error);
+}
+
+/* Create a metadata for the last component of the path. */
+int
+xfs_metadir_mkdir(
+	struct xfs_inode		*dp,
+	const char			*path,
+	struct xfs_inode		**ipp)
+{
+	struct xfs_metadir_update	upd = {
+		.dp			= dp,
+		.path			= path,
+		.metafile_type		= XFS_METAFILE_DIR,
+	};
+	int				error;
+
+	if (xfs_is_shutdown(dp->i_mount))
+		return -EIO;
+
+	/* Allocate a transaction to create the last directory. */
+	error = xfs_metadir_start_create(&upd);
+	if (error)
+		return error;
+
+	/* Create the subdirectory and take our reference. */
+	error = xfs_metadir_create(&upd, S_IFDIR);
+	if (error)
+		goto out_cancel;
+
+	error = xfs_metadir_commit(&upd);
+	if (error)
+		goto out_irele;
+
+	xfs_finish_inode_setup(upd.ip);
+	*ipp = upd.ip;
+	return 0;
+
+out_cancel:
+	xfs_metadir_cancel(&upd, error);
+out_irele:
+	/* Have to finish setting up the inode to ensure it's deleted. */
+	if (upd.ip) {
+		xfs_finish_inode_setup(upd.ip);
+		xfs_irele(upd.ip);
+	}
+	return error;
+}
diff --git a/fs/xfs/libxfs/xfs_metadir.h b/fs/xfs/libxfs/xfs_metadir.h
new file mode 100644
index 00000000000000..bfecac7d3d1472
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_metadir.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_METADIR_H__
+#define __XFS_METADIR_H__
+
+/* Cleanup widget for metadata inode creation and deletion. */
+struct xfs_metadir_update {
+	/* Parent directory */
+	struct xfs_inode	*dp;
+
+	/* Path to metadata file */
+	const char		*path;
+
+	/* Parent pointer update context */
+	struct xfs_parent_args	*ppargs;
+
+	/* Child metadata file */
+	struct xfs_inode	*ip;
+
+	struct xfs_trans	*tp;
+
+	enum xfs_metafile_type	metafile_type;
+
+	unsigned int		dp_locked:1;
+	unsigned int		ip_locked:1;
+};
+
+int xfs_metadir_load(struct xfs_trans *tp, struct xfs_inode *dp,
+		const char *path, enum xfs_metafile_type metafile_type,
+		struct xfs_inode **ipp);
+
+int xfs_metadir_start_create(struct xfs_metadir_update *upd);
+int xfs_metadir_create(struct xfs_metadir_update *upd, umode_t mode);
+
+int xfs_metadir_start_link(struct xfs_metadir_update *upd);
+int xfs_metadir_link(struct xfs_metadir_update *upd);
+
+int xfs_metadir_commit(struct xfs_metadir_update *upd);
+void xfs_metadir_cancel(struct xfs_metadir_update *upd, int error);
+
+int xfs_metadir_mkdir(struct xfs_inode *dp, const char *path,
+		struct xfs_inode **ipp);
+
+#endif /* __XFS_METADIR_H__ */
diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c
new file mode 100644
index 00000000000000..adeb25d1a444ca
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_metafile.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_trans.h"
+#include "xfs_metafile.h"
+#include "xfs_trace.h"
+#include "xfs_inode.h"
+
+/* Set up an inode to be recognized as a metadata directory inode. */
+void
+xfs_metafile_set_iflag(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	enum xfs_metafile_type	metafile_type)
+{
+	VFS_I(ip)->i_mode &= ~0777;
+	VFS_I(ip)->i_uid = GLOBAL_ROOT_UID;
+	VFS_I(ip)->i_gid = GLOBAL_ROOT_GID;
+	if (S_ISDIR(VFS_I(ip)->i_mode))
+		ip->i_diflags |= XFS_METADIR_DIFLAGS;
+	else
+		ip->i_diflags |= XFS_METAFILE_DIFLAGS;
+	ip->i_diflags2 &= ~XFS_DIFLAG2_DAX;
+	ip->i_diflags2 |= XFS_DIFLAG2_METADATA;
+	ip->i_metatype = metafile_type;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/* Clear the metadata directory inode flag. */
+void
+xfs_metafile_clear_iflag(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	ASSERT(xfs_is_metadir_inode(ip));
+	ASSERT(VFS_I(ip)->i_nlink == 0);
+
+	ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
diff --git a/fs/xfs/libxfs/xfs_metafile.h b/fs/xfs/libxfs/xfs_metafile.h
index c66b0c51b461a8..acec400123db05 100644
--- a/fs/xfs/libxfs/xfs_metafile.h
+++ b/fs/xfs/libxfs/xfs_metafile.h
@@ -17,6 +17,10 @@
 #define XFS_METADIR_DIFLAGS	(XFS_METAFILE_DIFLAGS | \
 				 XFS_DIFLAG_NOSYMLINKS)
 
+void xfs_metafile_set_iflag(struct xfs_trans *tp, struct xfs_inode *ip,
+		enum xfs_metafile_type metafile_type);
+void xfs_metafile_clear_iflag(struct xfs_trans *tp, struct xfs_inode *ip);
+
 /* Code specific to kernel/userspace; must be provided externally. */
 
 int xfs_trans_metafile_iget(struct xfs_trans *tp, xfs_ino_t ino,
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 48543bf0f5ce83..5171ad93fc40e6 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -850,7 +850,7 @@ xfs_trans_metafile_iget(
 	int			error;
 
 	error = xfs_iget(mp, tp, ino, 0, 0, &ip);
-	if (error == -EFSCORRUPTED)
+	if (error == -EFSCORRUPTED || error == -EINVAL)
 		goto whine;
 	if (error)
 		return error;
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 17164b2d0472d4..1b9d75a54c5ea2 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -46,6 +46,8 @@
 #include "xfs_parent.h"
 #include "xfs_rmap.h"
 #include "xfs_refcount.h"
+#include "xfs_metafile.h"
+#include "xfs_metadir.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 8aa6af5c9c0174..e2db13ed08b59c 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -95,6 +95,7 @@ struct xfs_attrlist_cursor_kern;
 struct xfs_extent_free_item;
 struct xfs_rmap_intent;
 struct xfs_refcount_intent;
+struct xfs_metadir_update;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
@@ -5352,6 +5353,107 @@ DEFINE_EVENT(xfs_getparents_class, name, \
 DEFINE_XFS_GETPARENTS_EVENT(xfs_getparents_begin);
 DEFINE_XFS_GETPARENTS_EVENT(xfs_getparents_end);
 
+DECLARE_EVENT_CLASS(xfs_metadir_update_class,
+	TP_PROTO(const struct xfs_metadir_update *upd),
+	TP_ARGS(upd),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dp_ino)
+		__field(xfs_ino_t, ino)
+		__string(fname, upd->path)
+	),
+	TP_fast_assign(
+		__entry->dev = upd->dp->i_mount->m_super->s_dev;
+		__entry->dp_ino = upd->dp->i_ino;
+		__entry->ino = upd->ip ? upd->ip->i_ino : NULLFSINO;
+		__assign_str(fname);
+	),
+	TP_printk("dev %d:%d dp 0x%llx fname '%s' ino 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dp_ino,
+		  __get_str(fname),
+		  __entry->ino)
+)
+
+#define DEFINE_METADIR_UPDATE_EVENT(name) \
+DEFINE_EVENT(xfs_metadir_update_class, name, \
+	TP_PROTO(const struct xfs_metadir_update *upd), \
+	TP_ARGS(upd))
+DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_start_create);
+DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_start_link);
+DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_commit);
+DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_cancel);
+DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_try_create);
+DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_create);
+DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_link);
+
+DECLARE_EVENT_CLASS(xfs_metadir_update_error_class,
+	TP_PROTO(const struct xfs_metadir_update *upd, int error),
+	TP_ARGS(upd, error),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dp_ino)
+		__field(xfs_ino_t, ino)
+		__field(int, error)
+		__string(fname, upd->path)
+	),
+	TP_fast_assign(
+		__entry->dev = upd->dp->i_mount->m_super->s_dev;
+		__entry->dp_ino = upd->dp->i_ino;
+		__entry->ino = upd->ip ? upd->ip->i_ino : NULLFSINO;
+		__entry->error = error;
+		__assign_str(fname);
+	),
+	TP_printk("dev %d:%d dp 0x%llx fname '%s' ino 0x%llx error %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dp_ino,
+		  __get_str(fname),
+		  __entry->ino,
+		  __entry->error)
+)
+
+#define DEFINE_METADIR_UPDATE_ERROR_EVENT(name) \
+DEFINE_EVENT(xfs_metadir_update_error_class, name, \
+	TP_PROTO(const struct xfs_metadir_update *upd, int error), \
+	TP_ARGS(upd, error))
+DEFINE_METADIR_UPDATE_ERROR_EVENT(xfs_metadir_teardown);
+
+DECLARE_EVENT_CLASS(xfs_metadir_class,
+	TP_PROTO(struct xfs_inode *dp, struct xfs_name *name,
+		 xfs_ino_t ino),
+	TP_ARGS(dp, name, ino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dp_ino)
+		__field(xfs_ino_t, ino)
+		__field(int, ftype)
+		__field(int, namelen)
+		__dynamic_array(char, name, name->len)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(dp)->i_sb->s_dev;
+		__entry->dp_ino = dp->i_ino;
+		__entry->ino = ino,
+		__entry->ftype = name->type;
+		__entry->namelen = name->len;
+		memcpy(__get_str(name), name->name, name->len);
+	),
+	TP_printk("dev %d:%d dir 0x%llx type %s name '%.*s' ino 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dp_ino,
+		  __print_symbolic(__entry->ftype, XFS_DIR3_FTYPE_STR),
+		  __entry->namelen,
+		  __get_str(name),
+		  __entry->ino)
+)
+
+#define DEFINE_METADIR_EVENT(name) \
+DEFINE_EVENT(xfs_metadir_class, name, \
+	TP_PROTO(struct xfs_inode *dp, struct xfs_name *name, \
+		 xfs_ino_t ino), \
+	TP_ARGS(dp, name, ino))
+DEFINE_METADIR_EVENT(xfs_metadir_lookup);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH

[PATCH 10/28] xfs: disable the agi rotor for metadata inodes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Ideally, we'd put all the metadata inodes in one place if we could, so
that the metadata all stay reasonably close together instead of
spreading out over the disk.  Furthermore, if the log is internal we'd
probably prefer to keep the metadata near the log.  Therefore, disable
AGI rotoring for metadata inode allocations.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_ialloc.c |   58 ++++++++++++++++++++++++++++++--------------
 1 file changed, 40 insertions(+), 18 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index f0261c4d91061c..8b84e2cf711b19 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1841,6 +1841,40 @@ xfs_dialloc_try_ag(
 	return error;
 }
 
+/*
+ * Pick an AG for the new inode.
+ *
+ * Directories, symlinks, and regular files frequently allocate at least one
+ * block, so factor that potential expansion when we examine whether an AG has
+ * enough space for file creation.  Try to keep metadata files all in the same
+ * AG.
+ */
+static inline xfs_agnumber_t
+xfs_dialloc_pick_ag(
+	struct xfs_mount	*mp,
+	struct xfs_inode	*dp,
+	umode_t			mode)
+{
+	xfs_agnumber_t		start_agno;
+
+	if (!dp)
+		return 0;
+	if (xfs_is_metadir_inode(dp)) {
+		if (mp->m_sb.sb_logstart)
+			return XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart);
+		return 0;
+	}
+
+	if (S_ISDIR(mode))
+		return (atomic_inc_return(&mp->m_agirotor) - 1) % mp->m_maxagi;
+
+	start_agno = XFS_INO_TO_AGNO(mp, dp->i_ino);
+	if (start_agno >= mp->m_maxagi)
+		start_agno = 0;
+
+	return start_agno;
+}
+
 /*
  * Allocate an on-disk inode.
  *
@@ -1856,31 +1890,19 @@ xfs_dialloc(
 	xfs_ino_t		*new_ino)
 {
 	struct xfs_mount	*mp = (*tpp)->t_mountp;
+	struct xfs_perag	*pag;
+	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
+	xfs_ino_t		ino = NULLFSINO;
 	xfs_ino_t		parent = args->pip ? args->pip->i_ino : 0;
-	umode_t			mode = args->mode & S_IFMT;
 	xfs_agnumber_t		agno;
-	int			error = 0;
 	xfs_agnumber_t		start_agno;
-	struct xfs_perag	*pag;
-	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
+	umode_t			mode = args->mode & S_IFMT;
 	bool			ok_alloc = true;
 	bool			low_space = false;
 	int			flags;
-	xfs_ino_t		ino = NULLFSINO;
+	int			error = 0;
 
-	/*
-	 * Directories, symlinks, and regular files frequently allocate at least
-	 * one block, so factor that potential expansion when we examine whether
-	 * an AG has enough space for file creation.
-	 */
-	if (S_ISDIR(mode))
-		start_agno = (atomic_inc_return(&mp->m_agirotor) - 1) %
-				mp->m_maxagi;
-	else {
-		start_agno = XFS_INO_TO_AGNO(mp, parent);
-		if (start_agno >= mp->m_maxagi)
-			start_agno = 0;
-	}
+	start_agno = xfs_dialloc_pick_ag(mp, args->pip, mode);
 
 	/*
 	 * If we have already hit the ceiling of inode blocks then clear

[PATCH 11/28] xfs: hide metadata inodes from everyone because they are special

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Metadata inodes are private files and therefore cannot be exposed to
userspace.  This means no bulkstat, no open-by-handle, no linking them
into the directory tree, and no feeding them to LSMs.  As such, we mark
them S_PRIVATE, which stops all that.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/tempfile.c |    8 ++++++++
 fs/xfs/xfs_iops.c       |   15 ++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
index 177f922acfaf1b..3c5a1d77fefae9 100644
--- a/fs/xfs/scrub/tempfile.c
+++ b/fs/xfs/scrub/tempfile.c
@@ -844,6 +844,14 @@ xrep_is_tempfile(
 	const struct xfs_inode	*ip)
 {
 	const struct inode	*inode = &ip->i_vnode;
+	struct xfs_mount	*mp = ip->i_mount;
+
+	/*
+	 * Files in the metadata directory tree also have S_PRIVATE set and
+	 * IOP_XATTR unset, so we must distinguish them separately.
+	 */
+	if (xfs_has_metadir(mp) && (ip->i_diflags2 & XFS_DIFLAG2_METADATA))
+		return false;
 
 	if (IS_PRIVATE(inode) && !(inode->i_opflags & IOP_XATTR))
 		return true;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ee79cf161312ca..66a726a5fbbba2 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -42,7 +42,9 @@
  * held. For regular files, the lock order is the other way around - the
  * mmap_lock is taken during the page fault, and then we lock the ilock to do
  * block mapping. Hence we need a different class for the directory ilock so
- * that lockdep can tell them apart.
+ * that lockdep can tell them apart.  Directories in the metadata directory
+ * tree get a separate class so that lockdep reports will warn us if someone
+ * ever tries to lock regular directories after locking metadata directories.
  */
 static struct lock_class_key xfs_nondir_ilock_class;
 static struct lock_class_key xfs_dir_ilock_class;
@@ -1289,6 +1291,7 @@ xfs_setup_inode(
 {
 	struct inode		*inode = &ip->i_vnode;
 	gfp_t			gfp_mask;
+	bool			is_meta = xfs_is_internal_inode(ip);
 
 	inode->i_ino = ip->i_ino;
 	inode->i_state |= I_NEW;
@@ -1300,6 +1303,16 @@ xfs_setup_inode(
 	i_size_write(inode, ip->i_disk_size);
 	xfs_diflags_to_iflags(ip, true);
 
+	/*
+	 * Mark our metadata files as private so that LSMs and the ACL code
+	 * don't try to add their own metadata or reason about these files,
+	 * and users cannot ever obtain file handles to them.
+	 */
+	if (is_meta) {
+		inode->i_flags |= S_PRIVATE;
+		inode->i_opflags &= ~IOP_XATTR;
+	}
+
 	if (S_ISDIR(inode->i_mode)) {
 		/*
 		 * We set the i_rwsem class here to avoid potential races with

[PATCH 12/28] xfs: advertise metadata directory feature

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Advertise the existence of the metadata directory feature; this will be
used by scrub to decide if it needs to scan the metadir too.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_fs.h |    1 +
 fs/xfs/libxfs/xfs_sb.c |    2 ++
 2 files changed, 3 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 860284064c5aa9..a42c1a33691c0f 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -242,6 +242,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_NREXT64	(1 << 23) /* large extent counters */
 #define XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE (1 << 24) /* exchange range */
 #define XFS_FSOP_GEOM_FLAGS_PARENT	(1 << 25) /* linux parent pointers */
+#define XFS_FSOP_GEOM_FLAGS_METADIR	(1 << 26) /* metadata directories */
 
 /*
  * Minimum and maximum sizes need for growth checks.
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 19fa999b4032c8..4516824e3b9994 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1295,6 +1295,8 @@ xfs_fs_geometry(
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64;
 	if (xfs_has_exchange_range(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE;
+	if (xfs_has_metadir(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR;
 	geo->rtsectsize = sbp->sb_blocksize;
 	geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
 

[PATCH 13/28] xfs: allow bulkstat to return metadata directories

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Allow the V5 bulkstat ioctl to return information about metadata
directory files so that xfs_scrub can find and scrub them, since they
are otherwise ordinary directories.

(Metadata files of course require per-file scrub code and hence do not
need exposure.)

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_fs.h |   10 +++++++++-
 fs/xfs/xfs_ioctl.c     |    7 +++++++
 fs/xfs/xfs_itable.c    |   33 +++++++++++++++++++++++++++++----
 fs/xfs/xfs_itable.h    |    3 +++
 4 files changed, 48 insertions(+), 5 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index a42c1a33691c0f..499bea4ea8067f 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -490,9 +490,17 @@ struct xfs_bulk_ireq {
  */
 #define XFS_BULK_IREQ_NREXT64	(1U << 2)
 
+/*
+ * Allow bulkstat to return information about metadata directories.  This
+ * enables xfs_scrub to find them for scanning, as they are otherwise ordinary
+ * directories.
+ */
+#define XFS_BULK_IREQ_METADIR	(1U << 3)
+
 #define XFS_BULK_IREQ_FLAGS_ALL	(XFS_BULK_IREQ_AGNO |	 \
 				 XFS_BULK_IREQ_SPECIAL | \
-				 XFS_BULK_IREQ_NREXT64)
+				 XFS_BULK_IREQ_NREXT64 | \
+				 XFS_BULK_IREQ_METADIR)
 
 /* Operate on the root directory inode. */
 #define XFS_BULK_IREQ_SPECIAL_ROOT	(1)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 2567fd2a0994b9..f36fd8db388cca 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -233,6 +233,10 @@ xfs_bulk_ireq_setup(
 	if (hdr->flags & XFS_BULK_IREQ_NREXT64)
 		breq->flags |= XFS_IBULK_NREXT64;
 
+	/* Caller wants to see metadata directories in bulkstat output. */
+	if (hdr->flags & XFS_BULK_IREQ_METADIR)
+		breq->flags |= XFS_IBULK_METADIR;
+
 	return 0;
 }
 
@@ -323,6 +327,9 @@ xfs_ioc_inumbers(
 	if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr)))
 		return -EFAULT;
 
+	if (hdr.flags & XFS_BULK_IREQ_METADIR)
+		return -EINVAL;
+
 	error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->inumbers);
 	if (error == -ECANCELED)
 		goto out_teardown;
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 37c2b50d877e42..1fa1c0564b0c5a 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -36,6 +36,14 @@ struct xfs_bstat_chunk {
 	struct xfs_bulkstat	*buf;
 };
 
+static inline bool
+want_metadir_file(
+	struct xfs_inode	*ip,
+	struct xfs_ibulk	*breq)
+{
+	return xfs_is_metadir_inode(ip) && (breq->flags & XFS_IBULK_METADIR);
+}
+
 /*
  * Fill out the bulkstat info for a single inode and report it somewhere.
  *
@@ -69,9 +77,6 @@ xfs_bulkstat_one_int(
 	vfsuid_t		vfsuid;
 	vfsgid_t		vfsgid;
 
-	if (xfs_is_sb_inum(mp, ino))
-		goto out_advance;
-
 	error = xfs_iget(mp, tp, ino,
 			 (XFS_IGET_DONTCACHE | XFS_IGET_UNTRUSTED),
 			 XFS_ILOCK_SHARED, &ip);
@@ -97,8 +102,28 @@ xfs_bulkstat_one_int(
 	vfsuid = i_uid_into_vfsuid(idmap, inode);
 	vfsgid = i_gid_into_vfsgid(idmap, inode);
 
+	/*
+	 * If caller wants files from the metadata directories, push out the
+	 * bare minimum information for enabling scrub.
+	 */
+	if (want_metadir_file(ip, bc->breq)) {
+		memset(buf, 0, sizeof(*buf));
+		buf->bs_ino = ino;
+		buf->bs_gen = inode->i_generation;
+		buf->bs_mode = inode->i_mode & S_IFMT;
+		xfs_bulkstat_health(ip, buf);
+		buf->bs_version = XFS_BULKSTAT_VERSION_V5;
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		xfs_irele(ip);
+
+		error = bc->formatter(bc->breq, buf);
+		if (!error || error == -ECANCELED)
+			goto out_advance;
+		goto out;
+	}
+
 	/* If this is a private inode, don't leak its details to userspace. */
-	if (IS_PRIVATE(inode)) {
+	if (IS_PRIVATE(inode) || xfs_is_sb_inum(mp, ino)) {
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		xfs_irele(ip);
 		error = -EINVAL;
diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h
index 1659f13f17a89d..f10e8f8f233510 100644
--- a/fs/xfs/xfs_itable.h
+++ b/fs/xfs/xfs_itable.h
@@ -22,6 +22,9 @@ struct xfs_ibulk {
 /* Fill out the bs_extents64 field if set. */
 #define XFS_IBULK_NREXT64	(1U << 1)
 
+/* Signal that we can return metadata directories. */
+#define XFS_IBULK_METADIR	(1U << 2)
+
 /*
  * Advance the user buffer pointer by one record of the given size.  If the
  * buffer is now full, return the appropriate error code.

[PATCH 14/28] xfs: don't count metadata directory files to quota

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Files in the metadata directory tree are internal to the filesystem.
Don't count the inodes or the blocks they use in the root dquot because
users do not need to know about their resource usage.  This will also
quiet down complaints about dquot usage not matching du output.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_dquot.c       |    1 +
 fs/xfs/xfs_qm.c          |   11 +++++++++++
 fs/xfs/xfs_quota.h       |    5 +++++
 fs/xfs/xfs_trans_dquot.c |    6 ++++++
 4 files changed, 23 insertions(+)


diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index c1b211c260a9d5..3bf47458c517af 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -983,6 +983,7 @@ xfs_qm_dqget_inode(
 
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
 	ASSERT(xfs_inode_dquot(ip, type) == NULL);
+	ASSERT(!xfs_is_metadir_inode(ip));
 
 	id = xfs_qm_id_for_quotatype(ip, type);
 
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index d0674d84af3ec5..ec983cca9adaed 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -304,6 +304,8 @@ xfs_qm_need_dqattach(
 		return false;
 	if (xfs_is_quota_inode(&mp->m_sb, ip->i_ino))
 		return false;
+	if (xfs_is_metadir_inode(ip))
+		return false;
 	return true;
 }
 
@@ -326,6 +328,7 @@ xfs_qm_dqattach_locked(
 		return 0;
 
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+	ASSERT(!xfs_is_metadir_inode(ip));
 
 	if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) {
 		error = xfs_qm_dqattach_one(ip, XFS_DQTYPE_USER,
@@ -1204,6 +1207,10 @@ xfs_qm_dqusage_adjust(
 		}
 	}
 
+	/* Metadata directory files are not accounted to user-visible quotas. */
+	if (xfs_is_metadir_inode(ip))
+		goto error0;
+
 	ASSERT(ip->i_delayed_blks == 0);
 
 	if (XFS_IS_REALTIME_INODE(ip)) {
@@ -1754,6 +1761,8 @@ xfs_qm_vop_dqalloc(
 	if (!XFS_IS_QUOTA_ON(mp))
 		return 0;
 
+	ASSERT(!xfs_is_metadir_inode(ip));
+
 	lockflags = XFS_ILOCK_EXCL;
 	xfs_ilock(ip, lockflags);
 
@@ -1883,6 +1892,7 @@ xfs_qm_vop_chown(
 
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
 	ASSERT(XFS_IS_QUOTA_ON(ip->i_mount));
+	ASSERT(!xfs_is_metadir_inode(ip));
 
 	/* old dquot */
 	prevdq = *IO_olddq;
@@ -1970,6 +1980,7 @@ xfs_qm_vop_create_dqattach(
 		return;
 
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+	ASSERT(!xfs_is_metadir_inode(ip));
 
 	if (udqp && XFS_IS_UQUOTA_ON(mp)) {
 		ASSERT(ip->i_udquot == NULL);
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index 23d71a55bbc006..645761997bf2d9 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -29,6 +29,11 @@ struct xfs_buf;
 	 (XFS_IS_GQUOTA_ON(mp) && (ip)->i_gdquot == NULL) || \
 	 (XFS_IS_PQUOTA_ON(mp) && (ip)->i_pdquot == NULL))
 
+#define XFS_IS_DQDETACHED(ip) \
+	((ip)->i_udquot == NULL && \
+	 (ip)->i_gdquot == NULL && \
+	 (ip)->i_pdquot == NULL)
+
 #define XFS_QM_NEED_QUOTACHECK(mp) \
 	((XFS_IS_UQUOTA_ON(mp) && \
 		(mp->m_sb.sb_qflags & XFS_UQUOTA_CHKD) == 0) || \
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index b368e13424c4f4..ca7df018290e0e 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -156,6 +156,8 @@ xfs_trans_mod_ino_dquot(
 	unsigned int			field,
 	int64_t				delta)
 {
+	ASSERT(!xfs_is_metadir_inode(ip) || XFS_IS_DQDETACHED(ip));
+
 	xfs_trans_mod_dquot(tp, dqp, field, delta);
 
 	if (xfs_hooks_switched_on(&xfs_dqtrx_hooks_switch)) {
@@ -247,6 +249,8 @@ xfs_trans_mod_dquot_byino(
 	    xfs_is_quota_inode(&mp->m_sb, ip->i_ino))
 		return;
 
+	ASSERT(!xfs_is_metadir_inode(ip) || XFS_IS_DQDETACHED(ip));
+
 	if (XFS_IS_UQUOTA_ON(mp) && ip->i_udquot)
 		xfs_trans_mod_ino_dquot(tp, ip, ip->i_udquot, field, delta);
 	if (XFS_IS_GQUOTA_ON(mp) && ip->i_gdquot)
@@ -962,6 +966,8 @@ xfs_trans_reserve_quota_nblks(
 
 	if (!XFS_IS_QUOTA_ON(mp))
 		return 0;
+	if (xfs_is_metadir_inode(ip))
+		return 0;
 
 	ASSERT(!xfs_is_quota_inode(&mp->m_sb, ip->i_ino));
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);

[PATCH 15/28] xfs: mark quota inodes as metadata files

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When we're creating quota files at mount time, make sure to mark them as
metadir inodes if appropriate.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_qm.c |    2 ++
 1 file changed, 2 insertions(+)


diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index ec983cca9adaed..b94d6f192e7258 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -824,6 +824,8 @@ xfs_qm_qino_alloc(
 			xfs_trans_cancel(tp);
 			return error;
 		}
+		if (xfs_has_metadir(mp))
+			xfs_metafile_set_iflag(tp, *ipp, metafile_type);
 	}
 
 	/*

[PATCH 16/28] xfs: adjust xfs_bmap_add_attrfork for metadir

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Online repair might use the xfs_bmap_add_attrfork to repair a file in
the metadata directory tree if (say) the metadata file lacks the correct
parent pointers.  In that case, it is not correct to check that the file
is dqattached -- metadata files must be not have /any/ dquot attached at
all.  Adjust the assertions appropriately.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_attr.c |    5 ++++-
 fs/xfs/libxfs/xfs_bmap.c |    5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index c63da14eee0432..17875ad865f5d6 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -1004,7 +1004,10 @@ xfs_attr_add_fork(
 	unsigned int		blks;		/* space reservation */
 	int			error;		/* error return value */
 
-	ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
+	if (xfs_is_metadir_inode(ip))
+		ASSERT(XFS_IS_DQDETACHED(ip));
+	else
+		ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
 
 	blks = XFS_ADDAFORK_SPACE_RES(mp);
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 5eda036cf9bfa5..7805a36e98c491 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1042,7 +1042,10 @@ xfs_bmap_add_attrfork(
 	int			error;		/* error return value */
 
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
-	ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
+	if (xfs_is_metadir_inode(ip))
+		ASSERT(XFS_IS_DQDETACHED(ip));
+	else
+		ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
 	ASSERT(!xfs_inode_has_attr_fork(ip));
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

[PATCH 17/28] xfs: record health problems with the metadata directory

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Make a report to the health monitoring subsystem any time we encounter
something in the metadata directory tree that looks like corruption.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_fs.h      |    1 +
 fs/xfs/libxfs/xfs_health.h  |    4 +++-
 fs/xfs/libxfs/xfs_metadir.c |   13 ++++++++++---
 fs/xfs/xfs_health.c         |    1 +
 fs/xfs/xfs_icache.c         |    1 +
 fs/xfs/xfs_inode.c          |    1 +
 6 files changed, 17 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 499bea4ea8067f..b05e6fb1470351 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -198,6 +198,7 @@ struct xfs_fsop_geom {
 #define XFS_FSOP_GEOM_SICK_RT_SUMMARY	(1 << 5)  /* realtime summary */
 #define XFS_FSOP_GEOM_SICK_QUOTACHECK	(1 << 6)  /* quota counts */
 #define XFS_FSOP_GEOM_SICK_NLINKS	(1 << 7)  /* inode link counts */
+#define XFS_FSOP_GEOM_SICK_METADIR	(1 << 8)  /* metadata directory */
 
 /* Output for XFS_FS_COUNTS */
 typedef struct xfs_fsop_counts {
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 13301420a2f670..f90e8dfc050000 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -62,6 +62,7 @@ struct xfs_da_args;
 #define XFS_SICK_FS_PQUOTA	(1 << 3)  /* project quota */
 #define XFS_SICK_FS_QUOTACHECK	(1 << 4)  /* quota counts */
 #define XFS_SICK_FS_NLINKS	(1 << 5)  /* inode link counts */
+#define XFS_SICK_FS_METADIR	(1 << 6)  /* metadata directory tree */
 
 /* Observable health issues for realtime volume metadata. */
 #define XFS_SICK_RT_BITMAP	(1 << 0)  /* realtime bitmap */
@@ -105,7 +106,8 @@ struct xfs_da_args;
 				 XFS_SICK_FS_GQUOTA | \
 				 XFS_SICK_FS_PQUOTA | \
 				 XFS_SICK_FS_QUOTACHECK | \
-				 XFS_SICK_FS_NLINKS)
+				 XFS_SICK_FS_NLINKS | \
+				 XFS_SICK_FS_METADIR)
 
 #define XFS_SICK_RT_PRIMARY	(XFS_SICK_RT_BITMAP | \
 				 XFS_SICK_RT_SUMMARY)
diff --git a/fs/xfs/libxfs/xfs_metadir.c b/fs/xfs/libxfs/xfs_metadir.c
index 0a61316b4f520f..bae7377c0f228c 100644
--- a/fs/xfs/libxfs/xfs_metadir.c
+++ b/fs/xfs/libxfs/xfs_metadir.c
@@ -28,6 +28,7 @@
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_parent.h"
+#include "xfs_health.h"
 
 /*
  * Metadata Directory Tree
@@ -94,8 +95,10 @@ xfs_metadir_lookup(
 	};
 	int			error;
 
-	if (!S_ISDIR(VFS_I(dp)->i_mode))
+	if (!S_ISDIR(VFS_I(dp)->i_mode)) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
 		return -EFSCORRUPTED;
+	}
 	if (xfs_is_shutdown(mp))
 		return -EIO;
 
@@ -103,10 +106,14 @@ xfs_metadir_lookup(
 	if (error)
 		return error;
 
-	if (!xfs_verify_ino(mp, args.inumber))
+	if (!xfs_verify_ino(mp, args.inumber)) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
 		return -EFSCORRUPTED;
-	if (xname->type != XFS_DIR3_FT_UNKNOWN && xname->type != args.filetype)
+	}
+	if (xname->type != XFS_DIR3_FT_UNKNOWN && xname->type != args.filetype) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
 		return -EFSCORRUPTED;
+	}
 
 	trace_xfs_metadir_lookup(dp, xname, args.inumber);
 	*ino = args.inumber;
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index f45f125a669de7..238258701450f4 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -380,6 +380,7 @@ static const struct ioctl_sick_map fs_map[] = {
 	{ XFS_SICK_FS_PQUOTA,	XFS_FSOP_GEOM_SICK_PQUOTA },
 	{ XFS_SICK_FS_QUOTACHECK, XFS_FSOP_GEOM_SICK_QUOTACHECK },
 	{ XFS_SICK_FS_NLINKS,	XFS_FSOP_GEOM_SICK_NLINKS },
+	{ XFS_SICK_FS_METADIR,	XFS_FSOP_GEOM_SICK_METADIR },
 	{ 0, 0 },
 };
 
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 5171ad93fc40e6..7b6c026d01a1fc 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -878,6 +878,7 @@ xfs_trans_metafile_iget(
 whine:
 	xfs_err(mp, "metadata inode 0x%llx type %u is corrupt", ino,
 			metafile_type);
+	xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
 	return -EFSCORRUPTED;
 }
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ae94583ea3bbe7..103cf8b2af24d0 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -560,6 +560,7 @@ xfs_lookup(
 	 * a metadata file.
 	 */
 	if (XFS_IS_CORRUPT(dp->i_mount, xfs_is_metadir_inode(*ipp))) {
+		xfs_fs_mark_sick(dp->i_mount, XFS_SICK_FS_METADIR);
 		error = -EFSCORRUPTED;
 		goto out_irele;
 	}

[PATCH 18/28] xfs: refactor directory tree root predicates

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Metadata directory trees make reasoning about the parent of a file more
difficult.  Traditionally, user files are children of sb_rootino, and
metadata files are "children" of the superblock.  Now, we add a third
possibility -- some metadata files can be children of sb_metadirino, but
the classic ones (rt free space data and quotas) are left alone.

Let's add some helper functions (instead of open-coding the logic
everywhere) to make scrub logic easier to understand.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/common.c        |   29 +++++++++++++++++++++++++++++
 fs/xfs/scrub/common.h        |    4 ++++
 fs/xfs/scrub/dir.c           |    2 +-
 fs/xfs/scrub/dir_repair.c    |    2 +-
 fs/xfs/scrub/dirtree.c       |   15 ++++++++++++++-
 fs/xfs/scrub/dirtree.h       |   12 +-----------
 fs/xfs/scrub/findparent.c    |   15 +++++++++------
 fs/xfs/scrub/inode_repair.c  |   11 ++---------
 fs/xfs/scrub/nlinks.c        |    4 ++--
 fs/xfs/scrub/nlinks_repair.c |    4 +---
 fs/xfs/scrub/orphanage.c     |    4 +++-
 fs/xfs/scrub/parent.c        |   17 ++++++++---------
 fs/xfs/scrub/parent_repair.c |    2 +-
 13 files changed, 76 insertions(+), 45 deletions(-)


diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 001af49b298818..3ca3173c5a5498 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -1452,3 +1452,32 @@ xchk_inode_is_allocated(
 	rcu_read_unlock();
 	return error;
 }
+
+/* Is this inode a root directory for either tree? */
+bool
+xchk_inode_is_dirtree_root(const struct xfs_inode *ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	return ip == mp->m_rootip ||
+		(xfs_has_metadir(mp) && ip == mp->m_metadirip);
+}
+
+/* Does the superblock point down to this inode? */
+bool
+xchk_inode_is_sb_rooted(const struct xfs_inode *ip)
+{
+	return xchk_inode_is_dirtree_root(ip) ||
+	       xfs_is_sb_inum(ip->i_mount, ip->i_ino);
+}
+
+/* What is the root directory inumber for this inode? */
+xfs_ino_t
+xchk_inode_rootdir_inum(const struct xfs_inode *ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (xfs_is_metadir_inode(ip))
+		return mp->m_metadirip->i_ino;
+	return mp->m_rootip->i_ino;
+}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index f3db628b14e1b9..b419adc6e7cf2a 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -242,4 +242,8 @@ void xchk_fsgates_enable(struct xfs_scrub *sc, unsigned int scrub_fshooks);
 int xchk_inode_is_allocated(struct xfs_scrub *sc, xfs_agino_t agino,
 		bool *inuse);
 
+bool xchk_inode_is_dirtree_root(const struct xfs_inode *ip);
+bool xchk_inode_is_sb_rooted(const struct xfs_inode *ip);
+xfs_ino_t xchk_inode_rootdir_inum(const struct xfs_inode *ip);
+
 #endif	/* __XFS_SCRUB_COMMON_H__ */
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index bf9199e8df633f..6b719c8885ef75 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -253,7 +253,7 @@ xchk_dir_actor(
 		 * If this is ".." in the root inode, check that the inum
 		 * matches this dir.
 		 */
-		if (dp->i_ino == mp->m_sb.sb_rootino && ino != dp->i_ino)
+		if (xchk_inode_is_dirtree_root(dp) && ino != dp->i_ino)
 			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 	}
 
diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index 64679fe0844650..0c2cd42b3110f2 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/fs/xfs/scrub/dir_repair.c
@@ -1270,7 +1270,7 @@ xrep_dir_scan_dirtree(
 	int			error;
 
 	/* Roots of directory trees are their own parents. */
-	if (sc->ip == sc->mp->m_rootip)
+	if (xchk_inode_is_dirtree_root(sc->ip))
 		xrep_findparent_scan_found(&rd->pscan, sc->ip->i_ino);
 
 	/*
diff --git a/fs/xfs/scrub/dirtree.c b/fs/xfs/scrub/dirtree.c
index bde58fb561ea18..e43840733de946 100644
--- a/fs/xfs/scrub/dirtree.c
+++ b/fs/xfs/scrub/dirtree.c
@@ -917,7 +917,7 @@ xchk_dirtree(
 	 * scan, because the hook doesn't detach until after sc->ip gets
 	 * released during teardown.
 	 */
-	dl->root_ino = sc->mp->m_rootip->i_ino;
+	dl->root_ino = xchk_inode_rootdir_inum(sc->ip);
 	dl->scan_ino = sc->ip->i_ino;
 
 	trace_xchk_dirtree_start(sc->ip, sc->sm, 0);
@@ -983,3 +983,16 @@ xchk_dirtree(
 	trace_xchk_dirtree_done(sc->ip, sc->sm, error);
 	return error;
 }
+
+/* Does the directory targetted by this scrub have no parents? */
+bool
+xchk_dirtree_parentless(const struct xchk_dirtree *dl)
+{
+	struct xfs_scrub	*sc = dl->sc;
+
+	if (xchk_inode_is_dirtree_root(sc->ip))
+		return true;
+	if (VFS_I(sc->ip)->i_nlink == 0)
+		return true;
+	return false;
+}
diff --git a/fs/xfs/scrub/dirtree.h b/fs/xfs/scrub/dirtree.h
index 1e1686365c61c6..9e5d95492717d6 100644
--- a/fs/xfs/scrub/dirtree.h
+++ b/fs/xfs/scrub/dirtree.h
@@ -156,17 +156,7 @@ struct xchk_dirtree {
 #define xchk_dirtree_for_each_path(dl, path) \
 	list_for_each_entry((path), &(dl)->path_list, list)
 
-static inline bool
-xchk_dirtree_parentless(const struct xchk_dirtree *dl)
-{
-	struct xfs_scrub	*sc = dl->sc;
-
-	if (sc->ip == sc->mp->m_rootip)
-		return true;
-	if (VFS_I(sc->ip)->i_nlink == 0)
-		return true;
-	return false;
-}
+bool xchk_dirtree_parentless(const struct xchk_dirtree *dl);
 
 int xchk_dirtree_find_paths_to_root(struct xchk_dirtree *dl);
 int xchk_dirpath_append(struct xchk_dirtree *dl, struct xfs_inode *ip,
diff --git a/fs/xfs/scrub/findparent.c b/fs/xfs/scrub/findparent.c
index 01766041ba2cd8..153d185190d8ad 100644
--- a/fs/xfs/scrub/findparent.c
+++ b/fs/xfs/scrub/findparent.c
@@ -362,15 +362,18 @@ xrep_findparent_confirm(
 	};
 	int			error;
 
-	/*
-	 * The root directory always points to itself.  Unlinked dirs can point
-	 * anywhere, so we point them at the root dir too.
-	 */
-	if (sc->ip == sc->mp->m_rootip || VFS_I(sc->ip)->i_nlink == 0) {
+	/* The root directory always points to itself. */
+	if (sc->ip == sc->mp->m_rootip) {
 		*parent_ino = sc->mp->m_sb.sb_rootino;
 		return 0;
 	}
 
+	/* Unlinked dirs can point anywhere; point them up to the root dir. */
+	if (VFS_I(sc->ip)->i_nlink == 0) {
+		*parent_ino = xchk_inode_rootdir_inum(sc->ip);
+		return 0;
+	}
+
 	/* Reject garbage parent inode numbers and self-referential parents. */
 	if (*parent_ino == NULLFSINO)
 	       return 0;
@@ -413,7 +416,7 @@ xrep_findparent_self_reference(
 		return sc->mp->m_sb.sb_rootino;
 
 	if (VFS_I(sc->ip)->i_nlink == 0)
-		return sc->mp->m_sb.sb_rootino;
+		return xchk_inode_rootdir_inum(sc->ip);
 
 	return NULLFSINO;
 }
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 486cedbc40bb8e..eaa1e1afe3a4d0 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -1767,15 +1767,8 @@ xrep_inode_pptr(
 	if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
 		return 0;
 
-	/* The root directory doesn't have a parent pointer. */
-	if (ip == mp->m_rootip)
-		return 0;
-
-	/*
-	 * Metadata inodes are rooted in the superblock and do not have any
-	 * parents.
-	 */
-	if (xfs_is_internal_inode(ip))
+	/* Children of the superblock do not have parent pointers. */
+	if (xchk_inode_is_sb_rooted(ip))
 		return 0;
 
 	/* Inode already has an attr fork; no further work possible here. */
diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c
index 80aee30886c456..4a47d0aabf73bd 100644
--- a/fs/xfs/scrub/nlinks.c
+++ b/fs/xfs/scrub/nlinks.c
@@ -279,7 +279,7 @@ xchk_nlinks_collect_dirent(
 	 * determine the backref count.
 	 */
 	if (dotdot) {
-		if (dp == sc->mp->m_rootip)
+		if (xchk_inode_is_dirtree_root(dp))
 			error = xchk_nlinks_update_incore(xnc, ino, 1, 0, 0);
 		else if (!xfs_has_parent(sc->mp))
 			error = xchk_nlinks_update_incore(xnc, ino, 0, 1, 0);
@@ -735,7 +735,7 @@ xchk_nlinks_compare_inode(
 		}
 	}
 
-	if (ip == sc->mp->m_rootip) {
+	if (xchk_inode_is_dirtree_root(ip)) {
 		/*
 		 * For the root of a directory tree, both the '.' and '..'
 		 * entries should point to the root directory.  The dotdot
diff --git a/fs/xfs/scrub/nlinks_repair.c b/fs/xfs/scrub/nlinks_repair.c
index b3e707f47b7b52..4ebdee09542807 100644
--- a/fs/xfs/scrub/nlinks_repair.c
+++ b/fs/xfs/scrub/nlinks_repair.c
@@ -60,11 +60,9 @@ xrep_nlinks_is_orphaned(
 	unsigned int		actual_nlink,
 	const struct xchk_nlink	*obs)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-
 	if (obs->parents != 0)
 		return false;
-	if (ip == mp->m_rootip || ip == sc->orphanage)
+	if (xchk_inode_is_dirtree_root(ip) || ip == sc->orphanage)
 		return false;
 	return actual_nlink != 0;
 }
diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c
index 5f0d4239260862..c287c755f2c5c1 100644
--- a/fs/xfs/scrub/orphanage.c
+++ b/fs/xfs/scrub/orphanage.c
@@ -295,7 +295,9 @@ xrep_orphanage_can_adopt(
 		return false;
 	if (sc->ip == sc->orphanage)
 		return false;
-	if (xfs_is_sb_inum(sc->mp, sc->ip->i_ino))
+	if (xchk_inode_is_sb_rooted(sc->ip))
+		return false;
+	if (xfs_is_internal_inode(sc->ip))
 		return false;
 	return true;
 }
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 20711a68a87482..582536076433a4 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -300,7 +300,7 @@ xchk_parent_pptr_and_dotdot(
 	}
 
 	/* Is this the root dir?  Then '..' must point to itself. */
-	if (sc->ip == sc->mp->m_rootip) {
+	if (xchk_inode_is_dirtree_root(sc->ip)) {
 		if (sc->ip->i_ino != pp->parent_ino)
 			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		return 0;
@@ -711,7 +711,7 @@ xchk_parent_count_pptrs(
 	}
 
 	if (S_ISDIR(VFS_I(sc->ip)->i_mode)) {
-		if (sc->ip == sc->mp->m_rootip)
+		if (xchk_inode_is_dirtree_root(sc->ip))
 			pp->pptrs_found++;
 
 		if (VFS_I(sc->ip)->i_nlink == 0 && pp->pptrs_found > 0)
@@ -885,10 +885,9 @@ bool
 xchk_pptr_looks_zapped(
 	struct xfs_inode	*ip)
 {
-	struct xfs_mount	*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
 
-	ASSERT(xfs_has_parent(mp));
+	ASSERT(xfs_has_parent(ip->i_mount));
 
 	/*
 	 * Temporary files that cannot be linked into the directory tree do not
@@ -902,15 +901,15 @@ xchk_pptr_looks_zapped(
 	 * of a parent pointer scan is always the empty set.  It's safe to scan
 	 * them even if the attr fork was zapped.
 	 */
-	if (ip == mp->m_rootip)
+	if (xchk_inode_is_dirtree_root(ip))
 		return false;
 
 	/*
-	 * Metadata inodes are all rooted in the superblock and do not have
-	 * any parents.  Hence the attr fork will not be initialized, but
-	 * there are no parent pointers that might have been zapped.
+	 * Metadata inodes that are rooted in the superblock do not have any
+	 * parents.  Hence the attr fork will not be initialized, but there are
+	 * no parent pointers that might have been zapped.
 	 */
-	if (xfs_is_internal_inode(ip))
+	if (xchk_inode_is_sb_rooted(ip))
 		return false;
 
 	/*
diff --git a/fs/xfs/scrub/parent_repair.c b/fs/xfs/scrub/parent_repair.c
index 7b42b7f65a0bd3..f4e4845b7ec099 100644
--- a/fs/xfs/scrub/parent_repair.c
+++ b/fs/xfs/scrub/parent_repair.c
@@ -1334,7 +1334,7 @@ xrep_parent_rebuild_pptrs(
 	 * so that we can decide if we're moving this file to the orphanage.
 	 * For this purpose, root directories are their own parents.
 	 */
-	if (sc->ip == sc->mp->m_rootip) {
+	if (xchk_inode_is_dirtree_root(sc->ip)) {
 		xrep_findparent_scan_found(&rp->pscan, sc->ip->i_ino);
 	} else {
 		error = xrep_parent_lookup_pptrs(sc, &parent_ino);

[PATCH 19/28] xfs: do not count metadata directory files when doing online quotacheck

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Previously, we stated that files in the metadata directory tree are not
counted in the dquot information.  Fix the online quotacheck code to
reflect this.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/quotacheck.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/scrub/quotacheck.c b/fs/xfs/scrub/quotacheck.c
index c77eb2de8df71f..dc4033b91e440b 100644
--- a/fs/xfs/scrub/quotacheck.c
+++ b/fs/xfs/scrub/quotacheck.c
@@ -398,10 +398,13 @@ xqcheck_collect_inode(
 	bool			isreg = S_ISREG(VFS_I(ip)->i_mode);
 	int			error = 0;
 
-	if (xfs_is_quota_inode(&tp->t_mountp->m_sb, ip->i_ino)) {
+	if (xfs_is_metadir_inode(ip) ||
+	    xfs_is_quota_inode(&tp->t_mountp->m_sb, ip->i_ino)) {
 		/*
 		 * Quota files are never counted towards quota, so we do not
-		 * need to take the lock.
+		 * need to take the lock.  Files do not switch between the
+		 * metadata and regular directory trees without a reallocation,
+		 * so we do not need to ILOCK them either.
 		 */
 		xchk_iscan_mark_visited(&xqc->iscan, ip);
 		return 0;

[PATCH 20/28] xfs: metadata files can have xattrs if metadir is enabled

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If parent pointers are enabled, then metadata files will store parent
pointers in xattrs, just like files in the user visible directory tree.
Therefore, scrub and repair need to handle attr forks for metadata files
on metadir filesystems.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/common.c |   21 +++++++++++++++------
 fs/xfs/scrub/repair.c |   14 +++++++++++---
 2 files changed, 26 insertions(+), 9 deletions(-)


diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 3ca3173c5a5498..6d955580f608a4 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -1245,12 +1245,6 @@ xchk_metadata_inode_forks(
 		return 0;
 	}
 
-	/* They also should never have extended attributes. */
-	if (xfs_inode_hasattr(sc->ip)) {
-		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
-		return 0;
-	}
-
 	/* Invoke the data fork scrubber. */
 	error = xchk_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTD);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
@@ -1267,6 +1261,21 @@ xchk_metadata_inode_forks(
 			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 	}
 
+	/*
+	 * Metadata files can only have extended attributes on metadir
+	 * filesystems, either for parent pointers or for actual xattr data.
+	 */
+	if (xfs_inode_hasattr(sc->ip)) {
+		if (!xfs_has_metadir(sc->mp)) {
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+			return 0;
+		}
+
+		error = xchk_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA);
+		if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+			return error;
+	}
+
 	return 0;
 }
 
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 646ac8ade88d0b..f80000d7755242 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -1082,7 +1082,12 @@ xrep_metadata_inode_forks(
 	if (error)
 		return error;
 
-	/* Make sure the attr fork looks ok before we delete it. */
+	/*
+	 * Metadata files can only have extended attributes on metadir
+	 * filesystems, either for parent pointers or for actual xattr data.
+	 * For a non-metadir filesystem, make sure the attr fork looks ok
+	 * before we delete it.
+	 */
 	if (xfs_inode_hasattr(sc->ip)) {
 		error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA);
 		if (error)
@@ -1098,8 +1103,11 @@ xrep_metadata_inode_forks(
 			return error;
 	}
 
-	/* Clear the attr forks since metadata shouldn't have that. */
-	if (xfs_inode_hasattr(sc->ip)) {
+	/*
+	 * Metadata files on non-metadir filesystems cannot have attr forks,
+	 * so clear them now.
+	 */
+	if (xfs_inode_hasattr(sc->ip) && !xfs_has_metadir(sc->mp)) {
 		if (!dirty) {
 			dirty = true;
 			xfs_trans_ijoin(sc->tp, sc->ip, 0);

[PATCH 21/28] xfs: adjust parent pointer scrubber for sb-rooted metadata files

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Starting with the metadata directory feature, we're allowed to call the
directory and parent pointer scrubbers for every metadata file,
including the ones that are children of the superblock.

For these children, checking the link count against the number of parent
pointers is a bit funny -- there's no such thing as a parent pointer for
a child of the superblock since there's no corresponding dirent.  For
purposes of validating nlink, we pretend that there is a parent pointer.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/parent.c        |    8 ++++++++
 fs/xfs/scrub/parent_repair.c |   35 +++++++++++++++++++++++++++++++----
 2 files changed, 39 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 582536076433a4..d8ea393f505970 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -720,6 +720,14 @@ xchk_parent_count_pptrs(
 			 pp->pptrs_found == 0)
 			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 	} else {
+		/*
+		 * Starting with metadir, we allow checking of parent pointers
+		 * of non-directory files that are children of the superblock.
+		 * Pretend that we found a parent pointer attr.
+		 */
+		if (xfs_has_metadir(sc->mp) && xchk_inode_is_sb_rooted(sc->ip))
+			pp->pptrs_found++;
+
 		if (VFS_I(sc->ip)->i_nlink != pp->pptrs_found)
 			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 	}
diff --git a/fs/xfs/scrub/parent_repair.c b/fs/xfs/scrub/parent_repair.c
index f4e4845b7ec099..31bfe10be22a21 100644
--- a/fs/xfs/scrub/parent_repair.c
+++ b/fs/xfs/scrub/parent_repair.c
@@ -1354,21 +1354,40 @@ STATIC int
 xrep_parent_rebuild_tree(
 	struct xrep_parent	*rp)
 {
+	struct xfs_scrub	*sc = rp->sc;
+	bool			try_adoption;
 	int			error;
 
-	if (xfs_has_parent(rp->sc->mp)) {
+	if (xfs_has_parent(sc->mp)) {
 		error = xrep_parent_rebuild_pptrs(rp);
 		if (error)
 			return error;
 	}
 
-	if (rp->pscan.parent_ino == NULLFSINO) {
-		if (xrep_orphanage_can_adopt(rp->sc))
+	/*
+	 * Any file with no parent could be adopted.  This check happens after
+	 * rebuilding the parent pointer structure because we might have cycled
+	 * the ILOCK during that process.
+	 */
+	try_adoption = rp->pscan.parent_ino == NULLFSINO;
+
+	/*
+	 * Starting with metadir, we allow checking of parent pointers
+	 * of non-directory files that are children of the superblock.
+	 * Lack of parent is ok here.
+	 */
+	if (try_adoption && xfs_has_metadir(sc->mp) &&
+	    xchk_inode_is_sb_rooted(sc->ip))
+		try_adoption = false;
+
+	if (try_adoption) {
+		if (xrep_orphanage_can_adopt(sc))
 			return xrep_parent_move_to_orphanage(rp);
 		return -EFSCORRUPTED;
+
 	}
 
-	if (S_ISDIR(VFS_I(rp->sc->ip)->i_mode))
+	if (S_ISDIR(VFS_I(sc->ip)->i_mode))
 		return xrep_parent_reset_dotdot(rp);
 
 	return 0;
@@ -1422,6 +1441,14 @@ xrep_parent_set_nondir_nlink(
 	if (error)
 		return error;
 
+	/*
+	 * Starting with metadir, we allow checking of parent pointers of
+	 * non-directory files that are children of the superblock.  Pretend
+	 * that we found a parent pointer attr.
+	 */
+	if (xfs_has_metadir(sc->mp) && xchk_inode_is_sb_rooted(sc->ip))
+		rp->parents++;
+
 	if (rp->parents > 0 && xfs_inode_on_unlinked_list(ip)) {
 		xfs_trans_ijoin(sc->tp, sc->ip, 0);
 		joined = true;

[PATCH 22/28] xfs: fix di_metatype field of inodes that won't load

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Make sure that the di_metatype field is at least set plausibly so that
later scrubbers could set the real type.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/inode.c        |    9 +++++++--
 fs/xfs/scrub/inode_repair.c |    6 +++++-
 2 files changed, 12 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index ac5c5641653392..25ee66e7649d40 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -443,8 +443,13 @@ xchk_dinode(
 		break;
 	case 2:
 	case 3:
-		if (!xfs_dinode_is_metadir(dip) && dip->di_metatype)
-			xchk_ino_set_corrupt(sc, ino);
+		if (xfs_dinode_is_metadir(dip)) {
+			if (be16_to_cpu(dip->di_metatype) >= XFS_METAFILE_MAX)
+				xchk_ino_set_corrupt(sc, ino);
+		} else {
+			if (dip->di_metatype != 0)
+				xchk_ino_set_corrupt(sc, ino);
+		}
 
 		if (dip->di_mode == 0 && sc->ip)
 			xchk_ino_set_corrupt(sc, ino);
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index eaa1e1afe3a4d0..5a58ddd27bd2f5 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -526,8 +526,12 @@ xrep_dinode_nlinks(
 		return;
 	}
 
-	if (!xfs_dinode_is_metadir(dip))
+	if (xfs_dinode_is_metadir(dip)) {
+		if (be16_to_cpu(dip->di_metatype) >= XFS_METAFILE_MAX)
+			dip->di_metatype = cpu_to_be16(XFS_METAFILE_UNKNOWN);
+	} else {
 		dip->di_metatype = 0;
+	}
 }
 
 /* Fix any conflicting flags that the verifiers complain about. */

[PATCH 23/28] xfs: scrub metadata directories

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Teach online scrub about the metadata directory tree.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/dir.c        |    8 ++++++++
 fs/xfs/scrub/dir_repair.c |    6 ++++++
 fs/xfs/scrub/dirtree.c    |   17 ++++++++++++++---
 fs/xfs/scrub/findparent.c |   13 +++++++++++++
 fs/xfs/scrub/parent.c     |   14 ++++++++++++++
 fs/xfs/scrub/trace.h      |    1 +
 6 files changed, 56 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 6b719c8885ef75..c877bde71e6280 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -100,6 +100,14 @@ xchk_dir_check_ftype(
 
 	if (xfs_mode_to_ftype(VFS_I(ip)->i_mode) != ftype)
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+
+	/*
+	 * Metadata and regular inodes cannot cross trees.  This property
+	 * cannot change without a full inode free and realloc cycle, so it's
+	 * safe to check this without holding locks.
+	 */
+	if (xfs_is_metadir_inode(ip) != xfs_is_metadir_inode(sc->ip))
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 }
 
 /*
diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index 0c2cd42b3110f2..2456cf1cb74411 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/fs/xfs/scrub/dir_repair.c
@@ -415,6 +415,12 @@ xrep_dir_salvage_entry(
 	if (error)
 		return 0;
 
+	/* Don't mix metadata and regular directory trees. */
+	if (xfs_is_metadir_inode(ip) != xfs_is_metadir_inode(rd->sc->ip)) {
+		xchk_irele(sc, ip);
+		return 0;
+	}
+
 	xname.type = xfs_mode_to_ftype(VFS_I(ip)->i_mode);
 	xchk_irele(sc, ip);
 
diff --git a/fs/xfs/scrub/dirtree.c b/fs/xfs/scrub/dirtree.c
index e43840733de946..3a9cdf8738b6db 100644
--- a/fs/xfs/scrub/dirtree.c
+++ b/fs/xfs/scrub/dirtree.c
@@ -362,7 +362,8 @@ xchk_dirpath_set_outcome(
 STATIC int
 xchk_dirpath_step_up(
 	struct xchk_dirtree	*dl,
-	struct xchk_dirpath	*path)
+	struct xchk_dirpath	*path,
+	bool			is_metadir)
 {
 	struct xfs_scrub	*sc = dl->sc;
 	struct xfs_inode	*dp;
@@ -435,6 +436,14 @@ xchk_dirpath_step_up(
 		goto out_scanlock;
 	}
 
+	/* Parent must be in the same directory tree. */
+	if (is_metadir != xfs_is_metadir_inode(dp)) {
+		trace_xchk_dirpath_crosses_tree(dl->sc, dp, path->path_nr,
+				path->nr_steps, &dl->xname, &dl->pptr_rec);
+		error = -EFSCORRUPTED;
+		goto out_scanlock;
+	}
+
 	/*
 	 * If the extended attributes look as though they has been zapped by
 	 * the inode record repair code, we cannot scan for parent pointers.
@@ -508,6 +517,7 @@ xchk_dirpath_walk_upwards(
 	struct xchk_dirpath	*path)
 {
 	struct xfs_scrub	*sc = dl->sc;
+	bool			is_metadir;
 	int			error;
 
 	ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
@@ -538,6 +548,7 @@ xchk_dirpath_walk_upwards(
 	 * ILOCK state is no longer tracked in the scrub context.  Hence we
 	 * must drop @sc->ip's ILOCK during the walk.
 	 */
+	is_metadir = xfs_is_metadir_inode(sc->ip);
 	mutex_unlock(&dl->lock);
 	xchk_iunlock(sc, XFS_ILOCK_EXCL);
 
@@ -547,7 +558,7 @@ xchk_dirpath_walk_upwards(
 	 * If we see any kind of error here (including corruptions), the parent
 	 * pointer of @sc->ip is corrupt.  Stop the whole scan.
 	 */
-	error = xchk_dirpath_step_up(dl, path);
+	error = xchk_dirpath_step_up(dl, path, is_metadir);
 	if (error) {
 		xchk_ilock(sc, XFS_ILOCK_EXCL);
 		mutex_lock(&dl->lock);
@@ -560,7 +571,7 @@ xchk_dirpath_walk_upwards(
 	 * *somewhere* in the path, but we don't need to stop scanning.
 	 */
 	while (!error && path->outcome == XCHK_DIRPATH_SCANNING)
-		error = xchk_dirpath_step_up(dl, path);
+		error = xchk_dirpath_step_up(dl, path, is_metadir);
 
 	/* Retake the locks we had, mark paths, etc. */
 	xchk_ilock(sc, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/scrub/findparent.c b/fs/xfs/scrub/findparent.c
index 153d185190d8ad..84487072b6dd6f 100644
--- a/fs/xfs/scrub/findparent.c
+++ b/fs/xfs/scrub/findparent.c
@@ -172,6 +172,10 @@ xrep_findparent_walk_directory(
 	 */
 	lock_mode = xfs_ilock_data_map_shared(dp);
 
+	/* Don't mix metadata and regular directory trees. */
+	if (xfs_is_metadir_inode(dp) != xfs_is_metadir_inode(sc->ip))
+		goto out_unlock;
+
 	/*
 	 * If this directory is known to be sick, we cannot scan it reliably
 	 * and must abort.
@@ -368,6 +372,12 @@ xrep_findparent_confirm(
 		return 0;
 	}
 
+	/* The metadata root directory always points to itself. */
+	if (sc->ip == sc->mp->m_metadirip) {
+		*parent_ino = sc->mp->m_sb.sb_metadirino;
+		return 0;
+	}
+
 	/* Unlinked dirs can point anywhere; point them up to the root dir. */
 	if (VFS_I(sc->ip)->i_nlink == 0) {
 		*parent_ino = xchk_inode_rootdir_inum(sc->ip);
@@ -415,6 +425,9 @@ xrep_findparent_self_reference(
 	if (sc->ip->i_ino == sc->mp->m_sb.sb_rootino)
 		return sc->mp->m_sb.sb_rootino;
 
+	if (sc->ip->i_ino == sc->mp->m_sb.sb_metadirino)
+		return sc->mp->m_sb.sb_metadirino;
+
 	if (VFS_I(sc->ip)->i_nlink == 0)
 		return xchk_inode_rootdir_inum(sc->ip);
 
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index d8ea393f505970..3b692c4acc1e6f 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -132,6 +132,14 @@ xchk_parent_validate(
 		return 0;
 	}
 
+	/* Is this the metadata root dir?  Then '..' must point to itself. */
+	if (sc->ip == mp->m_metadirip) {
+		if (sc->ip->i_ino != mp->m_sb.sb_metadirino ||
+		    sc->ip->i_ino != parent_ino)
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		return 0;
+	}
+
 	/* '..' must not point to ourselves. */
 	if (sc->ip->i_ino == parent_ino) {
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
@@ -185,6 +193,12 @@ xchk_parent_validate(
 		goto out_unlock;
 	}
 
+	/* Metadata and regular inodes cannot cross trees. */
+	if (xfs_is_metadir_inode(dp) != xfs_is_metadir_inode(sc->ip)) {
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		goto out_unlock;
+	}
+
 	/* Look for a directory entry in the parent pointing to the child. */
 	error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc);
 	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 58cc61f2ed5372..bc246d86a5c89f 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1753,6 +1753,7 @@ DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_badgen);
 DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_nondir_parent);
 DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_unlinked_parent);
 DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_found_next_step);
+DEFINE_XCHK_DIRPATH_EVENT(xchk_dirpath_crosses_tree);
 
 TRACE_DEFINE_ENUM(XCHK_DIRPATH_SCANNING);
 TRACE_DEFINE_ENUM(XCHK_DIRPATH_DELETE);

[PATCH 24/28] xfs: check the metadata directory inumber in superblocks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When metadata directories are enabled, make sure that the secondary
superblocks point to the metadata directory.  This isn't strictly
required because the secondaries are only used to recover damaged
filesystems, and the metadir root inumber is fixed.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/agheader.c |    5 +++++
 1 file changed, 5 insertions(+)


diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index f8e5b67128d25a..cad997f38a424c 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -144,6 +144,11 @@ xchk_superblock(
 	if (sb->sb_rootino != cpu_to_be64(mp->m_sb.sb_rootino))
 		xchk_block_set_preen(sc, bp);
 
+	if (xfs_has_metadir(sc->mp)) {
+		if (sb->sb_metadirino != cpu_to_be64(mp->m_sb.sb_metadirino))
+			xchk_block_set_preen(sc, bp);
+	}
+
 	if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino))
 		xchk_block_set_preen(sc, bp);
 

[PATCH 25/28] xfs: move repair temporary files to the metadata directory tree

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Due to resource acquisition rules, we have to create the ondisk
temporary files used to stage a filesystem repair before we can acquire
a reference to the inode that we actually want to repair.  Therefore,
we do not know at tempfile creation time whether the tempfile will
belong to the regular directory tree or the metadata directory tree.

This distinction becomes important when the swapext code tries to figure
out the quota accounting of the two files whose mappings are being
swapped.  The swapext code assumes that accounting updates are required
for a file if dqattach attaches dquots.  Metadir files are never
accounted in quota, which means that swapext must not update the quota
accounting when swapping in a repaired directory/xattr/rtbitmap structure.

Prior to the swapext call, therefore, both files must be marked as
METADIR for dqattach so that dqattach will ignore them.  Add support for
a repair tempfile to be switched to the metadir tree and switched back
before being released so that ifree will just free the file.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/common.c   |    5 ++
 fs/xfs/scrub/tempfile.c |   97 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/tempfile.h |    3 +
 3 files changed, 105 insertions(+)


diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 6d955580f608a4..c26a3314237a69 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -39,6 +39,7 @@
 #include "scrub/trace.h"
 #include "scrub/repair.h"
 #include "scrub/health.h"
+#include "scrub/tempfile.h"
 
 /* Common code for the metadata scrubbers. */
 
@@ -1090,6 +1091,10 @@ xchk_setup_inode_contents(
 	if (error)
 		return error;
 
+	error = xrep_tempfile_adjust_directory_tree(sc);
+	if (error)
+		return error;
+
 	/* Lock the inode so the VFS cannot touch this file. */
 	xchk_ilock(sc, XFS_IOLOCK_EXCL);
 
diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
index 3c5a1d77fefae9..4b7f7860e37ece 100644
--- a/fs/xfs/scrub/tempfile.c
+++ b/fs/xfs/scrub/tempfile.c
@@ -22,6 +22,7 @@
 #include "xfs_exchmaps.h"
 #include "xfs_defer.h"
 #include "xfs_symlink_remote.h"
+#include "xfs_metafile.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
@@ -182,6 +183,101 @@ xrep_tempfile_create(
 	return error;
 }
 
+/*
+ * Temporary files have to be created before we even know which inode we're
+ * going to scrub, so we assume that they will be part of the regular directory
+ * tree.  If it turns out that we're actually scrubbing a file from the
+ * metadata directory tree, we have to subtract the temp file from the root
+ * dquots and detach the dquots.
+ */
+int
+xrep_tempfile_adjust_directory_tree(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	if (!sc->tempip)
+		return 0;
+
+	ASSERT(sc->tp == NULL);
+	ASSERT(!xfs_is_metadir_inode(sc->tempip));
+
+	if (!sc->ip || !xfs_is_metadir_inode(sc->ip))
+		return 0;
+
+	xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL);
+	sc->temp_ilock_flags |= XFS_IOLOCK_EXCL;
+
+	error = xchk_trans_alloc(sc, 0);
+	if (error)
+		goto out_iolock;
+
+	xrep_tempfile_ilock(sc);
+	xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+
+	/* Metadir files are not accounted in quota, so drop icount */
+	xfs_trans_mod_dquot_byino(sc->tp, sc->tempip, XFS_TRANS_DQ_ICOUNT, -1L);
+	xfs_metafile_set_iflag(sc->tp, sc->tempip, XFS_METAFILE_UNKNOWN);
+
+	error = xrep_trans_commit(sc);
+	if (error)
+		goto out_ilock;
+
+	xfs_qm_dqdetach(sc->tempip);
+out_ilock:
+	xrep_tempfile_iunlock(sc);
+out_iolock:
+	xrep_tempfile_iounlock(sc);
+	return error;
+}
+
+/*
+ * Remove this temporary file from the metadata directory tree so that it can
+ * be inactivated the normal way.
+ */
+STATIC int
+xrep_tempfile_remove_metadir(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	if (!sc->tempip || !xfs_is_metadir_inode(sc->tempip))
+		return 0;
+
+	ASSERT(sc->tp == NULL);
+
+	xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL);
+	sc->temp_ilock_flags |= XFS_IOLOCK_EXCL;
+
+	error = xchk_trans_alloc(sc, 0);
+	if (error)
+		goto out_iolock;
+
+	xrep_tempfile_ilock(sc);
+	xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+
+	xfs_metafile_clear_iflag(sc->tp, sc->tempip);
+
+	/* Non-metadir files are accounted in quota, so bump bcount/icount */
+	error = xfs_qm_dqattach_locked(sc->tempip, false);
+	if (error)
+		goto out_cancel;
+
+	xfs_trans_mod_dquot_byino(sc->tp, sc->tempip, XFS_TRANS_DQ_ICOUNT, 1L);
+	xfs_trans_mod_dquot_byino(sc->tp, sc->tempip, XFS_TRANS_DQ_BCOUNT,
+			sc->tempip->i_nblocks);
+	error = xrep_trans_commit(sc);
+	goto out_ilock;
+
+out_cancel:
+	xchk_trans_cancel(sc);
+out_ilock:
+	xrep_tempfile_iunlock(sc);
+out_iolock:
+	xrep_tempfile_iounlock(sc);
+	return error;
+}
+
 /* Take IOLOCK_EXCL on the temporary file, maybe. */
 bool
 xrep_tempfile_iolock_nowait(
@@ -290,6 +386,7 @@ xrep_tempfile_rele(
 		sc->temp_ilock_flags = 0;
 	}
 
+	xrep_tempfile_remove_metadir(sc);
 	xchk_irele(sc, sc->tempip);
 	sc->tempip = NULL;
 }
diff --git a/fs/xfs/scrub/tempfile.h b/fs/xfs/scrub/tempfile.h
index e51399f595fe9a..71c1b54599c306 100644
--- a/fs/xfs/scrub/tempfile.h
+++ b/fs/xfs/scrub/tempfile.h
@@ -10,6 +10,8 @@
 int xrep_tempfile_create(struct xfs_scrub *sc, uint16_t mode);
 void xrep_tempfile_rele(struct xfs_scrub *sc);
 
+int xrep_tempfile_adjust_directory_tree(struct xfs_scrub *sc);
+
 bool xrep_tempfile_iolock_nowait(struct xfs_scrub *sc);
 int xrep_tempfile_iolock_polled(struct xfs_scrub *sc);
 void xrep_tempfile_iounlock(struct xfs_scrub *sc);
@@ -42,6 +44,7 @@ static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc)
 	xchk_ilock(sc, XFS_IOLOCK_EXCL);
 }
 # define xrep_is_tempfile(ip)		(false)
+# define xrep_tempfile_adjust_directory_tree(sc)	(0)
 # define xrep_tempfile_rele(sc)
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 

[PATCH 26/28] xfs: check metadata directory file path connectivity

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new scrubber type that checks that well known metadata
directory paths are connected to the metadata inode that the incore
structures think is in use.  For example, check that "/quota/user" in
the metadata directory tree actually points to
mp->m_quotainfo->qi_uquotaip->i_ino.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/Makefile            |    1 
 fs/xfs/libxfs/xfs_fs.h     |   13 +++
 fs/xfs/libxfs/xfs_health.h |    4 +
 fs/xfs/scrub/common.h      |    1 
 fs/xfs/scrub/health.c      |    1 
 fs/xfs/scrub/metapath.c    |  174 ++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/scrub.c       |    9 ++
 fs/xfs/scrub/scrub.h       |    2 +
 fs/xfs/scrub/stats.c       |    1 
 fs/xfs/scrub/trace.c       |    1 
 fs/xfs/scrub/trace.h       |   36 +++++++++
 fs/xfs/xfs_health.c        |    1 
 12 files changed, 241 insertions(+), 3 deletions(-)
 create mode 100644 fs/xfs/scrub/metapath.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index ba418a40aeb528..d80c2817eb4892 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -174,6 +174,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   inode.o \
 				   iscan.o \
 				   listxattr.o \
+				   metapath.o \
 				   nlinks.o \
 				   parent.o \
 				   readdir.o \
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index b05e6fb1470351..faa38a7d1eb019 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -199,6 +199,7 @@ struct xfs_fsop_geom {
 #define XFS_FSOP_GEOM_SICK_QUOTACHECK	(1 << 6)  /* quota counts */
 #define XFS_FSOP_GEOM_SICK_NLINKS	(1 << 7)  /* inode link counts */
 #define XFS_FSOP_GEOM_SICK_METADIR	(1 << 8)  /* metadata directory */
+#define XFS_FSOP_GEOM_SICK_METAPATH	(1 << 9)  /* metadir tree path */
 
 /* Output for XFS_FS_COUNTS */
 typedef struct xfs_fsop_counts {
@@ -732,9 +733,10 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_NLINKS	26	/* inode link counts */
 #define XFS_SCRUB_TYPE_HEALTHY	27	/* everything checked out ok */
 #define XFS_SCRUB_TYPE_DIRTREE	28	/* directory tree structure */
+#define XFS_SCRUB_TYPE_METAPATH	29	/* metadata directory tree paths */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	29
+#define XFS_SCRUB_TYPE_NR	30
 
 /*
  * This special type code only applies to the vectored scrub implementation.
@@ -812,6 +814,15 @@ struct xfs_scrub_vec_head {
 
 #define XFS_SCRUB_VEC_FLAGS_ALL		(0)
 
+/*
+ * i: sm_ino values for XFS_SCRUB_TYPE_METAPATH to select a metadata file for
+ * path checking.
+ */
+#define XFS_SCRUB_METAPATH_PROBE	(0)  /* do we have a metapath scrubber? */
+
+/* Number of metapath sm_ino values */
+#define XFS_SCRUB_METAPATH_NR		(1)
+
 /*
  * ioctl limits
  */
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index f90e8dfc050000..a23df94319e5fb 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -63,6 +63,7 @@ struct xfs_da_args;
 #define XFS_SICK_FS_QUOTACHECK	(1 << 4)  /* quota counts */
 #define XFS_SICK_FS_NLINKS	(1 << 5)  /* inode link counts */
 #define XFS_SICK_FS_METADIR	(1 << 6)  /* metadata directory tree */
+#define XFS_SICK_FS_METAPATH	(1 << 7)  /* metadata directory tree path */
 
 /* Observable health issues for realtime volume metadata. */
 #define XFS_SICK_RT_BITMAP	(1 << 0)  /* realtime bitmap */
@@ -107,7 +108,8 @@ struct xfs_da_args;
 				 XFS_SICK_FS_PQUOTA | \
 				 XFS_SICK_FS_QUOTACHECK | \
 				 XFS_SICK_FS_NLINKS | \
-				 XFS_SICK_FS_METADIR)
+				 XFS_SICK_FS_METADIR | \
+				 XFS_SICK_FS_METAPATH)
 
 #define XFS_SICK_RT_PRIMARY	(XFS_SICK_RT_BITMAP | \
 				 XFS_SICK_RT_SUMMARY)
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index b419adc6e7cf2a..b2a81e85ded9cf 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -73,6 +73,7 @@ int xchk_setup_xattr(struct xfs_scrub *sc);
 int xchk_setup_symlink(struct xfs_scrub *sc);
 int xchk_setup_parent(struct xfs_scrub *sc);
 int xchk_setup_dirtree(struct xfs_scrub *sc);
+int xchk_setup_metapath(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
 int xchk_setup_rtbitmap(struct xfs_scrub *sc);
 int xchk_setup_rtsummary(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 6ceef3749e3b99..b8b92ff3a573a1 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -109,6 +109,7 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_QUOTACHECK]	= { XHG_FS,  XFS_SICK_FS_QUOTACHECK },
 	[XFS_SCRUB_TYPE_NLINKS]		= { XHG_FS,  XFS_SICK_FS_NLINKS },
 	[XFS_SCRUB_TYPE_DIRTREE]	= { XHG_INO, XFS_SICK_INO_DIRTREE },
+	[XFS_SCRUB_TYPE_METAPATH]	= { XHG_FS,  XFS_SICK_FS_METAPATH },
 };
 
 /* Return the health status mask for this scrub type. */
diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c
new file mode 100644
index 00000000000000..b7bd86df9877cd
--- /dev/null
+++ b/fs/xfs/scrub/metapath.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2023-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_metafile.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_dir2.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/readdir.h"
+
+/*
+ * Metadata Directory Tree Paths
+ * =============================
+ *
+ * A filesystem with metadir enabled expects to find metadata structures
+ * attached to files that are accessible by walking a path down the metadata
+ * directory tree.  Given the metadir path and the incore inode storing the
+ * metadata, this scrubber ensures that the ondisk metadir path points to the
+ * ondisk inode represented by the incore inode.
+ */
+
+struct xchk_metapath {
+	struct xfs_scrub		*sc;
+
+	/* Name for lookup */
+	struct xfs_name			xname;
+
+	/* Path for this metadata file and the parent directory */
+	const char			*path;
+	const char			*parent_path;
+
+	/* Directory parent of the metadata file. */
+	struct xfs_inode		*dp;
+
+	/* Locks held on dp */
+	unsigned int			dp_ilock_flags;
+};
+
+/* Release resources tracked in the buffer. */
+static inline void
+xchk_metapath_cleanup(
+	void			*buf)
+{
+	struct xchk_metapath	*mpath = buf;
+
+	if (mpath->dp_ilock_flags)
+		xfs_iunlock(mpath->dp, mpath->dp_ilock_flags);
+	kfree(mpath->path);
+}
+
+int
+xchk_setup_metapath(
+	struct xfs_scrub	*sc)
+{
+	if (!xfs_has_metadir(sc->mp))
+		return -ENOENT;
+	if (sc->sm->sm_gen)
+		return -EINVAL;
+
+	switch (sc->sm->sm_ino) {
+	case XFS_SCRUB_METAPATH_PROBE:
+		/* Just probing, nothing else to do. */
+		if (sc->sm->sm_agno)
+			return -EINVAL;
+		return 0;
+	default:
+		return -ENOENT;
+	}
+}
+
+/*
+ * Take the ILOCK on the metadata directory parent and child.  We do not know
+ * that the metadata directory is not corrupt, so we lock the parent and try
+ * to lock the child.  Returns 0 if successful, or -EINTR to abort the scrub.
+ */
+STATIC int
+xchk_metapath_ilock_both(
+	struct xchk_metapath	*mpath)
+{
+	struct xfs_scrub	*sc = mpath->sc;
+	int			error = 0;
+
+	while (true) {
+		xfs_ilock(mpath->dp, XFS_ILOCK_EXCL);
+		if (xchk_ilock_nowait(sc, XFS_ILOCK_EXCL)) {
+			mpath->dp_ilock_flags |= XFS_ILOCK_EXCL;
+			return 0;
+		}
+		xfs_iunlock(mpath->dp, XFS_ILOCK_EXCL);
+
+		if (xchk_should_terminate(sc, &error))
+			return error;
+
+		delay(1);
+	}
+
+	ASSERT(0);
+	return -EINTR;
+}
+
+/* Unlock parent and child inodes. */
+static inline void
+xchk_metapath_iunlock(
+	struct xchk_metapath	*mpath)
+{
+	struct xfs_scrub	*sc = mpath->sc;
+
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+	mpath->dp_ilock_flags &= ~XFS_ILOCK_EXCL;
+	xfs_iunlock(mpath->dp, XFS_ILOCK_EXCL);
+}
+
+int
+xchk_metapath(
+	struct xfs_scrub	*sc)
+{
+	struct xchk_metapath	*mpath = sc->buf;
+	xfs_ino_t		ino = NULLFSINO;
+	int			error;
+
+	/* Just probing, nothing else to do. */
+	if (sc->sm->sm_ino == XFS_SCRUB_METAPATH_PROBE)
+		return 0;
+
+	/* Parent required to do anything else. */
+	if (mpath->dp == NULL) {
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+		return 0;
+	}
+
+	error = xchk_trans_alloc_empty(sc);
+	if (error)
+		return error;
+
+	error = xchk_metapath_ilock_both(mpath);
+	if (error)
+		goto out_cancel;
+
+	/* Make sure the parent dir has a dirent pointing to this file. */
+	error = xchk_dir_lookup(sc, mpath->dp, &mpath->xname, &ino);
+	trace_xchk_metapath_lookup(sc, mpath->path, mpath->dp, ino);
+	if (error == -ENOENT) {
+		/* No directory entry at all */
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+		error = 0;
+		goto out_ilock;
+	}
+	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
+		goto out_ilock;
+	if (ino != sc->ip->i_ino) {
+		/* Pointing to wrong inode */
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+	}
+
+out_ilock:
+	xchk_metapath_iunlock(mpath);
+out_cancel:
+	xchk_trans_cancel(sc);
+	return error;
+}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 8a5c3af4cfda38..a30ed3d0dcaf79 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -442,6 +442,13 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.has	= xfs_has_parent,
 		.repair	= xrep_dirtree,
 	},
+	[XFS_SCRUB_TYPE_METAPATH] = {	/* metadata directory tree path */
+		.type	= ST_GENERIC,
+		.setup	= xchk_setup_metapath,
+		.scrub	= xchk_metapath,
+		.has	= xfs_has_metadir,
+		.repair	= xrep_notsupported,
+	},
 };
 
 static int
@@ -489,6 +496,8 @@ xchk_validate_inputs(
 		if (sm->sm_agno || (sm->sm_gen && !sm->sm_ino))
 			goto out;
 		break;
+	case ST_GENERIC:
+		break;
 	default:
 		goto out;
 	}
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 5993fcaffb2c9f..c688ff4fc7fc4c 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -73,6 +73,7 @@ enum xchk_type {
 	ST_PERAG,	/* per-AG metadata */
 	ST_FS,		/* per-FS metadata */
 	ST_INODE,	/* per-inode metadata */
+	ST_GENERIC,	/* determined by the scrubber */
 };
 
 struct xchk_meta_ops {
@@ -255,6 +256,7 @@ int xchk_xattr(struct xfs_scrub *sc);
 int xchk_symlink(struct xfs_scrub *sc);
 int xchk_parent(struct xfs_scrub *sc);
 int xchk_dirtree(struct xfs_scrub *sc);
+int xchk_metapath(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
 int xchk_rtbitmap(struct xfs_scrub *sc);
 int xchk_rtsummary(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c
index 7996c23354763d..edcd02dc2e62c0 100644
--- a/fs/xfs/scrub/stats.c
+++ b/fs/xfs/scrub/stats.c
@@ -80,6 +80,7 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_QUOTACHECK]	= "quotacheck",
 	[XFS_SCRUB_TYPE_NLINKS]		= "nlinks",
 	[XFS_SCRUB_TYPE_DIRTREE]	= "dirtree",
+	[XFS_SCRUB_TYPE_METAPATH]	= "metapath",
 };
 
 /* Format the scrub stats into a text buffer, similar to pcp style. */
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 4470ad0533b81d..98f923ae664d0e 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -20,6 +20,7 @@
 #include "xfs_dir2.h"
 #include "xfs_rmap.h"
 #include "xfs_parent.h"
+#include "xfs_metafile.h"
 #include "scrub/scrub.h"
 #include "scrub/xfile.h"
 #include "scrub/xfarray.h"
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index bc246d86a5c89f..bb52baaa2fa726 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -70,6 +70,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_NLINKS);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_HEALTHY);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_DIRTREE);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_BARRIER);
+TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_METAPATH);
 
 #define XFS_SCRUB_TYPE_STRINGS \
 	{ XFS_SCRUB_TYPE_PROBE,		"probe" }, \
@@ -101,7 +102,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_BARRIER);
 	{ XFS_SCRUB_TYPE_NLINKS,	"nlinks" }, \
 	{ XFS_SCRUB_TYPE_HEALTHY,	"healthy" }, \
 	{ XFS_SCRUB_TYPE_DIRTREE,	"dirtree" }, \
-	{ XFS_SCRUB_TYPE_BARRIER,	"barrier" }
+	{ XFS_SCRUB_TYPE_BARRIER,	"barrier" }, \
+	{ XFS_SCRUB_TYPE_METAPATH,	"metapath" }
 
 #define XFS_SCRUB_FLAG_STRINGS \
 	{ XFS_SCRUB_IFLAG_REPAIR,		"repair" }, \
@@ -1916,6 +1918,38 @@ TRACE_EVENT(xchk_dirtree_live_update,
 		  __get_str(name))
 );
 
+DECLARE_EVENT_CLASS(xchk_metapath_class,
+	TP_PROTO(struct xfs_scrub *sc, const char *path,
+		 struct xfs_inode *dp, xfs_ino_t ino),
+	TP_ARGS(sc, path, dp, ino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, scrub_ino)
+		__field(xfs_ino_t, parent_ino)
+		__field(xfs_ino_t, ino)
+		__string(name, path)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->scrub_ino = sc->ip ? sc->ip->i_ino : NULLFSINO;
+		__entry->parent_ino = dp ? dp->i_ino : NULLFSINO;
+		__entry->ino = ino;
+		__assign_str(name);
+	),
+	TP_printk("dev %d:%d ino 0x%llx parent_ino 0x%llx name '%s' ino 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->scrub_ino,
+		  __entry->parent_ino,
+		  __get_str(name),
+		  __entry->ino)
+);
+#define DEFINE_XCHK_METAPATH_EVENT(name) \
+DEFINE_EVENT(xchk_metapath_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, const char *path, \
+		 struct xfs_inode *dp, xfs_ino_t ino), \
+	TP_ARGS(sc, path, dp, ino))
+DEFINE_XCHK_METAPATH_EVENT(xchk_metapath_lookup);
+
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 238258701450f4..e5663e2ac9b853 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -381,6 +381,7 @@ static const struct ioctl_sick_map fs_map[] = {
 	{ XFS_SICK_FS_QUOTACHECK, XFS_FSOP_GEOM_SICK_QUOTACHECK },
 	{ XFS_SICK_FS_NLINKS,	XFS_FSOP_GEOM_SICK_NLINKS },
 	{ XFS_SICK_FS_METADIR,	XFS_FSOP_GEOM_SICK_METADIR },
+	{ XFS_SICK_FS_METAPATH,	XFS_FSOP_GEOM_SICK_METAPATH },
 	{ 0, 0 },
 };
 

[PATCH 27/28] xfs: confirm dotdot target before replacing it during a repair

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

xfs_dir_replace trips an assertion if you tell it to change a dirent to
point to an inumber that it already points at.  Look up the dotdot entry
directly to confirm that we need to make a change.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/dir_repair.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index 2456cf1cb74411..24931388210872 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/fs/xfs/scrub/dir_repair.c
@@ -1638,6 +1638,7 @@ xrep_dir_swap(
 	struct xrep_dir		*rd)
 {
 	struct xfs_scrub	*sc = rd->sc;
+	xfs_ino_t		ino;
 	bool			ip_local, temp_local;
 	int			error = 0;
 
@@ -1655,14 +1656,17 @@ xrep_dir_swap(
 
 	/*
 	 * Reset the temporary directory's '..' entry to point to the parent
-	 * that we found.  The temporary directory was created with the root
-	 * directory as the parent, so we can skip this if repairing a
-	 * subdirectory of the root.
+	 * that we found.  The dirent replace code asserts if the dirent
+	 * already points at the new inumber, so we look it up here.
 	 *
 	 * It's also possible that this replacement could also expand a sf
 	 * tempdir into block format.
 	 */
-	if (rd->pscan.parent_ino != sc->mp->m_rootip->i_ino) {
+	error = xchk_dir_lookup(sc, rd->sc->tempip, &xfs_name_dotdot, &ino);
+	if (error)
+		return error;
+
+	if (rd->pscan.parent_ino != ino) {
 		error = xrep_dir_replace(rd, rd->sc->tempip, &xfs_name_dotdot,
 				rd->pscan.parent_ino, rd->tx.req.resblks);
 		if (error)

[PATCH 28/28] xfs: repair metadata directory file path connectivity

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Fix disconnected or incorrect metadata directory paths.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/metapath.c |  351 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.h   |    3 
 fs/xfs/scrub/scrub.c    |    2 
 fs/xfs/scrub/trace.h    |    5 +
 4 files changed, 358 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c
index b7bd86df9877cd..edc1a395c4015a 100644
--- a/fs/xfs/scrub/metapath.c
+++ b/fs/xfs/scrub/metapath.c
@@ -16,10 +16,15 @@
 #include "xfs_quota.h"
 #include "xfs_qm.h"
 #include "xfs_dir2.h"
+#include "xfs_parent.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_attr.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/readdir.h"
+#include "scrub/repair.h"
 
 /*
  * Metadata Directory Tree Paths
@@ -38,15 +43,28 @@ struct xchk_metapath {
 	/* Name for lookup */
 	struct xfs_name			xname;
 
-	/* Path for this metadata file and the parent directory */
+	/* Directory update for repairs */
+	struct xfs_dir_update		du;
+
+	/* Path down to this metadata file from the parent directory */
 	const char			*path;
-	const char			*parent_path;
 
 	/* Directory parent of the metadata file. */
 	struct xfs_inode		*dp;
 
 	/* Locks held on dp */
 	unsigned int			dp_ilock_flags;
+
+	/* Transaction block reservations */
+	unsigned int			link_resblks;
+	unsigned int			unlink_resblks;
+
+	/* Parent pointer updates */
+	struct xfs_parent_args		link_ppargs;
+	struct xfs_parent_args		unlink_ppargs;
+
+	/* Scratchpads for removing links */
+	struct xfs_da_args		pptr_args;
 };
 
 /* Release resources tracked in the buffer. */
@@ -172,3 +190,332 @@ xchk_metapath(
 	xchk_trans_cancel(sc);
 	return error;
 }
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+/* Create the dirent represented by the final component of the path. */
+STATIC int
+xrep_metapath_link(
+	struct xchk_metapath	*mpath)
+{
+	struct xfs_scrub	*sc = mpath->sc;
+
+	mpath->du.dp = mpath->dp;
+	mpath->du.name = &mpath->xname;
+	mpath->du.ip = sc->ip;
+
+	if (xfs_has_parent(sc->mp))
+		mpath->du.ppargs = &mpath->link_ppargs;
+	else
+		mpath->du.ppargs = NULL;
+
+	trace_xrep_metapath_link(sc, mpath->path, mpath->dp, sc->ip->i_ino);
+
+	return xfs_dir_add_child(sc->tp, mpath->link_resblks, &mpath->du);
+}
+
+/* Remove the dirent at the final component of the path. */
+STATIC int
+xrep_metapath_unlink(
+	struct xchk_metapath	*mpath,
+	xfs_ino_t		ino,
+	struct xfs_inode	*ip)
+{
+	struct xfs_parent_rec	rec;
+	struct xfs_scrub	*sc = mpath->sc;
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
+
+	trace_xrep_metapath_unlink(sc, mpath->path, mpath->dp, ino);
+
+	if (!ip) {
+		/* The child inode isn't allocated.  Junk the dirent. */
+		xfs_trans_log_inode(sc->tp, mpath->dp, XFS_ILOG_CORE);
+		return xfs_dir_removename(sc->tp, mpath->dp, &mpath->xname,
+				ino, mpath->unlink_resblks);
+	}
+
+	mpath->du.dp = mpath->dp;
+	mpath->du.name = &mpath->xname;
+	mpath->du.ip = ip;
+	mpath->du.ppargs = NULL;
+
+	/* Figure out if we're removing a parent pointer too. */
+	if (xfs_has_parent(mp)) {
+		xfs_inode_to_parent_rec(&rec, ip);
+		error = xfs_parent_lookup(sc->tp, ip, &mpath->xname, &rec,
+				&mpath->pptr_args);
+		switch (error) {
+		case -ENOATTR:
+			break;
+		case 0:
+			mpath->du.ppargs = &mpath->unlink_ppargs;
+			break;
+		default:
+			return error;
+		}
+	}
+
+	return xfs_dir_remove_child(sc->tp, mpath->unlink_resblks, &mpath->du);
+}
+
+/*
+ * Try to create a dirent in @mpath->dp with the name @mpath->xname that points
+ * to @sc->ip.  Returns:
+ *
+ * -EEXIST and an @alleged_child if the dirent that points to the wrong inode;
+ * 0 if there is now a dirent pointing to @sc->ip; or
+ * A negative errno on error.
+ */
+STATIC int
+xrep_metapath_try_link(
+	struct xchk_metapath	*mpath,
+	xfs_ino_t		*alleged_child)
+{
+	struct xfs_scrub	*sc = mpath->sc;
+	xfs_ino_t		ino;
+	int			error;
+
+	/* Allocate transaction, lock inodes, join to transaction. */
+	error = xchk_trans_alloc(sc, mpath->link_resblks);
+	if (error)
+		return error;
+
+	error = xchk_metapath_ilock_both(mpath);
+	if (error) {
+		xchk_trans_cancel(sc);
+		return error;
+	}
+	xfs_trans_ijoin(sc->tp, mpath->dp, 0);
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	error = xchk_dir_lookup(sc, mpath->dp, &mpath->xname, &ino);
+	trace_xrep_metapath_lookup(sc, mpath->path, mpath->dp, ino);
+	if (error == -ENOENT) {
+		/*
+		 * There is no dirent in the directory.  Create an entry
+		 * pointing to @sc->ip.
+		 */
+		error = xrep_metapath_link(mpath);
+		if (error)
+			goto out_cancel;
+
+		error = xrep_trans_commit(sc);
+		xchk_metapath_iunlock(mpath);
+		return error;
+	}
+	if (error)
+		goto out_cancel;
+
+	if (ino == sc->ip->i_ino) {
+		/* The dirent already points to @sc->ip; we're done. */
+		error = 0;
+		goto out_cancel;
+	}
+
+	/*
+	 * The dirent points elsewhere; pass that back so that the caller
+	 * can try to remove the dirent.
+	 */
+	*alleged_child = ino;
+	error = -EEXIST;
+
+out_cancel:
+	xchk_trans_cancel(sc);
+	xchk_metapath_iunlock(mpath);
+	return error;
+}
+
+/*
+ * Take the ILOCK on the metadata directory parent and a bad child, if one is
+ * supplied.  We do not know that the metadata directory is not corrupt, so we
+ * lock the parent and try to lock the child.  Returns 0 if successful, or
+ * -EINTR to abort the repair.  The lock state of @dp is not recorded in @mpath.
+ */
+STATIC int
+xchk_metapath_ilock_parent_and_child(
+	struct xchk_metapath	*mpath,
+	struct xfs_inode	*ip)
+{
+	struct xfs_scrub	*sc = mpath->sc;
+	int			error = 0;
+
+	while (true) {
+		xfs_ilock(mpath->dp, XFS_ILOCK_EXCL);
+		if (!ip || xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+			return 0;
+		xfs_iunlock(mpath->dp, XFS_ILOCK_EXCL);
+
+		if (xchk_should_terminate(sc, &error))
+			return error;
+
+		delay(1);
+	}
+
+	ASSERT(0);
+	return -EINTR;
+}
+
+/*
+ * Try to remove a dirent in @mpath->dp with the name @mpath->xname that points
+ * to @alleged_child.  Returns:
+ *
+ * 0 if there is no longer a dirent;
+ * -EEXIST if the dirent points to @sc->ip;
+ * -EAGAIN and an updated @alleged_child if the dirent points elsewhere; or
+ * A negative errno for any other error.
+ */
+STATIC int
+xrep_metapath_try_unlink(
+	struct xchk_metapath	*mpath,
+	xfs_ino_t		*alleged_child)
+{
+	struct xfs_scrub	*sc = mpath->sc;
+	struct xfs_inode	*ip = NULL;
+	xfs_ino_t		ino;
+	int			error;
+
+	ASSERT(*alleged_child != sc->ip->i_ino);
+
+	trace_xrep_metapath_try_unlink(sc, mpath->path, mpath->dp,
+			*alleged_child);
+
+	/*
+	 * Allocate transaction, grab the alleged child inode, lock inodes,
+	 * join to transaction.
+	 */
+	error = xchk_trans_alloc(sc, mpath->unlink_resblks);
+	if (error)
+		return error;
+
+	error = xchk_iget(sc, *alleged_child, &ip);
+	if (error == -EINVAL || error == -ENOENT) {
+		/* inode number is bogus, junk the dirent */
+		error = 0;
+	}
+	if (error) {
+		xchk_trans_cancel(sc);
+		return error;
+	}
+
+	error = xchk_metapath_ilock_parent_and_child(mpath, ip);
+	if (error) {
+		xchk_trans_cancel(sc);
+		return error;
+	}
+	xfs_trans_ijoin(sc->tp, mpath->dp, 0);
+	if (ip)
+		xfs_trans_ijoin(sc->tp, ip, 0);
+
+	error = xchk_dir_lookup(sc, mpath->dp, &mpath->xname, &ino);
+	trace_xrep_metapath_lookup(sc, mpath->path, mpath->dp, ino);
+	if (error == -ENOENT) {
+		/*
+		 * There is no dirent in the directory anymore.  We're ready to
+		 * try the link operation again.
+		 */
+		error = 0;
+		goto out_cancel;
+	}
+	if (error)
+		goto out_cancel;
+
+	if (ino == sc->ip->i_ino) {
+		/* The dirent already points to @sc->ip; we're done. */
+		error = -EEXIST;
+		goto out_cancel;
+	}
+
+	/*
+	 * The dirent does not point to the alleged child.  Update the caller
+	 * and signal that we want to be called again.
+	 */
+	if (ino != *alleged_child) {
+		*alleged_child = ino;
+		error = -EAGAIN;
+		goto out_cancel;
+	}
+
+	/* Remove the link to the child. */
+	error = xrep_metapath_unlink(mpath, ino, ip);
+	if (error)
+		goto out_cancel;
+
+	error = xrep_trans_commit(sc);
+	goto out_unlock;
+
+out_cancel:
+	xchk_trans_cancel(sc);
+out_unlock:
+	xfs_iunlock(mpath->dp, XFS_ILOCK_EXCL);
+	if (ip) {
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		xchk_irele(sc, ip);
+	}
+	return error;
+}
+
+/*
+ * Make sure the metadata directory path points to the child being examined.
+ *
+ * Repair needs to be able to create a directory structure, create its own
+ * transactions, and take ILOCKs.  This function /must/ be called after all
+ * other repairs have completed.
+ */
+int
+xrep_metapath(
+	struct xfs_scrub	*sc)
+{
+	struct xchk_metapath	*mpath = sc->buf;
+	struct xfs_mount	*mp = sc->mp;
+	int			error = 0;
+
+	/* Just probing, nothing to repair. */
+	if (sc->sm->sm_ino == XFS_SCRUB_METAPATH_PROBE)
+		return 0;
+
+	/* Parent required to do anything else. */
+	if (mpath->dp == NULL)
+		return -EFSCORRUPTED;
+
+	/*
+	 * Make sure the child file actually has an attr fork to receive a new
+	 * parent pointer if the fs has parent pointers.
+	 */
+	if (xfs_has_parent(mp)) {
+		error = xfs_attr_add_fork(sc->ip,
+				sizeof(struct xfs_attr_sf_hdr), 1);
+		if (error)
+			return error;
+	}
+
+	/* Compute block reservation required to unlink and link a file. */
+	mpath->unlink_resblks = xfs_remove_space_res(mp, MAXNAMELEN);
+	mpath->link_resblks = xfs_link_space_res(mp, MAXNAMELEN);
+
+	do {
+		xfs_ino_t	alleged_child;
+
+		/* Re-establish the link, or tell us which inode to remove. */
+		error = xrep_metapath_try_link(mpath, &alleged_child);
+		if (!error)
+			return 0;
+		if (error != -EEXIST)
+			return error;
+
+		/*
+		 * Remove an incorrect link to an alleged child, or tell us
+		 * which inode to remove.
+		 */
+		do {
+			error = xrep_metapath_try_unlink(mpath, &alleged_child);
+		} while (error == -EAGAIN);
+		if (error == -EEXIST) {
+			/* Link established; we're done. */
+			error = 0;
+			break;
+		}
+	} while (!error);
+
+	return error;
+}
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 0e0dc2bf985c21..90f9cb3b5ad8ba 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -134,6 +134,7 @@ int xrep_directory(struct xfs_scrub *sc);
 int xrep_parent(struct xfs_scrub *sc);
 int xrep_symlink(struct xfs_scrub *sc);
 int xrep_dirtree(struct xfs_scrub *sc);
+int xrep_metapath(struct xfs_scrub *sc);
 
 #ifdef CONFIG_XFS_RT
 int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -208,6 +209,7 @@ xrep_setup_nothing(
 #define xrep_setup_parent		xrep_setup_nothing
 #define xrep_setup_nlinks		xrep_setup_nothing
 #define xrep_setup_dirtree		xrep_setup_nothing
+#define xrep_setup_metapath		xrep_setup_nothing
 
 #define xrep_setup_inode(sc, imap)	((void)0)
 
@@ -243,6 +245,7 @@ static inline int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *x)
 #define xrep_parent			xrep_notsupported
 #define xrep_symlink			xrep_notsupported
 #define xrep_dirtree			xrep_notsupported
+#define xrep_metapath			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index a30ed3d0dcaf79..1ac33bea6f0a72 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -447,7 +447,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.setup	= xchk_setup_metapath,
 		.scrub	= xchk_metapath,
 		.has	= xfs_has_metadir,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_metapath,
 	},
 };
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index bb52baaa2fa726..b6c8d0944fa453 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -3598,6 +3598,11 @@ DEFINE_XCHK_DIRTREE_EVENT(xrep_dirtree_delete_path);
 DEFINE_XCHK_DIRTREE_EVENT(xrep_dirtree_create_adoption);
 DEFINE_XCHK_DIRTREE_EVALUATE_EVENT(xrep_dirtree_decided_fate);
 
+DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_lookup);
+DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_try_unlink);
+DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_unlink);
+DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_link);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 #endif /* _TRACE_XFS_SCRUB_TRACE_H */

[PATCH 01/21] xfs: clean up xfs_getfsmap_helper arguments

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

The calling conventions for xfs_getfsmap_helper are confusing -- callers
pass in an rmap record, but they must also supply startblock and
blockcount in daddr units.  This was bolted onto the original fsmap
implementation so that we could report *something* for realtime
volumes, which do not support rmap and hence can draw only from the rt
free space bitmap.  Free space on the rt volume can be more than 2^32
fsblocks long, which means that we can't use the rmap startblock or
blockcount fields.

This is confusing for callers, because they must supplying redundant
data, but not all of it is used.  Streamline this by creating a separate
fsmap irec structure that contains exactly the data we need, once.

Note that we actually do need rm_startblock for rmap key comparisons
when we're actually querying an rmap btree, so leave that field but
document why it's there.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_fsmap.c |  225 +++++++++++++++++++++++++++-------------------------
 fs/xfs/xfs_fsmap.h |   15 +++
 fs/xfs/xfs_trace.h |   73 ++++++++++++-----
 3 files changed, 187 insertions(+), 126 deletions(-)


diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index a91677ac54e7e3..6cf4f00636a2d6 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -110,18 +110,18 @@ xfs_fsmap_owner_to_rmap(
 
 /* Convert an rmapbt owner into an fsmap owner. */
 static int
-xfs_fsmap_owner_from_rmap(
+xfs_fsmap_owner_from_frec(
 	struct xfs_fsmap		*dest,
-	const struct xfs_rmap_irec	*src)
+	const struct xfs_fsmap_irec	*frec)
 {
 	dest->fmr_flags = 0;
-	if (!XFS_RMAP_NON_INODE_OWNER(src->rm_owner)) {
-		dest->fmr_owner = src->rm_owner;
+	if (!XFS_RMAP_NON_INODE_OWNER(frec->owner)) {
+		dest->fmr_owner = frec->owner;
 		return 0;
 	}
 	dest->fmr_flags |= FMR_OF_SPECIAL_OWNER;
 
-	switch (src->rm_owner) {
+	switch (frec->owner) {
 	case XFS_RMAP_OWN_FS:
 		dest->fmr_owner = XFS_FMR_OWN_FS;
 		break;
@@ -203,7 +203,7 @@ STATIC int
 xfs_getfsmap_is_shared(
 	struct xfs_trans		*tp,
 	struct xfs_getfsmap_info	*info,
-	const struct xfs_rmap_irec	*rec,
+	const struct xfs_fsmap_irec	*frec,
 	bool				*stat)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
@@ -224,8 +224,9 @@ xfs_getfsmap_is_shared(
 	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);
+	error = xfs_refcount_find_shared(cur, frec->rec_key,
+			XFS_BB_TO_FSBT(mp, frec->len_daddr), &fbno, &flen,
+			false);
 
 	xfs_btree_del_cursor(cur, error);
 	if (error)
@@ -250,15 +251,22 @@ xfs_getfsmap_format(
 }
 
 static inline bool
-xfs_getfsmap_rec_before_start(
+xfs_getfsmap_frec_before_start(
 	struct xfs_getfsmap_info	*info,
-	const struct xfs_rmap_irec	*rec,
-	xfs_daddr_t			rec_daddr)
+	const struct xfs_fsmap_irec	*frec)
 {
 	if (info->low_daddr != XFS_BUF_DADDR_NULL)
-		return rec_daddr < info->low_daddr;
-	if (info->low.rm_blockcount)
-		return xfs_rmap_compare(rec, &info->low) < 0;
+		return frec->start_daddr < info->low_daddr;
+	if (info->low.rm_blockcount) {
+		struct xfs_rmap_irec	rec = {
+			.rm_startblock	= frec->rec_key,
+			.rm_owner	= frec->owner,
+			.rm_flags	= frec->rm_flags,
+		};
+
+		return xfs_rmap_compare(&rec, &info->low) < 0;
+	}
+
 	return false;
 }
 
@@ -271,61 +279,36 @@ STATIC int
 xfs_getfsmap_helper(
 	struct xfs_trans		*tp,
 	struct xfs_getfsmap_info	*info,
-	const struct xfs_rmap_irec	*rec,
-	xfs_daddr_t			rec_daddr,
-	xfs_daddr_t			len_daddr)
+	const struct xfs_fsmap_irec	*frec)
 {
 	struct xfs_fsmap		fmr;
 	struct xfs_mount		*mp = tp->t_mountp;
 	bool				shared;
-	int				error;
+	int				error = 0;
 
 	if (fatal_signal_pending(current))
 		return -EINTR;
 
-	if (len_daddr == 0)
-		len_daddr = XFS_FSB_TO_BB(mp, rec->rm_blockcount);
-
 	/*
 	 * Filter out records that start before our startpoint, if the
 	 * caller requested that.
 	 */
-	if (xfs_getfsmap_rec_before_start(info, rec, rec_daddr)) {
-		rec_daddr += len_daddr;
-		if (info->next_daddr < rec_daddr)
-			info->next_daddr = rec_daddr;
-		return 0;
-	}
-
-	/*
-	 * For an info->last query, we're looking for a gap between the last
-	 * mapping emitted and the high key specified by userspace.  If the
-	 * user's query spans less than 1 fsblock, then info->high and
-	 * info->low will have the same rm_startblock, which causes rec_daddr
-	 * and next_daddr to be the same.  Therefore, use the end_daddr that
-	 * we calculated from userspace's high key to synthesize the record.
-	 * Note that if the btree query found a mapping, there won't be a gap.
-	 */
-	if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL)
-		rec_daddr = info->end_daddr;
+	if (xfs_getfsmap_frec_before_start(info, frec))
+		goto out;
 
 	/* Are we just counting mappings? */
 	if (info->head->fmh_count == 0) {
 		if (info->head->fmh_entries == UINT_MAX)
 			return -ECANCELED;
 
-		if (rec_daddr > info->next_daddr)
+		if (frec->start_daddr > info->next_daddr)
 			info->head->fmh_entries++;
 
 		if (info->last)
 			return 0;
 
 		info->head->fmh_entries++;
-
-		rec_daddr += len_daddr;
-		if (info->next_daddr < rec_daddr)
-			info->next_daddr = rec_daddr;
-		return 0;
+		goto out;
 	}
 
 	/*
@@ -333,7 +316,7 @@ xfs_getfsmap_helper(
 	 * then we've found a gap.  Report the gap as being owned by
 	 * whatever the caller specified is the missing owner.
 	 */
-	if (rec_daddr > info->next_daddr) {
+	if (frec->start_daddr > info->next_daddr) {
 		if (info->head->fmh_entries >= info->head->fmh_count)
 			return -ECANCELED;
 
@@ -341,7 +324,7 @@ xfs_getfsmap_helper(
 		fmr.fmr_physical = info->next_daddr;
 		fmr.fmr_owner = info->missing_owner;
 		fmr.fmr_offset = 0;
-		fmr.fmr_length = rec_daddr - info->next_daddr;
+		fmr.fmr_length = frec->start_daddr - info->next_daddr;
 		fmr.fmr_flags = FMR_OF_SPECIAL_OWNER;
 		xfs_getfsmap_format(mp, &fmr, info);
 	}
@@ -355,23 +338,23 @@ xfs_getfsmap_helper(
 
 	trace_xfs_fsmap_mapping(mp, info->dev,
 			info->group ? info->group->xg_gno : NULLAGNUMBER,
-			rec);
+			frec);
 
 	fmr.fmr_device = info->dev;
-	fmr.fmr_physical = rec_daddr;
-	error = xfs_fsmap_owner_from_rmap(&fmr, rec);
+	fmr.fmr_physical = frec->start_daddr;
+	error = xfs_fsmap_owner_from_frec(&fmr, frec);
 	if (error)
 		return error;
-	fmr.fmr_offset = XFS_FSB_TO_BB(mp, rec->rm_offset);
-	fmr.fmr_length = len_daddr;
-	if (rec->rm_flags & XFS_RMAP_UNWRITTEN)
+	fmr.fmr_offset = XFS_FSB_TO_BB(mp, frec->offset);
+	fmr.fmr_length = frec->len_daddr;
+	if (frec->rm_flags & XFS_RMAP_UNWRITTEN)
 		fmr.fmr_flags |= FMR_OF_PREALLOC;
-	if (rec->rm_flags & XFS_RMAP_ATTR_FORK)
+	if (frec->rm_flags & XFS_RMAP_ATTR_FORK)
 		fmr.fmr_flags |= FMR_OF_ATTR_FORK;
-	if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK)
+	if (frec->rm_flags & XFS_RMAP_BMBT_BLOCK)
 		fmr.fmr_flags |= FMR_OF_EXTENT_MAP;
 	if (fmr.fmr_flags == 0) {
-		error = xfs_getfsmap_is_shared(tp, info, rec, &shared);
+		error = xfs_getfsmap_is_shared(tp, info, frec, &shared);
 		if (error)
 			return error;
 		if (shared)
@@ -380,25 +363,55 @@ xfs_getfsmap_helper(
 
 	xfs_getfsmap_format(mp, &fmr, info);
 out:
-	rec_daddr += len_daddr;
-	if (info->next_daddr < rec_daddr)
-		info->next_daddr = rec_daddr;
+	info->next_daddr = max(info->next_daddr,
+			       frec->start_daddr + frec->len_daddr);
 	return 0;
 }
 
+static inline int
+xfs_getfsmap_group_helper(
+	struct xfs_getfsmap_info	*info,
+	struct xfs_trans		*tp,
+	struct xfs_group		*xg,
+	xfs_agblock_t			startblock,
+	xfs_extlen_t			blockcount,
+	struct xfs_fsmap_irec		*frec)
+{
+	/*
+	 * For an info->last query, we're looking for a gap between the last
+	 * mapping emitted and the high key specified by userspace.  If the
+	 * user's query spans less than 1 fsblock, then info->high and
+	 * info->low will have the same rm_startblock, which causes rec_daddr
+	 * and next_daddr to be the same.  Therefore, use the end_daddr that
+	 * we calculated from userspace's high key to synthesize the record.
+	 * Note that if the btree query found a mapping, there won't be a gap.
+	 */
+	if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL)
+		frec->start_daddr = info->end_daddr;
+	else
+		frec->start_daddr = xfs_gbno_to_daddr(xg, startblock);
+
+	frec->len_daddr = XFS_FSB_TO_BB(xg->xg_mount, blockcount);
+	return xfs_getfsmap_helper(tp, info, frec);
+}
+
 /* Transform a rmapbt irec into a fsmap */
 STATIC int
-xfs_getfsmap_datadev_helper(
+xfs_getfsmap_rmapbt_helper(
 	struct xfs_btree_cur		*cur,
 	const struct xfs_rmap_irec	*rec,
 	void				*priv)
 {
+	struct xfs_fsmap_irec		frec = {
+		.owner			= rec->rm_owner,
+		.offset			= rec->rm_offset,
+		.rm_flags		= rec->rm_flags,
+		.rec_key		= rec->rm_startblock,
+	};
 	struct xfs_getfsmap_info	*info = priv;
 
-	return xfs_getfsmap_helper(cur->bc_tp, info, rec,
-			xfs_agbno_to_daddr(to_perag(cur->bc_group),
-				rec->rm_startblock),
-			0);
+	return xfs_getfsmap_group_helper(info, cur->bc_tp, cur->bc_group,
+			rec->rm_startblock, rec->rm_blockcount, &frec);
 }
 
 /* Transform a bnobt irec into a fsmap */
@@ -408,19 +421,14 @@ xfs_getfsmap_datadev_bnobt_helper(
 	const struct xfs_alloc_rec_incore *rec,
 	void				*priv)
 {
+	struct xfs_fsmap_irec		frec = {
+		.owner			= XFS_RMAP_OWN_NULL, /* "free" */
+		.rec_key		= rec->ar_startblock,
+	};
 	struct xfs_getfsmap_info	*info = priv;
-	struct xfs_rmap_irec		irec;
 
-	irec.rm_startblock = rec->ar_startblock;
-	irec.rm_blockcount = rec->ar_blockcount;
-	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
-	irec.rm_offset = 0;
-	irec.rm_flags = 0;
-
-	return xfs_getfsmap_helper(cur->bc_tp, info, &irec,
-			xfs_agbno_to_daddr(to_perag(cur->bc_group),
-				rec->ar_startblock),
-			0);
+	return xfs_getfsmap_group_helper(info, cur->bc_tp, cur->bc_group,
+			rec->ar_startblock, rec->ar_blockcount, &frec);
 }
 
 /* Set rmap flags based on the getfsmap flags */
@@ -544,9 +552,9 @@ __xfs_getfsmap_datadev(
 		if (error)
 			break;
 
-		trace_xfs_fsmap_low_key(mp, info->dev, pag_agno(pag),
+		trace_xfs_fsmap_low_group_key(mp, info->dev, pag_agno(pag),
 				&info->low);
-		trace_xfs_fsmap_high_key(mp, info->dev, pag_agno(pag),
+		trace_xfs_fsmap_high_group_key(mp, info->dev, pag_agno(pag),
 				&info->high);
 
 		error = query_fn(tp, info, &bt_cur, priv);
@@ -602,13 +610,13 @@ xfs_getfsmap_datadev_rmapbt_query(
 {
 	/* Report any gap at the end of the last AG. */
 	if (info->last)
-		return xfs_getfsmap_datadev_helper(*curpp, &info->high, info);
+		return xfs_getfsmap_rmapbt_helper(*curpp, &info->high, info);
 
 	/* Allocate cursor for this AG and query_range it. */
 	*curpp = xfs_rmapbt_init_cursor(tp->t_mountp, tp, info->agf_bp,
 			to_perag(info->group));
 	return xfs_rmap_query_range(*curpp, &info->low, &info->high,
-			xfs_getfsmap_datadev_helper, info);
+			xfs_getfsmap_rmapbt_helper, info);
 }
 
 /* Execute a getfsmap query against the regular data device rmapbt. */
@@ -668,9 +676,12 @@ xfs_getfsmap_logdev(
 	const struct xfs_fsmap		*keys,
 	struct xfs_getfsmap_info	*info)
 {
+	struct xfs_fsmap_irec		frec = {
+		.start_daddr		= 0,
+		.rec_key		= 0,
+		.owner			= XFS_RMAP_OWN_LOG,
+	};
 	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_rmap_irec		rmap;
-	xfs_daddr_t			rec_daddr, len_daddr;
 	xfs_fsblock_t			start_fsb, end_fsb;
 	uint64_t			eofs;
 
@@ -685,22 +696,15 @@ xfs_getfsmap_logdev(
 	if (keys[0].fmr_length > 0)
 		info->low_daddr = XFS_FSB_TO_BB(mp, start_fsb);
 
-	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_fsb);
-	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_fsb);
+	trace_xfs_fsmap_low_linear_key(mp, info->dev, start_fsb);
+	trace_xfs_fsmap_high_linear_key(mp, info->dev, end_fsb);
 
 	if (start_fsb > 0)
 		return 0;
 
 	/* Fabricate an rmap entry for the external log device. */
-	rmap.rm_startblock = 0;
-	rmap.rm_blockcount = mp->m_sb.sb_logblocks;
-	rmap.rm_owner = XFS_RMAP_OWN_LOG;
-	rmap.rm_offset = 0;
-	rmap.rm_flags = 0;
-
-	rec_daddr = XFS_FSB_TO_BB(mp, rmap.rm_startblock);
-	len_daddr = XFS_FSB_TO_BB(mp, rmap.rm_blockcount);
-	return xfs_getfsmap_helper(tp, info, &rmap, rec_daddr, len_daddr);
+	frec.len_daddr = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
+	return xfs_getfsmap_helper(tp, info, &frec);
 }
 
 #ifdef CONFIG_XFS_RT
@@ -712,24 +716,31 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
 	const struct xfs_rtalloc_rec	*rec,
 	void				*priv)
 {
+	struct xfs_fsmap_irec		frec = {
+		.owner			= XFS_RMAP_OWN_NULL, /* "free" */
+	};
 	struct xfs_getfsmap_info	*info = priv;
-	struct xfs_rmap_irec		irec;
 	xfs_rtblock_t			rtbno;
-	xfs_daddr_t			rec_daddr, len_daddr;
 
-	rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
-	rec_daddr = XFS_FSB_TO_BB(mp, rtbno);
-	irec.rm_startblock = rtbno;
+	/*
+	 * For an info->last query, we're looking for a gap between the last
+	 * mapping emitted and the high key specified by userspace.  If the
+	 * user's query spans less than 1 fsblock, then info->high and
+	 * info->low will have the same rm_startblock, which causes rec_daddr
+	 * and next_daddr to be the same.  Therefore, use the end_daddr that
+	 * we calculated from userspace's high key to synthesize the record.
+	 * Note that if the btree query found a mapping, there won't be a gap.
+	 */
+	if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL) {
+		frec.start_daddr = info->end_daddr;
+	} else {
+		rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
+		frec.start_daddr = XFS_FSB_TO_BB(mp, rtbno);
+	}
 
 	rtbno = xfs_rtx_to_rtb(mp, rec->ar_extcount);
-	len_daddr = XFS_FSB_TO_BB(mp, rtbno);
-	irec.rm_blockcount = rtbno;
-
-	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
-	irec.rm_offset = 0;
-	irec.rm_flags = 0;
-
-	return xfs_getfsmap_helper(tp, info, &irec, rec_daddr, len_daddr);
+	frec.len_daddr = XFS_FSB_TO_BB(mp, rtbno);
+	return xfs_getfsmap_helper(tp, info, &frec);
 }
 
 /* Execute a getfsmap query against the realtime device rtbitmap. */
@@ -764,8 +775,8 @@ xfs_getfsmap_rtdev_rtbitmap(
 			return 0;
 	}
 
-	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_rtb);
-	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_rtb);
+	trace_xfs_fsmap_low_linear_key(mp, info->dev, start_rtb);
+	trace_xfs_fsmap_high_linear_key(mp, info->dev, end_rtb);
 
 	xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);
 
diff --git a/fs/xfs/xfs_fsmap.h b/fs/xfs/xfs_fsmap.h
index a0bcc38486a569..06e492fd479de6 100644
--- a/fs/xfs/xfs_fsmap.h
+++ b/fs/xfs/xfs_fsmap.h
@@ -28,6 +28,21 @@ struct xfs_fsmap_head {
 	struct xfs_fsmap fmh_keys[2];	/* low and high keys */
 };
 
+/* internal fsmap record format */
+struct xfs_fsmap_irec {
+	xfs_daddr_t	start_daddr;
+	xfs_daddr_t	len_daddr;
+	uint64_t	owner;		/* extent owner */
+	uint64_t	offset;		/* offset within the owner */
+	unsigned int	rm_flags;	/* rmap state flags */
+
+	/*
+	 * rmapbt startblock corresponding to start_daddr, if the record came
+	 * from an rmap btree.
+	 */
+	xfs_agblock_t	rec_key;
+};
+
 int xfs_ioc_getfsmap(struct xfs_inode *ip, struct fsmap_head __user *arg);
 
 #endif /* __XFS_FSMAP_H__ */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index e2db13ed08b59c..0f3704f3c2e4e3 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_fsmap_irec;
 struct xfs_group;
 struct xfs_rmap_irec;
 struct xfs_icreate_log;
@@ -3877,7 +3878,45 @@ DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap_piece);
 DEFINE_INODE_ERROR_EVENT(xfs_swap_extent_rmap_error);
 
 /* fsmap traces */
-DECLARE_EVENT_CLASS(xfs_fsmap_class,
+TRACE_EVENT(xfs_fsmap_mapping,
+	TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_agnumber_t agno,
+		 const struct xfs_fsmap_irec *frec),
+	TP_ARGS(mp, keydev, agno, frec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, keydev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_daddr_t, start_daddr)
+		__field(xfs_daddr_t, len_daddr)
+		__field(uint64_t, owner)
+		__field(uint64_t, offset)
+		__field(unsigned int, flags)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->keydev = new_decode_dev(keydev);
+		__entry->agno = agno;
+		__entry->agbno = frec->rec_key;
+		__entry->start_daddr = frec->start_daddr;
+		__entry->len_daddr = frec->len_daddr;
+		__entry->owner = frec->owner;
+		__entry->offset = frec->offset;
+		__entry->flags = frec->rm_flags;
+	),
+	TP_printk("dev %d:%d keydev %d:%d agno 0x%x rmapbno 0x%x start_daddr 0x%llx len_daddr 0x%llx owner 0x%llx fileoff 0x%llx flags 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->keydev), MINOR(__entry->keydev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->start_daddr,
+		  __entry->len_daddr,
+		  __entry->owner,
+		  __entry->offset,
+		  __entry->flags)
+);
+
+DECLARE_EVENT_CLASS(xfs_fsmap_group_key_class,
 	TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_agnumber_t agno,
 		 const struct xfs_rmap_irec *rmap),
 	TP_ARGS(mp, keydev, agno, rmap),
@@ -3885,8 +3924,7 @@ DECLARE_EVENT_CLASS(xfs_fsmap_class,
 		__field(dev_t, dev)
 		__field(dev_t, keydev)
 		__field(xfs_agnumber_t, agno)
-		__field(xfs_fsblock_t, bno)
-		__field(xfs_filblks_t, len)
+		__field(xfs_agblock_t, agbno)
 		__field(uint64_t, owner)
 		__field(uint64_t, offset)
 		__field(unsigned int, flags)
@@ -3895,33 +3933,30 @@ DECLARE_EVENT_CLASS(xfs_fsmap_class,
 		__entry->dev = mp->m_super->s_dev;
 		__entry->keydev = new_decode_dev(keydev);
 		__entry->agno = agno;
-		__entry->bno = rmap->rm_startblock;
-		__entry->len = rmap->rm_blockcount;
+		__entry->agbno = rmap->rm_startblock;
 		__entry->owner = rmap->rm_owner;
 		__entry->offset = rmap->rm_offset;
 		__entry->flags = rmap->rm_flags;
 	),
-	TP_printk("dev %d:%d keydev %d:%d agno 0x%x startblock 0x%llx fsbcount 0x%llx owner 0x%llx fileoff 0x%llx flags 0x%x",
+	TP_printk("dev %d:%d keydev %d:%d agno 0x%x startblock 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  MAJOR(__entry->keydev), MINOR(__entry->keydev),
 		  __entry->agno,
-		  __entry->bno,
-		  __entry->len,
+		  __entry->agbno,
 		  __entry->owner,
 		  __entry->offset,
 		  __entry->flags)
 )
-#define DEFINE_FSMAP_EVENT(name) \
-DEFINE_EVENT(xfs_fsmap_class, name, \
+#define DEFINE_FSMAP_GROUP_KEY_EVENT(name) \
+DEFINE_EVENT(xfs_fsmap_group_key_class, name, \
 	TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_agnumber_t agno, \
 		 const struct xfs_rmap_irec *rmap), \
 	TP_ARGS(mp, keydev, agno, rmap))
-DEFINE_FSMAP_EVENT(xfs_fsmap_low_key);
-DEFINE_FSMAP_EVENT(xfs_fsmap_high_key);
-DEFINE_FSMAP_EVENT(xfs_fsmap_mapping);
+DEFINE_FSMAP_GROUP_KEY_EVENT(xfs_fsmap_low_group_key);
+DEFINE_FSMAP_GROUP_KEY_EVENT(xfs_fsmap_high_group_key);
 
-DECLARE_EVENT_CLASS(xfs_fsmap_linear_class,
-	TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno),
+DECLARE_EVENT_CLASS(xfs_fsmap_linear_key_class,
+	TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_fsblock_t bno),
 	TP_ARGS(mp, keydev, bno),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -3938,12 +3973,12 @@ DECLARE_EVENT_CLASS(xfs_fsmap_linear_class,
 		  MAJOR(__entry->keydev), MINOR(__entry->keydev),
 		  __entry->bno)
 )
-#define DEFINE_FSMAP_LINEAR_EVENT(name) \
-DEFINE_EVENT(xfs_fsmap_linear_class, name, \
+#define DEFINE_FSMAP_LINEAR_KEY_EVENT(name) \
+DEFINE_EVENT(xfs_fsmap_linear_key_class, name, \
 	TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno), \
 	TP_ARGS(mp, keydev, bno))
-DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_low_key_linear);
-DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_high_key_linear);
+DEFINE_FSMAP_LINEAR_KEY_EVENT(xfs_fsmap_low_linear_key);
+DEFINE_FSMAP_LINEAR_KEY_EVENT(xfs_fsmap_high_linear_key);
 
 DECLARE_EVENT_CLASS(xfs_getfsmap_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap),

[PATCH 02/21] xfs: create incore realtime group structures

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create an incore object that will contain information about a realtime
allocation group.  This will eventually enable us to shard the realtime
section in a similar manner to how we shard the data section, but for
now just a single object for the entire RT subvolume is created.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/Makefile               |    1 
 fs/xfs/libxfs/xfs_format.h    |    3 +
 fs/xfs/libxfs/xfs_rtgroup.c   |  151 +++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_rtgroup.h   |  217 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_sb.c        |   13 ++
 fs/xfs/libxfs/xfs_types.h     |    8 +-
 fs/xfs/xfs_bmap_util.c        |    3 -
 fs/xfs/xfs_buf_item_recover.c |   25 +++++
 fs/xfs/xfs_fsmap.c            |    5 +
 fs/xfs/xfs_mount.c            |   13 ++
 fs/xfs/xfs_mount.h            |   13 ++
 fs/xfs/xfs_rtalloc.c          |    5 +
 fs/xfs/xfs_trace.c            |    1 
 fs/xfs/xfs_trace.h            |    1 
 14 files changed, 454 insertions(+), 5 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_rtgroup.c
 create mode 100644 fs/xfs/libxfs/xfs_rtgroup.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index d80c2817eb4892..6814debac29929 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -61,6 +61,7 @@ xfs-y				+= $(addprefix libxfs/, \
 # xfs_rtbitmap is shared with libxfs
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix libxfs/, \
 				   xfs_rtbitmap.o \
+				   xfs_rtgroup.o \
 				   )
 
 # highlevel code
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 616f81045921b7..867060d60e8583 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -176,6 +176,9 @@ typedef struct xfs_sb {
 
 	xfs_ino_t	sb_metadirino;	/* metadata directory tree root */
 
+	xfs_rgnumber_t	sb_rgcount;	/* number of realtime groups */
+	xfs_rtxlen_t	sb_rgextents;	/* size of a realtime group in rtx */
+
 	/* must be padded to 64 bit alignment */
 } xfs_sb_t;
 
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
new file mode 100644
index 00000000000000..9d3842e83c9366
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_ag.h"
+#include "xfs_ag_resv.h"
+#include "xfs_health.h"
+#include "xfs_error.h"
+#include "xfs_bmap.h"
+#include "xfs_defer.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_trace.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtbitmap.h"
+
+int
+xfs_rtgroup_alloc(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgnumber_t		rgcount,
+	xfs_rtbxlen_t		rextents)
+{
+	struct xfs_rtgroup	*rtg;
+	int			error;
+
+	rtg = kzalloc(sizeof(struct xfs_rtgroup), GFP_KERNEL);
+	if (!rtg)
+		return -ENOMEM;
+
+	error = xfs_group_insert(mp, rtg_group(rtg), rgno, XG_TYPE_RTG);
+	if (error)
+		goto out_free_rtg;
+	return 0;
+
+out_free_rtg:
+	kfree(rtg);
+	return error;
+}
+
+void
+xfs_rtgroup_free(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	xfs_group_free(mp, rgno, XG_TYPE_RTG, NULL);
+}
+
+/* Free a range of incore rtgroup objects. */
+void
+xfs_free_rtgroups(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		first_rgno,
+	xfs_rgnumber_t		end_rgno)
+{
+	xfs_rgnumber_t		rgno;
+
+	for (rgno = first_rgno; rgno < end_rgno; rgno++)
+		xfs_rtgroup_free(mp, rgno);
+}
+
+/* Initialize some range of incore rtgroup objects. */
+int
+xfs_initialize_rtgroups(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		first_rgno,
+	xfs_rgnumber_t		end_rgno,
+	xfs_rtbxlen_t		rextents)
+{
+	xfs_rgnumber_t		index;
+	int			error;
+
+	if (first_rgno >= end_rgno)
+		return 0;
+
+	for (index = first_rgno; index < end_rgno; index++) {
+		error = xfs_rtgroup_alloc(mp, index, end_rgno, rextents);
+		if (error)
+			goto out_unwind_new_rtgs;
+	}
+
+	return 0;
+
+out_unwind_new_rtgs:
+	xfs_free_rtgroups(mp, first_rgno, index);
+	return error;
+}
+
+/* Compute the number of rt extents in this realtime group. */
+xfs_rtxnum_t
+__xfs_rtgroup_extents(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgnumber_t		rgcount,
+	xfs_rtbxlen_t		rextents)
+{
+	ASSERT(rgno < rgcount);
+	if (rgno == rgcount - 1)
+		return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents);
+
+	ASSERT(xfs_has_rtgroups(mp));
+	return mp->m_sb.sb_rgextents;
+}
+
+xfs_rtxnum_t
+xfs_rtgroup_extents(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount,
+			mp->m_sb.sb_rextents);
+}
+
+/*
+ * Update the rt extent count of the previous tail rtgroup if it changed during
+ * recovery (i.e. recovery of a growfs).
+ */
+int
+xfs_update_last_rtgroup_size(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		prev_rgcount)
+{
+	struct xfs_rtgroup	*rtg;
+
+	ASSERT(prev_rgcount > 0);
+
+	rtg = xfs_rtgroup_grab(mp, prev_rgcount - 1);
+	if (!rtg)
+		return -EFSCORRUPTED;
+	rtg->rtg_extents = __xfs_rtgroup_extents(mp, prev_rgcount - 1,
+			mp->m_sb.sb_rgcount, mp->m_sb.sb_rextents);
+	xfs_rtgroup_rele(rtg);
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
new file mode 100644
index 00000000000000..8872c27a9585fd
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __LIBXFS_RTGROUP_H
+#define __LIBXFS_RTGROUP_H 1
+
+#include "xfs_group.h"
+
+struct xfs_mount;
+struct xfs_trans;
+
+/*
+ * Realtime group incore structure, similar to the per-AG structure.
+ */
+struct xfs_rtgroup {
+	struct xfs_group	rtg_group;
+
+	/* Number of blocks in this group */
+	xfs_rtxnum_t		rtg_extents;
+};
+
+static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg)
+{
+	return container_of(xg, struct xfs_rtgroup, rtg_group);
+}
+
+static inline struct xfs_group *rtg_group(struct xfs_rtgroup *rtg)
+{
+	return &rtg->rtg_group;
+}
+
+static inline struct xfs_mount *rtg_mount(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_mount;
+}
+
+static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_gno;
+}
+
+/* Passive rtgroup references */
+static inline struct xfs_rtgroup *
+xfs_rtgroup_get(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return to_rtg(xfs_group_get(mp, rgno, XG_TYPE_RTG));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_hold(
+	struct xfs_rtgroup	*rtg)
+{
+	return to_rtg(xfs_group_hold(rtg_group(rtg)));
+}
+
+static inline void
+xfs_rtgroup_put(
+	struct xfs_rtgroup	*rtg)
+{
+	xfs_group_put(rtg_group(rtg));
+}
+
+/* Active rtgroup references */
+static inline struct xfs_rtgroup *
+xfs_rtgroup_grab(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	return to_rtg(xfs_group_grab(mp, rgno, XG_TYPE_RTG));
+}
+
+static inline void
+xfs_rtgroup_rele(
+	struct xfs_rtgroup	*rtg)
+{
+	xfs_group_rele(rtg_group(rtg));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_next_range(
+	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgnumber_t		start_rgno,
+	xfs_rgnumber_t		end_rgno)
+{
+	return to_rtg(xfs_group_next_range(mp, rtg ? rtg_group(rtg) : NULL,
+			start_rgno, end_rgno, XG_TYPE_RTG));
+}
+
+static inline struct xfs_rtgroup *
+xfs_rtgroup_next(
+	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg)
+{
+	return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1);
+}
+
+static inline xfs_rtblock_t
+xfs_rgno_start_rtb(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	if (mp->m_rgblklog >= 0)
+		return ((xfs_rtblock_t)rgno << mp->m_rgblklog);
+	return ((xfs_rtblock_t)rgno * mp->m_rgblocks);
+}
+
+static inline xfs_rtblock_t
+__xfs_rgbno_to_rtb(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	xfs_rgblock_t		rgbno)
+{
+	return xfs_rgno_start_rtb(mp, rgno) + rgbno;
+}
+
+static inline xfs_rtblock_t
+xfs_rgbno_to_rtb(
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		rgbno)
+{
+	return __xfs_rgbno_to_rtb(rtg_mount(rtg), rtg_rgno(rtg), rgbno);
+}
+
+static inline xfs_rgnumber_t
+xfs_rtb_to_rgno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	if (!xfs_has_rtgroups(mp))
+		return 0;
+
+	if (mp->m_rgblklog >= 0)
+		return rtbno >> mp->m_rgblklog;
+
+	return div_u64(rtbno, mp->m_rgblocks);
+}
+
+static inline uint64_t
+__xfs_rtb_to_rgbno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	uint32_t		rem;
+
+	if (!xfs_has_rtgroups(mp))
+		return rtbno;
+
+	if (mp->m_rgblklog >= 0)
+		return rtbno & mp->m_rgblkmask;
+
+	div_u64_rem(rtbno, mp->m_rgblocks, &rem);
+	return rem;
+}
+
+static inline xfs_rgblock_t
+xfs_rtb_to_rgbno(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return __xfs_rtb_to_rgbno(mp, rtbno);
+}
+
+static inline xfs_daddr_t
+xfs_rtb_to_daddr(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return rtbno << mp->m_blkbb_log;
+}
+
+static inline xfs_rtblock_t
+xfs_daddr_to_rtb(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		daddr)
+{
+	return daddr >> mp->m_blkbb_log;
+}
+
+#ifdef CONFIG_XFS_RT
+int xfs_rtgroup_alloc(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
+void xfs_rtgroup_free(struct xfs_mount *mp, xfs_rgnumber_t rgno);
+
+void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
+		xfs_rgnumber_t end_rgno);
+int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
+		xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents);
+
+xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
+xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno);
+
+int xfs_update_last_rtgroup_size(struct xfs_mount *mp,
+		xfs_rgnumber_t prev_rgcount);
+#else
+static inline void xfs_free_rtgroups(struct xfs_mount *mp,
+		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno)
+{
+}
+
+static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
+		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno,
+		xfs_rtbxlen_t rextents)
+{
+	return 0;
+}
+
+# define xfs_rtgroup_extents(mp, rgno)		(0)
+# define xfs_update_last_rtgroup_size(mp, rgno)	(-EOPNOTSUPP)
+#endif /* CONFIG_XFS_RT */
+
+#endif /* __LIBXFS_RTGROUP_H */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 4516824e3b9994..21891aa10ada02 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -696,6 +696,9 @@ __xfs_sb_from_disk(
 		to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
 	else
 		to->sb_metadirino = NULLFSINO;
+
+	to->sb_rgcount = 1;
+	to->sb_rgextents = 0;
 }
 
 void
@@ -980,8 +983,18 @@ xfs_mount_sb_set_rextsize(
 	struct xfs_mount	*mp,
 	struct xfs_sb		*sbp)
 {
+	struct xfs_groups	*rgs = &mp->m_groups[XG_TYPE_RTG];
+
 	mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize);
 	mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize);
+
+	mp->m_rgblocks = 0;
+	mp->m_rgblklog = 0;
+	mp->m_rgblkmask = (uint64_t)-1;
+
+	rgs->blocks = 0;
+	rgs->blklog = 0;
+	rgs->blkmask = (uint64_t)-1;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 25053a66c225ed..bf33c2b1e43e5f 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -9,10 +9,12 @@
 typedef uint32_t	prid_t;		/* project ID */
 
 typedef uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
+typedef uint32_t	xfs_rgblock_t;	/* blockno in realtime group */
 typedef uint32_t	xfs_agino_t;	/* inode # within allocation grp */
 typedef uint32_t	xfs_extlen_t;	/* extent length in blocks */
 typedef uint32_t	xfs_rtxlen_t;	/* file extent length in rtextents */
 typedef uint32_t	xfs_agnumber_t;	/* allocation group number */
+typedef uint32_t	xfs_rgnumber_t;	/* realtime group number */
 typedef uint64_t	xfs_extnum_t;	/* # of extents in a file */
 typedef uint32_t	xfs_aextnum_t;	/* # extents in an attribute fork */
 typedef int64_t		xfs_fsize_t;	/* bytes in a file */
@@ -53,7 +55,9 @@ typedef void *		xfs_failaddr_t;
 #define	NULLFILEOFF	((xfs_fileoff_t)-1)
 
 #define	NULLAGBLOCK	((xfs_agblock_t)-1)
+#define NULLRGBLOCK	((xfs_rgblock_t)-1)
 #define	NULLAGNUMBER	((xfs_agnumber_t)-1)
+#define	NULLRGNUMBER	((xfs_rgnumber_t)-1)
 
 #define NULLCOMMITLSN	((xfs_lsn_t)-1)
 
@@ -214,11 +218,13 @@ enum xbtree_recpacking {
 
 enum xfs_group_type {
 	XG_TYPE_AG,
+	XG_TYPE_RTG,
 	XG_TYPE_MAX,
 } __packed;
 
 #define XG_TYPE_STRINGS \
-	{ XG_TYPE_AG,	"ag" }
+	{ XG_TYPE_AG,	"ag" }, \
+	{ XG_TYPE_RTG,	"rtg" }
 
 /*
  * Type verifier functions
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index edaf193dbd5ccc..1ac0b0facb7fd3 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -29,6 +29,7 @@
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
 
 /* Kernel only BMAP related definitions and functions */
 
@@ -41,7 +42,7 @@ xfs_daddr_t
 xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
 {
 	if (XFS_IS_REALTIME_INODE(ip))
-		return XFS_FSB_TO_BB(ip->i_mount, fsb);
+		return xfs_rtb_to_daddr(ip->i_mount, fsb);
 	return XFS_FSB_TO_DADDR(ip->i_mount, fsb);
 }
 
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index c627ad3a3bbbfd..c8259ee482fd86 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -25,6 +25,7 @@
 #include "xfs_alloc.h"
 #include "xfs_ag.h"
 #include "xfs_sb.h"
+#include "xfs_rtgroup.h"
 
 /*
  * This is the number of entries in the l_buf_cancel_table used during
@@ -704,6 +705,7 @@ xlog_recover_do_primary_sb_buffer(
 {
 	struct xfs_dsb			*dsb = bp->b_addr;
 	xfs_agnumber_t			orig_agcount = mp->m_sb.sb_agcount;
+	xfs_rgnumber_t			orig_rgcount = mp->m_sb.sb_rgcount;
 	int				error;
 
 	xlog_recover_do_reg_buffer(mp, item, bp, buf_f, current_lsn);
@@ -722,6 +724,11 @@ xlog_recover_do_primary_sb_buffer(
 		xfs_alert(mp, "Shrinking AG count in log recovery not supported");
 		return -EFSCORRUPTED;
 	}
+	if (mp->m_sb.sb_rgcount < orig_rgcount) {
+		xfs_warn(mp,
+ "Shrinking rtgroup count in log recovery not supported");
+		return -EFSCORRUPTED;
+	}
 
 	/*
 	 * If the last AG was grown or shrunk, we also need to update the
@@ -731,6 +738,17 @@ xlog_recover_do_primary_sb_buffer(
 	if (error)
 		return error;
 
+	/*
+	 * If the last rtgroup was grown or shrunk, we also need to update the
+	 * length in the in-core rtgroup structure and values depending on it.
+	 * Ignore this on any filesystem with zero rtgroups.
+	 */
+	if (orig_rgcount > 0) {
+		error = xfs_update_last_rtgroup_size(mp, orig_rgcount);
+		if (error)
+			return error;
+	}
+
 	/*
 	 * Initialize the new perags, and also update various block and inode
 	 * allocator setting based off the number of AGs or total blocks.
@@ -744,6 +762,13 @@ xlog_recover_do_primary_sb_buffer(
 		return error;
 	}
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
+
+	error = xfs_initialize_rtgroups(mp, orig_rgcount, mp->m_sb.sb_rgcount,
+			mp->m_sb.sb_rextents);
+	if (error) {
+		xfs_warn(mp, "Failed recovery rtgroup init: %d", error);
+		return error;
+	}
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 6cf4f00636a2d6..40beb8d75f26b1 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -25,6 +25,7 @@
 #include "xfs_alloc_btree.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_ag.h"
+#include "xfs_rtgroup.h"
 
 /* Convert an xfs_fsmap to an fsmap. */
 static void
@@ -735,7 +736,7 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
 		frec.start_daddr = info->end_daddr;
 	} else {
 		rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
-		frec.start_daddr = XFS_FSB_TO_BB(mp, rtbno);
+		frec.start_daddr = xfs_rtb_to_daddr(mp, rtbno);
 	}
 
 	rtbno = xfs_rtx_to_rtb(mp, rec->ar_extcount);
@@ -770,7 +771,7 @@ xfs_getfsmap_rtdev_rtbitmap(
 
 	/* Adjust the low key if we are continuing from where we left off. */
 	if (keys[0].fmr_length > 0) {
-		info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb);
+		info->low_daddr = xfs_rtb_to_daddr(mp, start_rtb);
 		if (info->low_daddr >= eofs)
 			return 0;
 	}
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 2dd2606fc7e3e4..9464eddf9212e9 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -36,6 +36,7 @@
 #include "xfs_ag.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
 #include "scrub/stats.h"
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
@@ -834,10 +835,17 @@ xfs_mountfs(
 		goto out_free_dir;
 	}
 
+	error = xfs_initialize_rtgroups(mp, 0, sbp->sb_rgcount,
+			mp->m_sb.sb_rextents);
+	if (error) {
+		xfs_warn(mp, "Failed rtgroup init: %d", error);
+		goto out_free_perag;
+	}
+
 	if (XFS_IS_CORRUPT(mp, !sbp->sb_logblocks)) {
 		xfs_warn(mp, "no log defined");
 		error = -EFSCORRUPTED;
-		goto out_free_perag;
+		goto out_free_rtgroup;
 	}
 
 	error = xfs_inodegc_register_shrinker(mp);
@@ -1072,6 +1080,8 @@ xfs_mountfs(
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_buftarg_drain(mp->m_logdev_targp);
 	xfs_buftarg_drain(mp->m_ddev_targp);
+ out_free_rtgroup:
+	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
  out_free_perag:
 	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
  out_free_dir:
@@ -1156,6 +1166,7 @@ xfs_unmountfs(
 	xfs_errortag_clearall(mp);
 #endif
 	shrinker_free(mp->m_inodegc_shrinker);
+	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
 	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
 	xfs_errortag_del(mp);
 	xfs_error_sysfs_del(mp);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 71ed04ddd737de..d491e31d33aac3 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -155,6 +155,7 @@ typedef struct xfs_mount {
 	uint8_t			m_agno_log;	/* log #ag's */
 	uint8_t			m_sectbb_log;	/* sectlog - BBSHIFT */
 	int8_t			m_rtxblklog;	/* log2 of rextsize, if possible */
+	int8_t			m_rgblklog;	/* log2 of rt group sz if possible */
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
 	uint			m_blockwmask;	/* blockwsize-1 */
@@ -183,12 +184,14 @@ typedef struct xfs_mount {
 	int			m_logbsize;	/* size of each log buffer */
 	uint			m_rsumlevels;	/* rt summary levels */
 	xfs_filblks_t		m_rsumblocks;	/* size of rt summary, FSBs */
+	uint32_t		m_rgblocks;	/* size of rtgroup in rtblocks */
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_qflags;	/* quota status flags */
 	uint64_t		m_features;	/* active filesystem features */
 	uint64_t		m_low_space[XFS_LOWSP_MAX];
 	uint64_t		m_low_rtexts[XFS_LOWSP_MAX];
 	uint64_t		m_rtxblkmask;	/* rt extent block mask */
+	uint64_t		m_rgblkmask;	/* rt group block mask */
 	struct xfs_ino_geometry	m_ino_geo;	/* inode geometry */
 	struct xfs_trans_resv	m_resv;		/* precomputed res values */
 						/* low free space thresholds */
@@ -391,6 +394,16 @@ __XFS_HAS_FEAT(large_extent_counts, NREXT64)
 __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE)
 __XFS_HAS_FEAT(metadir, METADIR)
 
+static inline bool xfs_has_rtgroups(struct xfs_mount *mp)
+{
+	return false;
+}
+
+static inline bool xfs_has_rtsb(struct xfs_mount *mp)
+{
+	return false;
+}
+
 /*
  * Some features are always on for v5 file systems, allow the compiler to
  * eliminiate dead code when building without v4 support.
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 46a920b192d191..917c1a5e8f3180 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -27,6 +27,7 @@
 #include "xfs_health.h"
 #include "xfs_da_format.h"
 #include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
 
 /*
  * Return whether there are any free extents in the size range given
@@ -1136,6 +1137,7 @@ xfs_rtmount_inodes(
 {
 	struct xfs_trans	*tp;
 	struct xfs_sb		*sbp = &mp->m_sb;
+	struct xfs_rtgroup	*rtg = NULL;
 	int			error;
 
 	error = xfs_trans_alloc_empty(mp, &tp);
@@ -1166,6 +1168,9 @@ xfs_rtmount_inodes(
 	if (error)
 		goto out_rele_summary;
 
+	while ((rtg = xfs_rtgroup_next(mp, rtg)))
+		rtg->rtg_extents = xfs_rtgroup_extents(mp, rtg_rgno(rtg));
+
 	error = xfs_alloc_rsum_cache(mp, sbp->sb_rbmblocks);
 	if (error)
 		goto out_rele_summary;
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 1b9d75a54c5ea2..8f530e69c18ae7 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -48,6 +48,7 @@
 #include "xfs_refcount.h"
 #include "xfs_metafile.h"
 #include "xfs_metadir.h"
+#include "xfs_rtgroup.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 0f3704f3c2e4e3..f66e5b590d7597 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -219,6 +219,7 @@ DEFINE_PERAG_REF_EVENT(xfs_perag_clear_inode_tag);
 DEFINE_PERAG_REF_EVENT(xfs_reclaim_inodes_count);
 
 TRACE_DEFINE_ENUM(XG_TYPE_AG);
+TRACE_DEFINE_ENUM(XG_TYPE_RTG);
 
 DECLARE_EVENT_CLASS(xfs_group_class,
 	TP_PROTO(struct xfs_group *xg, unsigned long caller_ip),

[PATCH 03/21] xfs: define locking primitives for realtime groups

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Define helper functions to lock all metadata inodes related to a
realtime group.  There's not much to look at now, but this will become
important when we add per-rtgroup metadata files and online fsck code
for them.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_rtgroup.c |   49 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_rtgroup.h |   16 ++++++++++++++
 2 files changed, 65 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index 9d3842e83c9366..e3f167ce54793a 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -149,3 +149,52 @@ xfs_update_last_rtgroup_size(
 	xfs_rtgroup_rele(rtg);
 	return 0;
 }
+
+/* Lock metadata inodes associated with this rt group. */
+void
+xfs_rtgroup_lock(
+	struct xfs_rtgroup	*rtg,
+	unsigned int		rtglock_flags)
+{
+	ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
+	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
+	       !(rtglock_flags & XFS_RTGLOCK_BITMAP));
+
+	if (rtglock_flags & XFS_RTGLOCK_BITMAP)
+		xfs_rtbitmap_lock(rtg_mount(rtg));
+	else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED)
+		xfs_rtbitmap_lock_shared(rtg_mount(rtg), XFS_RBMLOCK_BITMAP);
+}
+
+/* Unlock metadata inodes associated with this rt group. */
+void
+xfs_rtgroup_unlock(
+	struct xfs_rtgroup	*rtg,
+	unsigned int		rtglock_flags)
+{
+	ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
+	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
+	       !(rtglock_flags & XFS_RTGLOCK_BITMAP));
+
+	if (rtglock_flags & XFS_RTGLOCK_BITMAP)
+		xfs_rtbitmap_unlock(rtg_mount(rtg));
+	else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED)
+		xfs_rtbitmap_unlock_shared(rtg_mount(rtg), XFS_RBMLOCK_BITMAP);
+}
+
+/*
+ * Join realtime group metadata inodes to the transaction.  The ILOCKs will be
+ * released on transaction commit.
+ */
+void
+xfs_rtgroup_trans_join(
+	struct xfs_trans	*tp,
+	struct xfs_rtgroup	*rtg,
+	unsigned int		rtglock_flags)
+{
+	ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
+	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED));
+
+	if (rtglock_flags & XFS_RTGLOCK_BITMAP)
+		xfs_rtbitmap_trans_join(tp);
+}
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 8872c27a9585fd..7d82eb753fd097 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -197,6 +197,19 @@ xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno);
 
 int xfs_update_last_rtgroup_size(struct xfs_mount *mp,
 		xfs_rgnumber_t prev_rgcount);
+
+/* Lock the rt bitmap inode in exclusive mode */
+#define XFS_RTGLOCK_BITMAP		(1U << 0)
+/* Lock the rt bitmap inode in shared mode */
+#define XFS_RTGLOCK_BITMAP_SHARED	(1U << 1)
+
+#define XFS_RTGLOCK_ALL_FLAGS	(XFS_RTGLOCK_BITMAP | \
+				 XFS_RTGLOCK_BITMAP_SHARED)
+
+void xfs_rtgroup_lock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
+void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
+void xfs_rtgroup_trans_join(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
+		unsigned int rtglock_flags);
 #else
 static inline void xfs_free_rtgroups(struct xfs_mount *mp,
 		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno)
@@ -212,6 +225,9 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
 
 # define xfs_rtgroup_extents(mp, rgno)		(0)
 # define xfs_update_last_rtgroup_size(mp, rgno)	(-EOPNOTSUPP)
+# define xfs_rtgroup_lock(rtg, gf)		((void)0)
+# define xfs_rtgroup_unlock(rtg, gf)		((void)0)
+# define xfs_rtgroup_trans_join(tp, rtg, gf)	((void)0)
 #endif /* CONFIG_XFS_RT */
 
 #endif /* __LIBXFS_RTGROUP_H */

[PATCH 04/21] xfs: add a lockdep class key for rtgroup inodes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a dynamic lockdep class key for rtgroup inodes.  This will enable
lockdep to deduce inconsistencies in the rtgroup metadata ILOCK locking
order.  Each class can have 8 subclasses, and for now we will only have
2 inodes per group.  This enables rtgroup order and inode order checks
when nesting ILOCKs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_rtgroup.c |   52 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index e3f167ce54793a..39e07e98eda1e5 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -198,3 +198,55 @@ xfs_rtgroup_trans_join(
 	if (rtglock_flags & XFS_RTGLOCK_BITMAP)
 		xfs_rtbitmap_trans_join(tp);
 }
+
+#ifdef CONFIG_PROVE_LOCKING
+static struct lock_class_key xfs_rtginode_lock_class;
+
+static int
+xfs_rtginode_ilock_cmp_fn(
+	const struct lockdep_map	*m1,
+	const struct lockdep_map	*m2)
+{
+	const struct xfs_inode *ip1 =
+		container_of(m1, struct xfs_inode, i_lock.dep_map);
+	const struct xfs_inode *ip2 =
+		container_of(m2, struct xfs_inode, i_lock.dep_map);
+
+	if (ip1->i_projid < ip2->i_projid)
+		return -1;
+	if (ip1->i_projid > ip2->i_projid)
+		return 1;
+	return 0;
+}
+
+static inline void
+xfs_rtginode_ilock_print_fn(
+	const struct lockdep_map	*m)
+{
+	const struct xfs_inode *ip =
+		container_of(m, struct xfs_inode, i_lock.dep_map);
+
+	printk(KERN_CONT " rgno=%u", ip->i_projid);
+}
+
+/*
+ * Most of the time each of the RTG inode locks are only taken one at a time.
+ * But when committing deferred ops, more than one of a kind can be taken.
+ * However, deferred rt ops will be committed in rgno order so there is no
+ * potential for deadlocks.  The code here is needed to tell lockdep about this
+ * order.
+ */
+static inline void
+xfs_rtginode_lockdep_setup(
+	struct xfs_inode	*ip,
+	xfs_rgnumber_t		rgno,
+	enum xfs_rtg_inodes	type)
+{
+	lockdep_set_class_and_subclass(&ip->i_lock, &xfs_rtginode_lock_class,
+			type);
+	lock_set_cmp_fn(&ip->i_lock, xfs_rtginode_ilock_cmp_fn,
+			xfs_rtginode_ilock_print_fn);
+}
+#else
+#define xfs_rtginode_lockdep_setup(ip, rgno, type)	do { } while (0)
+#endif /* CONFIG_PROVE_LOCKING */

[PATCH 05/21] xfs: support caching rtgroup metadata inodes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create the necessary per-rtgroup infrastructure that we need to load
metadata inodes into memory.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_rtgroup.c |  123 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_rtgroup.h |   27 +++++++++
 fs/xfs/xfs_mount.h          |    1 
 fs/xfs/xfs_rtalloc.c        |   69 +++++++++++++++++++++++-
 4 files changed, 217 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index 39e07e98eda1e5..9aa8f5e5525d3d 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -30,6 +30,8 @@
 #include "xfs_icache.h"
 #include "xfs_rtgroup.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_metafile.h"
+#include "xfs_metadir.h"
 
 int
 xfs_rtgroup_alloc(
@@ -250,3 +252,124 @@ xfs_rtginode_lockdep_setup(
 #else
 #define xfs_rtginode_lockdep_setup(ip, rgno, type)	do { } while (0)
 #endif /* CONFIG_PROVE_LOCKING */
+
+struct xfs_rtginode_ops {
+	const char		*name;	/* short name */
+
+	enum xfs_metafile_type	metafile_type;
+
+	/* Does the fs have this feature? */
+	bool			(*enabled)(struct xfs_mount *mp);
+};
+
+static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
+};
+
+/* Return the shortname of this rtgroup inode. */
+const char *
+xfs_rtginode_name(
+	enum xfs_rtg_inodes	type)
+{
+	return xfs_rtginode_ops[type].name;
+}
+
+/* Return the metafile type of this rtgroup inode. */
+enum xfs_metafile_type
+xfs_rtginode_metafile_type(
+	enum xfs_rtg_inodes	type)
+{
+	return xfs_rtginode_ops[type].metafile_type;
+}
+
+/* Should this rtgroup inode be present? */
+bool
+xfs_rtginode_enabled(
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type)
+{
+	const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
+
+	if (!ops->enabled)
+		return true;
+	return ops->enabled(rtg_mount(rtg));
+}
+
+/* Load and existing rtgroup inode into the rtgroup structure. */
+int
+xfs_rtginode_load(
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type,
+	struct xfs_trans	*tp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	const char		*path;
+	struct xfs_inode	*ip;
+	const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
+	int			error;
+
+	if (!xfs_rtginode_enabled(rtg, type))
+		return 0;
+
+	if (!mp->m_rtdirip)
+		return -EFSCORRUPTED;
+
+	path = xfs_rtginode_path(rtg_rgno(rtg), type);
+	if (!path)
+		return -ENOMEM;
+	error = xfs_metadir_load(tp, mp->m_rtdirip, path, ops->metafile_type,
+			&ip);
+	kfree(path);
+
+	if (error)
+		return error;
+
+	if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
+			       ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) {
+		xfs_irele(ip);
+		return -EFSCORRUPTED;
+	}
+
+	if (XFS_IS_CORRUPT(mp, ip->i_projid != rtg_rgno(rtg))) {
+		xfs_irele(ip);
+		return -EFSCORRUPTED;
+	}
+
+	xfs_rtginode_lockdep_setup(ip, rtg_rgno(rtg), type);
+	rtg->rtg_inodes[type] = ip;
+	return 0;
+}
+
+/* Release an rtgroup metadata inode. */
+void
+xfs_rtginode_irele(
+	struct xfs_inode	**ipp)
+{
+	if (*ipp)
+		xfs_irele(*ipp);
+	*ipp = NULL;
+}
+
+/* Create the parent directory for all rtgroup inodes and load it. */
+int
+xfs_rtginode_mkdir_parent(
+	struct xfs_mount	*mp)
+{
+	if (!mp->m_metadirip)
+		return -EFSCORRUPTED;
+
+	return xfs_metadir_mkdir(mp->m_metadirip, "rtgroups", &mp->m_rtdirip);
+}
+
+/* Load the parent directory of all rtgroup inodes. */
+int
+xfs_rtginode_load_parent(
+	struct xfs_trans	*tp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+
+	if (!mp->m_metadirip)
+		return -EFSCORRUPTED;
+
+	return xfs_metadir_load(tp, mp->m_metadirip, "rtgroups",
+			XFS_METAFILE_DIR, &mp->m_rtdirip);
+}
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 7d82eb753fd097..2c894df723a786 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -11,12 +11,23 @@
 struct xfs_mount;
 struct xfs_trans;
 
+enum xfs_rtg_inodes {
+	XFS_RTGI_MAX,
+};
+
+#ifdef MAX_LOCKDEP_SUBCLASSES
+static_assert(XFS_RTGI_MAX <= MAX_LOCKDEP_SUBCLASSES);
+#endif
+
 /*
  * Realtime group incore structure, similar to the per-AG structure.
  */
 struct xfs_rtgroup {
 	struct xfs_group	rtg_group;
 
+	/* per-rtgroup metadata inodes */
+	struct xfs_inode	*rtg_inodes[1 /* hack */];
+
 	/* Number of blocks in this group */
 	xfs_rtxnum_t		rtg_extents;
 };
@@ -210,6 +221,22 @@ void xfs_rtgroup_lock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
 void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
 void xfs_rtgroup_trans_join(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
 		unsigned int rtglock_flags);
+
+int xfs_rtginode_mkdir_parent(struct xfs_mount *mp);
+int xfs_rtginode_load_parent(struct xfs_trans *tp);
+
+const char *xfs_rtginode_name(enum xfs_rtg_inodes type);
+enum xfs_metafile_type xfs_rtginode_metafile_type(enum xfs_rtg_inodes type);
+bool xfs_rtginode_enabled(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type);
+int xfs_rtginode_load(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
+		struct xfs_trans *tp);
+void xfs_rtginode_irele(struct xfs_inode **ipp);
+
+static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno,
+		enum xfs_rtg_inodes type)
+{
+	return kasprintf(GFP_KERNEL, "%u.%s", rgno, xfs_rtginode_name(type));
+}
 #else
 static inline void xfs_free_rtgroups(struct xfs_mount *mp,
 		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno)
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index d491e31d33aac3..0c90625374a8ee 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -128,6 +128,7 @@ typedef struct xfs_mount {
 	struct xfs_inode	*m_rsumip;	/* pointer to summary inode */
 	struct xfs_inode	*m_rootip;	/* pointer to root directory */
 	struct xfs_inode	*m_metadirip;	/* ptr to metadata directory */
+	struct xfs_inode	*m_rtdirip;	/* ptr to realtime metadir */
 	struct xfs_quotainfo	*m_quotainfo;	/* disk quota information */
 	struct xfs_buftarg	*m_ddev_targp;	/* data device */
 	struct xfs_buftarg	*m_logdev_targp;/* log device */
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 917c1a5e8f3180..96225313686414 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -28,6 +28,7 @@
 #include "xfs_da_format.h"
 #include "xfs_metafile.h"
 #include "xfs_rtgroup.h"
+#include "xfs_error.h"
 
 /*
  * Return whether there are any free extents in the size range given
@@ -652,6 +653,16 @@ xfs_rtallocate_extent_size(
 	return -ENOSPC;
 }
 
+static void
+xfs_rtunmount_rtg(
+	struct xfs_rtgroup	*rtg)
+{
+	int			i;
+
+	for (i = 0; i < XFS_RTGI_MAX; i++)
+		xfs_rtginode_irele(&rtg->rtg_inodes[i]);
+}
+
 static int
 xfs_alloc_rsum_cache(
 	struct xfs_mount	*mp,
@@ -1127,6 +1138,43 @@ xfs_rtmount_iread_extents(
 	return error;
 }
 
+static void
+xfs_rtgroup_unmount_inodes(
+	struct xfs_mount	*mp)
+{
+	struct xfs_rtgroup	*rtg = NULL;
+
+	while ((rtg = xfs_rtgroup_next(mp, rtg)))
+		xfs_rtunmount_rtg(rtg);
+	xfs_rtginode_irele(&mp->m_rtdirip);
+}
+
+static int
+xfs_rtmount_rtg(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_rtgroup	*rtg)
+{
+	int			error, i;
+
+	rtg->rtg_extents = xfs_rtgroup_extents(mp, rtg_rgno(rtg));
+
+	for (i = 0; i < XFS_RTGI_MAX; i++) {
+		error = xfs_rtginode_load(rtg, i, tp);
+		if (error)
+			return error;
+
+		if (rtg->rtg_inodes[i]) {
+			error = xfs_rtmount_iread_extents(tp,
+					rtg->rtg_inodes[i], 0);
+			if (error)
+				return error;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Get the bitmap and summary inodes and the summary cache into the mount
  * structure at mount time.
@@ -1168,15 +1216,28 @@ xfs_rtmount_inodes(
 	if (error)
 		goto out_rele_summary;
 
-	while ((rtg = xfs_rtgroup_next(mp, rtg)))
-		rtg->rtg_extents = xfs_rtgroup_extents(mp, rtg_rgno(rtg));
+	if (xfs_has_rtgroups(mp) && mp->m_sb.sb_rgcount > 0) {
+		error = xfs_rtginode_load_parent(tp);
+		if (error)
+			goto out_rele_summary;
+	}
+
+	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+		error = xfs_rtmount_rtg(mp, tp, rtg);
+		if (error) {
+			xfs_rtgroup_rele(rtg);
+			goto out_rele_inodes;
+		}
+	}
 
 	error = xfs_alloc_rsum_cache(mp, sbp->sb_rbmblocks);
 	if (error)
-		goto out_rele_summary;
+		goto out_rele_inodes;
 	xfs_trans_cancel(tp);
 	return 0;
 
+out_rele_inodes:
+	xfs_rtgroup_unmount_inodes(mp);
 out_rele_summary:
 	xfs_irele(mp->m_rsumip);
 out_rele_bitmap:
@@ -1191,6 +1252,8 @@ xfs_rtunmount_inodes(
 	struct xfs_mount	*mp)
 {
 	kvfree(mp->m_rsum_cache);
+
+	xfs_rtgroup_unmount_inodes(mp);
 	if (mp->m_rbmip)
 		xfs_irele(mp->m_rbmip);
 	if (mp->m_rsumip)

[PATCH 06/21] xfs: add rtgroup-based realtime scrubbing context management

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a state tracking structure and helpers to initialize the tracking
structure so that we can check metadata records against the realtime
space management metadata.  Right now this is limited to grabbing the
incore rtgroup object, but we'll eventually add to the tracking
structure the ILOCK state and btree cursors.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/common.c |   78 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/common.h |   30 +++++++++++++++++++
 fs/xfs/scrub/repair.c |   24 +++++++++++++++
 fs/xfs/scrub/repair.h |    7 ++++
 fs/xfs/scrub/scrub.c  |   29 ++++++++++++++++++
 fs/xfs/scrub/scrub.h  |   13 ++++++++
 6 files changed, 181 insertions(+)


diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index c26a3314237a69..5cbd94b56582a4 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -34,6 +34,7 @@
 #include "xfs_quota.h"
 #include "xfs_exchmaps.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -121,6 +122,17 @@ xchk_process_error(
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
+bool
+xchk_process_rt_error(
+	struct xfs_scrub	*sc,
+	xfs_rgnumber_t		rgno,
+	xfs_rgblock_t		rgbno,
+	int			*error)
+{
+	return __xchk_process_error(sc, rgno, rgbno, error,
+			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
+}
+
 bool
 xchk_xref_process_error(
 	struct xfs_scrub	*sc,
@@ -684,6 +696,72 @@ xchk_ag_init(
 	return 0;
 }
 
+#ifdef CONFIG_XFS_RT
+/*
+ * For scrubbing a realtime group, grab all the in-core resources we'll need to
+ * check the metadata, which means taking the ILOCK of the realtime group's
+ * metadata inodes.  Callers must not join these inodes to the transaction with
+ * non-zero lockflags or concurrency problems will result.  The @rtglock_flags
+ * argument takes XFS_RTGLOCK_* flags.
+ */
+int
+xchk_rtgroup_init(
+	struct xfs_scrub	*sc,
+	xfs_rgnumber_t		rgno,
+	struct xchk_rt		*sr)
+{
+	ASSERT(sr->rtg == NULL);
+	ASSERT(sr->rtlock_flags == 0);
+
+	sr->rtg = xfs_rtgroup_get(sc->mp, rgno);
+	if (!sr->rtg)
+		return -ENOENT;
+	return 0;
+}
+
+void
+xchk_rtgroup_lock(
+	struct xchk_rt		*sr,
+	unsigned int		rtglock_flags)
+{
+	xfs_rtgroup_lock(sr->rtg, rtglock_flags);
+	sr->rtlock_flags = rtglock_flags;
+}
+
+/*
+ * Unlock the realtime group.  This must be done /after/ committing (or
+ * cancelling) the scrub transaction.
+ */
+static void
+xchk_rtgroup_unlock(
+	struct xchk_rt		*sr)
+{
+	ASSERT(sr->rtg != NULL);
+
+	if (sr->rtlock_flags) {
+		xfs_rtgroup_unlock(sr->rtg, sr->rtlock_flags);
+		sr->rtlock_flags = 0;
+	}
+}
+
+/*
+ * Unlock the realtime group and release its resources.  This must be done
+ * /after/ committing (or cancelling) the scrub transaction.
+ */
+void
+xchk_rtgroup_free(
+	struct xfs_scrub	*sc,
+	struct xchk_rt		*sr)
+{
+	ASSERT(sr->rtg != NULL);
+
+	xchk_rtgroup_unlock(sr);
+
+	xfs_rtgroup_put(sr->rtg);
+	sr->rtg = NULL;
+}
+#endif /* CONFIG_XFS_RT */
+
 /* Per-scrubber setup functions */
 
 void
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index b2a81e85ded9cf..672ed48d4a9fc3 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -12,6 +12,8 @@ void xchk_trans_cancel(struct xfs_scrub *sc);
 
 bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		xfs_agblock_t bno, int *error);
+bool xchk_process_rt_error(struct xfs_scrub *sc, xfs_rgnumber_t rgno,
+		xfs_rgblock_t rgbno, int *error);
 bool xchk_fblock_process_error(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset, int *error);
 
@@ -118,6 +120,34 @@ xchk_ag_init_existing(
 	return error == -ENOENT ? -EFSCORRUPTED : error;
 }
 
+#ifdef CONFIG_XFS_RT
+
+/* All the locks we need to check an rtgroup. */
+#define XCHK_RTGLOCK_ALL	(XFS_RTGLOCK_BITMAP)
+
+int xchk_rtgroup_init(struct xfs_scrub *sc, xfs_rgnumber_t rgno,
+		struct xchk_rt *sr);
+
+static inline int
+xchk_rtgroup_init_existing(
+	struct xfs_scrub	*sc,
+	xfs_rgnumber_t		rgno,
+	struct xchk_rt		*sr)
+{
+	int			error = xchk_rtgroup_init(sc, rgno, sr);
+
+	return error == -ENOENT ? -EFSCORRUPTED : error;
+}
+
+void xchk_rtgroup_lock(struct xchk_rt *sr, unsigned int rtglock_flags);
+void xchk_rtgroup_free(struct xfs_scrub *sc, struct xchk_rt *sr);
+#else
+# define xchk_rtgroup_init(sc, rgno, sr)		(-EFSCORRUPTED)
+# define xchk_rtgroup_init_existing(sc, rgno, sr)	(-EFSCORRUPTED)
+# define xchk_rtgroup_lock(sc, lockflags)		do { } while (0)
+# define xchk_rtgroup_free(sc, sr)			do { } while (0)
+#endif /* CONFIG_XFS_RT */
+
 int xchk_ag_read_headers(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		struct xchk_ag *sa);
 void xchk_ag_btcur_free(struct xchk_ag *sa);
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index f80000d7755242..5fdd00029cd6c0 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -21,6 +21,7 @@
 #include "xfs_rmap.h"
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
+#include "xfs_rtgroup.h"
 #include "xfs_extent_busy.h"
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
@@ -952,6 +953,29 @@ xrep_ag_init(
 	return 0;
 }
 
+#ifdef CONFIG_XFS_RT
+/*
+ * Given a reference to a rtgroup structure, lock rtgroup btree inodes and
+ * create btree cursors.  Must only be called to repair a regular rt file.
+ */
+int
+xrep_rtgroup_init(
+	struct xfs_scrub	*sc,
+	struct xfs_rtgroup	*rtg,
+	struct xchk_rt		*sr,
+	unsigned int		rtglock_flags)
+{
+	ASSERT(sr->rtg == NULL);
+
+	xfs_rtgroup_lock(rtg, rtglock_flags);
+	sr->rtlock_flags = rtglock_flags;
+
+	/* Grab our own passive reference from the caller's ref. */
+	sr->rtg = xfs_rtgroup_hold(rtg);
+	return 0;
+}
+#endif /* CONFIG_XFS_RT */
+
 /* Reinitialize the per-AG block reservation for the AG we just fixed. */
 int
 xrep_reset_perag_resv(
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 90f9cb3b5ad8ba..4052185743910d 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -8,6 +8,7 @@
 
 #include "xfs_quota_defs.h"
 
+struct xfs_rtgroup;
 struct xchk_stats_run;
 
 static inline int xrep_notsupported(struct xfs_scrub *sc)
@@ -106,6 +107,12 @@ int xrep_setup_inode(struct xfs_scrub *sc, const struct xfs_imap *imap);
 void xrep_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
 int xrep_ag_init(struct xfs_scrub *sc, struct xfs_perag *pag,
 		struct xchk_ag *sa);
+#ifdef CONFIG_XFS_RT
+int xrep_rtgroup_init(struct xfs_scrub *sc, struct xfs_rtgroup *rtg,
+		struct xchk_rt *sr, unsigned int rtglock_flags);
+#else
+# define xrep_rtgroup_init(sc, rtg, sr, lockflags)	(-ENOSYS)
+#endif /* CONFIG_XFS_RT */
 
 /* Metadata revalidators */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 1ac33bea6f0a72..03770b9f905c3d 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -225,6 +225,8 @@ xchk_teardown(
 			xfs_trans_cancel(sc->tp);
 		sc->tp = NULL;
 	}
+	if (sc->sr.rtg)
+		xchk_rtgroup_free(sc, &sc->sr);
 	if (sc->ip) {
 		if (sc->ilock_flags)
 			xchk_iunlock(sc, sc->ilock_flags);
@@ -498,6 +500,33 @@ xchk_validate_inputs(
 		break;
 	case ST_GENERIC:
 		break;
+	case ST_RTGROUP:
+		if (sm->sm_ino || sm->sm_gen)
+			goto out;
+		if (xfs_has_rtgroups(mp)) {
+			/*
+			 * On a rtgroups filesystem, there won't be an rtbitmap
+			 * or rtsummary file for group 0 unless there's
+			 * actually a realtime volume attached.  However, older
+			 * xfs_scrub always calls the rtbitmap/rtsummary
+			 * scrubbers with sm_agno==0 so transform the error
+			 * code to ENOENT.
+			 */
+			if (sm->sm_agno >= mp->m_sb.sb_rgcount) {
+				if (sm->sm_agno == 0)
+					error = -ENOENT;
+				goto out;
+			}
+		} else {
+			/*
+			 * Prior to rtgroups, the rtbitmap/rtsummary scrubbers
+			 * accepted sm_agno==0, so we still accept that for
+			 * scrubbing pre-rtgroups filesystems.
+			 */
+			if (sm->sm_agno != 0)
+				goto out;
+		}
+		break;
 	default:
 		goto out;
 	}
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index c688ff4fc7fc4c..f73c6d0d90a11a 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -74,6 +74,7 @@ enum xchk_type {
 	ST_FS,		/* per-FS metadata */
 	ST_INODE,	/* per-inode metadata */
 	ST_GENERIC,	/* determined by the scrubber */
+	ST_RTGROUP,	/* rtgroup metadata */
 };
 
 struct xchk_meta_ops {
@@ -118,6 +119,15 @@ struct xchk_ag {
 	struct xfs_btree_cur	*refc_cur;
 };
 
+/* Inode lock state for the RT volume. */
+struct xchk_rt {
+	/* incore rtgroup, if applicable */
+	struct xfs_rtgroup	*rtg;
+
+	/* XFS_RTGLOCK_* lock state if locked */
+	unsigned int		rtlock_flags;
+};
+
 struct xfs_scrub {
 	/* General scrub state. */
 	struct xfs_mount		*mp;
@@ -179,6 +189,9 @@ struct xfs_scrub {
 
 	/* State tracking for single-AG operations. */
 	struct xchk_ag			sa;
+
+	/* State tracking for realtime operations. */
+	struct xchk_rt			sr;
 };
 
 /* XCHK state flags grow up from zero, XREP state flags grown down from 2^31 */

[PATCH 07/21] xfs: add a xfs_bmap_free_rtblocks helper

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Split the RT extent freeing logic from xfs_bmap_del_extent_real because
it will become more complicated when adding RT group.

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_bmap.c |   33 ++++++++++++++++++++++-----------
 1 file changed, 22 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7805a36e98c491..4d9930ef42d9ae 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5116,6 +5116,27 @@ xfs_bmap_del_extent_cow(
 	ip->i_delayed_blks -= del->br_blockcount;
 }
 
+static int
+xfs_bmap_free_rtblocks(
+	struct xfs_trans	*tp,
+	struct xfs_bmbt_irec	*del)
+{
+	int			error;
+
+	/*
+	 * Ensure the bitmap and summary inodes are locked and joined to the
+	 * transaction before modifying them.
+	 */
+	if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
+		tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
+		xfs_rtbitmap_lock(tp->t_mountp);
+		xfs_rtbitmap_trans_join(tp);
+	}
+
+	error = xfs_rtfree_blocks(tp, del->br_startblock, del->br_blockcount);
+	return error;
+}
+
 /*
  * Called by xfs_bmapi to update file extent records and the btree
  * after removing space.
@@ -5331,17 +5352,7 @@ xfs_bmap_del_extent_real(
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
 			xfs_refcount_decrease_extent(tp, del);
 		} else if (xfs_ifork_is_realtime(ip, whichfork)) {
-			/*
-			 * Ensure the bitmap and summary inodes are locked
-			 * and joined to the transaction before modifying them.
-			 */
-			if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
-				tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
-				xfs_rtbitmap_lock(mp);
-				xfs_rtbitmap_trans_join(tp);
-			}
-			error = xfs_rtfree_blocks(tp, del->br_startblock,
-					del->br_blockcount);
+			error = xfs_bmap_free_rtblocks(tp, del);
 		} else {
 			unsigned int	efi_flags = 0;
 

[PATCH 08/21] xfs: add a xfs_qm_unmount_rt helper

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

RT group enabled file systems fix the bug where we pointlessly attach
quotas to the RT bitmap and summary files.  Split the code to detach the
quotas into a helper, make it conditional and document the differing
behavior for RT group and pre-RT group file systems.

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_qm.c |   22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index b94d6f192e7258..3663c4f89ed8a1 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -29,6 +29,7 @@
 #include "xfs_health.h"
 #include "xfs_da_format.h"
 #include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
 
 /*
  * The global quota manager. There is only one of these for the entire
@@ -210,6 +211,16 @@ xfs_qm_unmount(
 	}
 }
 
+static void
+xfs_qm_unmount_rt(
+	struct xfs_mount	*mp)
+{
+	if (mp->m_rbmip)
+		xfs_qm_dqdetach(mp->m_rbmip);
+	if (mp->m_rsumip)
+		xfs_qm_dqdetach(mp->m_rsumip);
+}
+
 /*
  * Called from the vfsops layer.
  */
@@ -223,10 +234,13 @@ xfs_qm_unmount_quotas(
 	 */
 	ASSERT(mp->m_rootip);
 	xfs_qm_dqdetach(mp->m_rootip);
-	if (mp->m_rbmip)
-		xfs_qm_dqdetach(mp->m_rbmip);
-	if (mp->m_rsumip)
-		xfs_qm_dqdetach(mp->m_rsumip);
+
+	/*
+	 * For pre-RTG file systems, the RT inodes have quotas attached,
+	 * detach them now.
+	 */
+	if (!xfs_has_rtgroups(mp))
+		xfs_qm_unmount_rt(mp);
 
 	/*
 	 * Release the quota inodes.

[PATCH 09/21] xfs: factor out a xfs_growfs_rt_alloc_blocks helper

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Split out a helper to allocate or grow the rtbitmap and rtsummary files
in preparation of per-RT group bitmap and summary files.

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_rtalloc.c |   56 +++++++++++++++++++++++++++++++++++---------------
 1 file changed, 39 insertions(+), 17 deletions(-)


diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 96225313686414..9a451f88bf4647 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -875,6 +875,43 @@ xfs_last_rt_bmblock(
 	return bmbno;
 }
 
+/*
+ * Allocate space to the bitmap and summary files, as necessary.
+ */
+static int
+xfs_growfs_rt_alloc_blocks(
+	struct xfs_mount	*mp,
+	xfs_rfsblock_t		nrblocks,
+	xfs_agblock_t		rextsize,
+	xfs_extlen_t		*nrbmblocks)
+{
+	struct xfs_inode	*rbmip = mp->m_rbmip;
+	struct xfs_inode	*rsumip = mp->m_rsumip;
+	xfs_rtxnum_t		nrextents = div_u64(nrblocks, rextsize);
+	xfs_extlen_t		orbmblocks;
+	xfs_extlen_t		orsumblocks;
+	xfs_extlen_t		nrsumblocks;
+	int			error;
+
+	/*
+	 * Get the old block counts for bitmap and summary inodes.
+	 * These can't change since other growfs callers are locked out.
+	 */
+	orbmblocks = XFS_B_TO_FSB(mp, rbmip->i_disk_size);
+	orsumblocks = XFS_B_TO_FSB(mp, rsumip->i_disk_size);
+
+	*nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents);
+	nrsumblocks = xfs_rtsummary_blockcount(mp,
+		xfs_compute_rextslog(nrextents) + 1, *nrbmblocks);
+
+	error = xfs_rtfile_initialize_blocks(rbmip, orbmblocks,
+			*nrbmblocks, NULL);
+	if (error)
+		return error;
+	return xfs_rtfile_initialize_blocks(rsumip, orsumblocks,
+			nrsumblocks, NULL);
+}
+
 /*
  * Grow the realtime area of the filesystem.
  */
@@ -889,8 +926,6 @@ xfs_growfs_rt(
 	xfs_extlen_t	nrbmblocks;	/* new number of rt bitmap blocks */
 	xfs_rtxnum_t	nrextents;	/* new number of realtime extents */
 	xfs_extlen_t	nrsumblocks;	/* new number of summary blocks */
-	xfs_extlen_t	rbmblocks;	/* current number of rt bitmap blocks */
-	xfs_extlen_t	rsumblocks;	/* current number of rt summary blks */
 	uint8_t		*rsum_cache;	/* old summary cache */
 	xfs_agblock_t	old_rextsize = mp->m_sb.sb_rextsize;
 
@@ -963,21 +998,8 @@ xfs_growfs_rt(
 		goto out_unlock;
 	}
 
-	/*
-	 * Get the old block counts for bitmap and summary inodes.
-	 * These can't change since other growfs callers are locked out.
-	 */
-	rbmblocks = XFS_B_TO_FSB(mp, mp->m_rbmip->i_disk_size);
-	rsumblocks = XFS_B_TO_FSB(mp, mp->m_rsumip->i_disk_size);
-	/*
-	 * Allocate space to the bitmap and summary files, as necessary.
-	 */
-	error = xfs_rtfile_initialize_blocks(mp->m_rbmip, rbmblocks,
-			nrbmblocks, NULL);
-	if (error)
-		goto out_unlock;
-	error = xfs_rtfile_initialize_blocks(mp->m_rsumip, rsumblocks,
-			nrsumblocks, NULL);
+	error = xfs_growfs_rt_alloc_blocks(mp, in->newblocks, in->extsize,
+			&nrbmblocks);
 	if (error)
 		goto out_unlock;
 

[PATCH 10/21] xfs: cleanup xfs_getfsmap_rtdev_rtbitmap

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Use mp->m_sb.sb_rblocks to calculate the end instead of sb_rextents that
needs a conversion, use consistent names to xfs_rtblock_t types, and
only calculated them by the time they are needed.  Remove the pointless
"high" local variable that only has a single user.

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 |   25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)


diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 40beb8d75f26b1..3d42153b4bdb29 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -754,30 +754,29 @@ xfs_getfsmap_rtdev_rtbitmap(
 
 	struct xfs_rtalloc_rec		ahigh = { 0 };
 	struct xfs_mount		*mp = tp->t_mountp;
-	xfs_rtblock_t			start_rtb;
-	xfs_rtblock_t			end_rtb;
-	xfs_rtxnum_t			high;
+	xfs_rtblock_t			start_rtbno, end_rtbno;
 	uint64_t			eofs;
 	int				error;
 
-	eofs = XFS_FSB_TO_BB(mp, xfs_rtx_to_rtb(mp, mp->m_sb.sb_rextents));
+	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
 	if (keys[0].fmr_physical >= eofs)
 		return 0;
-	start_rtb = XFS_BB_TO_FSBT(mp,
-				keys[0].fmr_physical + keys[0].fmr_length);
-	end_rtb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
 
 	info->missing_owner = XFS_FMR_OWN_UNKNOWN;
 
 	/* Adjust the low key if we are continuing from where we left off. */
+	start_rtbno = xfs_daddr_to_rtb(mp,
+			keys[0].fmr_physical + keys[0].fmr_length);
 	if (keys[0].fmr_length > 0) {
-		info->low_daddr = xfs_rtb_to_daddr(mp, start_rtb);
+		info->low_daddr = xfs_rtb_to_daddr(mp, start_rtbno);
 		if (info->low_daddr >= eofs)
 			return 0;
 	}
 
-	trace_xfs_fsmap_low_linear_key(mp, info->dev, start_rtb);
-	trace_xfs_fsmap_high_linear_key(mp, info->dev, end_rtb);
+	end_rtbno = xfs_daddr_to_rtb(mp, min(eofs - 1, keys[1].fmr_physical));
+
+	trace_xfs_fsmap_low_linear_key(mp, info->dev, start_rtbno);
+	trace_xfs_fsmap_high_linear_key(mp, info->dev, end_rtbno);
 
 	xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);
 
@@ -785,9 +784,9 @@ xfs_getfsmap_rtdev_rtbitmap(
 	 * Set up query parameters to return free rtextents covering the range
 	 * we want.
 	 */
-	high = xfs_rtb_to_rtxup(mp, end_rtb);
-	error = xfs_rtalloc_query_range(mp, tp, xfs_rtb_to_rtx(mp, start_rtb),
-			high, xfs_getfsmap_rtdev_rtbitmap_helper, info);
+	error = xfs_rtalloc_query_range(mp, tp, xfs_rtb_to_rtx(mp, start_rtbno),
+			xfs_rtb_to_rtxup(mp, end_rtbno),
+			xfs_getfsmap_rtdev_rtbitmap_helper, info);
 	if (error)
 		goto err;
 

[PATCH 11/21] xfs: split xfs_trim_rtdev_extents

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Split xfs_trim_rtdev_extents into two parts to prepare for reusing the
main validation also for RT group aware file systems.

Use the fully features xfs_daddr_to_rtb helper to convert from a daddr
to a xfs_rtblock_t to prepare for segmented addressing in RT 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/xfs_discard.c |   57 ++++++++++++++++++++++++++++----------------------
 1 file changed, 32 insertions(+), 25 deletions(-)


diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 019371c865d22a..412e3045561f13 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -21,6 +21,7 @@
 #include "xfs_ag.h"
 #include "xfs_health.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
 
 /*
  * Notes on an efficient, low latency fstrim algorithm
@@ -548,44 +549,23 @@ xfs_trim_gather_rtextent(
 }
 
 static int
-xfs_trim_rtdev_extents(
+xfs_trim_rtextents(
 	struct xfs_mount	*mp,
-	xfs_daddr_t		start,
-	xfs_daddr_t		end,
+	xfs_rtxnum_t		low,
+	xfs_rtxnum_t		high,
 	xfs_daddr_t		minlen)
 {
 	struct xfs_trim_rtdev	tr = {
 		.minlen_fsb	= XFS_BB_TO_FSB(mp, minlen),
+		.extent_list	= LIST_HEAD_INIT(tr.extent_list),
 	};
-	xfs_rtxnum_t		low, high;
 	struct xfs_trans	*tp;
-	xfs_daddr_t		rtdev_daddr;
 	int			error;
 
-	INIT_LIST_HEAD(&tr.extent_list);
-
-	/* Shift the start and end downwards to match the rt device. */
-	rtdev_daddr = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
-	if (start > rtdev_daddr)
-		start -= rtdev_daddr;
-	else
-		start = 0;
-
-	if (end <= rtdev_daddr)
-		return 0;
-	end -= rtdev_daddr;
-
 	error = xfs_trans_alloc_empty(mp, &tp);
 	if (error)
 		return error;
 
-	end = min_t(xfs_daddr_t, end,
-			XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks) - 1);
-
-	/* Convert the rt blocks to rt extents */
-	low = xfs_rtb_to_rtxup(mp, XFS_BB_TO_FSB(mp, start));
-	high = xfs_rtb_to_rtx(mp, XFS_BB_TO_FSBT(mp, end));
-
 	/*
 	 * Walk the free ranges between low and high.  The query_range function
 	 * trims the extents returned.
@@ -620,6 +600,33 @@ xfs_trim_rtdev_extents(
 	xfs_trans_cancel(tp);
 	return error;
 }
+
+static int
+xfs_trim_rtdev_extents(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		start,
+	xfs_daddr_t		end,
+	xfs_daddr_t		minlen)
+{
+	xfs_rtblock_t		start_rtbno, end_rtbno;
+	xfs_rtxnum_t		start_rtx, end_rtx;
+
+	/* Shift the start and end downwards to match the rt device. */
+	start_rtbno = xfs_daddr_to_rtb(mp, start);
+	if (start_rtbno > mp->m_sb.sb_dblocks)
+		start_rtbno -= mp->m_sb.sb_dblocks;
+	else
+		start_rtbno = 0;
+	start_rtx = xfs_rtb_to_rtx(mp, start_rtbno);
+
+	end_rtbno = xfs_daddr_to_rtb(mp, end);
+	if (end_rtbno <= mp->m_sb.sb_dblocks)
+		return 0;
+	end_rtbno -= mp->m_sb.sb_dblocks;
+	end_rtx = xfs_rtb_to_rtx(mp, end_rtbno + mp->m_sb.sb_rextsize - 1);
+
+	return xfs_trim_rtextents(mp, start_rtx, end_rtx, minlen);
+}
 #else
 # define xfs_trim_rtdev_extents(...)	(-EOPNOTSUPP)
 #endif /* CONFIG_XFS_RT */

[PATCH 12/21] xfs: move RT bitmap and summary information to the rtgroup

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Move the pointers to the RT bitmap and summary inodes as well as the
summary cache to the rtgroups structure to prepare for having a
separate bitmap and summary inodes for each rtgroup.

Code using the inodes now needs to operate on a rtgroup.  Where easily
possible such code is converted to iterate over all rtgroups, else
rtgroup 0 (the only one that can currently exist) is hardcoded.

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_bmap.c        |   13 +-
 fs/xfs/libxfs/xfs_rtbitmap.c    |  142 ++++++------------
 fs/xfs/libxfs/xfs_rtbitmap.h    |   64 +++-----
 fs/xfs/libxfs/xfs_rtgroup.c     |   80 +++++++---
 fs/xfs/libxfs/xfs_rtgroup.h     |   14 ++
 fs/xfs/scrub/bmap.c             |   13 ++
 fs/xfs/scrub/fscounters.c       |   25 ++-
 fs/xfs/scrub/repair.c           |    2 
 fs/xfs/scrub/rtbitmap.c         |   45 +++---
 fs/xfs/scrub/rtsummary.c        |   93 ++++++------
 fs/xfs/scrub/rtsummary_repair.c |    7 -
 fs/xfs/scrub/scrub.c            |    4 
 fs/xfs/xfs_discard.c            |   45 ++++--
 fs/xfs/xfs_fsmap.c              |   75 ++++++---
 fs/xfs/xfs_mount.h              |   10 -
 fs/xfs/xfs_qm.c                 |   13 +-
 fs/xfs/xfs_rtalloc.c            |  314 ++++++++++++++++++---------------------
 17 files changed, 502 insertions(+), 457 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 4d9930ef42d9ae..7ba75b4d161618 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5121,19 +5121,26 @@ xfs_bmap_free_rtblocks(
 	struct xfs_trans	*tp,
 	struct xfs_bmbt_irec	*del)
 {
+	struct xfs_rtgroup	*rtg;
 	int			error;
 
+	rtg = xfs_rtgroup_grab(tp->t_mountp, 0);
+	if (!rtg)
+		return -EIO;
+
 	/*
 	 * Ensure the bitmap and summary inodes are locked and joined to the
 	 * transaction before modifying them.
 	 */
 	if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
 		tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
-		xfs_rtbitmap_lock(tp->t_mountp);
-		xfs_rtbitmap_trans_join(tp);
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP);
+		xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_BITMAP);
 	}
 
-	error = xfs_rtfree_blocks(tp, del->br_startblock, del->br_blockcount);
+	error = xfs_rtfree_blocks(tp, rtg, del->br_startblock,
+			del->br_blockcount);
+	xfs_rtgroup_rele(rtg);
 	return error;
 }
 
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 27a4472402bacd..c54ac160b90994 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -90,12 +90,12 @@ xfs_rtbuf_get(
 	if (issum) {
 		cbpp = &args->sumbp;
 		coffp = &args->sumoff;
-		ip = mp->m_rsumip;
+		ip = args->rtg->rtg_inodes[XFS_RTGI_SUMMARY];
 		type = XFS_BLFT_RTSUMMARY_BUF;
 	} else {
 		cbpp = &args->rbmbp;
 		coffp = &args->rbmoff;
-		ip = mp->m_rbmip;
+		ip = args->rtg->rtg_inodes[XFS_RTGI_BITMAP];
 		type = XFS_BLFT_RTBITMAP_BUF;
 	}
 
@@ -503,6 +503,7 @@ xfs_rtmodify_summary(
 {
 	struct xfs_mount	*mp = args->mp;
 	xfs_rtsumoff_t		so = xfs_rtsumoffs(mp, log, bbno);
+	uint8_t			*rsum_cache = args->rtg->rtg_rsum_cache;
 	unsigned int		infoword;
 	xfs_suminfo_t		val;
 	int			error;
@@ -514,11 +515,11 @@ xfs_rtmodify_summary(
 	infoword = xfs_rtsumoffs_to_infoword(mp, so);
 	val = xfs_suminfo_add(args, infoword, delta);
 
-	if (mp->m_rsum_cache) {
-		if (val == 0 && log + 1 == mp->m_rsum_cache[bbno])
-			mp->m_rsum_cache[bbno] = log;
-		if (val != 0 && log >= mp->m_rsum_cache[bbno])
-			mp->m_rsum_cache[bbno] = log + 1;
+	if (rsum_cache) {
+		if (val == 0 && log + 1 == rsum_cache[bbno])
+			rsum_cache[bbno] = log;
+		if (val != 0 && log >= rsum_cache[bbno])
+			rsum_cache[bbno] = log + 1;
 	}
 
 	xfs_trans_log_rtsummary(args, infoword);
@@ -737,7 +738,7 @@ xfs_rtfree_range(
 	/*
 	 * Find the next allocated block (end of allocated extent).
 	 */
-	error = xfs_rtfind_forw(args, end, mp->m_sb.sb_rextents - 1,
+	error = xfs_rtfind_forw(args, end, args->rtg->rtg_extents - 1,
 			&postblock);
 	if (error)
 		return error;
@@ -961,19 +962,22 @@ xfs_rtcheck_alloc_range(
 int
 xfs_rtfree_extent(
 	struct xfs_trans	*tp,	/* transaction pointer */
+	struct xfs_rtgroup	*rtg,
 	xfs_rtxnum_t		start,	/* starting rtext number to free */
 	xfs_rtxlen_t		len)	/* length of extent freed */
 {
 	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
 	struct xfs_rtalloc_args	args = {
 		.mp		= mp,
 		.tp		= tp,
+		.rtg		= rtg,
 	};
 	int			error;
 	struct timespec64	atime;
 
-	ASSERT(mp->m_rbmip->i_itemp != NULL);
-	xfs_assert_ilocked(mp->m_rbmip, XFS_ILOCK_EXCL);
+	ASSERT(rbmip->i_itemp != NULL);
+	xfs_assert_ilocked(rbmip, XFS_ILOCK_EXCL);
 
 	error = xfs_rtcheck_alloc_range(&args, start, len);
 	if (error)
@@ -996,13 +1000,13 @@ xfs_rtfree_extent(
 	 */
 	if (tp->t_frextents_delta + mp->m_sb.sb_frextents ==
 	    mp->m_sb.sb_rextents) {
-		if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM))
-			mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
+		if (!(rbmip->i_diflags & XFS_DIFLAG_NEWRTBM))
+			rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
 
-		atime = inode_get_atime(VFS_I(mp->m_rbmip));
+		atime = inode_get_atime(VFS_I(rbmip));
 		atime.tv_sec = 0;
-		inode_set_atime_to_ts(VFS_I(mp->m_rbmip), atime);
-		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
+		inode_set_atime_to_ts(VFS_I(rbmip), atime);
+		xfs_trans_log_inode(tp, rbmip, XFS_ILOG_CORE);
 	}
 	error = 0;
 out:
@@ -1018,6 +1022,7 @@ xfs_rtfree_extent(
 int
 xfs_rtfree_blocks(
 	struct xfs_trans	*tp,
+	struct xfs_rtgroup	*rtg,
 	xfs_fsblock_t		rtbno,
 	xfs_filblks_t		rtlen)
 {
@@ -1038,21 +1043,23 @@ xfs_rtfree_blocks(
 		return -EIO;
 	}
 
-	return xfs_rtfree_extent(tp, xfs_rtb_to_rtx(mp, rtbno),
-			xfs_rtb_to_rtx(mp, rtlen));
+	return xfs_rtfree_extent(tp, rtg, xfs_rtb_to_rtx(mp, rtbno),
+			xfs_extlen_to_rtxlen(mp, rtlen));
 }
 
 /* Find all the free records within a given range. */
 int
 xfs_rtalloc_query_range(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	xfs_rtxnum_t			start,
 	xfs_rtxnum_t			end,
 	xfs_rtalloc_query_range_fn	fn,
 	void				*priv)
 {
+	struct xfs_mount		*mp = rtg_mount(rtg);
 	struct xfs_rtalloc_args		args = {
+		.rtg			= rtg,
 		.mp			= mp,
 		.tp			= tp,
 	};
@@ -1060,10 +1067,10 @@ xfs_rtalloc_query_range(
 
 	if (start > end)
 		return -EINVAL;
-	if (start == end || start >= mp->m_sb.sb_rextents)
+	if (start == end || start >= rtg->rtg_extents)
 		return 0;
 
-	end = min(end, mp->m_sb.sb_rextents - 1);
+	end = min(end, rtg->rtg_extents - 1);
 
 	/* Iterate the bitmap, looking for discrepancies. */
 	while (start <= end) {
@@ -1086,7 +1093,7 @@ xfs_rtalloc_query_range(
 			rec.ar_startext = start;
 			rec.ar_extcount = rtend - start + 1;
 
-			error = fn(mp, tp, &rec, priv);
+			error = fn(rtg, tp, &rec, priv);
 			if (error)
 				break;
 		}
@@ -1101,26 +1108,27 @@ xfs_rtalloc_query_range(
 /* Find all the free records. */
 int
 xfs_rtalloc_query_all(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	xfs_rtalloc_query_range_fn	fn,
 	void				*priv)
 {
-	return xfs_rtalloc_query_range(mp, tp, 0, mp->m_sb.sb_rextents - 1, fn,
+	return xfs_rtalloc_query_range(rtg, tp, 0, rtg->rtg_extents - 1, fn,
 			priv);
 }
 
 /* Is the given extent all free? */
 int
 xfs_rtalloc_extent_is_free(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	xfs_rtxnum_t			start,
 	xfs_rtxlen_t			len,
 	bool				*is_free)
 {
 	struct xfs_rtalloc_args		args = {
-		.mp			= mp,
+		.mp			= rtg_mount(rtg),
+		.rtg			= rtg,
 		.tp			= tp,
 	};
 	xfs_rtxnum_t			end;
@@ -1161,65 +1169,6 @@ xfs_rtsummary_blockcount(
 	return XFS_B_TO_FSB(mp, rsumwords << XFS_WORDLOG);
 }
 
-/* Lock both realtime free space metadata inodes for a freespace update. */
-void
-xfs_rtbitmap_lock(
-	struct xfs_mount	*mp)
-{
-	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
-	xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
-}
-
-/*
- * Join both realtime free space metadata inodes to the transaction.  The
- * ILOCKs will be released on transaction commit.
- */
-void
-xfs_rtbitmap_trans_join(
-	struct xfs_trans	*tp)
-{
-	xfs_trans_ijoin(tp, tp->t_mountp->m_rbmip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, tp->t_mountp->m_rsumip, XFS_ILOCK_EXCL);
-}
-
-/* Unlock both realtime free space metadata inodes after a freespace update. */
-void
-xfs_rtbitmap_unlock(
-	struct xfs_mount	*mp)
-{
-	xfs_iunlock(mp->m_rsumip, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
-	xfs_iunlock(mp->m_rbmip, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
-}
-
-/*
- * Lock the realtime free space metadata inodes for a freespace scan.  Callers
- * must walk metadata blocks in order of increasing file offset.
- */
-void
-xfs_rtbitmap_lock_shared(
-	struct xfs_mount	*mp,
-	unsigned int		rbmlock_flags)
-{
-	if (rbmlock_flags & XFS_RBMLOCK_BITMAP)
-		xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
-
-	if (rbmlock_flags & XFS_RBMLOCK_SUMMARY)
-		xfs_ilock(mp->m_rsumip, XFS_ILOCK_SHARED | XFS_ILOCK_RTSUM);
-}
-
-/* Unlock the realtime free space metadata inodes after a freespace scan. */
-void
-xfs_rtbitmap_unlock_shared(
-	struct xfs_mount	*mp,
-	unsigned int		rbmlock_flags)
-{
-	if (rbmlock_flags & XFS_RBMLOCK_SUMMARY)
-		xfs_iunlock(mp->m_rsumip, XFS_ILOCK_SHARED | XFS_ILOCK_RTSUM);
-
-	if (rbmlock_flags & XFS_RBMLOCK_BITMAP)
-		xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
-}
-
 static int
 xfs_rtfile_alloc_blocks(
 	struct xfs_inode	*ip,
@@ -1260,21 +1209,25 @@ xfs_rtfile_alloc_blocks(
 /* Get a buffer for the block. */
 static int
 xfs_rtfile_initialize_block(
-	struct xfs_inode	*ip,
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type,
 	xfs_fsblock_t		fsbno,
 	void			*data)
 {
-	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_inode	*ip = rtg->rtg_inodes[type];
 	struct xfs_trans	*tp;
 	struct xfs_buf		*bp;
 	const size_t		copylen = mp->m_blockwsize << XFS_WORDLOG;
 	enum xfs_blft		buf_type;
 	int			error;
 
-	if (ip == mp->m_rsumip)
-		buf_type = XFS_BLFT_RTSUMMARY_BUF;
-	else
+	if (type == XFS_RTGI_BITMAP)
 		buf_type = XFS_BLFT_RTBITMAP_BUF;
+	else if (type == XFS_RTGI_SUMMARY)
+		buf_type = XFS_BLFT_RTSUMMARY_BUF;
+	else
+		return -EINVAL;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtzero, 0, 0, 0, &tp);
 	if (error)
@@ -1306,12 +1259,13 @@ xfs_rtfile_initialize_block(
  */
 int
 xfs_rtfile_initialize_blocks(
-	struct xfs_inode	*ip,		/* inode (bitmap/summary) */
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type,
 	xfs_fileoff_t		offset_fsb,	/* offset to start from */
 	xfs_fileoff_t		end_fsb,	/* offset to allocate to */
 	void			*data)		/* data to fill the blocks */
 {
-	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_mount	*mp = rtg_mount(rtg);
 	const size_t		copylen = mp->m_blockwsize << XFS_WORDLOG;
 
 	while (offset_fsb < end_fsb) {
@@ -1319,8 +1273,8 @@ xfs_rtfile_initialize_blocks(
 		xfs_filblks_t		i;
 		int			error;
 
-		error = xfs_rtfile_alloc_blocks(ip, offset_fsb,
-				end_fsb - offset_fsb, &map);
+		error = xfs_rtfile_alloc_blocks(rtg->rtg_inodes[type],
+				offset_fsb, end_fsb - offset_fsb, &map);
 		if (error)
 			return error;
 
@@ -1330,7 +1284,7 @@ xfs_rtfile_initialize_blocks(
 		 * Do this one block per transaction, to keep it simple.
 		 */
 		for (i = 0; i < map.br_blockcount; i++) {
-			error = xfs_rtfile_initialize_block(ip,
+			error = xfs_rtfile_initialize_block(rtg, type,
 					map.br_startblock + i, data);
 			if (error)
 				return error;
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 140513d1d6bcf1..b3cbc56aa255ed 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -6,7 +6,10 @@
 #ifndef __XFS_RTBITMAP_H__
 #define	__XFS_RTBITMAP_H__
 
+#include "xfs_rtgroup.h"
+
 struct xfs_rtalloc_args {
+	struct xfs_rtgroup	*rtg;
 	struct xfs_mount	*mp;
 	struct xfs_trans	*tp;
 
@@ -268,7 +271,7 @@ struct xfs_rtalloc_rec {
 };
 
 typedef int (*xfs_rtalloc_query_range_fn)(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	const struct xfs_rtalloc_rec	*rec,
 	void				*priv);
@@ -291,53 +294,37 @@ int xfs_rtmodify_summary(struct xfs_rtalloc_args *args, int log,
 		xfs_fileoff_t bbno, int delta);
 int xfs_rtfree_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start,
 		xfs_rtxlen_t len);
-int xfs_rtalloc_query_range(struct xfs_mount *mp, struct xfs_trans *tp,
+int xfs_rtalloc_query_range(struct xfs_rtgroup *rtg, struct xfs_trans *tp,
 		xfs_rtxnum_t start, xfs_rtxnum_t end,
 		xfs_rtalloc_query_range_fn fn, void *priv);
-int xfs_rtalloc_query_all(struct xfs_mount *mp, struct xfs_trans *tp,
-			  xfs_rtalloc_query_range_fn fn,
-			  void *priv);
-int xfs_rtalloc_extent_is_free(struct xfs_mount *mp, struct xfs_trans *tp,
-			       xfs_rtxnum_t start, xfs_rtxlen_t len,
-			       bool *is_free);
-/*
- * Free an extent in the realtime subvolume.  Length is expressed in
- * realtime extents, as is the block number.
- */
-int					/* error */
-xfs_rtfree_extent(
-	struct xfs_trans	*tp,	/* transaction pointer */
-	xfs_rtxnum_t		start,	/* starting rtext number to free */
-	xfs_rtxlen_t		len);	/* length of extent freed */
-
+int xfs_rtalloc_query_all(struct xfs_rtgroup *rtg, struct xfs_trans *tp,
+		xfs_rtalloc_query_range_fn fn, void *priv);
+int xfs_rtalloc_extent_is_free(struct xfs_rtgroup *rtg, struct xfs_trans *tp,
+		xfs_rtxnum_t start, xfs_rtxlen_t len, bool *is_free);
+int xfs_rtfree_extent(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
+		xfs_rtxnum_t start, xfs_rtxlen_t len);
 /* Same as above, but in units of rt blocks. */
-int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
-		xfs_filblks_t rtlen);
+int xfs_rtfree_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
+		xfs_fsblock_t rtbno, xfs_filblks_t rtlen);
 
 xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
 		rtextents);
 xfs_filblks_t xfs_rtsummary_blockcount(struct xfs_mount *mp,
 		unsigned int rsumlevels, xfs_extlen_t rbmblocks);
 
-int xfs_rtfile_initialize_blocks(struct xfs_inode *ip,
-		xfs_fileoff_t offset_fsb, xfs_fileoff_t end_fsb, void *data);
+int xfs_rtfile_initialize_blocks(struct xfs_rtgroup *rtg,
+		enum xfs_rtg_inodes type, xfs_fileoff_t offset_fsb,
+		xfs_fileoff_t end_fsb, void *data);
 
-void xfs_rtbitmap_lock(struct xfs_mount *mp);
-void xfs_rtbitmap_unlock(struct xfs_mount *mp);
-void xfs_rtbitmap_trans_join(struct xfs_trans *tp);
-
-/* Lock the rt bitmap inode in shared mode */
-#define XFS_RBMLOCK_BITMAP	(1U << 0)
-/* Lock the rt summary inode in shared mode */
-#define XFS_RBMLOCK_SUMMARY	(1U << 1)
-
-void xfs_rtbitmap_lock_shared(struct xfs_mount *mp,
-		unsigned int rbmlock_flags);
-void xfs_rtbitmap_unlock_shared(struct xfs_mount *mp,
-		unsigned int rbmlock_flags);
 #else /* CONFIG_XFS_RT */
 # define xfs_rtfree_extent(t,b,l)			(-ENOSYS)
-# define xfs_rtfree_blocks(t,rb,rl)			(-ENOSYS)
+
+static inline int xfs_rtfree_blocks(struct xfs_trans *tp,
+		struct xfs_rtgroup *rtg, xfs_fsblock_t rtbno,
+		xfs_filblks_t rtlen)
+{
+	return -ENOSYS;
+}
 # define xfs_rtalloc_query_range(m,t,l,h,f,p)		(-ENOSYS)
 # define xfs_rtalloc_query_all(m,t,f,p)			(-ENOSYS)
 # define xfs_rtbitmap_read_buf(a,b)			(-ENOSYS)
@@ -351,11 +338,6 @@ xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 	return 0;
 }
 # define xfs_rtsummary_blockcount(mp, l, b)		(0)
-# define xfs_rtbitmap_lock(mp)			do { } while (0)
-# define xfs_rtbitmap_trans_join(tp)		do { } while (0)
-# define xfs_rtbitmap_unlock(mp)		do { } while (0)
-# define xfs_rtbitmap_lock_shared(mp, lf)	do { } while (0)
-# define xfs_rtbitmap_unlock_shared(mp, lf)	do { } while (0)
 #endif /* CONFIG_XFS_RT */
 
 #endif /* __XFS_RTBITMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index 9aa8f5e5525d3d..22901ecc2cbe22 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -162,10 +162,16 @@ xfs_rtgroup_lock(
 	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
 	       !(rtglock_flags & XFS_RTGLOCK_BITMAP));
 
-	if (rtglock_flags & XFS_RTGLOCK_BITMAP)
-		xfs_rtbitmap_lock(rtg_mount(rtg));
-	else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED)
-		xfs_rtbitmap_lock_shared(rtg_mount(rtg), XFS_RBMLOCK_BITMAP);
+	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+		/*
+		 * Lock both realtime free space metadata inodes for a freespace
+		 * update.
+		 */
+		xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL);
+		xfs_ilock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL);
+	} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
+		xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED);
+	}
 }
 
 /* Unlock metadata inodes associated with this rt group. */
@@ -178,10 +184,12 @@ xfs_rtgroup_unlock(
 	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
 	       !(rtglock_flags & XFS_RTGLOCK_BITMAP));
 
-	if (rtglock_flags & XFS_RTGLOCK_BITMAP)
-		xfs_rtbitmap_unlock(rtg_mount(rtg));
-	else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED)
-		xfs_rtbitmap_unlock_shared(rtg_mount(rtg), XFS_RBMLOCK_BITMAP);
+	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+		xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL);
+		xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL);
+	} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
+		xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED);
+	}
 }
 
 /*
@@ -197,8 +205,12 @@ xfs_rtgroup_trans_join(
 	ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
 	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED));
 
-	if (rtglock_flags & XFS_RTGLOCK_BITMAP)
-		xfs_rtbitmap_trans_join(tp);
+	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+		xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_BITMAP],
+				XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_SUMMARY],
+				XFS_ILOCK_EXCL);
+	}
 }
 
 #ifdef CONFIG_PROVE_LOCKING
@@ -263,6 +275,14 @@ struct xfs_rtginode_ops {
 };
 
 static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
+	[XFS_RTGI_BITMAP] = {
+		.name		= "bitmap",
+		.metafile_type	= XFS_METAFILE_RTBITMAP,
+	},
+	[XFS_RTGI_SUMMARY] = {
+		.name		= "summary",
+		.metafile_type	= XFS_METAFILE_RTSUMMARY,
+	},
 };
 
 /* Return the shortname of this rtgroup inode. */
@@ -302,7 +322,6 @@ xfs_rtginode_load(
 	struct xfs_trans	*tp)
 {
 	struct xfs_mount	*mp = tp->t_mountp;
-	const char		*path;
 	struct xfs_inode	*ip;
 	const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
 	int			error;
@@ -310,15 +329,36 @@ xfs_rtginode_load(
 	if (!xfs_rtginode_enabled(rtg, type))
 		return 0;
 
-	if (!mp->m_rtdirip)
-		return -EFSCORRUPTED;
-
-	path = xfs_rtginode_path(rtg_rgno(rtg), type);
-	if (!path)
-		return -ENOMEM;
-	error = xfs_metadir_load(tp, mp->m_rtdirip, path, ops->metafile_type,
-			&ip);
-	kfree(path);
+	if (!xfs_has_rtgroups(mp)) {
+		xfs_ino_t	ino;
+
+		switch (type) {
+		case XFS_RTGI_BITMAP:
+			ino = mp->m_sb.sb_rbmino;
+			break;
+		case XFS_RTGI_SUMMARY:
+			ino = mp->m_sb.sb_rsumino;
+			break;
+		default:
+			/* None of the other types exist on !rtgroups */
+			return 0;
+		}
+
+		error = xfs_trans_metafile_iget(tp, ino, ops->metafile_type,
+				&ip);
+	} else {
+		const char	*path;
+
+		if (!mp->m_rtdirip)
+			return -EFSCORRUPTED;
+
+		path = xfs_rtginode_path(rtg_rgno(rtg), type);
+		if (!path)
+			return -ENOMEM;
+		error = xfs_metadir_load(tp, mp->m_rtdirip, path,
+				ops->metafile_type, &ip);
+		kfree(path);
+	}
 
 	if (error)
 		return error;
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 2c894df723a786..3732f65ba8a1f6 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -12,6 +12,9 @@ struct xfs_mount;
 struct xfs_trans;
 
 enum xfs_rtg_inodes {
+	XFS_RTGI_BITMAP,	/* allocation bitmap */
+	XFS_RTGI_SUMMARY,	/* allocation summary */
+
 	XFS_RTGI_MAX,
 };
 
@@ -26,10 +29,19 @@ struct xfs_rtgroup {
 	struct xfs_group	rtg_group;
 
 	/* per-rtgroup metadata inodes */
-	struct xfs_inode	*rtg_inodes[1 /* hack */];
+	struct xfs_inode	*rtg_inodes[XFS_RTGI_MAX];
 
 	/* Number of blocks in this group */
 	xfs_rtxnum_t		rtg_extents;
+
+	/*
+	 * Cache of rt summary level per bitmap block with the invariant that
+	 * rtg_rsum_cache[bbno] > the maximum i for which rsum[i][bbno] != 0,
+	 * or 0 if rsum[i][bbno] == 0 for all i.
+	 *
+	 * Reads and writes are serialized by the rsumip inode lock.
+	 */
+	uint8_t			*rtg_rsum_cache;
 };
 
 static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg)
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 64168f2e42220a..008630b2b75263 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -19,6 +19,7 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_rmap.h"
 #include "xfs_rmap_btree.h"
+#include "xfs_rtgroup.h"
 #include "xfs_health.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -314,8 +315,20 @@ xchk_bmap_rt_iextent_xref(
 	struct xchk_bmap_info	*info,
 	struct xfs_bmbt_irec	*irec)
 {
+	int			error;
+
+	error = xchk_rtgroup_init_existing(info->sc,
+			xfs_rtb_to_rgno(ip->i_mount, irec->br_startblock),
+			&info->sc->sr);
+	if (!xchk_fblock_process_error(info->sc, info->whichfork,
+			irec->br_startoff, &error))
+		return;
+
+	xchk_rtgroup_lock(&info->sc->sr, XCHK_RTGLOCK_ALL);
 	xchk_xref_is_used_rt_space(info->sc, irec->br_startblock,
 			irec->br_blockcount);
+
+	xchk_rtgroup_free(info->sc, &info->sc->sr);
 }
 
 /* Cross-reference a single datadev extent record. */
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index 28db0c83819c20..4a50f8e0004092 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -19,6 +19,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_inode.h"
 #include "xfs_icache.h"
+#include "xfs_rtgroup.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -386,7 +387,7 @@ xchk_fscount_aggregate_agcounts(
 #ifdef CONFIG_XFS_RT
 STATIC int
 xchk_fscount_add_frextent(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	const struct xfs_rtalloc_rec	*rec,
 	void				*priv)
@@ -407,6 +408,7 @@ xchk_fscount_count_frextents(
 	struct xchk_fscounters	*fsc)
 {
 	struct xfs_mount	*mp = sc->mp;
+	struct xfs_rtgroup	*rtg = NULL;
 	int			error;
 
 	fsc->frextents = 0;
@@ -414,19 +416,20 @@ xchk_fscount_count_frextents(
 	if (!xfs_has_realtime(mp))
 		return 0;
 
-	xfs_rtbitmap_lock_shared(sc->mp, XFS_RBMLOCK_BITMAP);
-	error = xfs_rtalloc_query_all(sc->mp, sc->tp,
-			xchk_fscount_add_frextent, fsc);
-	if (error) {
-		xchk_set_incomplete(sc);
-		goto out_unlock;
+	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+		error = xfs_rtalloc_query_all(rtg, sc->tp,
+				xchk_fscount_add_frextent, fsc);
+		xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+		if (error) {
+			xchk_set_incomplete(sc);
+			xfs_rtgroup_rele(rtg);
+			return error;
+		}
 	}
 
 	fsc->frextents_delayed = percpu_counter_sum(&mp->m_delalloc_rtextents);
-
-out_unlock:
-	xfs_rtbitmap_unlock_shared(sc->mp, XFS_RBMLOCK_BITMAP);
-	return error;
+	return 0;
 }
 #else
 STATIC int
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 5fdd00029cd6c0..3fa009126170e6 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -21,7 +21,7 @@
 #include "xfs_rmap.h"
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
-#include "xfs_rtgroup.h"
+#include "xfs_rtbitmap.h"
 #include "xfs_extent_busy.h"
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 46583517377ffa..c68de973e5f26c 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -35,6 +35,10 @@ xchk_setup_rtbitmap(
 		return -ENOMEM;
 	sc->buf = rtb;
 
+	error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr);
+	if (error)
+		return error;
+
 	if (xchk_could_repair(sc)) {
 		error = xrep_setup_rtbitmap(sc, rtb);
 		if (error)
@@ -45,7 +49,8 @@ xchk_setup_rtbitmap(
 	if (error)
 		return error;
 
-	error = xchk_install_live_inode(sc, sc->mp->m_rbmip);
+	error = xchk_install_live_inode(sc,
+			sc->sr.rtg->rtg_inodes[XFS_RTGI_BITMAP]);
 	if (error)
 		return error;
 
@@ -53,18 +58,18 @@ xchk_setup_rtbitmap(
 	if (error)
 		return error;
 
-	xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
-
 	/*
 	 * Now that we've locked the rtbitmap, we can't race with growfsrt
 	 * trying to expand the bitmap or change the size of the rt volume.
 	 * Hence it is safe to compute and check the geometry values.
 	 */
+	xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP);
 	if (mp->m_sb.sb_rblocks) {
 		rtb->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
 		rtb->rextslog = xfs_compute_rextslog(rtb->rextents);
 		rtb->rbmblocks = xfs_rtbitmap_blockcount(mp, rtb->rextents);
 	}
+
 	return 0;
 }
 
@@ -73,11 +78,12 @@ xchk_setup_rtbitmap(
 /* Scrub a free extent record from the realtime bitmap. */
 STATIC int
 xchk_rtbitmap_rec(
-	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
 	struct xfs_trans	*tp,
 	const struct xfs_rtalloc_rec *rec,
 	void			*priv)
 {
+	struct xfs_mount	*mp = rtg_mount(rtg);
 	struct xfs_scrub	*sc = priv;
 	xfs_rtblock_t		startblock;
 	xfs_filblks_t		blockcount;
@@ -140,18 +146,20 @@ xchk_rtbitmap(
 	struct xfs_scrub	*sc)
 {
 	struct xfs_mount	*mp = sc->mp;
+	struct xfs_rtgroup	*rtg = sc->sr.rtg;
+	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
 	struct xchk_rtbitmap	*rtb = sc->buf;
 	int			error;
 
 	/* Is sb_rextents correct? */
 	if (mp->m_sb.sb_rextents != rtb->rextents) {
-		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		xchk_ino_set_corrupt(sc, rbmip->i_ino);
 		return 0;
 	}
 
 	/* Is sb_rextslog correct? */
 	if (mp->m_sb.sb_rextslog != rtb->rextslog) {
-		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		xchk_ino_set_corrupt(sc, rbmip->i_ino);
 		return 0;
 	}
 
@@ -160,17 +168,17 @@ xchk_rtbitmap(
 	 * case can we exceed 4bn bitmap blocks since the super field is a u32.
 	 */
 	if (rtb->rbmblocks > U32_MAX) {
-		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		xchk_ino_set_corrupt(sc, rbmip->i_ino);
 		return 0;
 	}
 	if (mp->m_sb.sb_rbmblocks != rtb->rbmblocks) {
-		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+		xchk_ino_set_corrupt(sc, rbmip->i_ino);
 		return 0;
 	}
 
 	/* The bitmap file length must be aligned to an fsblock. */
-	if (mp->m_rbmip->i_disk_size & mp->m_blockmask) {
-		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+	if (rbmip->i_disk_size & mp->m_blockmask) {
+		xchk_ino_set_corrupt(sc, rbmip->i_ino);
 		return 0;
 	}
 
@@ -179,8 +187,8 @@ xchk_rtbitmap(
 	 * growfsrt expands the bitmap file before updating sb_rextents, so the
 	 * file can be larger than sb_rbmblocks.
 	 */
-	if (mp->m_rbmip->i_disk_size < XFS_FSB_TO_B(mp, rtb->rbmblocks)) {
-		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
+	if (rbmip->i_disk_size < XFS_FSB_TO_B(mp, rtb->rbmblocks)) {
+		xchk_ino_set_corrupt(sc, rbmip->i_ino);
 		return 0;
 	}
 
@@ -193,7 +201,7 @@ xchk_rtbitmap(
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 
-	error = xfs_rtalloc_query_all(mp, sc->tp, xchk_rtbitmap_rec, sc);
+	error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, sc);
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		return error;
 
@@ -207,6 +215,8 @@ xchk_xref_is_used_rt_space(
 	xfs_rtblock_t		rtbno,
 	xfs_extlen_t		len)
 {
+	struct xfs_rtgroup	*rtg = sc->sr.rtg;
+	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
 	xfs_rtxnum_t		startext;
 	xfs_rtxnum_t		endext;
 	bool			is_free;
@@ -217,13 +227,10 @@ xchk_xref_is_used_rt_space(
 
 	startext = xfs_rtb_to_rtx(sc->mp, rtbno);
 	endext = xfs_rtb_to_rtx(sc->mp, rtbno + len - 1);
-	xfs_ilock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
-	error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, startext,
+	error = xfs_rtalloc_extent_is_free(rtg, sc->tp, startext,
 			endext - startext + 1, &is_free);
 	if (!xchk_should_check_xref(sc, &error, NULL))
-		goto out_unlock;
+		return;
 	if (is_free)
-		xchk_ino_xref_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
-out_unlock:
-	xfs_iunlock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+		xchk_ino_xref_set_corrupt(sc, rbmip->i_ino);
 }
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 7c7366c98338b0..cda5e836862178 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -18,6 +18,7 @@
 #include "xfs_bmap.h"
 #include "xfs_sb.h"
 #include "xfs_exchmaps.h"
+#include "xfs_rtgroup.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -46,12 +47,19 @@ xchk_setup_rtsummary(
 	struct xchk_rtsummary	*rts;
 	int			error;
 
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
 	rts = kvzalloc(struct_size(rts, words, mp->m_blockwsize),
 			XCHK_GFP_FLAGS);
 	if (!rts)
 		return -ENOMEM;
 	sc->buf = rts;
 
+	error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr);
+	if (error)
+		return error;
+
 	if (xchk_could_repair(sc)) {
 		error = xrep_setup_rtsummary(sc, rts);
 		if (error)
@@ -73,7 +81,8 @@ xchk_setup_rtsummary(
 	if (error)
 		return error;
 
-	error = xchk_install_live_inode(sc, mp->m_rsumip);
+	error = xchk_install_live_inode(sc,
+			sc->sr.rtg->rtg_inodes[XFS_RTGI_SUMMARY]);
 	if (error)
 		return error;
 
@@ -81,20 +90,17 @@ xchk_setup_rtsummary(
 	if (error)
 		return error;
 
-	/*
-	 * Locking order requires us to take the rtbitmap first.  We must be
-	 * careful to unlock it ourselves when we are done with the rtbitmap
-	 * file since the scrub infrastructure won't do that for us.  Only
-	 * then we can lock the rtsummary inode.
-	 */
-	xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
-	xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
-
 	/*
 	 * Now that we've locked the rtbitmap and rtsummary, we can't race with
 	 * growfsrt trying to expand the summary or change the size of the rt
 	 * volume.  Hence it is safe to compute and check the geometry values.
+	 *
+	 * Note that there is no strict requirement for an exclusive lock on the
+	 * summary here, but to keep the locking APIs simple we lock both inodes
+	 * exclusively here.  If we ever start caring about running concurrent
+	 * fsmap with scrub this could be changed.
 	 */
+	xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP);
 	if (mp->m_sb.sb_rblocks) {
 		int		rextslog;
 
@@ -105,6 +111,7 @@ xchk_setup_rtsummary(
 		rts->rsumblocks = xfs_rtsummary_blockcount(mp, rts->rsumlevels,
 				rts->rbmblocks);
 	}
+
 	return 0;
 }
 
@@ -155,11 +162,12 @@ xchk_rtsum_inc(
 /* Update the summary file to reflect the free extent that we've accumulated. */
 STATIC int
 xchk_rtsum_record_free(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	const struct xfs_rtalloc_rec	*rec,
 	void				*priv)
 {
+	struct xfs_mount		*mp = rtg_mount(rtg);
 	struct xfs_scrub		*sc = priv;
 	xfs_fileoff_t			rbmoff;
 	xfs_rtblock_t			rtbno;
@@ -182,7 +190,8 @@ xchk_rtsum_record_free(
 	rtlen = xfs_rtx_to_rtb(mp, rec->ar_extcount);
 
 	if (!xfs_verify_rtbext(mp, rtbno, rtlen)) {
-		xchk_ino_xref_set_corrupt(sc, mp->m_rbmip->i_ino);
+		xchk_ino_xref_set_corrupt(sc,
+				rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_ino);
 		return -EFSCORRUPTED;
 	}
 
@@ -204,15 +213,16 @@ xchk_rtsum_compute(
 	struct xfs_scrub	*sc)
 {
 	struct xfs_mount	*mp = sc->mp;
+	struct xfs_rtgroup	*rtg = sc->sr.rtg;
 	unsigned long long	rtbmp_blocks;
 
 	/* If the bitmap size doesn't match the computed size, bail. */
 	rtbmp_blocks = xfs_rtbitmap_blockcount(mp, mp->m_sb.sb_rextents);
-	if (XFS_FSB_TO_B(mp, rtbmp_blocks) != mp->m_rbmip->i_disk_size)
+	if (XFS_FSB_TO_B(mp, rtbmp_blocks) !=
+	    rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_disk_size)
 		return -EFSCORRUPTED;
 
-	return xfs_rtalloc_query_all(sc->mp, sc->tp, xchk_rtsum_record_free,
-			sc);
+	return xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtsum_record_free, sc);
 }
 
 /* Compare the rtsummary file against the one we computed. */
@@ -231,8 +241,9 @@ xchk_rtsum_compare(
 	xfs_rtsumoff_t		sumoff = 0;
 	int			error = 0;
 
-	rts->args.mp = sc->mp;
+	rts->args.mp = mp;
 	rts->args.tp = sc->tp;
+	rts->args.rtg = sc->sr.rtg;
 
 	/* Mappings may not cross or lie beyond EOF. */
 	endoff = XFS_B_TO_FSB(mp, ip->i_disk_size);
@@ -299,31 +310,34 @@ xchk_rtsummary(
 	struct xfs_scrub	*sc)
 {
 	struct xfs_mount	*mp = sc->mp;
+	struct xfs_rtgroup	*rtg = sc->sr.rtg;
+	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
+	struct xfs_inode	*rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
 	struct xchk_rtsummary	*rts = sc->buf;
-	int			error = 0;
+	int			error;
 
 	/* Is sb_rextents correct? */
 	if (mp->m_sb.sb_rextents != rts->rextents) {
-		xchk_ino_set_corrupt(sc, mp->m_rbmip->i_ino);
-		goto out_rbm;
+		xchk_ino_set_corrupt(sc, rbmip->i_ino);
+		return 0;
 	}
 
 	/* Is m_rsumlevels correct? */
 	if (mp->m_rsumlevels != rts->rsumlevels) {
-		xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
-		goto out_rbm;
+		xchk_ino_set_corrupt(sc, rsumip->i_ino);
+		return 0;
 	}
 
 	/* Is m_rsumsize correct? */
 	if (mp->m_rsumblocks != rts->rsumblocks) {
-		xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
-		goto out_rbm;
+		xchk_ino_set_corrupt(sc, rsumip->i_ino);
+		return 0;
 	}
 
 	/* The summary file length must be aligned to an fsblock. */
-	if (mp->m_rsumip->i_disk_size & mp->m_blockmask) {
-		xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
-		goto out_rbm;
+	if (rsumip->i_disk_size & mp->m_blockmask) {
+		xchk_ino_set_corrupt(sc, rsumip->i_ino);
+		return 0;
 	}
 
 	/*
@@ -331,15 +345,15 @@ xchk_rtsummary(
 	 * growfsrt expands the summary file before updating sb_rextents, so
 	 * the file can be larger than rsumsize.
 	 */
-	if (mp->m_rsumip->i_disk_size < XFS_FSB_TO_B(mp, rts->rsumblocks)) {
-		xchk_ino_set_corrupt(sc, mp->m_rsumip->i_ino);
-		goto out_rbm;
+	if (rsumip->i_disk_size < XFS_FSB_TO_B(mp, rts->rsumblocks)) {
+		xchk_ino_set_corrupt(sc, rsumip->i_ino);
+		return 0;
 	}
 
 	/* Invoke the fork scrubber. */
 	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
-		goto out_rbm;
+		return error;
 
 	/* Construct the new summary file from the rtbitmap. */
 	error = xchk_rtsum_compute(sc);
@@ -348,23 +362,12 @@ xchk_rtsummary(
 		 * EFSCORRUPTED means the rtbitmap is corrupt, which is an xref
 		 * error since we're checking the summary file.
 		 */
-		xchk_ino_xref_set_corrupt(sc, mp->m_rbmip->i_ino);
-		error = 0;
-		goto out_rbm;
+		xchk_ino_set_corrupt(sc, rbmip->i_ino);
+		return 0;
 	}
 	if (error)
-		goto out_rbm;
+		return error;
 
 	/* Does the computed summary file match the actual rtsummary file? */
-	error = xchk_rtsum_compare(sc);
-
-out_rbm:
-	/*
-	 * Unlock the rtbitmap since we're done with it.  All other writers of
-	 * the rt free space metadata grab the bitmap and summary ILOCKs in
-	 * that order, so we're still protected against allocation activities
-	 * even if we continue on to the repair function.
-	 */
-	xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
-	return error;
+	return xchk_rtsum_compare(sc);
 }
diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c
index 7deeb948cb7027..1688380988007f 100644
--- a/fs/xfs/scrub/rtsummary_repair.c
+++ b/fs/xfs/scrub/rtsummary_repair.c
@@ -76,8 +76,9 @@ xrep_rtsummary_prep_buf(
 	union xfs_suminfo_raw	*ondisk;
 	int			error;
 
-	rts->args.mp = sc->mp;
+	rts->args.mp = mp;
 	rts->args.tp = sc->tp;
+	rts->args.rtg = sc->sr.rtg;
 	rts->args.sumbp = bp;
 	ondisk = xfs_rsumblock_infoptr(&rts->args, 0);
 	rts->args.sumbp = NULL;
@@ -162,8 +163,8 @@ xrep_rtsummary(
 		return error;
 
 	/* Reset incore state and blow out the summary cache. */
-	if (mp->m_rsum_cache)
-		memset(mp->m_rsum_cache, 0xFF, mp->m_sb.sb_rbmblocks);
+	if (sc->sr.rtg->rtg_rsum_cache)
+		memset(sc->sr.rtg->rtg_rsum_cache, 0xFF, mp->m_sb.sb_rbmblocks);
 
 	mp->m_rsumlevels = rts->rsumlevels;
 	mp->m_rsumblocks = rts->rsumblocks;
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 03770b9f905c3d..8cd7e36c09990e 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -384,13 +384,13 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.repair	= xrep_parent,
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
-		.type	= ST_FS,
+		.type	= ST_RTGROUP,
 		.setup	= xchk_setup_rtbitmap,
 		.scrub	= xchk_rtbitmap,
 		.repair	= xrep_rtbitmap,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
-		.type	= ST_FS,
+		.type	= ST_RTGROUP,
 		.setup	= xchk_setup_rtsummary,
 		.scrub	= xchk_rtsummary,
 		.repair	= xrep_rtsummary,
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 412e3045561f13..fe9d6b81ea2a2f 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -507,7 +507,7 @@ xfs_discard_rtdev_extents(
 
 static int
 xfs_trim_gather_rtextent(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	const struct xfs_rtalloc_rec	*rec,
 	void				*priv)
@@ -526,12 +526,12 @@ xfs_trim_gather_rtextent(
 		return -ECANCELED;
 	}
 
-	rbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
-	rlen = xfs_rtx_to_rtb(mp, rec->ar_extcount);
+	rbno = xfs_rtx_to_rtb(rtg_mount(rtg), rec->ar_startext);
+	rlen = xfs_rtx_to_rtb(rtg_mount(rtg), rec->ar_extcount);
 
 	/* Ignore too small. */
 	if (rlen < tr->minlen_fsb) {
-		trace_xfs_discard_rttoosmall(mp, rbno, rlen);
+		trace_xfs_discard_rttoosmall(rtg_mount(rtg), rbno, rlen);
 		return 0;
 	}
 
@@ -550,11 +550,12 @@ xfs_trim_gather_rtextent(
 
 static int
 xfs_trim_rtextents(
-	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
 	xfs_rtxnum_t		low,
 	xfs_rtxnum_t		high,
 	xfs_daddr_t		minlen)
 {
+	struct xfs_mount	*mp = rtg_mount(rtg);
 	struct xfs_trim_rtdev	tr = {
 		.minlen_fsb	= XFS_BB_TO_FSB(mp, minlen),
 		.extent_list	= LIST_HEAD_INIT(tr.extent_list),
@@ -572,25 +573,25 @@ xfs_trim_rtextents(
 	 */
 	do {
 		tr.stop_rtx = low + (mp->m_sb.sb_blocksize * NBBY);
-		xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);
-		error = xfs_rtalloc_query_range(mp, tp, low, high,
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+		error = xfs_rtalloc_query_range(rtg, tp, low, high,
 				xfs_trim_gather_rtextent, &tr);
 
 		if (error == -ECANCELED)
 			error = 0;
 		if (error) {
-			xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+			xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
 			xfs_discard_free_rtdev_extents(&tr);
 			break;
 		}
 
 		if (list_empty(&tr.extent_list)) {
-			xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+			xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
 			break;
 		}
 
 		error = xfs_discard_rtdev_extents(mp, &tr);
-		xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+		xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
 		if (error)
 			break;
 
@@ -610,6 +611,9 @@ xfs_trim_rtdev_extents(
 {
 	xfs_rtblock_t		start_rtbno, end_rtbno;
 	xfs_rtxnum_t		start_rtx, end_rtx;
+	xfs_rgnumber_t		start_rgno, end_rgno;
+	int			last_error = 0, error;
+	struct xfs_rtgroup	*rtg = NULL;
 
 	/* Shift the start and end downwards to match the rt device. */
 	start_rtbno = xfs_daddr_to_rtb(mp, start);
@@ -618,14 +622,33 @@ xfs_trim_rtdev_extents(
 	else
 		start_rtbno = 0;
 	start_rtx = xfs_rtb_to_rtx(mp, start_rtbno);
+	start_rgno = xfs_rtb_to_rgno(mp, start_rtbno);
 
 	end_rtbno = xfs_daddr_to_rtb(mp, end);
 	if (end_rtbno <= mp->m_sb.sb_dblocks)
 		return 0;
 	end_rtbno -= mp->m_sb.sb_dblocks;
 	end_rtx = xfs_rtb_to_rtx(mp, end_rtbno + mp->m_sb.sb_rextsize - 1);
+	end_rgno = xfs_rtb_to_rgno(mp, end_rtbno);
 
-	return xfs_trim_rtextents(mp, start_rtx, end_rtx, minlen);
+	while ((rtg = xfs_rtgroup_next_range(mp, rtg, start_rgno, end_rgno))) {
+		xfs_rtxnum_t	rtg_end = rtg->rtg_extents;
+
+		if (rtg_rgno(rtg) == end_rgno)
+			rtg_end = min(rtg_end, end_rtx);
+
+		error = xfs_trim_rtextents(rtg, start_rtx, rtg_end, minlen);
+		if (error)
+			last_error = error;
+
+		if (xfs_trim_should_stop()) {
+			xfs_rtgroup_rele(rtg);
+			break;
+		}
+		start_rtx = 0;
+	}
+
+	return last_error;
 }
 #else
 # define xfs_trim_rtdev_extents(...)	(-EOPNOTSUPP)
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 3d42153b4bdb29..b14e0e306f8a34 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -712,7 +712,7 @@ xfs_getfsmap_logdev(
 /* Transform a rtbitmap "record" into a fsmap */
 STATIC int
 xfs_getfsmap_rtdev_rtbitmap_helper(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	const struct xfs_rtalloc_rec	*rec,
 	void				*priv)
@@ -720,6 +720,7 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
 	struct xfs_fsmap_irec		frec = {
 		.owner			= XFS_RMAP_OWN_NULL, /* "free" */
 	};
+	struct xfs_mount		*mp = rtg_mount(rtg);
 	struct xfs_getfsmap_info	*info = priv;
 	xfs_rtblock_t			rtbno;
 
@@ -751,10 +752,11 @@ xfs_getfsmap_rtdev_rtbitmap(
 	const struct xfs_fsmap		*keys,
 	struct xfs_getfsmap_info	*info)
 {
-
-	struct xfs_rtalloc_rec		ahigh = { 0 };
 	struct xfs_mount		*mp = tp->t_mountp;
 	xfs_rtblock_t			start_rtbno, end_rtbno;
+	xfs_rtxnum_t			start_rtx, end_rtx;
+	xfs_rgnumber_t			start_rgno, end_rgno;
+	struct xfs_rtgroup		*rtg = NULL;
 	uint64_t			eofs;
 	int				error;
 
@@ -772,36 +774,61 @@ xfs_getfsmap_rtdev_rtbitmap(
 		if (info->low_daddr >= eofs)
 			return 0;
 	}
+	start_rtx = xfs_rtb_to_rtx(mp, start_rtbno);
+	start_rgno = xfs_rtb_to_rgno(mp, start_rtbno);
 
 	end_rtbno = xfs_daddr_to_rtb(mp, min(eofs - 1, keys[1].fmr_physical));
+	end_rgno = xfs_rtb_to_rgno(mp, end_rtbno);
 
 	trace_xfs_fsmap_low_linear_key(mp, info->dev, start_rtbno);
 	trace_xfs_fsmap_high_linear_key(mp, info->dev, end_rtbno);
 
-	xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);
+	end_rtx = -1ULL;
 
-	/*
-	 * Set up query parameters to return free rtextents covering the range
-	 * we want.
-	 */
-	error = xfs_rtalloc_query_range(mp, tp, xfs_rtb_to_rtx(mp, start_rtbno),
-			xfs_rtb_to_rtxup(mp, end_rtbno),
-			xfs_getfsmap_rtdev_rtbitmap_helper, info);
-	if (error)
-		goto err;
+	while ((rtg = xfs_rtgroup_next_range(mp, rtg, start_rgno, end_rgno))) {
+		if (rtg_rgno(rtg) == end_rgno)
+			end_rtx = xfs_rtb_to_rtx(mp,
+					end_rtbno + mp->m_sb.sb_rextsize - 1);
 
-	/*
-	 * Report any gaps at the end of the rtbitmap by simulating a null
-	 * rmap starting at the block after the end of the query range.
-	 */
-	info->last = true;
-	ahigh.ar_startext = min(mp->m_sb.sb_rextents, high);
+		info->group = rtg_group(rtg);
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+		error = xfs_rtalloc_query_range(rtg, tp, start_rtx, end_rtx,
+				xfs_getfsmap_rtdev_rtbitmap_helper, info);
+		if (error)
+			break;
+
+		/*
+		 * Report any gaps at the end of the rtbitmap by simulating a
+		 * zero-length free extent starting at the rtx after the end
+		 * of the query range.
+		 */
+		if (rtg_rgno(rtg) == end_rgno) {
+			struct xfs_rtalloc_rec	ahigh = {
+				.ar_startext	= min(end_rtx + 1,
+						      rtg->rtg_extents),
+			};
+
+			info->last = true;
+			error = xfs_getfsmap_rtdev_rtbitmap_helper(rtg, tp,
+					&ahigh, info);
+			if (error)
+				break;
+		}
+
+		xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+		info->group = NULL;
+		start_rtx = 0;
+	}
+
+	/* loop termination case */
+	if (rtg) {
+		if (info->group) {
+			xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+			info->group = NULL;
+		}
+		xfs_rtgroup_rele(rtg);
+	}
 
-	error = xfs_getfsmap_rtdev_rtbitmap_helper(mp, tp, &ahigh, info);
-	if (error)
-		goto err;
-err:
-	xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
 	return error;
 }
 #endif /* CONFIG_XFS_RT */
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 0c90625374a8ee..26ee80a2f391e4 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -124,8 +124,6 @@ typedef struct xfs_mount {
 	struct xfs_da_geometry	*m_dir_geo;	/* directory block geometry */
 	struct xfs_da_geometry	*m_attr_geo;	/* attribute block geometry */
 	struct xlog		*m_log;		/* log specific stuff */
-	struct xfs_inode	*m_rbmip;	/* pointer to bitmap inode */
-	struct xfs_inode	*m_rsumip;	/* pointer to summary inode */
 	struct xfs_inode	*m_rootip;	/* pointer to root directory */
 	struct xfs_inode	*m_metadirip;	/* ptr to metadata directory */
 	struct xfs_inode	*m_rtdirip;	/* ptr to realtime metadir */
@@ -134,14 +132,6 @@ typedef struct xfs_mount {
 	struct xfs_buftarg	*m_logdev_targp;/* log device */
 	struct xfs_buftarg	*m_rtdev_targp;	/* rt device */
 	void __percpu		*m_inodegc;	/* percpu inodegc structures */
-
-	/*
-	 * Optional cache of rt summary level per bitmap block with the
-	 * invariant that m_rsum_cache[bbno] > the maximum i for which
-	 * rsum[i][bbno] != 0, or 0 if rsum[i][bbno] == 0 for all i.
-	 * Reads and writes are serialized by the rsumip inode lock.
-	 */
-	uint8_t			*m_rsum_cache;
 	struct xfs_mru_cache	*m_filestream;  /* per-mount filestream data */
 	struct workqueue_struct *m_buf_workqueue;
 	struct workqueue_struct	*m_unwritten_workqueue;
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 3663c4f89ed8a1..28b1420bac1dd2 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -215,10 +215,15 @@ static void
 xfs_qm_unmount_rt(
 	struct xfs_mount	*mp)
 {
-	if (mp->m_rbmip)
-		xfs_qm_dqdetach(mp->m_rbmip);
-	if (mp->m_rsumip)
-		xfs_qm_dqdetach(mp->m_rsumip);
+	struct xfs_rtgroup	*rtg = xfs_rtgroup_grab(mp, 0);
+
+	if (!rtg)
+		return;
+	if (rtg->rtg_inodes[XFS_RTGI_BITMAP])
+		xfs_qm_dqdetach(rtg->rtg_inodes[XFS_RTGI_BITMAP]);
+	if (rtg->rtg_inodes[XFS_RTGI_SUMMARY])
+		xfs_qm_dqdetach(rtg->rtg_inodes[XFS_RTGI_SUMMARY]);
+	xfs_rtgroup_rele(rtg);
 }
 
 /*
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 9a451f88bf4647..3b3ce971a19758 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -42,14 +42,14 @@ xfs_rtany_summary(
 	xfs_fileoff_t		bbno,	/* bitmap block number */
 	int			*maxlog) /* out: max log2 extent size free */
 {
-	struct xfs_mount	*mp = args->mp;
+	uint8_t			*rsum_cache = args->rtg->rtg_rsum_cache;
 	int			error;
 	int			log;	/* loop counter, log2 of ext. size */
 	xfs_suminfo_t		sum;	/* summary data */
 
-	/* There are no extents at levels >= m_rsum_cache[bbno]. */
-	if (mp->m_rsum_cache) {
-		high = min(high, mp->m_rsum_cache[bbno] - 1);
+	/* There are no extents at levels >= rsum_cache[bbno]. */
+	if (rsum_cache) {
+		high = min(high, rsum_cache[bbno] - 1);
 		if (low > high) {
 			*maxlog = -1;
 			return 0;
@@ -81,12 +81,11 @@ xfs_rtany_summary(
 	*maxlog = -1;
 out:
 	/* There were no extents at levels > log. */
-	if (mp->m_rsum_cache && log + 1 < mp->m_rsum_cache[bbno])
-		mp->m_rsum_cache[bbno] = log + 1;
+	if (rsum_cache && log + 1 < rsum_cache[bbno])
+		rsum_cache[bbno] = log + 1;
 	return 0;
 }
 
-
 /*
  * Copy and transform the summary file, given the old and new
  * parameters in the mount structures.
@@ -153,7 +152,7 @@ xfs_rtallocate_range(
 	/*
 	 * Find the next allocated block (end of free extent).
 	 */
-	error = xfs_rtfind_forw(args, end, mp->m_sb.sb_rextents - 1,
+	error = xfs_rtfind_forw(args, end, args->rtg->rtg_extents - 1,
 			&postblock);
 	if (error)
 		return error;
@@ -215,14 +214,14 @@ xfs_rtalloc_align_len(
  */
 static inline xfs_rtxlen_t
 xfs_rtallocate_clamp_len(
-	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
 	xfs_rtxnum_t		startrtx,
 	xfs_rtxlen_t		rtxlen,
 	xfs_rtxlen_t		prod)
 {
 	xfs_rtxlen_t		ret;
 
-	ret = min(mp->m_sb.sb_rextents, startrtx + rtxlen) - startrtx;
+	ret = min(rtg->rtg_extents, startrtx + rtxlen) - startrtx;
 	return xfs_rtalloc_align_len(ret, prod);
 }
 
@@ -257,10 +256,11 @@ xfs_rtallocate_extent_block(
 	 * Loop over all the extents starting in this bitmap block up to the
 	 * end of the rt volume, looking for one that's long enough.
 	 */
-	end = min(mp->m_sb.sb_rextents, xfs_rbmblock_to_rtx(mp, bbno + 1)) - 1;
+	end = min(args->rtg->rtg_extents, xfs_rbmblock_to_rtx(mp, bbno + 1)) -
+		1;
 	for (i = xfs_rbmblock_to_rtx(mp, bbno); i <= end; i++) {
 		/* Make sure we don't scan off the end of the rt volume. */
-		scanlen = xfs_rtallocate_clamp_len(mp, i, maxlen, prod);
+		scanlen = xfs_rtallocate_clamp_len(args->rtg, i, maxlen, prod);
 		if (scanlen < minlen)
 			break;
 
@@ -345,7 +345,6 @@ xfs_rtallocate_extent_exact(
 	xfs_rtxlen_t		prod,	/* extent product factor */
 	xfs_rtxnum_t		*rtx)	/* out: start rtext allocated */
 {
-	struct xfs_mount	*mp = args->mp;
 	xfs_rtxnum_t		next;	/* next rtext to try (dummy) */
 	xfs_rtxlen_t		alloclen; /* candidate length */
 	xfs_rtxlen_t		scanlen; /* number of free rtx to look for */
@@ -356,7 +355,7 @@ xfs_rtallocate_extent_exact(
 	ASSERT(maxlen % prod == 0);
 
 	/* Make sure we don't run off the end of the rt volume. */
-	scanlen = xfs_rtallocate_clamp_len(mp, start, maxlen, prod);
+	scanlen = xfs_rtallocate_clamp_len(args->rtg, start, maxlen, prod);
 	if (scanlen < minlen)
 		return -ENOSPC;
 
@@ -417,11 +416,10 @@ xfs_rtallocate_extent_near(
 	ASSERT(maxlen % prod == 0);
 
 	/*
-	 * If the block number given is off the end, silently set it to
-	 * the last block.
+	 * If the block number given is off the end, silently set it to the last
+	 * block.
 	 */
-	if (start >= mp->m_sb.sb_rextents)
-		start = mp->m_sb.sb_rextents - 1;
+	start = min(start, args->rtg->rtg_extents - 1);
 
 	/*
 	 * Try the exact allocation first.
@@ -661,21 +659,22 @@ xfs_rtunmount_rtg(
 
 	for (i = 0; i < XFS_RTGI_MAX; i++)
 		xfs_rtginode_irele(&rtg->rtg_inodes[i]);
+	kvfree(rtg->rtg_rsum_cache);
 }
 
 static int
 xfs_alloc_rsum_cache(
-	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
 	xfs_extlen_t		rbmblocks)
 {
 	/*
 	 * The rsum cache is initialized to the maximum value, which is
 	 * trivially an upper bound on the maximum level with any free extents.
 	 */
-	mp->m_rsum_cache = kvmalloc(rbmblocks, GFP_KERNEL);
-	if (!mp->m_rsum_cache)
+	rtg->rtg_rsum_cache = kvmalloc(rbmblocks, GFP_KERNEL);
+	if (!rtg->rtg_rsum_cache)
 		return -ENOMEM;
-	memset(mp->m_rsum_cache, -1, rbmblocks);
+	memset(rtg->rtg_rsum_cache, -1, rbmblocks);
 	return 0;
 }
 
@@ -714,17 +713,20 @@ xfs_growfs_rt_fixup_extsize(
 
 static int
 xfs_growfs_rt_bmblock(
-	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
 	xfs_rfsblock_t		nrblocks,
 	xfs_agblock_t		rextsize,
 	xfs_fileoff_t		bmbno)
 {
-	struct xfs_inode	*rbmip = mp->m_rbmip;
-	struct xfs_inode	*rsumip = mp->m_rsumip;
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
+	struct xfs_inode	*rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
 	struct xfs_rtalloc_args	args = {
 		.mp		= mp,
+		.rtg		= rtg,
 	};
 	struct xfs_rtalloc_args	nargs = {
+		.rtg		= rtg,
 	};
 	struct xfs_mount	*nmp;
 	xfs_rfsblock_t		nrblocks_step;
@@ -750,6 +752,7 @@ xfs_growfs_rt_bmblock(
 	nmp->m_rsumlevels = nmp->m_sb.sb_rextslog + 1;
 	nmp->m_rsumblocks = xfs_rtsummary_blockcount(mp, nmp->m_rsumlevels,
 			nmp->m_sb.sb_rbmblocks);
+	rtg->rtg_extents = xfs_rtgroup_extents(nmp, rtg_rgno(rtg));
 
 	/*
 	 * Recompute the growfsrt reservation from the new rsumsize, so that the
@@ -762,8 +765,8 @@ xfs_growfs_rt_bmblock(
 		goto out_free;
 	nargs.tp = args.tp;
 
-	xfs_rtbitmap_lock(mp);
-	xfs_rtbitmap_trans_join(args.tp);
+	xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP);
+	xfs_rtgroup_trans_join(args.tp, args.rtg, XFS_RTGLOCK_BITMAP);
 
 	/*
 	 * Update the bitmap inode's size ondisk and incore.  We need to update
@@ -865,8 +868,9 @@ xfs_growfs_rt_bmblock(
  */
 static xfs_fileoff_t
 xfs_last_rt_bmblock(
-	struct xfs_mount	*mp)
+	struct xfs_rtgroup	*rtg)
 {
+	struct xfs_mount	*mp = rtg_mount(rtg);
 	xfs_fileoff_t		bmbno = mp->m_sb.sb_rbmblocks;
 
 	/* Skip the current block if it is exactly full. */
@@ -880,13 +884,14 @@ xfs_last_rt_bmblock(
  */
 static int
 xfs_growfs_rt_alloc_blocks(
-	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
 	xfs_rfsblock_t		nrblocks,
 	xfs_agblock_t		rextsize,
 	xfs_extlen_t		*nrbmblocks)
 {
-	struct xfs_inode	*rbmip = mp->m_rbmip;
-	struct xfs_inode	*rsumip = mp->m_rsumip;
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
+	struct xfs_inode	*rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
 	xfs_rtxnum_t		nrextents = div_u64(nrblocks, rextsize);
 	xfs_extlen_t		orbmblocks;
 	xfs_extlen_t		orsumblocks;
@@ -904,14 +909,66 @@ xfs_growfs_rt_alloc_blocks(
 	nrsumblocks = xfs_rtsummary_blockcount(mp,
 		xfs_compute_rextslog(nrextents) + 1, *nrbmblocks);
 
-	error = xfs_rtfile_initialize_blocks(rbmip, orbmblocks,
+	error = xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_BITMAP, orbmblocks,
 			*nrbmblocks, NULL);
 	if (error)
 		return error;
-	return xfs_rtfile_initialize_blocks(rsumip, orsumblocks,
+	return xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_SUMMARY, orsumblocks,
 			nrsumblocks, NULL);
 }
 
+static int
+xfs_growfs_rtg(
+	struct xfs_mount	*mp,
+	xfs_rfsblock_t		nrblocks,
+	xfs_agblock_t		rextsize)
+{
+	uint8_t			*old_rsum_cache = NULL;
+	xfs_extlen_t		bmblocks;
+	xfs_fileoff_t		bmbno;
+	struct xfs_rtgroup	*rtg;
+	int			error;
+
+	rtg = xfs_rtgroup_grab(mp, 0);
+	if (!rtg)
+		return -EINVAL;
+
+	error = xfs_growfs_rt_alloc_blocks(rtg, nrblocks, rextsize, &bmblocks);
+	if (error)
+		goto out_rele;
+
+	if (bmblocks != rtg_mount(rtg)->m_sb.sb_rbmblocks) {
+		old_rsum_cache = rtg->rtg_rsum_cache;
+		error = xfs_alloc_rsum_cache(rtg, bmblocks);
+		if (error)
+			goto out_rele;
+	}
+
+	for (bmbno = xfs_last_rt_bmblock(rtg); bmbno < bmblocks; bmbno++) {
+		error = xfs_growfs_rt_bmblock(rtg, nrblocks, rextsize, bmbno);
+		if (error)
+			goto out_error;
+	}
+
+	if (old_rsum_cache)
+		kvfree(old_rsum_cache);
+	xfs_rtgroup_rele(rtg);
+	return 0;
+
+out_error:
+	/*
+	 * Reset rtg_extents to the old value if adding more blocks failed.
+	 */
+	rtg->rtg_extents = xfs_rtgroup_extents(rtg_mount(rtg), rtg_rgno(rtg));
+	if (old_rsum_cache) {
+		kvfree(rtg->rtg_rsum_cache);
+		rtg->rtg_rsum_cache = old_rsum_cache;
+	}
+out_rele:
+	xfs_rtgroup_rele(rtg);
+	return error;
+}
+
 /*
  * Grow the realtime area of the filesystem.
  */
@@ -920,14 +977,12 @@ xfs_growfs_rt(
 	xfs_mount_t	*mp,		/* mount point for filesystem */
 	xfs_growfs_rt_t	*in)		/* growfs rt input struct */
 {
-	xfs_fileoff_t	bmbno;		/* bitmap block number */
-	struct xfs_buf	*bp;		/* temporary buffer */
-	int		error;		/* error return value */
-	xfs_extlen_t	nrbmblocks;	/* new number of rt bitmap blocks */
-	xfs_rtxnum_t	nrextents;	/* new number of realtime extents */
-	xfs_extlen_t	nrsumblocks;	/* new number of summary blocks */
-	uint8_t		*rsum_cache;	/* old summary cache */
-	xfs_agblock_t	old_rextsize = mp->m_sb.sb_rextsize;
+	xfs_rtxnum_t		nrextents;
+	xfs_extlen_t		nrbmblocks;
+	xfs_extlen_t		nrsumblocks;
+	struct xfs_buf		*bp;
+	xfs_agblock_t		old_rextsize = mp->m_sb.sb_rextsize;
+	int			error;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -938,15 +993,9 @@ xfs_growfs_rt(
 
 	if (!mutex_trylock(&mp->m_growlock))
 		return -EWOULDBLOCK;
-	/*
-	 * Mount should fail if the rt bitmap/summary files don't load, but
-	 * we'll check anyway.
-	 */
-	error = -EINVAL;
-	if (!mp->m_rbmip || !mp->m_rsumip)
-		goto out_unlock;
 
 	/* Shrink not supported. */
+	error = -EINVAL;
 	if (in->newblocks <= mp->m_sb.sb_rblocks)
 		goto out_unlock;
 	/* Can only change rt extent size when adding rt volume. */
@@ -980,10 +1029,9 @@ xfs_growfs_rt(
 	 * Calculate new parameters.  These are the final values to be reached.
 	 */
 	nrextents = div_u64(in->newblocks, in->extsize);
-	if (nrextents == 0) {
-		error = -EINVAL;
+	error = -EINVAL;
+	if (nrextents == 0)
 		goto out_unlock;
-	}
 	nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents);
 	nrsumblocks = xfs_rtsummary_blockcount(mp,
 			xfs_compute_rextslog(nrextents) + 1, nrbmblocks);
@@ -993,55 +1041,22 @@ xfs_growfs_rt(
 	 * the log.  This prevents us from getting a log overflow,
 	 * since we'll log basically the whole summary file at once.
 	 */
-	if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1)) {
-		error = -EINVAL;
+	if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1))
 		goto out_unlock;
-	}
 
-	error = xfs_growfs_rt_alloc_blocks(mp, in->newblocks, in->extsize,
-			&nrbmblocks);
+	error = xfs_growfs_rtg(mp, in->newblocks, in->extsize);
 	if (error)
 		goto out_unlock;
 
-	rsum_cache = mp->m_rsum_cache;
-	if (nrbmblocks != mp->m_sb.sb_rbmblocks) {
-		error = xfs_alloc_rsum_cache(mp, nrbmblocks);
-		if (error)
-			goto out_unlock;
-	}
-
-	/* Initialize the free space bitmap one bitmap block at a time. */
-	for (bmbno = xfs_last_rt_bmblock(mp); bmbno < nrbmblocks; bmbno++) {
-		error = xfs_growfs_rt_bmblock(mp, in->newblocks, in->extsize,
-				bmbno);
-		if (error)
-			goto out_free;
-	}
-
 	if (old_rextsize != in->extsize) {
 		error = xfs_growfs_rt_fixup_extsize(mp);
 		if (error)
-			goto out_free;
+			goto out_unlock;
 	}
 
 	/* Update secondary superblocks now the physical grow has completed */
 	error = xfs_update_secondary_sbs(mp);
 
-out_free:
-	/*
-	 * If we had to allocate a new rsum_cache, we either need to free the
-	 * old one (if we succeeded) or free the new one and restore the old one
-	 * (if there was an error).
-	 */
-	if (rsum_cache != mp->m_rsum_cache) {
-		if (error) {
-			kvfree(mp->m_rsum_cache);
-			mp->m_rsum_cache = rsum_cache;
-		} else {
-			kvfree(rsum_cache);
-		}
-	}
-
 out_unlock:
 	mutex_unlock(&mp->m_growlock);
 	return error;
@@ -1070,7 +1085,7 @@ xfs_rtmount_init(
 	mp->m_rsumlevels = sbp->sb_rextslog + 1;
 	mp->m_rsumblocks = xfs_rtsummary_blockcount(mp, mp->m_rsumlevels,
 			mp->m_sb.sb_rbmblocks);
-	mp->m_rbmip = mp->m_rsumip = NULL;
+
 	/*
 	 * Check that the realtime section is an ok size.
 	 */
@@ -1094,7 +1109,7 @@ xfs_rtmount_init(
 
 static int
 xfs_rtalloc_count_frextent(
-	struct xfs_mount		*mp,
+	struct xfs_rtgroup		*rtg,
 	struct xfs_trans		*tp,
 	const struct xfs_rtalloc_rec	*rec,
 	void				*priv)
@@ -1116,12 +1131,18 @@ xfs_rtalloc_reinit_frextents(
 	uint64_t		val = 0;
 	int			error;
 
-	xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);
-	error = xfs_rtalloc_query_all(mp, NULL, xfs_rtalloc_count_frextent,
-			&val);
-	xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
-	if (error)
-		return error;
+	struct xfs_rtgroup	*rtg = NULL;
+
+	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+		error = xfs_rtalloc_query_all(rtg, NULL,
+				xfs_rtalloc_count_frextent, &val);
+		xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+		if (error) {
+			xfs_rtgroup_rele(rtg);
+			return error;
+		}
+	}
 
 	spin_lock(&mp->m_sb_lock);
 	mp->m_sb.sb_frextents = val;
@@ -1160,17 +1181,6 @@ xfs_rtmount_iread_extents(
 	return error;
 }
 
-static void
-xfs_rtgroup_unmount_inodes(
-	struct xfs_mount	*mp)
-{
-	struct xfs_rtgroup	*rtg = NULL;
-
-	while ((rtg = xfs_rtgroup_next(mp, rtg)))
-		xfs_rtunmount_rtg(rtg);
-	xfs_rtginode_irele(&mp->m_rtdirip);
-}
-
 static int
 xfs_rtmount_rtg(
 	struct xfs_mount	*mp,
@@ -1194,7 +1204,7 @@ xfs_rtmount_rtg(
 		}
 	}
 
-	return 0;
+	return xfs_alloc_rsum_cache(rtg, mp->m_sb.sb_rbmblocks);
 }
 
 /*
@@ -1206,7 +1216,6 @@ xfs_rtmount_inodes(
 	struct xfs_mount	*mp)
 {
 	struct xfs_trans	*tp;
-	struct xfs_sb		*sbp = &mp->m_sb;
 	struct xfs_rtgroup	*rtg = NULL;
 	int			error;
 
@@ -1214,57 +1223,22 @@ xfs_rtmount_inodes(
 	if (error)
 		return error;
 
-	error = xfs_trans_metafile_iget(tp, mp->m_sb.sb_rbmino,
-			XFS_METAFILE_RTBITMAP, &mp->m_rbmip);
-	if (xfs_metadata_is_sick(error))
-		xfs_rt_mark_sick(mp, XFS_SICK_RT_BITMAP);
-	if (error)
-		goto out_trans;
-	ASSERT(mp->m_rbmip != NULL);
-
-	error = xfs_rtmount_iread_extents(tp, mp->m_rbmip, XFS_ILOCK_RTBITMAP);
-	if (error)
-		goto out_rele_bitmap;
-
-	error = xfs_trans_metafile_iget(tp, mp->m_sb.sb_rsumino,
-			XFS_METAFILE_RTSUMMARY, &mp->m_rsumip);
-	if (xfs_metadata_is_sick(error))
-		xfs_rt_mark_sick(mp, XFS_SICK_RT_SUMMARY);
-	if (error)
-		goto out_rele_bitmap;
-	ASSERT(mp->m_rsumip != NULL);
-
-	error = xfs_rtmount_iread_extents(tp, mp->m_rsumip, XFS_ILOCK_RTSUM);
-	if (error)
-		goto out_rele_summary;
-
 	if (xfs_has_rtgroups(mp) && mp->m_sb.sb_rgcount > 0) {
 		error = xfs_rtginode_load_parent(tp);
 		if (error)
-			goto out_rele_summary;
+			goto out_cancel;
 	}
 
 	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
 		error = xfs_rtmount_rtg(mp, tp, rtg);
 		if (error) {
 			xfs_rtgroup_rele(rtg);
-			goto out_rele_inodes;
+			xfs_rtunmount_inodes(mp);
+			break;
 		}
 	}
 
-	error = xfs_alloc_rsum_cache(mp, sbp->sb_rbmblocks);
-	if (error)
-		goto out_rele_inodes;
-	xfs_trans_cancel(tp);
-	return 0;
-
-out_rele_inodes:
-	xfs_rtgroup_unmount_inodes(mp);
-out_rele_summary:
-	xfs_irele(mp->m_rsumip);
-out_rele_bitmap:
-	xfs_irele(mp->m_rbmip);
-out_trans:
+out_cancel:
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -1273,13 +1247,11 @@ void
 xfs_rtunmount_inodes(
 	struct xfs_mount	*mp)
 {
-	kvfree(mp->m_rsum_cache);
+	struct xfs_rtgroup	*rtg = NULL;
 
-	xfs_rtgroup_unmount_inodes(mp);
-	if (mp->m_rbmip)
-		xfs_irele(mp->m_rbmip);
-	if (mp->m_rsumip)
-		xfs_irele(mp->m_rsumip);
+	while ((rtg = xfs_rtgroup_next(mp, rtg)))
+		xfs_rtunmount_rtg(rtg);
+	xfs_rtginode_irele(&mp->m_rtdirip);
 }
 
 /*
@@ -1291,28 +1263,29 @@ xfs_rtunmount_inodes(
  */
 static xfs_rtxnum_t
 xfs_rtpick_extent(
-	xfs_mount_t		*mp,		/* file system mount point */
-	xfs_trans_t		*tp,		/* transaction pointer */
+	struct xfs_rtgroup	*rtg,
+	struct xfs_trans	*tp,
 	xfs_rtxlen_t		len)		/* allocation length (rtextents) */
 {
-	xfs_rtxnum_t		b;		/* result rtext */
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
+	xfs_rtxnum_t		b = 0;		/* result rtext */
 	int			log2;		/* log of sequence number */
 	uint64_t		resid;		/* residual after log removed */
 	uint64_t		seq;		/* sequence number of file creation */
 	struct timespec64	ts;		/* timespec in inode */
 
-	xfs_assert_ilocked(mp->m_rbmip, XFS_ILOCK_EXCL);
+	xfs_assert_ilocked(rbmip, XFS_ILOCK_EXCL);
 
-	ts = inode_get_atime(VFS_I(mp->m_rbmip));
-	if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) {
-		mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
+	ts = inode_get_atime(VFS_I(rbmip));
+	if (!(rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) {
+		rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
 		seq = 0;
 	} else {
 		seq = ts.tv_sec;
 	}
-	if ((log2 = xfs_highbit64(seq)) == -1)
-		b = 0;
-	else {
+	log2 = xfs_highbit64(seq);
+	if (log2 != -1) {
 		resid = seq - (1ULL << log2);
 		b = (mp->m_sb.sb_rextents * ((resid << 1) + 1ULL)) >>
 		    (log2 + 1);
@@ -1322,8 +1295,8 @@ xfs_rtpick_extent(
 			b = mp->m_sb.sb_rextents - len;
 	}
 	ts.tv_sec = seq + 1;
-	inode_set_atime_to_ts(VFS_I(mp->m_rbmip), ts);
-	xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
+	inode_set_atime_to_ts(VFS_I(rbmip), ts);
+	xfs_trans_log_inode(tp, rbmip, XFS_ILOG_CORE);
 	return b;
 }
 
@@ -1378,12 +1351,16 @@ xfs_rtallocate(
 	xfs_rtxlen_t		len = 0;
 	int			error = 0;
 
+	args.rtg = xfs_rtgroup_grab(args.mp, 0);
+	if (!args.rtg)
+		return -ENOSPC;
+
 	/*
 	 * Lock out modifications to both the RT bitmap and summary inodes.
 	 */
 	if (!*rtlocked) {
-		xfs_rtbitmap_lock(args.mp);
-		xfs_rtbitmap_trans_join(tp);
+		xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP);
+		xfs_rtgroup_trans_join(tp, args.rtg, XFS_RTGLOCK_BITMAP);
 		*rtlocked = true;
 	}
 
@@ -1394,7 +1371,7 @@ xfs_rtallocate(
 	if (bno_hint)
 		start = xfs_rtb_to_rtx(args.mp, bno_hint);
 	else if (initial_user_data)
-		start = xfs_rtpick_extent(args.mp, tp, maxlen);
+		start = xfs_rtpick_extent(args.rtg, tp, maxlen);
 
 	if (start) {
 		error = xfs_rtallocate_extent_near(&args, start, minlen, maxlen,
@@ -1428,6 +1405,7 @@ xfs_rtallocate(
 	*blen = xfs_rtxlen_to_extlen(args.mp, len);
 
 out_release:
+	xfs_rtgroup_rele(args.rtg);
 	xfs_rtbuf_cache_relse(&args);
 	return error;
 }

[PATCH 13/21] xfs: support creating per-RTG files in growfs

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

To support adding new RT groups in growfs, we need to be able to create
the per-RT group files.  Add a new xfs_rtginode_create helper to create
a given per-RTG file.  Most of the code for that is shared, but the
details of the actual file are abstracted out using a new create method
in struct xfs_rtginode_ops.

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_rtbitmap.c |   32 +++++++++++++++++++
 fs/xfs/libxfs/xfs_rtbitmap.h |    4 ++
 fs/xfs/libxfs/xfs_rtgroup.c  |   69 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_rtgroup.h  |    2 +
 fs/xfs/xfs_rtalloc.c         |   30 ++++++++++++++++++
 5 files changed, 137 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index c54ac160b90994..6c3354c8efdafa 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1297,3 +1297,35 @@ xfs_rtfile_initialize_blocks(
 
 	return 0;
 }
+
+int
+xfs_rtbitmap_create(
+	struct xfs_rtgroup	*rtg,
+	struct xfs_inode	*ip,
+	struct xfs_trans	*tp,
+	bool			init)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	ip->i_disk_size = mp->m_sb.sb_rbmblocks * mp->m_sb.sb_blocksize;
+	if (init && !xfs_has_rtgroups(mp)) {
+		ip->i_diflags |= XFS_DIFLAG_NEWRTBM;
+		inode_set_atime(VFS_I(ip), 0, 0);
+	}
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return 0;
+}
+
+int
+xfs_rtsummary_create(
+	struct xfs_rtgroup	*rtg,
+	struct xfs_inode	*ip,
+	struct xfs_trans	*tp,
+	bool			init)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	ip->i_disk_size = mp->m_rsumblocks * mp->m_sb.sb_blocksize;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index b3cbc56aa255ed..e4994a3e461d33 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -315,6 +315,10 @@ xfs_filblks_t xfs_rtsummary_blockcount(struct xfs_mount *mp,
 int xfs_rtfile_initialize_blocks(struct xfs_rtgroup *rtg,
 		enum xfs_rtg_inodes type, xfs_fileoff_t offset_fsb,
 		xfs_fileoff_t end_fsb, void *data);
+int xfs_rtbitmap_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip,
+		struct xfs_trans *tp, bool init);
+int xfs_rtsummary_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip,
+		struct xfs_trans *tp, bool init);
 
 #else /* CONFIG_XFS_RT */
 # define xfs_rtfree_extent(t,b,l)			(-ENOSYS)
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index 22901ecc2cbe22..da29f41e51f1e1 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -272,16 +272,24 @@ struct xfs_rtginode_ops {
 
 	/* Does the fs have this feature? */
 	bool			(*enabled)(struct xfs_mount *mp);
+
+	/* Create this rtgroup metadata inode and initialize it. */
+	int			(*create)(struct xfs_rtgroup *rtg,
+					  struct xfs_inode *ip,
+					  struct xfs_trans *tp,
+					  bool init);
 };
 
 static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
 	[XFS_RTGI_BITMAP] = {
 		.name		= "bitmap",
 		.metafile_type	= XFS_METAFILE_RTBITMAP,
+		.create		= xfs_rtbitmap_create,
 	},
 	[XFS_RTGI_SUMMARY] = {
 		.name		= "summary",
 		.metafile_type	= XFS_METAFILE_RTSUMMARY,
+		.create		= xfs_rtsummary_create,
 	},
 };
 
@@ -389,6 +397,67 @@ xfs_rtginode_irele(
 	*ipp = NULL;
 }
 
+/* Add a metadata inode for a realtime rmap btree. */
+int
+xfs_rtginode_create(
+	struct xfs_rtgroup		*rtg,
+	enum xfs_rtg_inodes		type,
+	bool				init)
+{
+	const struct xfs_rtginode_ops	*ops = &xfs_rtginode_ops[type];
+	struct xfs_mount		*mp = rtg_mount(rtg);
+	struct xfs_metadir_update	upd = {
+		.dp			= mp->m_rtdirip,
+		.metafile_type		= ops->metafile_type,
+	};
+	int				error;
+
+	if (!xfs_rtginode_enabled(rtg, type))
+		return 0;
+
+	if (!mp->m_rtdirip)
+		return -EFSCORRUPTED;
+
+	upd.path = xfs_rtginode_path(rtg_rgno(rtg), type);
+	if (!upd.path)
+		return -ENOMEM;
+
+	error = xfs_metadir_start_create(&upd);
+	if (error)
+		goto out_path;
+
+	error = xfs_metadir_create(&upd, S_IFREG);
+	if (error)
+		return error;
+
+	xfs_rtginode_lockdep_setup(upd.ip, rtg_rgno(rtg), type);
+
+	upd.ip->i_projid = rtg_rgno(rtg);
+	error = ops->create(rtg, upd.ip, upd.tp, init);
+	if (error)
+		goto out_cancel;
+
+	error = xfs_metadir_commit(&upd);
+	if (error)
+		goto out_path;
+
+	kfree(upd.path);
+	xfs_finish_inode_setup(upd.ip);
+	rtg->rtg_inodes[type] = upd.ip;
+	return 0;
+
+out_cancel:
+	xfs_metadir_cancel(&upd, error);
+	/* Have to finish setting up the inode to ensure it's deleted. */
+	if (upd.ip) {
+		xfs_finish_inode_setup(upd.ip);
+		xfs_irele(upd.ip);
+	}
+out_path:
+	kfree(upd.path);
+	return error;
+}
+
 /* Create the parent directory for all rtgroup inodes and load it. */
 int
 xfs_rtginode_mkdir_parent(
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 3732f65ba8a1f6..6ccf31bb6bc7a7 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -242,6 +242,8 @@ enum xfs_metafile_type xfs_rtginode_metafile_type(enum xfs_rtg_inodes type);
 bool xfs_rtginode_enabled(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type);
 int xfs_rtginode_load(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
 		struct xfs_trans *tp);
+int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
+		bool init);
 void xfs_rtginode_irele(struct xfs_inode **ipp);
 
 static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno,
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 3b3ce971a19758..5c1df67b63d6d1 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -711,6 +711,29 @@ xfs_growfs_rt_fixup_extsize(
 	return error;
 }
 
+/* Ensure that the rtgroup metadata inode is loaded, creating it if neeeded. */
+static int
+xfs_rtginode_ensure(
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type)
+{
+	struct xfs_trans	*tp;
+	int			error;
+
+	if (rtg->rtg_inodes[type])
+		return 0;
+
+	error = xfs_trans_alloc_empty(rtg_mount(rtg), &tp);
+	if (error)
+		return error;
+	error = xfs_rtginode_load(rtg, type, tp);
+	xfs_trans_cancel(tp);
+
+	if (error != -ENOENT)
+		return 0;
+	return xfs_rtginode_create(rtg, type, true);
+}
+
 static int
 xfs_growfs_rt_bmblock(
 	struct xfs_rtgroup	*rtg,
@@ -927,12 +950,19 @@ xfs_growfs_rtg(
 	xfs_extlen_t		bmblocks;
 	xfs_fileoff_t		bmbno;
 	struct xfs_rtgroup	*rtg;
+	unsigned int		i;
 	int			error;
 
 	rtg = xfs_rtgroup_grab(mp, 0);
 	if (!rtg)
 		return -EINVAL;
 
+	for (i = 0; i < XFS_RTGI_MAX; i++) {
+		error = xfs_rtginode_ensure(rtg, i);
+		if (error)
+			goto out_rele;
+	}
+
 	error = xfs_growfs_rt_alloc_blocks(rtg, nrblocks, rextsize, &bmblocks);
 	if (error)
 		goto out_rele;

[PATCH 14/21] xfs: remove XFS_ILOCK_RT*

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we've centralized the realtime metadata locking routines, get
rid of the ILOCK subclasses since we now use explicit lockdep classes.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_inode.c   |    3 +--
 fs/xfs/xfs_inode.h   |   13 ++++---------
 fs/xfs/xfs_rtalloc.c |    9 ++++-----
 3 files changed, 9 insertions(+), 16 deletions(-)


diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 103cf8b2af24d0..c8ad2606f928b2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -342,8 +342,7 @@ xfs_lock_inumorder(
 {
 	uint	class = 0;
 
-	ASSERT(!(lock_mode & (XFS_ILOCK_PARENT | XFS_ILOCK_RTBITMAP |
-			      XFS_ILOCK_RTSUM)));
+	ASSERT(!(lock_mode & XFS_ILOCK_PARENT));
 	ASSERT(xfs_lockdep_subclass_ok(subclass));
 
 	if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) {
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index b6e959563547fd..2a4485fb990846 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -448,9 +448,8 @@ static inline bool xfs_inode_has_bigrtalloc(const struct xfs_inode *ip)
  * However, MAX_LOCKDEP_SUBCLASSES == 8, which means we are greatly
  * limited to the subclasses we can represent via nesting. We need at least
  * 5 inodes nest depth for the ILOCK through rename, and we also have to support
- * XFS_ILOCK_PARENT, which gives 6 subclasses. Then we have XFS_ILOCK_RTBITMAP
- * and XFS_ILOCK_RTSUM, which are another 2 unique subclasses, so that's all
- * 8 subclasses supported by lockdep.
+ * XFS_ILOCK_PARENT, which gives 6 subclasses.  That's 6 of the 8 subclasses
+ * supported by lockdep.
  *
  * This also means we have to number the sub-classes in the lowest bits of
  * the mask we keep, and we have to ensure we never exceed 3 bits of lockdep
@@ -476,8 +475,8 @@ static inline bool xfs_inode_has_bigrtalloc(const struct xfs_inode *ip)
  * ILOCK values
  * 0-4		subclass values
  * 5		PARENT subclass (not nestable)
- * 6		RTBITMAP subclass (not nestable)
- * 7		RTSUM subclass (not nestable)
+ * 6		unused
+ * 7		unused
  * 
  */
 #define XFS_IOLOCK_SHIFT		16
@@ -492,12 +491,8 @@ static inline bool xfs_inode_has_bigrtalloc(const struct xfs_inode *ip)
 #define XFS_ILOCK_SHIFT			24
 #define XFS_ILOCK_PARENT_VAL		5u
 #define XFS_ILOCK_MAX_SUBCLASS		(XFS_ILOCK_PARENT_VAL - 1)
-#define XFS_ILOCK_RTBITMAP_VAL		6u
-#define XFS_ILOCK_RTSUM_VAL		7u
 #define XFS_ILOCK_DEP_MASK		0xff000000u
 #define	XFS_ILOCK_PARENT		(XFS_ILOCK_PARENT_VAL << XFS_ILOCK_SHIFT)
-#define	XFS_ILOCK_RTBITMAP		(XFS_ILOCK_RTBITMAP_VAL << XFS_ILOCK_SHIFT)
-#define	XFS_ILOCK_RTSUM			(XFS_ILOCK_RTSUM_VAL << XFS_ILOCK_SHIFT)
 
 #define XFS_LOCK_SUBCLASS_MASK	(XFS_IOLOCK_DEP_MASK | \
 				 XFS_MMAPLOCK_DEP_MASK | \
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 5c1df67b63d6d1..7f3b5e24458bf3 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1189,12 +1189,11 @@ xfs_rtalloc_reinit_frextents(
 static inline int
 xfs_rtmount_iread_extents(
 	struct xfs_trans	*tp,
-	struct xfs_inode	*ip,
-	unsigned int		lock_class)
+	struct xfs_inode	*ip)
 {
 	int			error;
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL | lock_class);
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
 	error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
 	if (error)
@@ -1207,7 +1206,7 @@ xfs_rtmount_iread_extents(
 	}
 
 out_unlock:
-	xfs_iunlock(ip, XFS_ILOCK_EXCL | lock_class);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
 
@@ -1228,7 +1227,7 @@ xfs_rtmount_rtg(
 
 		if (rtg->rtg_inodes[i]) {
 			error = xfs_rtmount_iread_extents(tp,
-					rtg->rtg_inodes[i], 0);
+					rtg->rtg_inodes[i]);
 			if (error)
 				return error;
 		}

[PATCH 15/21] xfs: calculate RT bitmap and summary blocks based on sb_rextents

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Use the on-disk rextents to calculate the bitmap and summary blocks
instead of the calculated one so that we can refactor the helpers for
calculating them.

As the RT bitmap and summary scrubbers already check that sb_rextents
match the block count this does not change coverage of the scrubber.

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/rtbitmap.c  |    3 ++-
 fs/xfs/scrub/rtsummary.c |    5 +++--
 2 files changed, 5 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index c68de973e5f26c..5b42e01a07ac8b 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -67,7 +67,8 @@ xchk_setup_rtbitmap(
 	if (mp->m_sb.sb_rblocks) {
 		rtb->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
 		rtb->rextslog = xfs_compute_rextslog(rtb->rextents);
-		rtb->rbmblocks = xfs_rtbitmap_blockcount(mp, rtb->rextents);
+		rtb->rbmblocks = xfs_rtbitmap_blockcount(mp,
+				mp->m_sb.sb_rextents);
 	}
 
 	return 0;
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index cda5e836862178..7c2b6add44e8c9 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -105,9 +105,10 @@ xchk_setup_rtsummary(
 		int		rextslog;
 
 		rts->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
-		rextslog = xfs_compute_rextslog(rts->rextents);
+		rextslog = xfs_compute_rextslog(mp->m_sb.sb_rextents);
 		rts->rsumlevels = rextslog + 1;
-		rts->rbmblocks = xfs_rtbitmap_blockcount(mp, rts->rextents);
+		rts->rbmblocks = xfs_rtbitmap_blockcount(mp,
+				mp->m_sb.sb_rextents);
 		rts->rsumblocks = xfs_rtsummary_blockcount(mp, rts->rsumlevels,
 				rts->rbmblocks);
 	}

[PATCH 16/21] xfs: factor out a xfs_growfs_rt_alloc_fake_mount helper

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Split the code to set up a fake mount point to calculate new RT
geometry out of xfs_growfs_rt_bmblock so that it can be reused.

Note that this changes the rmblocks calculation method to be based
on the passed in rblocks and extsize and not the explicitly passed
one, but both methods will always lead to the same result.  The new
version just does a little bit more math while being more general.

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_rtalloc.c |   52 +++++++++++++++++++++++++++++++++++---------------
 1 file changed, 36 insertions(+), 16 deletions(-)


diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 7f3b5e24458bf3..e557eee5210419 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -734,6 +734,36 @@ xfs_rtginode_ensure(
 	return xfs_rtginode_create(rtg, type, true);
 }
 
+static struct xfs_mount *
+xfs_growfs_rt_alloc_fake_mount(
+	const struct xfs_mount	*mp,
+	xfs_rfsblock_t		rblocks,
+	xfs_agblock_t		rextsize)
+{
+	struct xfs_mount	*nmp;
+
+	nmp = kmemdup(mp, sizeof(*mp), GFP_KERNEL);
+	if (!nmp)
+		return NULL;
+	nmp->m_sb.sb_rextsize = rextsize;
+	xfs_mount_sb_set_rextsize(nmp, &nmp->m_sb);
+	nmp->m_sb.sb_rblocks = rblocks;
+	nmp->m_sb.sb_rextents = xfs_rtb_to_rtx(nmp, nmp->m_sb.sb_rblocks);
+	nmp->m_sb.sb_rbmblocks = xfs_rtbitmap_blockcount(nmp,
+			nmp->m_sb.sb_rextents);
+	nmp->m_sb.sb_rextslog = xfs_compute_rextslog(nmp->m_sb.sb_rextents);
+	nmp->m_rsumlevels = nmp->m_sb.sb_rextslog + 1;
+	nmp->m_rsumblocks = xfs_rtsummary_blockcount(nmp, nmp->m_rsumlevels,
+			nmp->m_sb.sb_rbmblocks);
+
+	if (rblocks > 0)
+		nmp->m_features |= XFS_FEAT_REALTIME;
+
+	/* recompute growfsrt reservation from new rsumsize */
+	xfs_trans_resv_calc(nmp, &nmp->m_resv);
+	return nmp;
+}
+
 static int
 xfs_growfs_rt_bmblock(
 	struct xfs_rtgroup	*rtg,
@@ -756,25 +786,15 @@ xfs_growfs_rt_bmblock(
 	xfs_rtbxlen_t		freed_rtx;
 	int			error;
 
-
-	nrblocks_step = (bmbno + 1) * NBBY * mp->m_sb.sb_blocksize * rextsize;
-
-	nmp = nargs.mp = kmemdup(mp, sizeof(*mp), GFP_KERNEL);
-	if (!nmp)
-		return -ENOMEM;
-
 	/*
 	 * Calculate new sb and mount fields for this round.
 	 */
-	nmp->m_sb.sb_rextsize = rextsize;
-	xfs_mount_sb_set_rextsize(nmp, &nmp->m_sb);
-	nmp->m_sb.sb_rbmblocks = bmbno + 1;
-	nmp->m_sb.sb_rblocks = min(nrblocks, nrblocks_step);
-	nmp->m_sb.sb_rextents = xfs_rtb_to_rtx(nmp, nmp->m_sb.sb_rblocks);
-	nmp->m_sb.sb_rextslog = xfs_compute_rextslog(nmp->m_sb.sb_rextents);
-	nmp->m_rsumlevels = nmp->m_sb.sb_rextslog + 1;
-	nmp->m_rsumblocks = xfs_rtsummary_blockcount(mp, nmp->m_rsumlevels,
-			nmp->m_sb.sb_rbmblocks);
+	nrblocks_step = (bmbno + 1) * NBBY * mp->m_sb.sb_blocksize * rextsize;
+	nmp = nargs.mp = xfs_growfs_rt_alloc_fake_mount(mp,
+			min(nrblocks, nrblocks_step), rextsize);
+	if (!nmp)
+		return -ENOMEM;
+
 	rtg->rtg_extents = xfs_rtgroup_extents(nmp, rtg_rgno(rtg));
 
 	/*

[PATCH 17/21] xfs: use xfs_growfs_rt_alloc_fake_mount in xfs_growfs_rt_alloc_blocks

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Use xfs_growfs_rt_alloc_fake_mount instead of manually recalculating
the RT bitmap geometry.

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_rtalloc.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index e557eee5210419..e69728c80caf11 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -935,10 +935,10 @@ xfs_growfs_rt_alloc_blocks(
 	struct xfs_mount	*mp = rtg_mount(rtg);
 	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
 	struct xfs_inode	*rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
-	xfs_rtxnum_t		nrextents = div_u64(nrblocks, rextsize);
 	xfs_extlen_t		orbmblocks;
 	xfs_extlen_t		orsumblocks;
 	xfs_extlen_t		nrsumblocks;
+	struct xfs_mount	*nmp;
 	int			error;
 
 	/*
@@ -948,9 +948,13 @@ xfs_growfs_rt_alloc_blocks(
 	orbmblocks = XFS_B_TO_FSB(mp, rbmip->i_disk_size);
 	orsumblocks = XFS_B_TO_FSB(mp, rsumip->i_disk_size);
 
-	*nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents);
-	nrsumblocks = xfs_rtsummary_blockcount(mp,
-		xfs_compute_rextslog(nrextents) + 1, *nrbmblocks);
+	nmp = xfs_growfs_rt_alloc_fake_mount(mp, nrblocks, rextsize);
+	if (!nmp)
+		return -ENOMEM;
+
+	*nrbmblocks = nmp->m_sb.sb_rbmblocks;
+	nrsumblocks = nmp->m_rsumblocks;
+	kfree(nmp);
 
 	error = xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_BITMAP, orbmblocks,
 			*nrbmblocks, NULL);

[PATCH 18/21] xfs: factor out a xfs_growfs_check_rtgeom helper

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Split the check that the rtsummary fits into the log into a separate
helper, and use xfs_growfs_rt_alloc_fake_mount to calculate the new RT
geometry.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
[djwong: avoid division for the 0-rtx growfs check]
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_rtalloc.c |   43 +++++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 14 deletions(-)


diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index e69728c80caf11..d4e55893f8562f 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1023,6 +1023,31 @@ xfs_growfs_rtg(
 	return error;
 }
 
+static int
+xfs_growfs_check_rtgeom(
+	const struct xfs_mount	*mp,
+	xfs_rfsblock_t		rblocks,
+	xfs_extlen_t		rextsize)
+{
+	struct xfs_mount	*nmp;
+	int			error = 0;
+
+	nmp = xfs_growfs_rt_alloc_fake_mount(mp, rblocks, rextsize);
+	if (!nmp)
+		return -ENOMEM;
+
+	/*
+	 * New summary size can't be more than half the size of the log.  This
+	 * prevents us from getting a log overflow, since we'll log basically
+	 * the whole summary file at once.
+	 */
+	if (nmp->m_rsumblocks > (mp->m_sb.sb_logblocks >> 1))
+		error = -EINVAL;
+
+	kfree(nmp);
+	return error;
+}
+
 /*
  * Grow the realtime area of the filesystem.
  */
@@ -1031,9 +1056,6 @@ xfs_growfs_rt(
 	xfs_mount_t	*mp,		/* mount point for filesystem */
 	xfs_growfs_rt_t	*in)		/* growfs rt input struct */
 {
-	xfs_rtxnum_t		nrextents;
-	xfs_extlen_t		nrbmblocks;
-	xfs_extlen_t		nrsumblocks;
 	struct xfs_buf		*bp;
 	xfs_agblock_t		old_rextsize = mp->m_sb.sb_rextsize;
 	int			error;
@@ -1082,20 +1104,13 @@ xfs_growfs_rt(
 	/*
 	 * Calculate new parameters.  These are the final values to be reached.
 	 */
-	nrextents = div_u64(in->newblocks, in->extsize);
 	error = -EINVAL;
-	if (nrextents == 0)
+	if (in->newblocks < in->extsize)
 		goto out_unlock;
-	nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents);
-	nrsumblocks = xfs_rtsummary_blockcount(mp,
-			xfs_compute_rextslog(nrextents) + 1, nrbmblocks);
 
-	/*
-	 * New summary size can't be more than half the size of
-	 * the log.  This prevents us from getting a log overflow,
-	 * since we'll log basically the whole summary file at once.
-	 */
-	if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1))
+	/* Make sure the new fs size won't cause problems with the log. */
+	error = xfs_growfs_check_rtgeom(mp, in->newblocks, in->extsize);
+	if (error)
 		goto out_unlock;
 
 	error = xfs_growfs_rtg(mp, in->newblocks, in->extsize);

[PATCH 19/21] xfs: refactor xfs_rtbitmap_blockcount

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Rename the existing xfs_rtbitmap_blockcount to
xfs_rtbitmap_blockcount_len and add a new xfs_rtbitmap_blockcount wrapper
around it that takes the number of extents from the mount structure.

This will simplify the move to per-rtgroup bitmaps as those will need to
pass in the number of extents per rtgroup instead.

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_rtbitmap.c   |   12 +++++++++++-
 fs/xfs/libxfs/xfs_rtbitmap.h   |    7 ++++---
 fs/xfs/libxfs/xfs_trans_resv.c |    2 +-
 fs/xfs/scrub/rtbitmap.c        |    3 +--
 fs/xfs/scrub/rtsummary.c       |    7 ++-----
 fs/xfs/xfs_rtalloc.c           |    3 +--
 6 files changed, 20 insertions(+), 14 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 6c3354c8efdafa..e9b80ef166c0e8 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1149,13 +1149,23 @@ xfs_rtalloc_extent_is_free(
  * extents.
  */
 xfs_filblks_t
-xfs_rtbitmap_blockcount(
+xfs_rtbitmap_blockcount_len(
 	struct xfs_mount	*mp,
 	xfs_rtbxlen_t		rtextents)
 {
 	return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize);
 }
 
+/*
+ * Compute the number of rtbitmap blocks used for a given file system.
+ */
+xfs_filblks_t
+xfs_rtbitmap_blockcount(
+	struct xfs_mount	*mp)
+{
+	return xfs_rtbitmap_blockcount_len(mp, mp->m_sb.sb_rextents);
+}
+
 /* Compute the number of rtsummary blocks needed to track the given rt space. */
 xfs_filblks_t
 xfs_rtsummary_blockcount(
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index e4994a3e461d33..58672863053a94 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -307,8 +307,9 @@ int xfs_rtfree_extent(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
 int xfs_rtfree_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
 		xfs_fsblock_t rtbno, xfs_filblks_t rtlen);
 
-xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
-		rtextents);
+xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp);
+xfs_filblks_t xfs_rtbitmap_blockcount_len(struct xfs_mount *mp,
+		xfs_rtbxlen_t rtextents);
 xfs_filblks_t xfs_rtsummary_blockcount(struct xfs_mount *mp,
 		unsigned int rsumlevels, xfs_extlen_t rbmblocks);
 
@@ -336,7 +337,7 @@ static inline int xfs_rtfree_blocks(struct xfs_trans *tp,
 # define xfs_rtbuf_cache_relse(a)			(0)
 # define xfs_rtalloc_extent_is_free(m,t,s,l,i)		(-ENOSYS)
 static inline xfs_filblks_t
-xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
+xfs_rtbitmap_blockcount_len(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 {
 	/* shut up gcc */
 	return 0;
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 1a7f95bcf06955..bab402340b5da8 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -224,7 +224,7 @@ xfs_rtalloc_block_count(
 	xfs_rtxlen_t		rtxlen;
 
 	rtxlen = xfs_extlen_to_rtxlen(mp, XFS_MAX_BMBT_EXTLEN);
-	rtbmp_blocks = xfs_rtbitmap_blockcount(mp, rtxlen);
+	rtbmp_blocks = xfs_rtbitmap_blockcount_len(mp, rtxlen);
 	return (rtbmp_blocks + 1) * num_ops;
 }
 
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 5b42e01a07ac8b..ababbf4068d600 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -67,8 +67,7 @@ xchk_setup_rtbitmap(
 	if (mp->m_sb.sb_rblocks) {
 		rtb->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
 		rtb->rextslog = xfs_compute_rextslog(rtb->rextents);
-		rtb->rbmblocks = xfs_rtbitmap_blockcount(mp,
-				mp->m_sb.sb_rextents);
+		rtb->rbmblocks = xfs_rtbitmap_blockcount(mp);
 	}
 
 	return 0;
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 7c2b6add44e8c9..0a6b7902a04cbb 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -107,8 +107,7 @@ xchk_setup_rtsummary(
 		rts->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
 		rextslog = xfs_compute_rextslog(mp->m_sb.sb_rextents);
 		rts->rsumlevels = rextslog + 1;
-		rts->rbmblocks = xfs_rtbitmap_blockcount(mp,
-				mp->m_sb.sb_rextents);
+		rts->rbmblocks = xfs_rtbitmap_blockcount(mp);
 		rts->rsumblocks = xfs_rtsummary_blockcount(mp, rts->rsumlevels,
 				rts->rbmblocks);
 	}
@@ -215,11 +214,9 @@ xchk_rtsum_compute(
 {
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_rtgroup	*rtg = sc->sr.rtg;
-	unsigned long long	rtbmp_blocks;
 
 	/* If the bitmap size doesn't match the computed size, bail. */
-	rtbmp_blocks = xfs_rtbitmap_blockcount(mp, mp->m_sb.sb_rextents);
-	if (XFS_FSB_TO_B(mp, rtbmp_blocks) !=
+	if (XFS_FSB_TO_B(mp, xfs_rtbitmap_blockcount(mp)) !=
 	    rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_disk_size)
 		return -EFSCORRUPTED;
 
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index d4e55893f8562f..7280077a977081 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -749,8 +749,7 @@ xfs_growfs_rt_alloc_fake_mount(
 	xfs_mount_sb_set_rextsize(nmp, &nmp->m_sb);
 	nmp->m_sb.sb_rblocks = rblocks;
 	nmp->m_sb.sb_rextents = xfs_rtb_to_rtx(nmp, nmp->m_sb.sb_rblocks);
-	nmp->m_sb.sb_rbmblocks = xfs_rtbitmap_blockcount(nmp,
-			nmp->m_sb.sb_rextents);
+	nmp->m_sb.sb_rbmblocks = xfs_rtbitmap_blockcount(nmp);
 	nmp->m_sb.sb_rextslog = xfs_compute_rextslog(nmp->m_sb.sb_rextents);
 	nmp->m_rsumlevels = nmp->m_sb.sb_rextslog + 1;
 	nmp->m_rsumblocks = xfs_rtsummary_blockcount(nmp, nmp->m_rsumlevels,

[PATCH 20/21] xfs: refactor xfs_rtsummary_blockcount

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Make xfs_rtsummary_blockcount take all the required information from
the mount structure and return the number of summary levels from it
as well.  This cleans up many of the callers and prepares for making the
rtsummary files per-rtgroup where they need to look at different value.

This means we recalculate some values in some callers, but as all these
calculations are outside the fast path and cheap, which seems like a
price worth paying.

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_rtbitmap.c |   13 +++++++++----
 fs/xfs/libxfs/xfs_rtbitmap.h |    3 +--
 fs/xfs/scrub/rtsummary.c     |    8 ++------
 fs/xfs/xfs_mount.h           |    2 +-
 fs/xfs/xfs_rtalloc.c         |   13 ++++---------
 5 files changed, 17 insertions(+), 22 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index e9b80ef166c0e8..54079edfe10feb 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -20,6 +20,7 @@
 #include "xfs_error.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_health.h"
+#include "xfs_sb.h"
 
 /*
  * Realtime allocator bitmap functions shared with userspace.
@@ -1166,16 +1167,20 @@ xfs_rtbitmap_blockcount(
 	return xfs_rtbitmap_blockcount_len(mp, mp->m_sb.sb_rextents);
 }
 
-/* Compute the number of rtsummary blocks needed to track the given rt space. */
+/*
+ * Compute the geometry of the rtsummary file needed to track the given rt
+ * space.
+ */
 xfs_filblks_t
 xfs_rtsummary_blockcount(
 	struct xfs_mount	*mp,
-	unsigned int		rsumlevels,
-	xfs_extlen_t		rbmblocks)
+	unsigned int		*rsumlevels)
 {
 	unsigned long long	rsumwords;
 
-	rsumwords = (unsigned long long)rsumlevels * rbmblocks;
+	*rsumlevels = xfs_compute_rextslog(mp->m_sb.sb_rextents) + 1;
+
+	rsumwords = xfs_rtbitmap_blockcount(mp) * (*rsumlevels);
 	return XFS_B_TO_FSB(mp, rsumwords << XFS_WORDLOG);
 }
 
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 58672863053a94..776cca9e41bf05 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -311,7 +311,7 @@ xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp);
 xfs_filblks_t xfs_rtbitmap_blockcount_len(struct xfs_mount *mp,
 		xfs_rtbxlen_t rtextents);
 xfs_filblks_t xfs_rtsummary_blockcount(struct xfs_mount *mp,
-		unsigned int rsumlevels, xfs_extlen_t rbmblocks);
+		unsigned int *rsumlevels);
 
 int xfs_rtfile_initialize_blocks(struct xfs_rtgroup *rtg,
 		enum xfs_rtg_inodes type, xfs_fileoff_t offset_fsb,
@@ -342,7 +342,6 @@ xfs_rtbitmap_blockcount_len(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 	/* shut up gcc */
 	return 0;
 }
-# define xfs_rtsummary_blockcount(mp, l, b)		(0)
 #endif /* CONFIG_XFS_RT */
 
 #endif /* __XFS_RTBITMAP_H__ */
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 0a6b7902a04cbb..4125883c6da080 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -102,14 +102,10 @@ xchk_setup_rtsummary(
 	 */
 	xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP);
 	if (mp->m_sb.sb_rblocks) {
-		int		rextslog;
-
 		rts->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
-		rextslog = xfs_compute_rextslog(mp->m_sb.sb_rextents);
-		rts->rsumlevels = rextslog + 1;
 		rts->rbmblocks = xfs_rtbitmap_blockcount(mp);
-		rts->rsumblocks = xfs_rtsummary_blockcount(mp, rts->rsumlevels,
-				rts->rbmblocks);
+		rts->rsumblocks =
+			xfs_rtsummary_blockcount(mp, &rts->rsumlevels);
 	}
 
 	return 0;
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 26ee80a2f391e4..b3554893f38815 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -173,7 +173,7 @@ typedef struct xfs_mount {
 	uint			m_allocsize_blocks; /* min write size blocks */
 	int			m_logbufs;	/* number of log buffers */
 	int			m_logbsize;	/* size of each log buffer */
-	uint			m_rsumlevels;	/* rt summary levels */
+	unsigned int		m_rsumlevels;	/* rt summary levels */
 	xfs_filblks_t		m_rsumblocks;	/* size of rt summary, FSBs */
 	uint32_t		m_rgblocks;	/* size of rtgroup in rtblocks */
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 7280077a977081..2a5c7c1856c912 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -751,9 +751,7 @@ xfs_growfs_rt_alloc_fake_mount(
 	nmp->m_sb.sb_rextents = xfs_rtb_to_rtx(nmp, nmp->m_sb.sb_rblocks);
 	nmp->m_sb.sb_rbmblocks = xfs_rtbitmap_blockcount(nmp);
 	nmp->m_sb.sb_rextslog = xfs_compute_rextslog(nmp->m_sb.sb_rextents);
-	nmp->m_rsumlevels = nmp->m_sb.sb_rextslog + 1;
-	nmp->m_rsumblocks = xfs_rtsummary_blockcount(nmp, nmp->m_rsumlevels,
-			nmp->m_sb.sb_rbmblocks);
+	nmp->m_rsumblocks = xfs_rtsummary_blockcount(nmp, &nmp->m_rsumlevels);
 
 	if (rblocks > 0)
 		nmp->m_features |= XFS_FEAT_REALTIME;
@@ -1138,21 +1136,18 @@ xfs_rtmount_init(
 	struct xfs_mount	*mp)	/* file system mount structure */
 {
 	struct xfs_buf		*bp;	/* buffer for last block of subvolume */
-	struct xfs_sb		*sbp;	/* filesystem superblock copy in mount */
 	xfs_daddr_t		d;	/* address of last block of subvolume */
 	int			error;
 
-	sbp = &mp->m_sb;
-	if (sbp->sb_rblocks == 0)
+	if (mp->m_sb.sb_rblocks == 0)
 		return 0;
 	if (mp->m_rtdev_targp == NULL) {
 		xfs_warn(mp,
 	"Filesystem has a realtime volume, use rtdev=device option");
 		return -ENODEV;
 	}
-	mp->m_rsumlevels = sbp->sb_rextslog + 1;
-	mp->m_rsumblocks = xfs_rtsummary_blockcount(mp, mp->m_rsumlevels,
-			mp->m_sb.sb_rbmblocks);
+
+	mp->m_rsumblocks = xfs_rtsummary_blockcount(mp, &mp->m_rsumlevels);
 
 	/*
 	 * Check that the realtime section is an ok size.

[PATCH 21/21] xfs: make RT extent numbers relative to the rtgroup

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

To prepare for adding per-rtgroup bitmap files, make the xfs_rtxnum_t
type encode the RT extent number relative to the rtgroup.  The biggest
part of this to clearly distinguish between the relative extent number
that gets masked when converting from a global block number and length
values that just have a factor applied to them when converting from
file system blocks.

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_bmap.c     |    6 ++--
 fs/xfs/libxfs/xfs_rtbitmap.h |   69 ++++++++++++++++++++++++++----------------
 fs/xfs/scrub/rtbitmap.c      |    9 ++---
 fs/xfs/scrub/rtsummary.c     |    6 ++--
 fs/xfs/xfs_discard.c         |    4 +-
 fs/xfs/xfs_fsmap.c           |   11 ++++---
 fs/xfs/xfs_iomap.c           |    4 +-
 fs/xfs/xfs_mount.c           |    2 +
 fs/xfs/xfs_rtalloc.c         |    4 +-
 fs/xfs/xfs_super.c           |    3 +-
 10 files changed, 68 insertions(+), 50 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7ba75b4d161618..9bfa8247854d41 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4094,7 +4094,7 @@ xfs_bmapi_reserve_delalloc(
 
 	fdblocks = indlen;
 	if (XFS_IS_REALTIME_INODE(ip)) {
-		error = xfs_dec_frextents(mp, xfs_rtb_to_rtx(mp, alen));
+		error = xfs_dec_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
 		if (error)
 			goto out_unreserve_quota;
 	} else {
@@ -4129,7 +4129,7 @@ xfs_bmapi_reserve_delalloc(
 
 out_unreserve_frextents:
 	if (XFS_IS_REALTIME_INODE(ip))
-		xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, alen));
+		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
 out_unreserve_quota:
 	if (XFS_IS_QUOTA_ON(mp))
 		xfs_quota_unreserve_blkres(ip, alen);
@@ -5037,7 +5037,7 @@ xfs_bmap_del_extent_delay(
 	fdblocks = da_diff;
 
 	if (isrt)
-		xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, del->br_blockcount));
+		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, del->br_blockcount));
 	else
 		fdblocks += del->br_blockcount;
 
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 776cca9e41bf05..b2b9e59a87a278 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -22,13 +22,37 @@ struct xfs_rtalloc_args {
 
 static inline xfs_rtblock_t
 xfs_rtx_to_rtb(
-	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
 	xfs_rtxnum_t		rtx)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	xfs_rtblock_t		start = xfs_rgno_start_rtb(mp, rtg_rgno(rtg));
+
+	if (mp->m_rtxblklog >= 0)
+		return start + (rtx << mp->m_rtxblklog);
+	return start + (rtx * mp->m_sb.sb_rextsize);
+}
+
+/* Convert an rgbno into an rt extent number. */
+static inline xfs_rtxnum_t
+xfs_rgbno_to_rtx(
+	struct xfs_mount	*mp,
+	xfs_rgblock_t		rgbno)
+{
+	if (likely(mp->m_rtxblklog >= 0))
+		return rgbno >> mp->m_rtxblklog;
+	return rgbno / mp->m_sb.sb_rextsize;
+}
+
+static inline uint64_t
+xfs_rtbxlen_to_blen(
+	struct xfs_mount	*mp,
+	xfs_rtbxlen_t		rtbxlen)
 {
 	if (mp->m_rtxblklog >= 0)
-		return rtx << mp->m_rtxblklog;
+		return rtbxlen << mp->m_rtxblklog;
 
-	return rtx * mp->m_sb.sb_rextsize;
+	return rtbxlen * mp->m_sb.sb_rextsize;
 }
 
 static inline xfs_extlen_t
@@ -65,16 +89,29 @@ xfs_extlen_to_rtxlen(
 	return len / mp->m_sb.sb_rextsize;
 }
 
+/* Convert an rt block count into an rt extent count. */
+static inline xfs_rtbxlen_t
+xfs_blen_to_rtbxlen(
+	struct xfs_mount	*mp,
+	uint64_t		blen)
+{
+	if (likely(mp->m_rtxblklog >= 0))
+		return blen >> mp->m_rtxblklog;
+
+	return div_u64(blen, mp->m_sb.sb_rextsize);
+}
+
 /* Convert an rt block number into an rt extent number. */
 static inline xfs_rtxnum_t
 xfs_rtb_to_rtx(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
-	if (likely(mp->m_rtxblklog >= 0))
-		return rtbno >> mp->m_rtxblklog;
+	uint64_t		__rgbno = __xfs_rtb_to_rgbno(mp, rtbno);
 
-	return div_u64(rtbno, mp->m_sb.sb_rextsize);
+	if (likely(mp->m_rtxblklog >= 0))
+		return __rgbno >> mp->m_rtxblklog;
+	return div_u64(__rgbno, mp->m_sb.sb_rextsize);
 }
 
 /* Return the offset of an rt block number within an rt extent. */
@@ -89,26 +126,6 @@ xfs_rtb_to_rtxoff(
 	return do_div(rtbno, mp->m_sb.sb_rextsize);
 }
 
-/*
- * Convert an rt block number into an rt extent number, rounding up to the next
- * rt extent if the rt block is not aligned to an rt extent boundary.
- */
-static inline xfs_rtxnum_t
-xfs_rtb_to_rtxup(
-	struct xfs_mount	*mp,
-	xfs_rtblock_t		rtbno)
-{
-	if (likely(mp->m_rtxblklog >= 0)) {
-		if (rtbno & mp->m_rtxblkmask)
-			return (rtbno >> mp->m_rtxblklog) + 1;
-		return rtbno >> mp->m_rtxblklog;
-	}
-
-	if (do_div(rtbno, mp->m_sb.sb_rextsize))
-		rtbno++;
-	return rtbno;
-}
-
 /* Round this rtblock up to the nearest rt extent size. */
 static inline xfs_rtblock_t
 xfs_rtb_roundup_rtx(
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index ababbf4068d600..376a36fd9a9cdd 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -65,7 +65,7 @@ xchk_setup_rtbitmap(
 	 */
 	xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP);
 	if (mp->m_sb.sb_rblocks) {
-		rtb->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
+		rtb->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks);
 		rtb->rextslog = xfs_compute_rextslog(rtb->rextents);
 		rtb->rbmblocks = xfs_rtbitmap_blockcount(mp);
 	}
@@ -83,15 +83,14 @@ xchk_rtbitmap_rec(
 	const struct xfs_rtalloc_rec *rec,
 	void			*priv)
 {
-	struct xfs_mount	*mp = rtg_mount(rtg);
 	struct xfs_scrub	*sc = priv;
 	xfs_rtblock_t		startblock;
 	xfs_filblks_t		blockcount;
 
-	startblock = xfs_rtx_to_rtb(mp, rec->ar_startext);
-	blockcount = xfs_rtx_to_rtb(mp, rec->ar_extcount);
+	startblock = xfs_rtx_to_rtb(rtg, rec->ar_startext);
+	blockcount = xfs_rtxlen_to_extlen(rtg_mount(rtg), rec->ar_extcount);
 
-	if (!xfs_verify_rtbext(mp, startblock, blockcount))
+	if (!xfs_verify_rtbext(rtg_mount(rtg), startblock, blockcount))
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 	return 0;
 }
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 4125883c6da080..8f3f69b26cad04 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -102,7 +102,7 @@ xchk_setup_rtsummary(
 	 */
 	xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP);
 	if (mp->m_sb.sb_rblocks) {
-		rts->rextents = xfs_rtb_to_rtx(mp, mp->m_sb.sb_rblocks);
+		rts->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks);
 		rts->rbmblocks = xfs_rtbitmap_blockcount(mp);
 		rts->rsumblocks =
 			xfs_rtsummary_blockcount(mp, &rts->rsumlevels);
@@ -182,8 +182,8 @@ xchk_rtsum_record_free(
 	lenlog = xfs_highbit64(rec->ar_extcount);
 	offs = xfs_rtsumoffs(mp, lenlog, rbmoff);
 
-	rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
-	rtlen = xfs_rtx_to_rtb(mp, rec->ar_extcount);
+	rtbno = xfs_rtx_to_rtb(rtg, rec->ar_startext);
+	rtlen = xfs_rtxlen_to_extlen(mp, rec->ar_extcount);
 
 	if (!xfs_verify_rtbext(mp, rtbno, rtlen)) {
 		xchk_ino_xref_set_corrupt(sc,
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index fe9d6b81ea2a2f..4f3e4736f13ea6 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -526,8 +526,8 @@ xfs_trim_gather_rtextent(
 		return -ECANCELED;
 	}
 
-	rbno = xfs_rtx_to_rtb(rtg_mount(rtg), rec->ar_startext);
-	rlen = xfs_rtx_to_rtb(rtg_mount(rtg), rec->ar_extcount);
+	rbno = xfs_rtx_to_rtb(rtg, rec->ar_startext);
+	rlen = xfs_rtbxlen_to_blen(rtg_mount(rtg), rec->ar_extcount);
 
 	/* Ignore too small. */
 	if (rlen < tr->minlen_fsb) {
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index b14e0e306f8a34..82f2e0dd224997 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -722,7 +722,10 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
 	};
 	struct xfs_mount		*mp = rtg_mount(rtg);
 	struct xfs_getfsmap_info	*info = priv;
-	xfs_rtblock_t			rtbno;
+	xfs_rtblock_t			start_rtb =
+				xfs_rtx_to_rtb(rtg, rec->ar_startext);
+	uint64_t			rtbcount =
+				xfs_rtbxlen_to_blen(mp, rec->ar_extcount);
 
 	/*
 	 * For an info->last query, we're looking for a gap between the last
@@ -736,12 +739,10 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
 	if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL) {
 		frec.start_daddr = info->end_daddr;
 	} else {
-		rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
-		frec.start_daddr = xfs_rtb_to_daddr(mp, rtbno);
+		frec.start_daddr = xfs_rtb_to_daddr(mp, start_rtb);
 	}
 
-	rtbno = xfs_rtx_to_rtb(mp, rec->ar_extcount);
-	frec.len_daddr = XFS_FSB_TO_BB(mp, rtbno);
+	frec.len_daddr = XFS_FSB_TO_BB(mp, rtbcount);
 	return xfs_getfsmap_helper(tp, info, &frec);
 }
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 86da16f54be9d7..e810e901cd3576 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -501,8 +501,8 @@ xfs_iomap_prealloc_size(
 				       alloc_blocks);
 
 	if (unlikely(XFS_IS_REALTIME_INODE(ip)))
-		freesp = xfs_rtx_to_rtb(mp,
-			xfs_iomap_freesp(&mp->m_frextents,
+		freesp = xfs_rtbxlen_to_blen(mp,
+				xfs_iomap_freesp(&mp->m_frextents,
 					mp->m_low_rtexts, &shift));
 	else
 		freesp = xfs_iomap_freesp(&mp->m_fdblocks, mp->m_low_space,
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 9464eddf9212e9..dba1f6fc688166 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1474,7 +1474,7 @@ xfs_mod_delalloc(
 
 	if (XFS_IS_REALTIME_INODE(ip)) {
 		percpu_counter_add_batch(&mp->m_delalloc_rtextents,
-				xfs_rtb_to_rtx(mp, data_delta),
+				xfs_blen_to_rtbxlen(mp, data_delta),
 				XFS_DELALLOC_BATCH);
 		if (!ind_delta)
 			return;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 2a5c7c1856c912..d9fb5e9c0aaf87 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -748,7 +748,7 @@ xfs_growfs_rt_alloc_fake_mount(
 	nmp->m_sb.sb_rextsize = rextsize;
 	xfs_mount_sb_set_rextsize(nmp, &nmp->m_sb);
 	nmp->m_sb.sb_rblocks = rblocks;
-	nmp->m_sb.sb_rextents = xfs_rtb_to_rtx(nmp, nmp->m_sb.sb_rblocks);
+	nmp->m_sb.sb_rextents = xfs_blen_to_rtbxlen(nmp, nmp->m_sb.sb_rblocks);
 	nmp->m_sb.sb_rbmblocks = xfs_rtbitmap_blockcount(nmp);
 	nmp->m_sb.sb_rextslog = xfs_compute_rextslog(nmp->m_sb.sb_rextents);
 	nmp->m_rsumblocks = xfs_rtsummary_blockcount(nmp, &nmp->m_rsumlevels);
@@ -1463,7 +1463,7 @@ xfs_rtallocate(
 	xfs_trans_mod_sb(tp, wasdel ?
 			XFS_TRANS_SB_RES_FREXTENTS : XFS_TRANS_SB_FREXTENTS,
 			-(long)len);
-	*bno = xfs_rtx_to_rtb(args.mp, rtx);
+	*bno = xfs_rtx_to_rtb(args.rtg, rtx);
 	*blen = xfs_rtxlen_to_extlen(args.mp, len);
 
 out_release:
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index be493d39296005..9ae352dfdd6c57 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -885,7 +885,8 @@ xfs_fs_statfs(
 
 		statp->f_blocks = sbp->sb_rblocks;
 		freertx = percpu_counter_sum_positive(&mp->m_frextents);
-		statp->f_bavail = statp->f_bfree = xfs_rtx_to_rtb(mp, freertx);
+		statp->f_bavail = statp->f_bfree =
+			xfs_rtbxlen_to_blen(mp, freertx);
 	}
 
 	return 0;

[PATCH 1/2] xfs: fix rt device offset calculations for FITRIM

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

FITRIM on xfs has this bizarro uapi where we flatten all the physically
addressable storage across two block devices into a linear address
space.  In this address space, the realtime device comes immediately
after the data device.  Therefore, the xfs_trim_rtdev_extents has to
convert its input parameters from the linear address space to actual
rtdev block addresses on the realtime volume.

Right now the address space conversion is done in units of rtblocks.
However, a future patchset will convert xfs_rtblock_t to be a segmented
address space (group:blkno) like the data device.  Change the conversion
code to be done in units of daddrs since those will never be segmented.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_discard.c |   19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)


diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 4f3e4736f13ea6..42b8b5e0e931b7 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -480,7 +480,7 @@ xfs_discard_rtdev_extents(
 		trace_xfs_discard_rtextent(mp, busyp->bno, busyp->length);
 
 		error = __blkdev_issue_discard(bdev,
-				XFS_FSB_TO_BB(mp, busyp->bno),
+				xfs_rtb_to_daddr(mp, busyp->bno),
 				XFS_FSB_TO_BB(mp, busyp->length),
 				GFP_NOFS, &bio);
 		if (error)
@@ -612,22 +612,25 @@ xfs_trim_rtdev_extents(
 	xfs_rtblock_t		start_rtbno, end_rtbno;
 	xfs_rtxnum_t		start_rtx, end_rtx;
 	xfs_rgnumber_t		start_rgno, end_rgno;
+	xfs_daddr_t		daddr_offset;
 	int			last_error = 0, error;
 	struct xfs_rtgroup	*rtg = NULL;
 
 	/* Shift the start and end downwards to match the rt device. */
+	daddr_offset = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
+	if (start > daddr_offset)
+		start -= daddr_offset;
+	else
+		start = 0;
 	start_rtbno = xfs_daddr_to_rtb(mp, start);
-	if (start_rtbno > mp->m_sb.sb_dblocks)
-		start_rtbno -= mp->m_sb.sb_dblocks;
-	else
-		start_rtbno = 0;
 	start_rtx = xfs_rtb_to_rtx(mp, start_rtbno);
 	start_rgno = xfs_rtb_to_rgno(mp, start_rtbno);
 
+	if (end <= daddr_offset)
+		return 0;
+	else
+		end -= daddr_offset;
 	end_rtbno = xfs_daddr_to_rtb(mp, end);
-	if (end_rtbno <= mp->m_sb.sb_dblocks)
-		return 0;
-	end_rtbno -= mp->m_sb.sb_dblocks;
 	end_rtx = xfs_rtb_to_rtx(mp, end_rtbno + mp->m_sb.sb_rextsize - 1);
 	end_rgno = xfs_rtb_to_rgno(mp, end_rtbno);
 

[PATCH 2/2] iomap: add a merge boundary flag

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

File systems might have boundaries over which merges aren't possible.
In fact these are very common, although most of the time some kind of
header at the beginning of this region (e.g. XFS alloation groups, ext4
block groups) automatically create a merge barrier.  But if that is
not present, say for a device purely used for data we need to manually
communicate that to iomap.

Add a IOMAP_F_BOUNDARY flag to never merge I/O into a previous mapping.

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/iomap/buffered-io.c |    6 ++++++
 include/linux/iomap.h  |    4 ++++
 2 files changed, 10 insertions(+)


diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index ef0b68bccbb612..fcadd31017d138 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1601,6 +1601,8 @@ iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
 {
 	if (ioend->io_bio.bi_status != next->io_bio.bi_status)
 		return false;
+	if (next->io_flags & IOMAP_F_BOUNDARY)
+		return false;
 	if ((ioend->io_flags & IOMAP_F_SHARED) ^
 	    (next->io_flags & IOMAP_F_SHARED))
 		return false;
@@ -1720,6 +1722,8 @@ static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
 	INIT_LIST_HEAD(&ioend->io_list);
 	ioend->io_type = wpc->iomap.type;
 	ioend->io_flags = wpc->iomap.flags;
+	if (pos > wpc->iomap.offset)
+		wpc->iomap.flags &= ~IOMAP_F_BOUNDARY;
 	ioend->io_inode = inode;
 	ioend->io_size = 0;
 	ioend->io_offset = pos;
@@ -1731,6 +1735,8 @@ static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
 
 static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos)
 {
+	if (wpc->iomap.offset == pos && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
+		return false;
 	if ((wpc->iomap.flags & IOMAP_F_SHARED) !=
 	    (wpc->ioend->io_flags & IOMAP_F_SHARED))
 		return false;
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index f61407e3b12192..9ecb8ea7714cf9 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -53,6 +53,9 @@ struct vm_fault;
  *
  * IOMAP_F_XATTR indicates that the iomap is for an extended attribute extent
  * rather than a file data extent.
+ *
+ * IOMAP_F_BOUNDARY indicates that I/O and I/O completions for this iomap must
+ * never be merged with the mapping before it.
  */
 #define IOMAP_F_NEW		(1U << 0)
 #define IOMAP_F_DIRTY		(1U << 1)
@@ -64,6 +67,7 @@ struct vm_fault;
 #define IOMAP_F_BUFFER_HEAD	0
 #endif /* CONFIG_BUFFER_HEAD */
 #define IOMAP_F_XATTR		(1U << 5)
+#define IOMAP_F_BOUNDARY	(1U << 6)
 
 /*
  * Flags set by the core iomap code during operations:

[PATCH 01/34] xfs: define the format of rt groups

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Define the ondisk format of realtime group metadata, and a superblock
for realtime volumes.  rt supers are conditionally enabled by a
predicate function so that they can be disabled if we ever implement
zoned storage support for the realtime volume.

For rt group enabled file systems there is a separate bitmap and summary
file for each group and thus the number of bitmap and summary blocks
needs to be calculated differently.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_format.h   |   42 +++++++++++++++++-
 fs/xfs/libxfs/xfs_ondisk.h   |    3 +
 fs/xfs/libxfs/xfs_rtbitmap.c |   20 +++++++-
 fs/xfs/libxfs/xfs_rtgroup.c  |   82 ++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_sb.c       |  100 +++++++++++++++++++++++++++++++++++++-----
 fs/xfs/libxfs/xfs_shared.h   |    1 
 fs/xfs/xfs_mount.h           |    6 ++-
 fs/xfs/xfs_rtalloc.c         |   30 +++++++++++--
 8 files changed, 262 insertions(+), 22 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 867060d60e8583..3cf044a2d5f2a9 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -265,8 +265,15 @@ struct xfs_dsb {
 	uuid_t		sb_meta_uuid;	/* metadata file system unique id */
 
 	__be64		sb_metadirino;	/* metadata directory tree root */
+	__be32		sb_rgcount;	/* # of realtime groups */
+	__be32		sb_rgextents;	/* size of rtgroup in rtx */
 
-	/* must be padded to 64 bit alignment */
+	/*
+	 * The size of this structure must be padded to 64 bit alignment.
+	 *
+	 * NOTE: Don't forget to update secondary_sb_whack in xfs_repair when
+	 * adding new fields here.
+	 */
 };
 
 #define XFS_SB_CRC_OFF		offsetof(struct xfs_dsb, sb_crc)
@@ -716,6 +723,39 @@ union xfs_suminfo_raw {
 	__u32		old;
 };
 
+/*
+ * Realtime allocation groups break the rt section into multiple pieces that
+ * could be locked independently.  Realtime block group numbers are 32-bit
+ * quantities.  Block numbers within a group are also 32-bit quantities, but
+ * the upper bit must never be set.  rtgroup 0 might have a superblock in it,
+ * so the minimum size of an rtgroup is 2 rtx.
+ */
+#define XFS_MAX_RGBLOCKS	((xfs_rgblock_t)(1U << 31) - 1)
+#define XFS_MIN_RGEXTENTS	((xfs_rtxlen_t)2)
+#define XFS_MAX_RGNUMBER	((xfs_rgnumber_t)(-1U))
+
+#define XFS_RTSB_MAGIC	0x46726F67	/* 'Frog' */
+
+/*
+ * Realtime superblock - on disk version.  Must be padded to 64 bit alignment.
+ * The first block of the realtime volume contains this superblock.
+ */
+struct xfs_rtsb {
+	__be32		rsb_magicnum;	/* magic number == XFS_RTSB_MAGIC */
+	__le32		rsb_crc;	/* superblock crc */
+
+	__be32		rsb_pad;	/* zero */
+	unsigned char	rsb_fname[XFSLABEL_MAX]; /* file system name */
+
+	uuid_t		rsb_uuid;	/* user-visible file system unique id */
+	uuid_t		rsb_meta_uuid;	/* metadata file system unique id */
+
+	/* must be padded to 64 bit alignment */
+};
+
+#define XFS_RTSB_CRC_OFF	offsetof(struct xfs_rtsb, rsb_crc)
+#define XFS_RTSB_DADDR		((xfs_daddr_t)0) /* daddr in rt section */
+
 /*
  * XFS Timestamps
  * ==============
diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 8bca86e350fdc1..38b314113d8f24 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -37,7 +37,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dinode,		176);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot,		104);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk,			136);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			272);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			280);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr,		56);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key,		4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec,		16);
@@ -53,6 +53,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t,			4);
 	XFS_CHECK_STRUCT_SIZE(xfs_refcount_ptr_t,		4);
 	XFS_CHECK_STRUCT_SIZE(xfs_rmap_ptr_t,			4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rtsb,			56);
 
 	/* dir/attr trees */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr,	80);
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 54079edfe10feb..416bbcd92af2ad 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1157,6 +1157,21 @@ xfs_rtbitmap_blockcount_len(
 	return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize);
 }
 
+/* How many rt extents does each rtbitmap file track? */
+static inline xfs_rtbxlen_t
+xfs_rtbitmap_bitcount(
+	struct xfs_mount	*mp)
+{
+	if (!mp->m_sb.sb_rextents)
+		return 0;
+
+	/* rtgroup size can be nonzero even if rextents is zero */
+	if (xfs_has_rtgroups(mp))
+		return mp->m_sb.sb_rgextents;
+
+	return mp->m_sb.sb_rextents;
+}
+
 /*
  * Compute the number of rtbitmap blocks used for a given file system.
  */
@@ -1164,7 +1179,7 @@ xfs_filblks_t
 xfs_rtbitmap_blockcount(
 	struct xfs_mount	*mp)
 {
-	return xfs_rtbitmap_blockcount_len(mp, mp->m_sb.sb_rextents);
+	return xfs_rtbitmap_blockcount_len(mp, xfs_rtbitmap_bitcount(mp));
 }
 
 /*
@@ -1178,8 +1193,7 @@ xfs_rtsummary_blockcount(
 {
 	unsigned long long	rsumwords;
 
-	*rsumlevels = xfs_compute_rextslog(mp->m_sb.sb_rextents) + 1;
-
+	*rsumlevels = xfs_compute_rextslog(xfs_rtbitmap_bitcount(mp)) + 1;
 	rsumwords = xfs_rtbitmap_blockcount(mp) * (*rsumlevels);
 	return XFS_B_TO_FSB(mp, rsumwords << XFS_WORDLOG);
 }
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index da29f41e51f1e1..9e2ca61559f45e 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -28,6 +28,7 @@
 #include "xfs_trace.h"
 #include "xfs_inode.h"
 #include "xfs_icache.h"
+#include "xfs_buf_item.h"
 #include "xfs_rtgroup.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_metafile.h"
@@ -482,3 +483,84 @@ xfs_rtginode_load_parent(
 	return xfs_metadir_load(tp, mp->m_metadirip, "rtgroups",
 			XFS_METAFILE_DIR, &mp->m_rtdirip);
 }
+
+/* Check superblock fields for a read or a write. */
+static xfs_failaddr_t
+xfs_rtsb_verify_common(
+	struct xfs_buf		*bp)
+{
+	struct xfs_rtsb		*rsb = bp->b_addr;
+
+	if (!xfs_verify_magic(bp, rsb->rsb_magicnum))
+		return __this_address;
+	if (rsb->rsb_pad)
+		return __this_address;
+
+	/* Everything to the end of the fs block must be zero */
+	if (memchr_inv(rsb + 1, 0, BBTOB(bp->b_length) - sizeof(*rsb)))
+		return __this_address;
+
+	return NULL;
+}
+
+/* Check superblock fields for a read or revalidation. */
+static inline xfs_failaddr_t
+xfs_rtsb_verify_all(
+	struct xfs_buf		*bp)
+{
+	struct xfs_rtsb		*rsb = bp->b_addr;
+	struct xfs_mount	*mp = bp->b_mount;
+	xfs_failaddr_t		fa;
+
+	fa = xfs_rtsb_verify_common(bp);
+	if (fa)
+		return fa;
+
+	if (memcmp(&rsb->rsb_fname, &mp->m_sb.sb_fname, XFSLABEL_MAX))
+		return __this_address;
+	if (!uuid_equal(&rsb->rsb_uuid, &mp->m_sb.sb_uuid))
+		return __this_address;
+	if (!uuid_equal(&rsb->rsb_meta_uuid, &mp->m_sb.sb_meta_uuid))
+		return  __this_address;
+
+	return NULL;
+}
+
+static void
+xfs_rtsb_read_verify(
+	struct xfs_buf		*bp)
+{
+	xfs_failaddr_t		fa;
+
+	if (!xfs_buf_verify_cksum(bp, XFS_RTSB_CRC_OFF)) {
+		xfs_verifier_error(bp, -EFSBADCRC, __this_address);
+		return;
+	}
+
+	fa = xfs_rtsb_verify_all(bp);
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+static void
+xfs_rtsb_write_verify(
+	struct xfs_buf		*bp)
+{
+	xfs_failaddr_t		fa;
+
+	fa = xfs_rtsb_verify_common(bp);
+	if (fa) {
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+		return;
+	}
+
+	xfs_buf_update_cksum(bp, XFS_RTSB_CRC_OFF);
+}
+
+const struct xfs_buf_ops xfs_rtsb_buf_ops = {
+	.name		= "xfs_rtsb",
+	.magic		= { 0, cpu_to_be32(XFS_RTSB_MAGIC) },
+	.verify_read	= xfs_rtsb_read_verify,
+	.verify_write	= xfs_rtsb_write_verify,
+	.verify_struct	= xfs_rtsb_verify_all,
+};
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 21891aa10ada02..b5f798d01dba05 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -234,11 +234,22 @@ xfs_validate_sb_read(
 	return 0;
 }
 
+/* Return the number of extents covered by a single rt bitmap file */
+static xfs_rtbxlen_t
+xfs_extents_per_rbm(
+	struct xfs_sb		*sbp)
+{
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR))
+		return sbp->sb_rgextents;
+	return sbp->sb_rextents;
+}
+
 static uint64_t
-xfs_sb_calc_rbmblocks(
+xfs_expected_rbmblocks(
 	struct xfs_sb		*sbp)
 {
-	return howmany_64(sbp->sb_rextents, NBBY * sbp->sb_blocksize);
+	return howmany_64(xfs_extents_per_rbm(sbp), NBBY * sbp->sb_blocksize);
 }
 
 /* Validate the realtime geometry */
@@ -260,7 +271,7 @@ xfs_validate_rt_geometry(
 	if (sbp->sb_rextents == 0 ||
 	    sbp->sb_rextents != div_u64(sbp->sb_rblocks, sbp->sb_rextsize) ||
 	    sbp->sb_rextslog != xfs_compute_rextslog(sbp->sb_rextents) ||
-	    sbp->sb_rbmblocks != xfs_sb_calc_rbmblocks(sbp))
+	    sbp->sb_rbmblocks != xfs_expected_rbmblocks(sbp))
 		return false;
 
 	return true;
@@ -341,6 +352,59 @@ xfs_validate_sb_write(
 	return 0;
 }
 
+static int
+xfs_validate_sb_rtgroups(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp)
+{
+	uint64_t		groups;
+
+	if (sbp->sb_rextsize == 0) {
+		xfs_warn(mp,
+"Realtime extent size must not be zero.");
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rgextents > XFS_MAX_RGBLOCKS / sbp->sb_rextsize) {
+		xfs_warn(mp,
+"Realtime group size (%u) must be less than %u rt extents.",
+				sbp->sb_rgextents,
+				XFS_MAX_RGBLOCKS / sbp->sb_rextsize);
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rgextents < XFS_MIN_RGEXTENTS) {
+		xfs_warn(mp,
+"Realtime group size (%u) must be at least %u rt extents.",
+				sbp->sb_rgextents, XFS_MIN_RGEXTENTS);
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rgcount > XFS_MAX_RGNUMBER) {
+		xfs_warn(mp,
+"Realtime groups (%u) must be less than %u.",
+				sbp->sb_rgcount, XFS_MAX_RGNUMBER);
+		return -EINVAL;
+	}
+
+	groups = howmany_64(sbp->sb_rextents, sbp->sb_rgextents);
+	if (groups != sbp->sb_rgcount) {
+		xfs_warn(mp,
+"Realtime groups (%u) do not cover the entire rt section; need (%llu) groups.",
+				sbp->sb_rgcount, groups);
+		return -EINVAL;
+	}
+
+	/* Exchange-range is required for fsr to work on realtime files */
+	if (!(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE)) {
+		xfs_warn(mp,
+"Realtime groups feature requires exchange-range support.");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* Check the validity of the SB. */
 STATIC int
 xfs_validate_sb_common(
@@ -352,6 +416,7 @@ xfs_validate_sb_common(
 	uint32_t		agcount = 0;
 	uint32_t		rem;
 	bool			has_dalign;
+	int			error;
 
 	if (!xfs_verify_magic(bp, dsb->sb_magicnum)) {
 		xfs_warn(mp,
@@ -401,6 +466,12 @@ xfs_validate_sb_common(
 				return -EINVAL;
 			}
 		}
+
+		if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
+			error = xfs_validate_sb_rtgroups(mp, sbp);
+			if (error)
+				return error;
+		}
 	} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
 				XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
 			xfs_notice(mp,
@@ -692,13 +763,15 @@ __xfs_sb_from_disk(
 	if (convert_xquota)
 		xfs_sb_quota_from_disk(to);
 
-	if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
+	if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
 		to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
-	else
+		to->sb_rgcount = be32_to_cpu(from->sb_rgcount);
+		to->sb_rgextents = be32_to_cpu(from->sb_rgextents);
+	} else {
 		to->sb_metadirino = NULLFSINO;
-
-	to->sb_rgcount = 1;
-	to->sb_rgextents = 0;
+		to->sb_rgcount = 1;
+		to->sb_rgextents = 0;
+	}
 }
 
 void
@@ -847,8 +920,11 @@ xfs_sb_to_disk(
 	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID)
 		uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid);
 
-	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
+	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
 		to->sb_metadirino = cpu_to_be64(from->sb_metadirino);
+		to->sb_rgcount = cpu_to_be32(from->sb_rgcount);
+		to->sb_rgextents = cpu_to_be32(from->sb_rgextents);
+	}
 }
 
 /*
@@ -988,9 +1064,9 @@ xfs_mount_sb_set_rextsize(
 	mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize);
 	mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize);
 
-	mp->m_rgblocks = 0;
-	mp->m_rgblklog = 0;
-	mp->m_rgblkmask = (uint64_t)-1;
+	mp->m_rgblocks = sbp->sb_rgextents * sbp->sb_rextsize;
+	mp->m_rgblklog = log2_if_power2(mp->m_rgblocks);
+	mp->m_rgblkmask = mask64_if_power2(mp->m_rgblocks);
 
 	rgs->blocks = 0;
 	rgs->blklog = 0;
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 33b84a3a83ff63..552365d212ea26 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -39,6 +39,7 @@ extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_refcountbt_buf_ops;
 extern const struct xfs_buf_ops xfs_rmapbt_buf_ops;
 extern const struct xfs_buf_ops xfs_rtbuf_ops;
+extern const struct xfs_buf_ops xfs_rtsb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
 extern const struct xfs_buf_ops xfs_symlink_buf_ops;
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index b3554893f38815..c8ac858dc95bc5 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -387,12 +387,14 @@ __XFS_HAS_FEAT(metadir, METADIR)
 
 static inline bool xfs_has_rtgroups(struct xfs_mount *mp)
 {
-	return false;
+	/* all metadir file systems also allow rtgroups */
+	return xfs_has_metadir(mp);
 }
 
 static inline bool xfs_has_rtsb(struct xfs_mount *mp)
 {
-	return false;
+	/* all rtgroups filesystems with an rt section have an rtsb */
+	return xfs_has_rtgroups(mp) && xfs_has_realtime(mp);
 }
 
 /*
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index d9fb5e9c0aaf87..b4687a8759b171 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -751,6 +751,11 @@ xfs_growfs_rt_alloc_fake_mount(
 	nmp->m_sb.sb_rextents = xfs_blen_to_rtbxlen(nmp, nmp->m_sb.sb_rblocks);
 	nmp->m_sb.sb_rbmblocks = xfs_rtbitmap_blockcount(nmp);
 	nmp->m_sb.sb_rextslog = xfs_compute_rextslog(nmp->m_sb.sb_rextents);
+	if (xfs_has_rtgroups(nmp))
+		nmp->m_sb.sb_rgcount = howmany_64(nmp->m_sb.sb_rextents,
+						  nmp->m_sb.sb_rgextents);
+	else
+		nmp->m_sb.sb_rgcount = 1;
 	nmp->m_rsumblocks = xfs_rtsummary_blockcount(nmp, &nmp->m_rsumlevels);
 
 	if (rblocks > 0)
@@ -761,6 +766,26 @@ xfs_growfs_rt_alloc_fake_mount(
 	return nmp;
 }
 
+static xfs_rfsblock_t
+xfs_growfs_rt_nrblocks(
+	struct xfs_rtgroup	*rtg,
+	xfs_rfsblock_t		nrblocks,
+	xfs_agblock_t		rextsize,
+	xfs_fileoff_t		bmbno)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	xfs_rfsblock_t		step;
+
+	step = (bmbno + 1) * NBBY * mp->m_sb.sb_blocksize * rextsize;
+	if (xfs_has_rtgroups(mp)) {
+		xfs_rfsblock_t	rgblocks = mp->m_sb.sb_rgextents * rextsize;
+
+		step = min(rgblocks, step) + rgblocks * rtg_rgno(rtg);
+	}
+
+	return min(nrblocks, step);
+}
+
 static int
 xfs_growfs_rt_bmblock(
 	struct xfs_rtgroup	*rtg,
@@ -779,16 +804,15 @@ xfs_growfs_rt_bmblock(
 		.rtg		= rtg,
 	};
 	struct xfs_mount	*nmp;
-	xfs_rfsblock_t		nrblocks_step;
 	xfs_rtbxlen_t		freed_rtx;
 	int			error;
 
 	/*
 	 * Calculate new sb and mount fields for this round.
 	 */
-	nrblocks_step = (bmbno + 1) * NBBY * mp->m_sb.sb_blocksize * rextsize;
 	nmp = nargs.mp = xfs_growfs_rt_alloc_fake_mount(mp,
-			min(nrblocks, nrblocks_step), rextsize);
+			xfs_growfs_rt_nrblocks(rtg, nrblocks, rextsize, bmbno),
+			rextsize);
 	if (!nmp)
 		return -ENOMEM;
 

[PATCH 02/34] xfs: check the realtime superblock at mount time

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check the realtime superblock at mount time, to ensure that the label
and uuids actually match the primary superblock on the data device.  If
the rt superblock is good, attach it to the xfs_mount so that the log
can use ordered buffers to keep this primary in sync with the primary
super on the data device.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_mount.h   |    1 +
 fs/xfs/xfs_rtalloc.c |   50 ++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_rtalloc.h |    6 ++++++
 fs/xfs/xfs_super.c   |   12 ++++++++++--
 4 files changed, 67 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index c8ac858dc95bc5..33fb03547c88ac 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -119,6 +119,7 @@ typedef struct xfs_mount {
 	struct super_block	*m_super;
 	struct xfs_ail		*m_ail;		/* fs active log item list */
 	struct xfs_buf		*m_sb_bp;	/* buffer for superblock */
+	struct xfs_buf		*m_rtsb_bp;	/* realtime superblock */
 	char			*m_rtname;	/* realtime device name */
 	char			*m_logname;	/* external log device name */
 	struct xfs_da_geometry	*m_dir_geo;	/* directory block geometry */
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index b4687a8759b171..abeedc848b3bd2 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1152,6 +1152,56 @@ xfs_growfs_rt(
 	return error;
 }
 
+/* Read the realtime superblock and attach it to the mount. */
+int
+xfs_rtmount_readsb(
+	struct xfs_mount	*mp)
+{
+	struct xfs_buf		*bp;
+	int			error;
+
+	if (!xfs_has_rtsb(mp))
+		return 0;
+	if (mp->m_sb.sb_rblocks == 0)
+		return 0;
+	if (mp->m_rtdev_targp == NULL) {
+		xfs_warn(mp,
+	"Filesystem has a realtime volume, use rtdev=device option");
+		return -ENODEV;
+	}
+
+	/* m_blkbb_log is not set up yet */
+	error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_RTSB_DADDR,
+			mp->m_sb.sb_blocksize >> BBSHIFT, XBF_NO_IOACCT, &bp,
+			&xfs_rtsb_buf_ops);
+	if (error) {
+		xfs_warn(mp, "rt sb validate failed with error %d.", error);
+		/* bad CRC means corrupted metadata */
+		if (error == -EFSBADCRC)
+			error = -EFSCORRUPTED;
+		return error;
+	}
+
+	mp->m_rtsb_bp = bp;
+	xfs_buf_unlock(bp);
+	return 0;
+}
+
+/* Detach the realtime superblock from the mount and free it. */
+void
+xfs_rtmount_freesb(
+	struct xfs_mount	*mp)
+{
+	struct xfs_buf		*bp = mp->m_rtsb_bp;
+
+	if (!bp)
+		return;
+
+	xfs_buf_lock(bp);
+	mp->m_rtsb_bp = NULL;
+	xfs_buf_relse(bp);
+}
+
 /*
  * Initialize realtime fields in the mount structure.
  */
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index a6836da9bebef5..8e2a07b8174b74 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -12,6 +12,10 @@ struct xfs_mount;
 struct xfs_trans;
 
 #ifdef CONFIG_XFS_RT
+/* rtgroup superblock initialization */
+int xfs_rtmount_readsb(struct xfs_mount *mp);
+void xfs_rtmount_freesb(struct xfs_mount *mp);
+
 /*
  * Initialize realtime fields in the mount structure.
  */
@@ -42,6 +46,8 @@ int xfs_rtalloc_reinit_frextents(struct xfs_mount *mp);
 #else
 # define xfs_growfs_rt(mp,in)				(-ENOSYS)
 # define xfs_rtalloc_reinit_frextents(m)		(0)
+# define xfs_rtmount_readsb(mp)				(0)
+# define xfs_rtmount_freesb(mp)				((void)0)
 static inline int		/* error */
 xfs_rtmount_init(
 	xfs_mount_t	*mp)	/* file system mount structure */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 9ae352dfdd6c57..3afeab6844680a 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -45,6 +45,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_exchmaps_item.h"
 #include "xfs_parent.h"
+#include "xfs_rtalloc.h"
 #include "scrub/stats.h"
 #include "scrub/rcbag_btree.h"
 
@@ -1145,6 +1146,7 @@ xfs_fs_put_super(
 	xfs_filestream_unmount(mp);
 	xfs_unmountfs(mp);
 
+	xfs_rtmount_freesb(mp);
 	xfs_freesb(mp);
 	xchk_mount_stats_free(mp);
 	free_percpu(mp->m_stats.xs_stats);
@@ -1690,9 +1692,13 @@ xfs_fs_fill_super(
 		goto out_free_sb;
 	}
 
+	error = xfs_rtmount_readsb(mp);
+	if (error)
+		goto out_free_sb;
+
 	error = xfs_filestream_mount(mp);
 	if (error)
-		goto out_free_sb;
+		goto out_free_rtsb;
 
 	/*
 	 * we must configure the block size in the superblock before we run the
@@ -1781,6 +1787,8 @@ xfs_fs_fill_super(
 
  out_filestream_unmount:
 	xfs_filestream_unmount(mp);
+ out_free_rtsb:
+	xfs_rtmount_freesb(mp);
  out_free_sb:
 	xfs_freesb(mp);
  out_free_scrub_stats:
@@ -1800,7 +1808,7 @@ xfs_fs_fill_super(
  out_unmount:
 	xfs_filestream_unmount(mp);
 	xfs_unmountfs(mp);
-	goto out_free_sb;
+	goto out_free_rtsb;
 }
 
 static int

[PATCH 03/34] xfs: update realtime super every time we update the primary fs super

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Every time we update parts of the primary filesystem superblock that are
echoed in the rt superblock, we must update the rt super.  Avoid
changing the log to support logging to the rt device by using ordered
buffers.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_rtgroup.c   |   60 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_rtgroup.h   |    7 +++++
 fs/xfs/libxfs/xfs_sb.c        |   14 +++++++++-
 fs/xfs/libxfs/xfs_sb.h        |    2 +
 fs/xfs/xfs_buf_item_recover.c |   12 ++++++++
 fs/xfs/xfs_ioctl.c            |    4 ++-
 fs/xfs/xfs_trans.c            |    1 +
 fs/xfs/xfs_trans.h            |    1 +
 fs/xfs/xfs_trans_buf.c        |   25 ++++++++++++++---
 9 files changed, 118 insertions(+), 8 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index 9e2ca61559f45e..470260c911c8d1 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -564,3 +564,63 @@ const struct xfs_buf_ops xfs_rtsb_buf_ops = {
 	.verify_write	= xfs_rtsb_write_verify,
 	.verify_struct	= xfs_rtsb_verify_all,
 };
+
+/* Update a realtime superblock from the primary fs super */
+void
+xfs_update_rtsb(
+	struct xfs_buf		*rtsb_bp,
+	const struct xfs_buf	*sb_bp)
+{
+	const struct xfs_dsb	*dsb = sb_bp->b_addr;
+	struct xfs_rtsb		*rsb = rtsb_bp->b_addr;
+	const uuid_t		*meta_uuid;
+
+	rsb->rsb_magicnum = cpu_to_be32(XFS_RTSB_MAGIC);
+
+	rsb->rsb_pad = 0;
+	memcpy(&rsb->rsb_fname, &dsb->sb_fname, XFSLABEL_MAX);
+
+	memcpy(&rsb->rsb_uuid, &dsb->sb_uuid, sizeof(rsb->rsb_uuid));
+
+	/*
+	 * The metadata uuid is the fs uuid if the metauuid feature is not
+	 * enabled.
+	 */
+	if (dsb->sb_features_incompat &
+				cpu_to_be32(XFS_SB_FEAT_INCOMPAT_META_UUID))
+		meta_uuid = &dsb->sb_meta_uuid;
+	else
+		meta_uuid = &dsb->sb_uuid;
+	memcpy(&rsb->rsb_meta_uuid, meta_uuid, sizeof(rsb->rsb_meta_uuid));
+}
+
+/*
+ * Update the realtime superblock from a filesystem superblock and log it to
+ * the given transaction.
+ */
+struct xfs_buf *
+xfs_log_rtsb(
+	struct xfs_trans	*tp,
+	const struct xfs_buf	*sb_bp)
+{
+	struct xfs_buf		*rtsb_bp;
+
+	if (!xfs_has_rtsb(tp->t_mountp))
+		return NULL;
+
+	rtsb_bp = xfs_trans_getrtsb(tp);
+	if (!rtsb_bp) {
+		/*
+		 * It's possible for the rtgroups feature to be enabled but
+		 * there is no incore rt superblock buffer if the rt geometry
+		 * was specified at mkfs time but the rt section has not yet
+		 * been attached.  In this case, rblocks must be zero.
+		 */
+		ASSERT(tp->t_mountp->m_sb.sb_rblocks == 0);
+		return NULL;
+	}
+
+	xfs_update_rtsb(rtsb_bp, sb_bp);
+	xfs_trans_ordered_buf(tp, rtsb_bp);
+	return rtsb_bp;
+}
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 6ccf31bb6bc7a7..e7679fafff8ce7 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -251,6 +251,11 @@ static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno,
 {
 	return kasprintf(GFP_KERNEL, "%u.%s", rgno, xfs_rtginode_name(type));
 }
+
+void xfs_update_rtsb(struct xfs_buf *rtsb_bp,
+		const struct xfs_buf *sb_bp);
+struct xfs_buf *xfs_log_rtsb(struct xfs_trans *tp,
+		const struct xfs_buf *sb_bp);
 #else
 static inline void xfs_free_rtgroups(struct xfs_mount *mp,
 		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno)
@@ -269,6 +274,8 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
 # define xfs_rtgroup_lock(rtg, gf)		((void)0)
 # define xfs_rtgroup_unlock(rtg, gf)		((void)0)
 # define xfs_rtgroup_trans_join(tp, rtg, gf)	((void)0)
+# define xfs_update_rtsb(bp, sb_bp)	((void)0)
+# define xfs_log_rtsb(tp, sb_bp)	(NULL)
 #endif /* CONFIG_XFS_RT */
 
 #endif /* __LIBXFS_RTGROUP_H */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index b5f798d01dba05..6b0757d60cf3af 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -27,6 +27,7 @@
 #include "xfs_ag.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_exchrange.h"
+#include "xfs_rtgroup.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -1276,10 +1277,12 @@ xfs_update_secondary_sbs(
  */
 int
 xfs_sync_sb_buf(
-	struct xfs_mount	*mp)
+	struct xfs_mount	*mp,
+	bool			update_rtsb)
 {
 	struct xfs_trans	*tp;
 	struct xfs_buf		*bp;
+	struct xfs_buf		*rtsb_bp = NULL;
 	int			error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp);
@@ -1289,6 +1292,11 @@ xfs_sync_sb_buf(
 	bp = xfs_trans_getsb(tp);
 	xfs_log_sb(tp);
 	xfs_trans_bhold(tp, bp);
+	if (update_rtsb) {
+		rtsb_bp = xfs_log_rtsb(tp, bp);
+		if (rtsb_bp)
+			xfs_trans_bhold(tp, rtsb_bp);
+	}
 	xfs_trans_set_sync(tp);
 	error = xfs_trans_commit(tp);
 	if (error)
@@ -1297,7 +1305,11 @@ xfs_sync_sb_buf(
 	 * write out the sb buffer to get the changes to disk
 	 */
 	error = xfs_bwrite(bp);
+	if (!error && rtsb_bp)
+		error = xfs_bwrite(rtsb_bp);
 out:
+	if (rtsb_bp)
+		xfs_buf_relse(rtsb_bp);
 	xfs_buf_relse(bp);
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 885c837559914d..999dcfccdaf960 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -15,7 +15,7 @@ struct xfs_perag;
 
 extern void	xfs_log_sb(struct xfs_trans *tp);
 extern int	xfs_sync_sb(struct xfs_mount *mp, bool wait);
-extern int	xfs_sync_sb_buf(struct xfs_mount *mp);
+extern int	xfs_sync_sb_buf(struct xfs_mount *mp, bool update_rtsb);
 extern void	xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp);
 void		xfs_mount_sb_set_rextsize(struct xfs_mount *mp,
 			struct xfs_sb *sbp);
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index c8259ee482fd86..feb3db2e891614 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -1061,6 +1061,18 @@ xlog_recover_buf_commit_pass2(
 				current_lsn);
 		if (error)
 			goto out_release;
+
+		/* Update the rt superblock if we have one. */
+		if (xfs_has_rtsb(mp) && mp->m_rtsb_bp) {
+			struct xfs_buf	*rtsb_bp = mp->m_rtsb_bp;
+
+			xfs_buf_lock(rtsb_bp);
+			xfs_buf_hold(rtsb_bp);
+			xfs_update_rtsb(rtsb_bp, bp);
+			rtsb_bp->b_flags |= _XBF_LOGRECOVERY;
+			xfs_buf_delwri_queue(rtsb_bp, buffer_list);
+			xfs_buf_relse(rtsb_bp);
+		}
 	} else {
 		xlog_recover_do_reg_buffer(mp, item, bp, buf_f, current_lsn);
 	}
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index f36fd8db388cca..1e233abed7ce6d 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1028,7 +1028,7 @@ xfs_ioc_setlabel(
 	 * buffered reads from userspace (i.e. from blkid) are invalidated,
 	 * and userspace will see the newly-written label.
 	 */
-	error = xfs_sync_sb_buf(mp);
+	error = xfs_sync_sb_buf(mp, true);
 	if (error)
 		goto out;
 	/*
@@ -1039,6 +1039,8 @@ xfs_ioc_setlabel(
 	mutex_unlock(&mp->m_growlock);
 
 	invalidate_bdev(mp->m_ddev_targp->bt_bdev);
+	if (xfs_has_rtsb(mp) && mp->m_rtdev_targp)
+		invalidate_bdev(mp->m_rtdev_targp->bt_bdev);
 
 out:
 	mnt_drop_write_file(filp);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index cee7f0564409bd..118d31e11127be 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -25,6 +25,7 @@
 #include "xfs_dquot.h"
 #include "xfs_icache.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
 
 struct kmem_cache	*xfs_trans_cache;
 
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index f06cc0f41665ad..f97e5c416efad1 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -214,6 +214,7 @@ xfs_trans_read_buf(
 }
 
 struct xfs_buf	*xfs_trans_getsb(struct xfs_trans *);
+struct xfs_buf	*xfs_trans_getrtsb(struct xfs_trans *tp);
 
 void		xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_bjoin(xfs_trans_t *, struct xfs_buf *);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index e28ab74af4f0e1..8e886ecfd69a3b 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -168,12 +168,11 @@ xfs_trans_get_buf_map(
 /*
  * Get and lock the superblock buffer for the given transaction.
  */
-struct xfs_buf *
-xfs_trans_getsb(
-	struct xfs_trans	*tp)
+static struct xfs_buf *
+__xfs_trans_getsb(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
-	struct xfs_buf		*bp = tp->t_mountp->m_sb_bp;
-
 	/*
 	 * Just increment the lock recursion count if the buffer is already
 	 * attached to this transaction.
@@ -197,6 +196,22 @@ xfs_trans_getsb(
 	return bp;
 }
 
+struct xfs_buf *
+xfs_trans_getsb(
+	struct xfs_trans	*tp)
+{
+	return __xfs_trans_getsb(tp, tp->t_mountp->m_sb_bp);
+}
+
+struct xfs_buf *
+xfs_trans_getrtsb(
+	struct xfs_trans	*tp)
+{
+	if (!tp->t_mountp->m_rtsb_bp)
+		return NULL;
+	return __xfs_trans_getsb(tp, tp->t_mountp->m_rtsb_bp);
+}
+
 /*
  * Get and lock the buffer for the caller if it is not already
  * locked within the given transaction.  If it has not yet been

[PATCH 04/34] xfs: export realtime group geometry via XFS_FSOP_GEOM

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Export the realtime geometry information so that userspace can query it.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_fs.h |    4 +++-
 fs/xfs/libxfs/xfs_sb.c |    5 +++++
 2 files changed, 8 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index faa38a7d1eb019..5c224d03270ce9 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -187,7 +187,9 @@ struct xfs_fsop_geom {
 	__u32		logsunit;	/* log stripe unit, bytes	*/
 	uint32_t	sick;		/* o: unhealthy fs & rt metadata */
 	uint32_t	checked;	/* o: checked fs & rt metadata	*/
-	__u64		reserved[17];	/* reserved space		*/
+	__u32		rgextents;	/* rt extents in a realtime group */
+	__u32		rgcount;	/* number of realtime groups	*/
+	__u64		reserved[16];	/* reserved space		*/
 };
 
 #define XFS_FSOP_GEOM_SICK_COUNTERS	(1 << 0)  /* summary counters */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 6b0757d60cf3af..b1e12c7e7dbe23 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1413,6 +1413,11 @@ xfs_fs_geometry(
 		return;
 
 	geo->version = XFS_FSOP_GEOM_VERSION_V5;
+
+	if (xfs_has_rtgroups(mp)) {
+		geo->rgcount = sbp->sb_rgcount;
+		geo->rgextents = sbp->sb_rgextents;
+	}
 }
 
 /* Read a secondary superblock. */

[PATCH 05/34] xfs: check that rtblock extents do not break rtsupers or rtgroups

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check that rt block pointers do not point to the realtime superblock and
that allocated rt space extents do not cross rtgroup boundaries.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_types.c |   38 +++++++++++++++++++++++++++++++++-----
 1 file changed, 33 insertions(+), 5 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index 1cbfe57e971d5c..a4c30844d42be1 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -12,6 +12,8 @@
 #include "xfs_bit.h"
 #include "xfs_mount.h"
 #include "xfs_ag.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
 
 
 /*
@@ -135,18 +137,37 @@ xfs_verify_dir_ino(
 }
 
 /*
- * Verify that an realtime block number pointer doesn't point off the
- * end of the realtime device.
+ * Verify that a realtime block number pointer neither points outside the
+ * allocatable areas of the rtgroup nor off the end of the realtime
+ * device.
  */
 inline bool
 xfs_verify_rtbno(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
-	return rtbno < mp->m_sb.sb_rblocks;
+	if (rtbno >= mp->m_sb.sb_rblocks)
+		return false;
+
+	if (xfs_has_rtgroups(mp)) {
+		xfs_rgnumber_t	rgno = xfs_rtb_to_rgno(mp, rtbno);
+		xfs_rtxnum_t	rtx = xfs_rtb_to_rtx(mp, rtbno);
+
+		if (rgno >= mp->m_sb.sb_rgcount)
+			return false;
+		if (rtx >= xfs_rtgroup_extents(mp, rgno))
+			return false;
+		if (xfs_has_rtsb(mp) && rgno == 0 && rtx == 0)
+			return false;
+	}
+	return true;
 }
 
-/* Verify that a realtime device extent is fully contained inside the volume. */
+/*
+ * Verify that an allocated realtime device extent neither points outside
+ * allocatable areas of the rtgroup, across an rtgroup boundary, nor off the
+ * end of the realtime device.
+ */
 bool
 xfs_verify_rtbext(
 	struct xfs_mount	*mp,
@@ -159,7 +180,14 @@ xfs_verify_rtbext(
 	if (!xfs_verify_rtbno(mp, rtbno))
 		return false;
 
-	return xfs_verify_rtbno(mp, rtbno + len - 1);
+	if (!xfs_verify_rtbno(mp, rtbno + len - 1))
+		return false;
+
+	if (xfs_has_rtgroups(mp) &&
+	    xfs_rtb_to_rgno(mp, rtbno) != xfs_rtb_to_rgno(mp, rtbno + len - 1))
+		return false;
+
+	return true;
 }
 
 /* Calculate the range of valid icount values. */

[PATCH 06/34] xfs: add a helper to prevent bmap merges across rtgroup boundaries

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Except for the rt superblock, realtime groups do not store any metadata
at the start (or end) of the group.  There is nothing to prevent the
bmap code from merging allocations from multiple groups into a single
bmap record.  Add a helper to check for this case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
[djwong: massage the commit message after pulling this into rtgroups]
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c |   56 ++++++++++++++++++++++++++++++++++++----------
 1 file changed, 44 insertions(+), 12 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 9bfa8247854d41..482b4c0cd6b193 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -40,6 +40,7 @@
 #include "xfs_bmap_item.h"
 #include "xfs_symlink_remote.h"
 #include "xfs_inode_util.h"
+#include "xfs_rtgroup.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
@@ -1426,6 +1427,24 @@ xfs_bmap_last_offset(
  * Extent tree manipulation functions used during allocation.
  */
 
+static inline bool
+xfs_bmap_same_rtgroup(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	struct xfs_bmbt_irec	*left,
+	struct xfs_bmbt_irec	*right)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (xfs_ifork_is_realtime(ip, whichfork) && xfs_has_rtgroups(mp)) {
+		if (xfs_rtb_to_rgno(mp, left->br_startblock) !=
+		    xfs_rtb_to_rgno(mp, right->br_startblock))
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * Convert a delayed allocation to a real allocation.
  */
@@ -1495,7 +1514,8 @@ xfs_bmap_add_extent_delay_real(
 	    LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
 	    LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
 	    LEFT.br_state == new->br_state &&
-	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
+	    xfs_bmap_same_rtgroup(bma->ip, whichfork, &LEFT, new))
 		state |= BMAP_LEFT_CONTIG;
 
 	/*
@@ -1519,7 +1539,8 @@ xfs_bmap_add_extent_delay_real(
 		      (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
 		       BMAP_RIGHT_FILLING) ||
 	     LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
-			<= XFS_MAX_BMBT_EXTLEN))
+			<= XFS_MAX_BMBT_EXTLEN) &&
+	    xfs_bmap_same_rtgroup(bma->ip, whichfork, new, &RIGHT))
 		state |= BMAP_RIGHT_CONTIG;
 
 	error = 0;
@@ -2064,7 +2085,8 @@ xfs_bmap_add_extent_unwritten_real(
 	    LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
 	    LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
 	    LEFT.br_state == new->br_state &&
-	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, &LEFT, new))
 		state |= BMAP_LEFT_CONTIG;
 
 	/*
@@ -2088,7 +2110,8 @@ xfs_bmap_add_extent_unwritten_real(
 		      (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
 		       BMAP_RIGHT_FILLING) ||
 	     LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
-			<= XFS_MAX_BMBT_EXTLEN))
+			<= XFS_MAX_BMBT_EXTLEN) &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, new, &RIGHT))
 		state |= BMAP_RIGHT_CONTIG;
 
 	/*
@@ -2597,7 +2620,8 @@ xfs_bmap_add_extent_hole_delay(
 	 */
 	if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) &&
 	    left.br_startoff + left.br_blockcount == new->br_startoff &&
-	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, &left, new))
 		state |= BMAP_LEFT_CONTIG;
 
 	if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) &&
@@ -2605,7 +2629,8 @@ xfs_bmap_add_extent_hole_delay(
 	    new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
 	    (!(state & BMAP_LEFT_CONTIG) ||
 	     (left.br_blockcount + new->br_blockcount +
-	      right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)))
+	      right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)) &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, new, &right))
 		state |= BMAP_RIGHT_CONTIG;
 
 	/*
@@ -2748,7 +2773,8 @@ xfs_bmap_add_extent_hole_real(
 	    left.br_startoff + left.br_blockcount == new->br_startoff &&
 	    left.br_startblock + left.br_blockcount == new->br_startblock &&
 	    left.br_state == new->br_state &&
-	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, &left, new))
 		state |= BMAP_LEFT_CONTIG;
 
 	if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) &&
@@ -2758,7 +2784,8 @@ xfs_bmap_add_extent_hole_real(
 	    new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
 	    (!(state & BMAP_LEFT_CONTIG) ||
 	     left.br_blockcount + new->br_blockcount +
-	     right.br_blockcount <= XFS_MAX_BMBT_EXTLEN))
+	     right.br_blockcount <= XFS_MAX_BMBT_EXTLEN) &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, new, &right))
 		state |= BMAP_RIGHT_CONTIG;
 
 	error = 0;
@@ -5715,6 +5742,8 @@ xfs_bunmapi(
  */
 STATIC bool
 xfs_bmse_can_merge(
+	struct xfs_inode	*ip,
+	int			whichfork,
 	struct xfs_bmbt_irec	*left,	/* preceding extent */
 	struct xfs_bmbt_irec	*got,	/* current extent to shift */
 	xfs_fileoff_t		shift)	/* shift fsb */
@@ -5730,7 +5759,8 @@ xfs_bmse_can_merge(
 	if ((left->br_startoff + left->br_blockcount != startoff) ||
 	    (left->br_startblock + left->br_blockcount != got->br_startblock) ||
 	    (left->br_state != got->br_state) ||
-	    (left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN))
+	    (left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN) ||
+	    !xfs_bmap_same_rtgroup(ip, whichfork, left, got))
 		return false;
 
 	return true;
@@ -5766,7 +5796,7 @@ xfs_bmse_merge(
 	blockcount = left->br_blockcount + got->br_blockcount;
 
 	xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
-	ASSERT(xfs_bmse_can_merge(left, got, shift));
+	ASSERT(xfs_bmse_can_merge(ip, whichfork, left, got, shift));
 
 	new = *left;
 	new.br_blockcount = blockcount;
@@ -5928,7 +5958,8 @@ xfs_bmap_collapse_extents(
 			goto del_cursor;
 		}
 
-		if (xfs_bmse_can_merge(&prev, &got, offset_shift_fsb)) {
+		if (xfs_bmse_can_merge(ip, whichfork, &prev, &got,
+				offset_shift_fsb)) {
 			error = xfs_bmse_merge(tp, ip, whichfork,
 					offset_shift_fsb, &icur, &got, &prev,
 					cur, &logflags);
@@ -6064,7 +6095,8 @@ xfs_bmap_insert_extents(
 		 * never find mergeable extents in this scenario.  Check anyways
 		 * and warn if we encounter two extents that could be one.
 		 */
-		if (xfs_bmse_can_merge(&got, &next, offset_shift_fsb))
+		if (xfs_bmse_can_merge(ip, whichfork, &got, &next,
+				offset_shift_fsb))
 			WARN_ON_ONCE(1);
 	}
 

[PATCH 07/34] xfs: add frextents to the lazysbcounters when rtgroups enabled

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Make the free rt extent count a part of the lazy sb counters when the
realtime groups feature is enabled.  This is possible because the patch
to recompute frextents from the rtbitmap during log recovery predates
the code adding rtgroup support, hence we know that the value will
always be correct during runtime.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_sb.c           |   15 ++++++++++-----
 fs/xfs/scrub/fscounters_repair.c |    9 +++++----
 fs/xfs/xfs_trans.c               |   33 +++++++++++++++++++--------------
 3 files changed, 34 insertions(+), 23 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index b1e12c7e7dbe23..d5bf886e18ab9e 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1152,11 +1152,6 @@ xfs_log_sb(
 	 * reservations that have been taken out percpu counters. If we have an
 	 * unclean shutdown, this will be corrected by log recovery rebuilding
 	 * the counters from the AGF block counts.
-	 *
-	 * Do not update sb_frextents here because it is not part of the lazy
-	 * sb counters, despite having a percpu counter. It is always kept
-	 * consistent with the ondisk rtbitmap by xfs_trans_apply_sb_deltas()
-	 * and hence we don't need have to update it here.
 	 */
 	if (xfs_has_lazysbcount(mp)) {
 		mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount);
@@ -1167,6 +1162,16 @@ xfs_log_sb(
 				percpu_counter_sum_positive(&mp->m_fdblocks);
 	}
 
+	/*
+	 * sb_frextents was added to the lazy sb counters when the rt groups
+	 * feature was introduced.  This counter can go negative due to the way
+	 * we handle nearly-lockless reservations, so we must use the _positive
+	 * variant here to avoid writing out nonsense frextents.
+	 */
+	if (xfs_has_rtgroups(mp))
+		mp->m_sb.sb_frextents =
+				percpu_counter_sum_positive(&mp->m_frextents);
+
 	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
 	xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb) - 1);
diff --git a/fs/xfs/scrub/fscounters_repair.c b/fs/xfs/scrub/fscounters_repair.c
index 469bf645dbea52..cda13447a373e1 100644
--- a/fs/xfs/scrub/fscounters_repair.c
+++ b/fs/xfs/scrub/fscounters_repair.c
@@ -68,15 +68,16 @@ xrep_fscounters(
 
 	/*
 	 * Online repair is only supported on v5 file systems, which require
-	 * lazy sb counters and thus no update of sb_fdblocks here.  But as of
-	 * now we don't support lazy counting sb_frextents yet, and thus need
-	 * to also update it directly here.  And for that we need to keep
+	 * lazy sb counters and thus no update of sb_fdblocks here.  But
+	 * sb_frextents only uses a lazy counter with rtgroups, and thus needs
+	 * to be updated directly here otherwise.  And for that we need to keep
 	 * track of the delalloc reservations separately, as they are are
 	 * subtracted from m_frextents, but not included in sb_frextents.
 	 */
 	percpu_counter_set(&mp->m_frextents,
 		fsc->frextents - fsc->frextents_delayed);
-	mp->m_sb.sb_frextents = fsc->frextents;
+	if (!xfs_has_rtgroups(mp))
+		mp->m_sb.sb_frextents = fsc->frextents;
 
 	return 0;
 }
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 118d31e11127be..01b5f5b32af467 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -421,6 +421,8 @@ xfs_trans_mod_sb(
 			ASSERT(tp->t_rtx_res_used <= tp->t_rtx_res);
 		}
 		tp->t_frextents_delta += delta;
+		if (xfs_has_rtgroups(mp))
+			flags &= ~XFS_TRANS_SB_DIRTY;
 		break;
 	case XFS_TRANS_SB_RES_FREXTENTS:
 		/*
@@ -430,6 +432,8 @@ xfs_trans_mod_sb(
 		 */
 		ASSERT(delta < 0);
 		tp->t_res_frextents_delta += delta;
+		if (xfs_has_rtgroups(mp))
+			flags &= ~XFS_TRANS_SB_DIRTY;
 		break;
 	case XFS_TRANS_SB_DBLOCKS:
 		tp->t_dblocks_delta += delta;
@@ -498,20 +502,22 @@ xfs_trans_apply_sb_deltas(
 	}
 
 	/*
-	 * Updating frextents requires careful handling because it does not
-	 * behave like the lazysb counters because we cannot rely on log
-	 * recovery in older kenels to recompute the value from the rtbitmap.
-	 * This means that the ondisk frextents must be consistent with the
-	 * rtbitmap.
+	 * sb_frextents was added to the lazy sb counters when the rt groups
+	 * feature was introduced.  This is possible because we know that all
+	 * kernels supporting rtgroups will also recompute frextents from the
+	 * realtime bitmap.
+	 *
+	 * For older file systems, updating frextents requires careful handling
+	 * because we cannot rely on log recovery in older kernels to recompute
+	 * the value from the rtbitmap.  This means that the ondisk frextents
+	 * must be consistent with the rtbitmap.
 	 *
 	 * Therefore, log the frextents change to the ondisk superblock and
 	 * update the incore superblock so that future calls to xfs_log_sb
 	 * write the correct value ondisk.
-	 *
-	 * Don't touch m_frextents because it includes incore reservations,
-	 * and those are handled by the unreserve function.
 	 */
-	if (tp->t_frextents_delta || tp->t_res_frextents_delta) {
+	if ((tp->t_frextents_delta || tp->t_res_frextents_delta) &&
+	    !xfs_has_rtgroups(tp->t_mountp)) {
 		struct xfs_mount	*mp = tp->t_mountp;
 		int64_t			rtxdelta;
 
@@ -619,7 +625,7 @@ xfs_trans_unreserve_and_mod_sb(
 	}
 
 	ASSERT(tp->t_rtx_res || tp->t_frextents_delta >= 0);
-	if (tp->t_flags & XFS_TRANS_SB_DIRTY) {
+	if (xfs_has_rtgroups(mp) || (tp->t_flags & XFS_TRANS_SB_DIRTY)) {
 		rtxdelta += tp->t_frextents_delta;
 		ASSERT(rtxdelta >= 0);
 	}
@@ -652,10 +658,9 @@ xfs_trans_unreserve_and_mod_sb(
 	mp->m_sb.sb_icount += idelta;
 	mp->m_sb.sb_ifree += ifreedelta;
 	/*
-	 * Do not touch sb_frextents here because we are dealing with incore
-	 * reservation.  sb_frextents is not part of the lazy sb counters so it
-	 * must be consistent with the ondisk rtbitmap and must never include
-	 * incore reservations.
+	 * Do not touch sb_frextents here because it is handled in
+	 * xfs_trans_apply_sb_deltas for file systems where it isn't a lazy
+	 * counter anyway.
 	 */
 	mp->m_sb.sb_dblocks += tp->t_dblocks_delta;
 	mp->m_sb.sb_agcount += tp->t_agcount_delta;

[PATCH 08/34] xfs: convert sick_map loops to use ARRAY_SIZE

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Convert these arrays to use ARRAY_SIZE insteead of requiring an empty
sentinel array element at the end.  This saves memory and would have
avoided a bug that worked its way into the next patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_health.c |   15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)


diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index e5663e2ac9b853..b0d0c6bd9fa29c 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -373,6 +373,9 @@ struct ioctl_sick_map {
 	unsigned int		ioctl_mask;
 };
 
+#define for_each_sick_map(map, m) \
+	for ((m) = (map); (m) < (map) + ARRAY_SIZE(map); (m)++)
+
 static const struct ioctl_sick_map fs_map[] = {
 	{ XFS_SICK_FS_COUNTERS,	XFS_FSOP_GEOM_SICK_COUNTERS},
 	{ XFS_SICK_FS_UQUOTA,	XFS_FSOP_GEOM_SICK_UQUOTA },
@@ -382,13 +385,11 @@ static const struct ioctl_sick_map fs_map[] = {
 	{ XFS_SICK_FS_NLINKS,	XFS_FSOP_GEOM_SICK_NLINKS },
 	{ XFS_SICK_FS_METADIR,	XFS_FSOP_GEOM_SICK_METADIR },
 	{ XFS_SICK_FS_METAPATH,	XFS_FSOP_GEOM_SICK_METAPATH },
-	{ 0, 0 },
 };
 
 static const struct ioctl_sick_map rt_map[] = {
 	{ XFS_SICK_RT_BITMAP,	XFS_FSOP_GEOM_SICK_RT_BITMAP },
 	{ XFS_SICK_RT_SUMMARY,	XFS_FSOP_GEOM_SICK_RT_SUMMARY },
-	{ 0, 0 },
 };
 
 static inline void
@@ -418,11 +419,11 @@ xfs_fsop_geom_health(
 	geo->checked = 0;
 
 	xfs_fs_measure_sickness(mp, &sick, &checked);
-	for (m = fs_map; m->sick_mask; m++)
+	for_each_sick_map(fs_map, m)
 		xfgeo_health_tick(geo, sick, checked, m);
 
 	xfs_rt_measure_sickness(mp, &sick, &checked);
-	for (m = rt_map; m->sick_mask; m++)
+	for_each_sick_map(rt_map, m)
 		xfgeo_health_tick(geo, sick, checked, m);
 }
 
@@ -438,7 +439,6 @@ static const struct ioctl_sick_map ag_map[] = {
 	{ XFS_SICK_AG_RMAPBT,	XFS_AG_GEOM_SICK_RMAPBT },
 	{ XFS_SICK_AG_REFCNTBT,	XFS_AG_GEOM_SICK_REFCNTBT },
 	{ XFS_SICK_AG_INODES,	XFS_AG_GEOM_SICK_INODES },
-	{ 0, 0 },
 };
 
 /* Fill out ag geometry health info. */
@@ -455,7 +455,7 @@ xfs_ag_geom_health(
 	ageo->ag_checked = 0;
 
 	xfs_group_measure_sickness(pag_group(pag), &sick, &checked);
-	for (m = ag_map; m->sick_mask; m++) {
+	for_each_sick_map(ag_map, m) {
 		if (checked & m->sick_mask)
 			ageo->ag_checked |= m->ioctl_mask;
 		if (sick & m->sick_mask)
@@ -477,7 +477,6 @@ static const struct ioctl_sick_map ino_map[] = {
 	{ XFS_SICK_INO_DIR_ZAPPED,	XFS_BS_SICK_DIR },
 	{ XFS_SICK_INO_SYMLINK_ZAPPED,	XFS_BS_SICK_SYMLINK },
 	{ XFS_SICK_INO_DIRTREE,	XFS_BS_SICK_DIRTREE },
-	{ 0, 0 },
 };
 
 /* Fill out bulkstat health info. */
@@ -494,7 +493,7 @@ xfs_bulkstat_health(
 	bs->bs_checked = 0;
 
 	xfs_inode_measure_sickness(ip, &sick, &checked);
-	for (m = ino_map; m->sick_mask; m++) {
+	for_each_sick_map(ino_map, m) {
 		if (checked & m->sick_mask)
 			bs->bs_checked |= m->ioctl_mask;
 		if (sick & m->sick_mask)

[PATCH 09/34] xfs: record rt group metadata errors in the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Record the state of per-rtgroup metadata sickness in the rtgroup
structure for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_health.h   |   40 +++++++-----
 fs/xfs/libxfs/xfs_rtbitmap.c |   37 ++++++-----
 fs/xfs/libxfs/xfs_rtgroup.c  |   38 ++++++++++-
 fs/xfs/libxfs/xfs_rtgroup.h  |    1 
 fs/xfs/scrub/health.c        |   31 ++++++---
 fs/xfs/xfs_health.c          |  142 ++++++++++++++++++------------------------
 fs/xfs/xfs_trace.h           |    4 -
 7 files changed, 157 insertions(+), 136 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index a23df94319e5fb..3d93b57cf57143 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -54,6 +54,7 @@ struct xfs_inode;
 struct xfs_fsop_geom;
 struct xfs_btree_cur;
 struct xfs_da_args;
+struct xfs_rtgroup;
 
 /* Observable health issues for metadata spanning the entire filesystem. */
 #define XFS_SICK_FS_COUNTERS	(1 << 0)  /* summary counters */
@@ -65,9 +66,10 @@ struct xfs_da_args;
 #define XFS_SICK_FS_METADIR	(1 << 6)  /* metadata directory tree */
 #define XFS_SICK_FS_METAPATH	(1 << 7)  /* metadata directory tree path */
 
-/* Observable health issues for realtime volume metadata. */
-#define XFS_SICK_RT_BITMAP	(1 << 0)  /* realtime bitmap */
-#define XFS_SICK_RT_SUMMARY	(1 << 1)  /* realtime summary */
+/* Observable health issues for realtime group metadata. */
+#define XFS_SICK_RG_SUPER	(1 << 0)  /* rt group superblock */
+#define XFS_SICK_RG_BITMAP	(1 << 1)  /* rt group bitmap */
+#define XFS_SICK_RG_SUMMARY	(1 << 2)  /* rt groups summary */
 
 /* Observable health issues for AG metadata. */
 #define XFS_SICK_AG_SB		(1 << 0)  /* superblock */
@@ -111,8 +113,9 @@ struct xfs_da_args;
 				 XFS_SICK_FS_METADIR | \
 				 XFS_SICK_FS_METAPATH)
 
-#define XFS_SICK_RT_PRIMARY	(XFS_SICK_RT_BITMAP | \
-				 XFS_SICK_RT_SUMMARY)
+#define XFS_SICK_RG_PRIMARY	(XFS_SICK_RG_SUPER | \
+				 XFS_SICK_RG_BITMAP | \
+				 XFS_SICK_RG_SUMMARY)
 
 #define XFS_SICK_AG_PRIMARY	(XFS_SICK_AG_SB | \
 				 XFS_SICK_AG_AGF | \
@@ -142,26 +145,26 @@ struct xfs_da_args;
 
 /* Secondary state related to (but not primary evidence of) health problems. */
 #define XFS_SICK_FS_SECONDARY	(0)
-#define XFS_SICK_RT_SECONDARY	(0)
+#define XFS_SICK_RG_SECONDARY	(0)
 #define XFS_SICK_AG_SECONDARY	(0)
 #define XFS_SICK_INO_SECONDARY	(XFS_SICK_INO_FORGET)
 
 /* Evidence of health problems elsewhere. */
 #define XFS_SICK_FS_INDIRECT	(0)
-#define XFS_SICK_RT_INDIRECT	(0)
+#define XFS_SICK_RG_INDIRECT	(0)
 #define XFS_SICK_AG_INDIRECT	(XFS_SICK_AG_INODES)
 #define XFS_SICK_INO_INDIRECT	(0)
 
 /* All health masks. */
-#define XFS_SICK_FS_ALL	(XFS_SICK_FS_PRIMARY | \
+#define XFS_SICK_FS_ALL		(XFS_SICK_FS_PRIMARY | \
 				 XFS_SICK_FS_SECONDARY | \
 				 XFS_SICK_FS_INDIRECT)
 
-#define XFS_SICK_RT_ALL	(XFS_SICK_RT_PRIMARY | \
-				 XFS_SICK_RT_SECONDARY | \
-				 XFS_SICK_RT_INDIRECT)
+#define XFS_SICK_RG_ALL		(XFS_SICK_RG_PRIMARY | \
+				 XFS_SICK_RG_SECONDARY | \
+				 XFS_SICK_RG_INDIRECT)
 
-#define XFS_SICK_AG_ALL	(XFS_SICK_AG_PRIMARY | \
+#define XFS_SICK_AG_ALL		(XFS_SICK_AG_PRIMARY | \
 				 XFS_SICK_AG_SECONDARY | \
 				 XFS_SICK_AG_INDIRECT)
 
@@ -195,11 +198,8 @@ void xfs_fs_mark_healthy(struct xfs_mount *mp, unsigned int mask);
 void xfs_fs_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
 		unsigned int *checked);
 
-void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask);
-void xfs_rt_mark_corrupt(struct xfs_mount *mp, unsigned int mask);
-void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask);
-void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
-		unsigned int *checked);
+void xfs_rgno_mark_sick(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		unsigned int mask);
 
 void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
 		unsigned int mask);
@@ -244,11 +244,17 @@ xfs_group_has_sickness(
 	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))
 
+#define xfs_rtgroup_has_sickness(rtg, mask) \
+	xfs_group_has_sickness(rtg_group(rtg), (mask))
+#define xfs_rtgroup_is_healthy(rtg) \
+	(!xfs_rtgroup_has_sickness((rtg), UINT_MAX))
+
 static inline bool
 xfs_inode_has_sickness(struct xfs_inode *ip, unsigned int mask)
 {
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 416bbcd92af2ad..e201064764d489 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -76,28 +76,31 @@ static int
 xfs_rtbuf_get(
 	struct xfs_rtalloc_args	*args,
 	xfs_fileoff_t		block,	/* block number in bitmap or summary */
-	int			issum)	/* is summary not bitmap */
+	enum xfs_rtg_inodes	type)
 {
+	struct xfs_inode	*ip = args->rtg->rtg_inodes[type];
 	struct xfs_mount	*mp = args->mp;
 	struct xfs_buf		**cbpp;	/* cached block buffer */
 	xfs_fileoff_t		*coffp;	/* cached block number */
 	struct xfs_buf		*bp;	/* block buffer, result */
-	struct xfs_inode	*ip;	/* bitmap or summary inode */
 	struct xfs_bmbt_irec	map;
-	enum xfs_blft		type;
+	enum xfs_blft		buf_type;
 	int			nmap = 1;
 	int			error;
 
-	if (issum) {
+	switch (type) {
+	case XFS_RTGI_SUMMARY:
 		cbpp = &args->sumbp;
 		coffp = &args->sumoff;
-		ip = args->rtg->rtg_inodes[XFS_RTGI_SUMMARY];
-		type = XFS_BLFT_RTSUMMARY_BUF;
-	} else {
+		buf_type = XFS_BLFT_RTSUMMARY_BUF;
+		break;
+	case XFS_RTGI_BITMAP:
 		cbpp = &args->rbmbp;
 		coffp = &args->rbmoff;
-		ip = args->rtg->rtg_inodes[XFS_RTGI_BITMAP];
-		type = XFS_BLFT_RTBITMAP_BUF;
+		buf_type = XFS_BLFT_RTBITMAP_BUF;
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	/*
@@ -120,8 +123,7 @@ xfs_rtbuf_get(
 		return error;
 
 	if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map))) {
-		xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
-					     XFS_SICK_RT_BITMAP);
+		xfs_rtginode_mark_sick(args->rtg, type);
 		return -EFSCORRUPTED;
 	}
 
@@ -130,12 +132,11 @@ xfs_rtbuf_get(
 				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
 				   mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
 	if (xfs_metadata_is_sick(error))
-		xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
-					     XFS_SICK_RT_BITMAP);
+		xfs_rtginode_mark_sick(args->rtg, type);
 	if (error)
 		return error;
 
-	xfs_trans_buf_set_type(args->tp, bp, type);
+	xfs_trans_buf_set_type(args->tp, bp, buf_type);
 	*cbpp = bp;
 	*coffp = block;
 	return 0;
@@ -149,11 +150,11 @@ xfs_rtbitmap_read_buf(
 	struct xfs_mount		*mp = args->mp;
 
 	if (XFS_IS_CORRUPT(mp, block >= mp->m_sb.sb_rbmblocks)) {
-		xfs_rt_mark_sick(mp, XFS_SICK_RT_BITMAP);
+		xfs_rtginode_mark_sick(args->rtg, XFS_RTGI_BITMAP);
 		return -EFSCORRUPTED;
 	}
 
-	return xfs_rtbuf_get(args, block, 0);
+	return xfs_rtbuf_get(args, block, XFS_RTGI_BITMAP);
 }
 
 int
@@ -164,10 +165,10 @@ xfs_rtsummary_read_buf(
 	struct xfs_mount		*mp = args->mp;
 
 	if (XFS_IS_CORRUPT(mp, block >= mp->m_rsumblocks)) {
-		xfs_rt_mark_sick(args->mp, XFS_SICK_RT_SUMMARY);
+		xfs_rtginode_mark_sick(args->rtg, XFS_RTGI_SUMMARY);
 		return -EFSCORRUPTED;
 	}
-	return xfs_rtbuf_get(args, block, 1);
+	return xfs_rtbuf_get(args, block, XFS_RTGI_SUMMARY);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index 470260c911c8d1..790a0b8c137fc8 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -271,6 +271,8 @@ struct xfs_rtginode_ops {
 
 	enum xfs_metafile_type	metafile_type;
 
+	unsigned int		sick;	/* rtgroup sickness flag */
+
 	/* Does the fs have this feature? */
 	bool			(*enabled)(struct xfs_mount *mp);
 
@@ -285,11 +287,13 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
 	[XFS_RTGI_BITMAP] = {
 		.name		= "bitmap",
 		.metafile_type	= XFS_METAFILE_RTBITMAP,
+		.sick		= XFS_SICK_RG_BITMAP,
 		.create		= xfs_rtbitmap_create,
 	},
 	[XFS_RTGI_SUMMARY] = {
 		.name		= "summary",
 		.metafile_type	= XFS_METAFILE_RTSUMMARY,
+		.sick		= XFS_SICK_RG_SUMMARY,
 		.create		= xfs_rtsummary_create,
 	},
 };
@@ -323,6 +327,17 @@ xfs_rtginode_enabled(
 	return ops->enabled(rtg_mount(rtg));
 }
 
+/* Mark an rtgroup inode sick */
+void
+xfs_rtginode_mark_sick(
+	struct xfs_rtgroup	*rtg,
+	enum xfs_rtg_inodes	type)
+{
+	const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type];
+
+	xfs_group_mark_sick(rtg_group(rtg), ops->sick);
+}
+
 /* Load and existing rtgroup inode into the rtgroup structure. */
 int
 xfs_rtginode_load(
@@ -358,8 +373,10 @@ xfs_rtginode_load(
 	} else {
 		const char	*path;
 
-		if (!mp->m_rtdirip)
+		if (!mp->m_rtdirip) {
+			xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
 			return -EFSCORRUPTED;
+		}
 
 		path = xfs_rtginode_path(rtg_rgno(rtg), type);
 		if (!path)
@@ -369,17 +386,22 @@ xfs_rtginode_load(
 		kfree(path);
 	}
 
-	if (error)
+	if (error) {
+		if (xfs_metadata_is_sick(error))
+			xfs_rtginode_mark_sick(rtg, type);
 		return error;
+	}
 
 	if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
 			       ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) {
 		xfs_irele(ip);
+		xfs_rtginode_mark_sick(rtg, type);
 		return -EFSCORRUPTED;
 	}
 
 	if (XFS_IS_CORRUPT(mp, ip->i_projid != rtg_rgno(rtg))) {
 		xfs_irele(ip);
+		xfs_rtginode_mark_sick(rtg, type);
 		return -EFSCORRUPTED;
 	}
 
@@ -416,8 +438,10 @@ xfs_rtginode_create(
 	if (!xfs_rtginode_enabled(rtg, type))
 		return 0;
 
-	if (!mp->m_rtdirip)
+	if (!mp->m_rtdirip) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
 		return -EFSCORRUPTED;
+	}
 
 	upd.path = xfs_rtginode_path(rtg_rgno(rtg), type);
 	if (!upd.path)
@@ -464,8 +488,10 @@ int
 xfs_rtginode_mkdir_parent(
 	struct xfs_mount	*mp)
 {
-	if (!mp->m_metadirip)
+	if (!mp->m_metadirip) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
 		return -EFSCORRUPTED;
+	}
 
 	return xfs_metadir_mkdir(mp->m_metadirip, "rtgroups", &mp->m_rtdirip);
 }
@@ -477,8 +503,10 @@ xfs_rtginode_load_parent(
 {
 	struct xfs_mount	*mp = tp->t_mountp;
 
-	if (!mp->m_metadirip)
+	if (!mp->m_metadirip) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
 		return -EFSCORRUPTED;
+	}
 
 	return xfs_metadir_load(tp, mp->m_metadirip, "rtgroups",
 			XFS_METAFILE_DIR, &mp->m_rtdirip);
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index e7679fafff8ce7..fba62b26912a89 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -240,6 +240,7 @@ int xfs_rtginode_load_parent(struct xfs_trans *tp);
 const char *xfs_rtginode_name(enum xfs_rtg_inodes type);
 enum xfs_metafile_type xfs_rtginode_metafile_type(enum xfs_rtg_inodes type);
 bool xfs_rtginode_enabled(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type);
+void xfs_rtginode_mark_sick(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type);
 int xfs_rtginode_load(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
 		struct xfs_trans *tp);
 int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index b8b92ff3a573a1..7547fb5bcd7272 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -12,6 +12,7 @@
 #include "xfs_btree.h"
 #include "xfs_ag.h"
 #include "xfs_health.h"
+#include "xfs_rtgroup.h"
 #include "scrub/scrub.h"
 #include "scrub/health.h"
 #include "scrub/common.h"
@@ -71,9 +72,9 @@
 
 enum xchk_health_group {
 	XHG_FS = 1,
-	XHG_RT,
 	XHG_AG,
 	XHG_INO,
+	XHG_RTGROUP,
 };
 
 struct xchk_health_map {
@@ -100,8 +101,8 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_XATTR]		= { XHG_INO, XFS_SICK_INO_XATTR },
 	[XFS_SCRUB_TYPE_SYMLINK]	= { XHG_INO, XFS_SICK_INO_SYMLINK },
 	[XFS_SCRUB_TYPE_PARENT]		= { XHG_INO, XFS_SICK_INO_PARENT },
-	[XFS_SCRUB_TYPE_RTBITMAP]	= { XHG_RT,  XFS_SICK_RT_BITMAP },
-	[XFS_SCRUB_TYPE_RTSUM]		= { XHG_RT,  XFS_SICK_RT_SUMMARY },
+	[XFS_SCRUB_TYPE_RTBITMAP]	= { XHG_RTGROUP, XFS_SICK_RG_BITMAP },
+	[XFS_SCRUB_TYPE_RTSUM]		= { XHG_RTGROUP, XFS_SICK_RG_SUMMARY },
 	[XFS_SCRUB_TYPE_UQUOTA]		= { XHG_FS,  XFS_SICK_FS_UQUOTA },
 	[XFS_SCRUB_TYPE_GQUOTA]		= { XHG_FS,  XFS_SICK_FS_GQUOTA },
 	[XFS_SCRUB_TYPE_PQUOTA]		= { XHG_FS,  XFS_SICK_FS_PQUOTA },
@@ -162,11 +163,13 @@ xchk_mark_all_healthy(
 	struct xfs_mount	*mp)
 {
 	struct xfs_perag	*pag = NULL;
+	struct xfs_rtgroup	*rtg = NULL;
 
 	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_group_mark_healthy(pag_group(pag), XFS_SICK_AG_INDIRECT);
+	while ((rtg = xfs_rtgroup_next(mp, rtg)))
+		xfs_group_mark_healthy(rtg_group(rtg), XFS_SICK_RG_INDIRECT);
 }
 
 /*
@@ -184,6 +187,7 @@ xchk_update_health(
 	struct xfs_scrub	*sc)
 {
 	struct xfs_perag	*pag;
+	struct xfs_rtgroup	*rtg;
 	bool			bad;
 
 	/*
@@ -236,11 +240,13 @@ xchk_update_health(
 		else
 			xfs_fs_mark_healthy(sc->mp, sc->sick_mask);
 		break;
-	case XHG_RT:
+	case XHG_RTGROUP:
+		rtg = xfs_rtgroup_get(sc->mp, sc->sm->sm_agno);
 		if (bad)
-			xfs_rt_mark_corrupt(sc->mp, sc->sick_mask);
+			xfs_group_mark_corrupt(rtg_group(rtg), sc->sick_mask);
 		else
-			xfs_rt_mark_healthy(sc->mp, sc->sick_mask);
+			xfs_group_mark_healthy(rtg_group(rtg), sc->sick_mask);
+		xfs_rtgroup_put(rtg);
 		break;
 	default:
 		ASSERT(0);
@@ -295,6 +301,7 @@ xchk_health_record(
 {
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_perag	*pag = NULL;
+	struct xfs_rtgroup	*rtg = NULL;
 	unsigned int		sick;
 	unsigned int		checked;
 
@@ -302,15 +309,17 @@ xchk_health_record(
 	if (sick & XFS_SICK_FS_PRIMARY)
 		xchk_set_corrupt(sc);
 
-	xfs_rt_measure_sickness(mp, &sick, &checked);
-	if (sick & XFS_SICK_RT_PRIMARY)
-		xchk_set_corrupt(sc);
-
 	while ((pag = xfs_perag_next(mp, pag))) {
 		xfs_group_measure_sickness(pag_group(pag), &sick, &checked);
 		if (sick & XFS_SICK_AG_PRIMARY)
 			xchk_set_corrupt(sc);
 	}
 
+	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+		xfs_group_measure_sickness(rtg_group(rtg), &sick, &checked);
+		if (sick & XFS_SICK_RG_PRIMARY)
+			xchk_set_corrupt(sc);
+	}
+
 	return 0;
 }
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index b0d0c6bd9fa29c..9d8ee01cd163ef 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -18,6 +18,22 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 #include "xfs_quota_defs.h"
+#include "xfs_rtgroup.h"
+
+static void
+xfs_health_unmount_group(
+	struct xfs_group	*xg,
+	bool			*warn)
+{
+	unsigned int		sick = 0;
+	unsigned int		checked = 0;
+
+	xfs_group_measure_sickness(xg, &sick, &checked);
+	if (sick) {
+		trace_xfs_group_unfixed_corruption(xg, sick);
+		*warn = true;
+	}
+}
 
 /*
  * Warn about metadata corruption that we detected but haven't fixed, and
@@ -29,6 +45,7 @@ xfs_health_unmount(
 	struct xfs_mount	*mp)
 {
 	struct xfs_perag	*pag = NULL;
+	struct xfs_rtgroup	*rtg = NULL;
 	unsigned int		sick = 0;
 	unsigned int		checked = 0;
 	bool			warn = false;
@@ -37,21 +54,12 @@ xfs_health_unmount(
 		return;
 
 	/* Measure AG corruption levels. */
-	while ((pag = xfs_perag_next(mp, pag))) {
-		xfs_group_measure_sickness(pag_group(pag), &sick, &checked);
-		if (sick) {
-			trace_xfs_group_unfixed_corruption(pag_group(pag),
-					sick);
-			warn = true;
-		}
-	}
+	while ((pag = xfs_perag_next(mp, pag)))
+		xfs_health_unmount_group(pag_group(pag), &warn);
 
-	/* Measure realtime volume corruption levels. */
-	xfs_rt_measure_sickness(mp, &sick, &checked);
-	if (sick) {
-		trace_xfs_rt_unfixed_corruption(mp, sick);
-		warn = true;
-	}
+	/* Measure realtime group corruption levels. */
+	while ((rtg = xfs_rtgroup_next(mp, rtg)))
+		xfs_health_unmount_group(rtg_group(rtg), &warn);
 
 	/*
 	 * Measure fs corruption and keep the sample around for the warning.
@@ -150,65 +158,6 @@ xfs_fs_measure_sickness(
 	spin_unlock(&mp->m_sb_lock);
 }
 
-/* Mark unhealthy realtime metadata. */
-void
-xfs_rt_mark_sick(
-	struct xfs_mount	*mp,
-	unsigned int		mask)
-{
-	ASSERT(!(mask & ~XFS_SICK_RT_ALL));
-	trace_xfs_rt_mark_sick(mp, mask);
-
-	spin_lock(&mp->m_sb_lock);
-	mp->m_rt_sick |= mask;
-	spin_unlock(&mp->m_sb_lock);
-}
-
-/* Mark realtime metadata as having been checked and found unhealthy by fsck. */
-void
-xfs_rt_mark_corrupt(
-	struct xfs_mount	*mp,
-	unsigned int		mask)
-{
-	ASSERT(!(mask & ~XFS_SICK_RT_ALL));
-	trace_xfs_rt_mark_corrupt(mp, mask);
-
-	spin_lock(&mp->m_sb_lock);
-	mp->m_rt_sick |= mask;
-	mp->m_rt_checked |= mask;
-	spin_unlock(&mp->m_sb_lock);
-}
-
-/* Mark a realtime metadata healed. */
-void
-xfs_rt_mark_healthy(
-	struct xfs_mount	*mp,
-	unsigned int		mask)
-{
-	ASSERT(!(mask & ~XFS_SICK_RT_ALL));
-	trace_xfs_rt_mark_healthy(mp, mask);
-
-	spin_lock(&mp->m_sb_lock);
-	mp->m_rt_sick &= ~mask;
-	if (!(mp->m_rt_sick & XFS_SICK_RT_PRIMARY))
-		mp->m_rt_sick &= ~XFS_SICK_RT_SECONDARY;
-	mp->m_rt_checked |= mask;
-	spin_unlock(&mp->m_sb_lock);
-}
-
-/* Sample which realtime metadata are unhealthy. */
-void
-xfs_rt_measure_sickness(
-	struct xfs_mount	*mp,
-	unsigned int		*sick,
-	unsigned int		*checked)
-{
-	spin_lock(&mp->m_sb_lock);
-	*sick = mp->m_rt_sick;
-	*checked = mp->m_rt_checked;
-	spin_unlock(&mp->m_sb_lock);
-}
-
 /* Mark unhealthy per-ag metadata given a raw AG number. */
 void
 xfs_agno_mark_sick(
@@ -226,13 +175,24 @@ xfs_agno_mark_sick(
 	xfs_perag_put(pag);
 }
 
+static inline void
+xfs_group_check_mask(
+	struct xfs_group	*xg,
+	unsigned int		mask)
+{
+	if (xg->xg_type == XG_TYPE_AG)
+		ASSERT(!(mask & ~XFS_SICK_AG_ALL));
+	else
+		ASSERT(!(mask & ~XFS_SICK_RG_ALL));
+}
+
 /* Mark unhealthy per-ag metadata. */
 void
 xfs_group_mark_sick(
 	struct xfs_group	*xg,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
+	xfs_group_check_mask(xg, mask);
 	trace_xfs_group_mark_sick(xg, mask);
 
 	spin_lock(&xg->xg_state_lock);
@@ -248,7 +208,7 @@ xfs_group_mark_corrupt(
 	struct xfs_group	*xg,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
+	xfs_group_check_mask(xg, mask);
 	trace_xfs_group_mark_corrupt(xg, mask);
 
 	spin_lock(&xg->xg_state_lock);
@@ -265,7 +225,7 @@ xfs_group_mark_healthy(
 	struct xfs_group	*xg,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
+	xfs_group_check_mask(xg, mask);
 	trace_xfs_group_mark_healthy(xg, mask);
 
 	spin_lock(&xg->xg_state_lock);
@@ -289,6 +249,23 @@ xfs_group_measure_sickness(
 	spin_unlock(&xg->xg_state_lock);
 }
 
+/* Mark unhealthy per-rtgroup metadata given a raw rt group number. */
+void
+xfs_rgno_mark_sick(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
+	unsigned int		mask)
+{
+	struct xfs_rtgroup	*rtg = xfs_rtgroup_get(mp, rgno);
+
+	/* per-rtgroup structure not set up yet? */
+	if (!rtg)
+		return;
+
+	xfs_group_mark_sick(rtg_group(rtg), mask);
+	xfs_rtgroup_put(rtg);
+}
+
 /* Mark the unhealthy parts of an inode. */
 void
 xfs_inode_mark_sick(
@@ -388,8 +365,8 @@ static const struct ioctl_sick_map fs_map[] = {
 };
 
 static const struct ioctl_sick_map rt_map[] = {
-	{ XFS_SICK_RT_BITMAP,	XFS_FSOP_GEOM_SICK_RT_BITMAP },
-	{ XFS_SICK_RT_SUMMARY,	XFS_FSOP_GEOM_SICK_RT_SUMMARY },
+	{ XFS_SICK_RG_BITMAP,	XFS_FSOP_GEOM_SICK_RT_BITMAP },
+	{ XFS_SICK_RG_SUMMARY,	XFS_FSOP_GEOM_SICK_RT_SUMMARY },
 };
 
 static inline void
@@ -411,6 +388,7 @@ xfs_fsop_geom_health(
 	struct xfs_mount		*mp,
 	struct xfs_fsop_geom		*geo)
 {
+	struct xfs_rtgroup		*rtg = NULL;
 	const struct ioctl_sick_map	*m;
 	unsigned int			sick;
 	unsigned int			checked;
@@ -422,9 +400,11 @@ xfs_fsop_geom_health(
 	for_each_sick_map(fs_map, m)
 		xfgeo_health_tick(geo, sick, checked, m);
 
-	xfs_rt_measure_sickness(mp, &sick, &checked);
-	for_each_sick_map(rt_map, m)
-		xfgeo_health_tick(geo, sick, checked, m);
+	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+		xfs_group_measure_sickness(rtg_group(rtg), &sick, &checked);
+		for_each_sick_map(rt_map, m)
+			xfgeo_health_tick(geo, sick, checked, m);
+	}
 }
 
 static const struct ioctl_sick_map ag_map[] = {
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index f66e5b590d7597..62169c2ec38789 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -4255,10 +4255,6 @@ DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_sick);
 DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_corrupt);
 DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_healthy);
 DEFINE_FS_CORRUPT_EVENT(xfs_fs_unfixed_corruption);
-DEFINE_FS_CORRUPT_EVENT(xfs_rt_mark_sick);
-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_group_corrupt_class,
 	TP_PROTO(const struct xfs_group *xg, unsigned int flags),

[PATCH 10/34] xfs: export the geometry of realtime groups to userspace

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create an ioctl so that the kernel can report the status of realtime
groups to userspace.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_fs.h      |   16 ++++++++++++++++
 fs/xfs/libxfs/xfs_health.h  |    2 ++
 fs/xfs/libxfs/xfs_rtgroup.c |   14 ++++++++++++++
 fs/xfs/libxfs/xfs_rtgroup.h |    4 ++++
 fs/xfs/xfs_health.c         |   28 ++++++++++++++++++++++++++++
 fs/xfs/xfs_ioctl.c          |   35 +++++++++++++++++++++++++++++++++++
 6 files changed, 99 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 5c224d03270ce9..4c0682173d6144 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -971,6 +971,21 @@ struct xfs_getparents_by_handle {
 	struct xfs_getparents		gph_request;
 };
 
+/*
+ * Output for XFS_IOC_RTGROUP_GEOMETRY
+ */
+struct xfs_rtgroup_geometry {
+	__u32 rg_number;	/* i/o: rtgroup number */
+	__u32 rg_length;	/* o: length in blocks */
+	__u32 rg_sick;		/* o: sick things in ag */
+	__u32 rg_checked;	/* o: checked metadata in ag */
+	__u32 rg_flags;		/* i/o: flags for this ag */
+	__u32 rg_reserved[27];	/* o: zero */
+};
+#define XFS_RTGROUP_GEOM_SICK_SUPER	(1U << 0)  /* superblock */
+#define XFS_RTGROUP_GEOM_SICK_BITMAP	(1U << 1)  /* rtbitmap */
+#define XFS_RTGROUP_GEOM_SICK_SUMMARY	(1U << 2)  /* rtsummary */
+
 /*
  * ioctl commands that are used by Linux filesystems
  */
@@ -1009,6 +1024,7 @@ struct xfs_getparents_by_handle {
 #define XFS_IOC_GETPARENTS	_IOWR('X', 62, struct xfs_getparents)
 #define XFS_IOC_GETPARENTS_BY_HANDLE _IOWR('X', 63, struct xfs_getparents_by_handle)
 #define XFS_IOC_SCRUBV_METADATA	_IOWR('X', 64, struct xfs_scrub_vec_head)
+#define XFS_IOC_RTGROUP_GEOMETRY _IOWR('X', 65, struct xfs_rtgroup_geometry)
 
 /*
  * ioctl commands that replace IRIX syssgi()'s
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 3d93b57cf57143..d34986ac18c3fa 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -278,6 +278,8 @@ xfs_inode_is_healthy(struct xfs_inode *ip)
 
 void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo);
 void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
+void xfs_rtgroup_geom_health(struct xfs_rtgroup *rtg,
+		struct xfs_rtgroup_geometry *rgeo);
 void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bulkstat *bs);
 
 #define xfs_metadata_is_sick(error) \
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index 790a0b8c137fc8..624d8b25eba0ec 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -214,6 +214,20 @@ xfs_rtgroup_trans_join(
 	}
 }
 
+/* Retrieve rt group geometry. */
+int
+xfs_rtgroup_get_geometry(
+	struct xfs_rtgroup	*rtg,
+	struct xfs_rtgroup_geometry *rgeo)
+{
+	/* Fill out form. */
+	memset(rgeo, 0, sizeof(*rgeo));
+	rgeo->rg_number = rtg_rgno(rtg);
+	rgeo->rg_length = rtg->rtg_extents * rtg_mount(rtg)->m_sb.sb_rextsize;
+	xfs_rtgroup_geom_health(rtg, rgeo);
+	return 0;
+}
+
 #ifdef CONFIG_PROVE_LOCKING
 static struct lock_class_key xfs_rtginode_lock_class;
 
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index fba62b26912a89..026f34f984b32f 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -234,6 +234,9 @@ void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
 void xfs_rtgroup_trans_join(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
 		unsigned int rtglock_flags);
 
+int xfs_rtgroup_get_geometry(struct xfs_rtgroup *rtg,
+		struct xfs_rtgroup_geometry *rgeo);
+
 int xfs_rtginode_mkdir_parent(struct xfs_mount *mp);
 int xfs_rtginode_load_parent(struct xfs_trans *tp);
 
@@ -277,6 +280,7 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
 # define xfs_rtgroup_trans_join(tp, rtg, gf)	((void)0)
 # define xfs_update_rtsb(bp, sb_bp)	((void)0)
 # define xfs_log_rtsb(tp, sb_bp)	(NULL)
+# define xfs_rtgroup_get_geometry(rtg, rgeo)	(-EOPNOTSUPP)
 #endif /* CONFIG_XFS_RT */
 
 #endif /* __LIBXFS_RTGROUP_H */
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 9d8ee01cd163ef..c7c2e656199862 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -443,6 +443,34 @@ xfs_ag_geom_health(
 	}
 }
 
+static const struct ioctl_sick_map rtgroup_map[] = {
+	{ XFS_SICK_RG_SUPER,	XFS_RTGROUP_GEOM_SICK_SUPER },
+	{ XFS_SICK_RG_BITMAP,	XFS_RTGROUP_GEOM_SICK_BITMAP },
+	{ XFS_SICK_RG_SUMMARY,	XFS_RTGROUP_GEOM_SICK_SUMMARY },
+};
+
+/* Fill out rtgroup geometry health info. */
+void
+xfs_rtgroup_geom_health(
+	struct xfs_rtgroup	*rtg,
+	struct xfs_rtgroup_geometry *rgeo)
+{
+	const struct ioctl_sick_map	*m;
+	unsigned int			sick;
+	unsigned int			checked;
+
+	rgeo->rg_sick = 0;
+	rgeo->rg_checked = 0;
+
+	xfs_group_measure_sickness(rtg_group(rtg), &sick, &checked);
+	for_each_sick_map(rtgroup_map, m) {
+		if (checked & m->sick_mask)
+			rgeo->rg_checked |= m->ioctl_mask;
+		if (sick & m->sick_mask)
+			rgeo->rg_sick |= m->ioctl_mask;
+	}
+}
+
 static const struct ioctl_sick_map ino_map[] = {
 	{ XFS_SICK_INO_CORE,	XFS_BS_SICK_INODE },
 	{ XFS_SICK_INO_BMBTD,	XFS_BS_SICK_BMBTD },
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 1e233abed7ce6d..64cf51c8a15d06 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -40,6 +40,7 @@
 #include "xfs_file.h"
 #include "xfs_exchrange.h"
 #include "xfs_handle.h"
+#include "xfs_rtgroup.h"
 
 #include <linux/mount.h>
 #include <linux/fileattr.h>
@@ -403,6 +404,38 @@ xfs_ioc_ag_geometry(
 	return 0;
 }
 
+STATIC int
+xfs_ioc_rtgroup_geometry(
+	struct xfs_mount	*mp,
+	void			__user *arg)
+{
+	struct xfs_rtgroup	*rtg;
+	struct xfs_rtgroup_geometry rgeo;
+	int			error;
+
+	if (copy_from_user(&rgeo, arg, sizeof(rgeo)))
+		return -EFAULT;
+	if (rgeo.rg_flags)
+		return -EINVAL;
+	if (memchr_inv(&rgeo.rg_reserved, 0, sizeof(rgeo.rg_reserved)))
+		return -EINVAL;
+	if (!xfs_has_rtgroups(mp))
+		return -EINVAL;
+
+	rtg = xfs_rtgroup_get(mp, rgeo.rg_number);
+	if (!rtg)
+		return -EINVAL;
+
+	error = xfs_rtgroup_get_geometry(rtg, &rgeo);
+	xfs_rtgroup_put(rtg);
+	if (error)
+		return error;
+
+	if (copy_to_user(arg, &rgeo, sizeof(rgeo)))
+		return -EFAULT;
+	return 0;
+}
+
 /*
  * Linux extended inode flags interface.
  */
@@ -1225,6 +1258,8 @@ xfs_file_ioctl(
 
 	case XFS_IOC_AG_GEOMETRY:
 		return xfs_ioc_ag_geometry(mp, arg);
+	case XFS_IOC_RTGROUP_GEOMETRY:
+		return xfs_ioc_rtgroup_geometry(mp, arg);
 
 	case XFS_IOC_GETVERSION:
 		return put_user(inode->i_generation, (int __user *)arg);

[PATCH 11/34] xfs: add block headers to realtime bitmap and summary blocks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Upgrade rtbitmap and rtsummary blocks to have self describing metadata
like most every other thing in XFS.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_format.h      |   18 +++++
 fs/xfs/libxfs/xfs_ondisk.h      |    1 
 fs/xfs/libxfs/xfs_rtbitmap.c    |  146 +++++++++++++++++++++++++++++++++++----
 fs/xfs/libxfs/xfs_rtbitmap.h    |   50 +++++++++++++
 fs/xfs/libxfs/xfs_sb.c          |   21 +++++-
 fs/xfs/libxfs/xfs_shared.h      |    2 +
 fs/xfs/scrub/rtsummary_repair.c |   15 +++-
 fs/xfs/xfs_buf_item_recover.c   |   25 ++++++-
 fs/xfs/xfs_discard.c            |    2 -
 fs/xfs/xfs_mount.h              |    3 +
 fs/xfs/xfs_rtalloc.c            |    2 -
 11 files changed, 257 insertions(+), 28 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 3cf044a2d5f2a9..016ee4ff537440 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1278,6 +1278,24 @@ static inline bool xfs_dinode_is_metadir(const struct xfs_dinode *dip)
 #define	XFS_DFL_RTEXTSIZE	(64 * 1024)	        /* 64kB */
 #define	XFS_MIN_RTEXTSIZE	(4 * 1024)		/* 4kB */
 
+/*
+ * RT bit manipulation macros.
+ */
+#define XFS_RTBITMAP_MAGIC	0x424D505A	/* BMPZ */
+#define XFS_RTSUMMARY_MAGIC	0x53554D59	/* SUMY */
+
+struct xfs_rtbuf_blkinfo {
+	__be32		rt_magic;	/* validity check on block */
+	__be32		rt_crc;		/* CRC of block */
+	__be64		rt_owner;	/* inode that owns the block */
+	__be64		rt_blkno;	/* first block of the buffer */
+	__be64		rt_lsn;		/* sequence number of last write */
+	uuid_t		rt_uuid;	/* filesystem we belong to */
+};
+
+#define XFS_RTBUF_CRC_OFF \
+	offsetof(struct xfs_rtbuf_blkinfo, rt_crc)
+
 /*
  * Dquot and dquot block format definitions
  */
diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 38b314113d8f24..6a2bcbc392842c 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -76,6 +76,7 @@ xfs_check_ondisk_structs(void)
 	/* realtime structures */
 	XFS_CHECK_STRUCT_SIZE(union xfs_rtword_raw,		4);
 	XFS_CHECK_STRUCT_SIZE(union xfs_suminfo_raw,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rtbuf_blkinfo,		48);
 
 	/*
 	 * m68k has problems with xfs_attr_leaf_name_remote_t, but we pad it to
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index e201064764d489..cae0b22397d007 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -21,28 +21,84 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_health.h"
 #include "xfs_sb.h"
+#include "xfs_log.h"
+#include "xfs_buf_item.h"
 
 /*
  * Realtime allocator bitmap functions shared with userspace.
  */
 
-/*
- * Real time buffers need verifiers to avoid runtime warnings during IO.
- * We don't have anything to verify, however, so these are just dummy
- * operations.
- */
+static xfs_failaddr_t
+xfs_rtbuf_verify(
+	struct xfs_buf			*bp)
+{
+	struct xfs_mount		*mp = bp->b_mount;
+	struct xfs_rtbuf_blkinfo	*hdr = bp->b_addr;
+
+	if (!xfs_verify_magic(bp, hdr->rt_magic))
+		return __this_address;
+	if (!xfs_has_rtgroups(mp))
+		return __this_address;
+	if (!xfs_has_crc(mp))
+		return __this_address;
+	if (!uuid_equal(&hdr->rt_uuid, &mp->m_sb.sb_meta_uuid))
+		return __this_address;
+	if (hdr->rt_blkno != cpu_to_be64(xfs_buf_daddr(bp)))
+		return __this_address;
+	return NULL;
+}
+
 static void
 xfs_rtbuf_verify_read(
-	struct xfs_buf	*bp)
+	struct xfs_buf			*bp)
 {
+	struct xfs_mount		*mp = bp->b_mount;
+	struct xfs_rtbuf_blkinfo	*hdr = bp->b_addr;
+	xfs_failaddr_t			fa;
+
+	if (!xfs_has_rtgroups(mp))
+		return;
+
+	if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr->rt_lsn))) {
+		fa = __this_address;
+		goto fail;
+	}
+
+	if (!xfs_buf_verify_cksum(bp, XFS_RTBUF_CRC_OFF)) {
+		fa = __this_address;
+		goto fail;
+	}
+
+	fa = xfs_rtbuf_verify(bp);
+	if (fa)
+		goto fail;
+
 	return;
+fail:
+	xfs_verifier_error(bp, -EFSCORRUPTED, fa);
 }
 
 static void
 xfs_rtbuf_verify_write(
 	struct xfs_buf	*bp)
 {
-	return;
+	struct xfs_mount		*mp = bp->b_mount;
+	struct xfs_rtbuf_blkinfo	*hdr = bp->b_addr;
+	struct xfs_buf_log_item		*bip = bp->b_log_item;
+	xfs_failaddr_t			fa;
+
+	if (!xfs_has_rtgroups(mp))
+		return;
+
+	fa = xfs_rtbuf_verify(bp);
+	if (fa) {
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+		return;
+	}
+
+	if (bip)
+		hdr->rt_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+	xfs_buf_update_cksum(bp, XFS_RTBUF_CRC_OFF);
 }
 
 const struct xfs_buf_ops xfs_rtbuf_ops = {
@@ -51,6 +107,22 @@ const struct xfs_buf_ops xfs_rtbuf_ops = {
 	.verify_write = xfs_rtbuf_verify_write,
 };
 
+const struct xfs_buf_ops xfs_rtbitmap_buf_ops = {
+	.name		= "xfs_rtbitmap",
+	.magic		= { 0, cpu_to_be32(XFS_RTBITMAP_MAGIC) },
+	.verify_read	= xfs_rtbuf_verify_read,
+	.verify_write	= xfs_rtbuf_verify_write,
+	.verify_struct	= xfs_rtbuf_verify,
+};
+
+const struct xfs_buf_ops xfs_rtsummary_buf_ops = {
+	.name		= "xfs_rtsummary",
+	.magic		= { 0, cpu_to_be32(XFS_RTSUMMARY_MAGIC) },
+	.verify_read	= xfs_rtbuf_verify_read,
+	.verify_write	= xfs_rtbuf_verify_write,
+	.verify_struct	= xfs_rtbuf_verify,
+};
+
 /* Release cached rt bitmap and summary buffers. */
 void
 xfs_rtbuf_cache_relse(
@@ -130,12 +202,24 @@ xfs_rtbuf_get(
 	ASSERT(map.br_startblock != NULLFSBLOCK);
 	error = xfs_trans_read_buf(mp, args->tp, mp->m_ddev_targp,
 				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
-				   mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
+				   mp->m_bsize, 0, &bp,
+				   xfs_rtblock_ops(mp, type));
 	if (xfs_metadata_is_sick(error))
 		xfs_rtginode_mark_sick(args->rtg, type);
 	if (error)
 		return error;
 
+	if (xfs_has_rtgroups(mp)) {
+		struct xfs_rtbuf_blkinfo	*hdr = bp->b_addr;
+
+		if (hdr->rt_owner != cpu_to_be64(ip->i_ino)) {
+			xfs_buf_mark_corrupt(bp);
+			xfs_trans_brelse(args->tp, bp);
+			xfs_rtginode_mark_sick(args->rtg, type);
+			return -EFSCORRUPTED;
+		}
+	}
+
 	xfs_trans_buf_set_type(args->tp, bp, buf_type);
 	*cbpp = bp;
 	*coffp = block;
@@ -1146,6 +1230,19 @@ xfs_rtalloc_extent_is_free(
 	return 0;
 }
 
+/* Compute the number of rt extents tracked by a single bitmap block. */
+xfs_rtxnum_t
+xfs_rtbitmap_rtx_per_rbmblock(
+	struct xfs_mount	*mp)
+{
+	unsigned int		rbmblock_bytes = mp->m_sb.sb_blocksize;
+
+	if (xfs_has_rtgroups(mp))
+		rbmblock_bytes -= sizeof(struct xfs_rtbuf_blkinfo);
+
+	return rbmblock_bytes * NBBY;
+}
+
 /*
  * Compute the number of rtbitmap blocks needed to track the given number of rt
  * extents.
@@ -1155,7 +1252,7 @@ xfs_rtbitmap_blockcount_len(
 	struct xfs_mount	*mp,
 	xfs_rtbxlen_t		rtextents)
 {
-	return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize);
+	return howmany_64(rtextents, xfs_rtbitmap_rtx_per_rbmblock(mp));
 }
 
 /* How many rt extents does each rtbitmap file track? */
@@ -1192,11 +1289,12 @@ xfs_rtsummary_blockcount(
 	struct xfs_mount	*mp,
 	unsigned int		*rsumlevels)
 {
+	xfs_rtbxlen_t		rextents = xfs_rtbitmap_bitcount(mp);
 	unsigned long long	rsumwords;
 
-	*rsumlevels = xfs_compute_rextslog(xfs_rtbitmap_bitcount(mp)) + 1;
-	rsumwords = xfs_rtbitmap_blockcount(mp) * (*rsumlevels);
-	return XFS_B_TO_FSB(mp, rsumwords << XFS_WORDLOG);
+	*rsumlevels = xfs_compute_rextslog(rextents) + 1;
+	rsumwords = xfs_rtbitmap_blockcount_len(mp, rextents) * (*rsumlevels);
+	return howmany_64(rsumwords, mp->m_blockwsize);
 }
 
 static int
@@ -1248,6 +1346,7 @@ xfs_rtfile_initialize_block(
 	struct xfs_inode	*ip = rtg->rtg_inodes[type];
 	struct xfs_trans	*tp;
 	struct xfs_buf		*bp;
+	void			*bufdata;
 	const size_t		copylen = mp->m_blockwsize << XFS_WORDLOG;
 	enum xfs_blft		buf_type;
 	int			error;
@@ -1271,13 +1370,30 @@ xfs_rtfile_initialize_block(
 		xfs_trans_cancel(tp);
 		return error;
 	}
+	bufdata = bp->b_addr;
 
 	xfs_trans_buf_set_type(tp, bp, buf_type);
-	bp->b_ops = &xfs_rtbuf_ops;
+	bp->b_ops = xfs_rtblock_ops(mp, type);
+
+	if (xfs_has_rtgroups(mp)) {
+		struct xfs_rtbuf_blkinfo	*hdr = bp->b_addr;
+
+		if (type == XFS_RTGI_BITMAP)
+			hdr->rt_magic = cpu_to_be32(XFS_RTBITMAP_MAGIC);
+		else
+			hdr->rt_magic = cpu_to_be32(XFS_RTSUMMARY_MAGIC);
+		hdr->rt_owner = cpu_to_be64(ip->i_ino);
+		hdr->rt_blkno = cpu_to_be64(XFS_FSB_TO_DADDR(mp, fsbno));
+		hdr->rt_lsn = 0;
+		uuid_copy(&hdr->rt_uuid, &mp->m_sb.sb_meta_uuid);
+
+		bufdata += sizeof(*hdr);
+	}
+
 	if (data)
-		memcpy(bp->b_addr, data, copylen);
+		memcpy(bufdata, data, copylen);
 	else
-		memset(bp->b_addr, 0, copylen);
+		memset(bufdata, 0, copylen);
 	xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1);
 	return xfs_trans_commit(tp);
 }
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index b2b9e59a87a278..2286a98ecb32bb 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -150,6 +150,9 @@ xfs_rtx_to_rbmblock(
 	struct xfs_mount	*mp,
 	xfs_rtxnum_t		rtx)
 {
+	if (xfs_has_rtgroups(mp))
+		return div_u64(rtx, mp->m_rtx_per_rbmblock);
+
 	return rtx >> mp->m_blkbit_log;
 }
 
@@ -159,6 +162,13 @@ xfs_rtx_to_rbmword(
 	struct xfs_mount	*mp,
 	xfs_rtxnum_t		rtx)
 {
+	if (xfs_has_rtgroups(mp)) {
+		unsigned int	mod;
+
+		div_u64_rem(rtx >> XFS_NBWORDLOG, mp->m_blockwsize, &mod);
+		return mod;
+	}
+
 	return (rtx >> XFS_NBWORDLOG) & (mp->m_blockwsize - 1);
 }
 
@@ -168,6 +178,9 @@ xfs_rbmblock_to_rtx(
 	struct xfs_mount	*mp,
 	xfs_fileoff_t		rbmoff)
 {
+	if (xfs_has_rtgroups(mp))
+		return rbmoff * mp->m_rtx_per_rbmblock;
+
 	return rbmoff << mp->m_blkbit_log;
 }
 
@@ -177,7 +190,14 @@ xfs_rbmblock_wordptr(
 	struct xfs_rtalloc_args	*args,
 	unsigned int		index)
 {
-	union xfs_rtword_raw	*words = args->rbmbp->b_addr;
+	struct xfs_mount	*mp = args->mp;
+	union xfs_rtword_raw	*words;
+	struct xfs_rtbuf_blkinfo *hdr = args->rbmbp->b_addr;
+
+	if (xfs_has_rtgroups(mp))
+		words = (union xfs_rtword_raw *)(hdr + 1);
+	else
+		words = args->rbmbp->b_addr;
 
 	return words + index;
 }
@@ -227,6 +247,9 @@ xfs_rtsumoffs_to_block(
 	struct xfs_mount	*mp,
 	xfs_rtsumoff_t		rsumoff)
 {
+	if (xfs_has_rtgroups(mp))
+		return rsumoff / mp->m_blockwsize;
+
 	return XFS_B_TO_FSBT(mp, rsumoff * sizeof(xfs_suminfo_t));
 }
 
@@ -241,6 +264,9 @@ xfs_rtsumoffs_to_infoword(
 {
 	unsigned int		mask = mp->m_blockmask >> XFS_SUMINFOLOG;
 
+	if (xfs_has_rtgroups(mp))
+		return rsumoff % mp->m_blockwsize;
+
 	return rsumoff & mask;
 }
 
@@ -250,7 +276,13 @@ xfs_rsumblock_infoptr(
 	struct xfs_rtalloc_args	*args,
 	unsigned int		index)
 {
-	union xfs_suminfo_raw	*info = args->sumbp->b_addr;
+	union xfs_suminfo_raw	*info;
+	struct xfs_rtbuf_blkinfo *hdr = args->sumbp->b_addr;
+
+	if (xfs_has_rtgroups(args->mp))
+		info = (union xfs_suminfo_raw *)(hdr + 1);
+	else
+		info = args->sumbp->b_addr;
 
 	return info + index;
 }
@@ -279,6 +311,19 @@ xfs_suminfo_add(
 	return info->old;
 }
 
+static inline const struct xfs_buf_ops *
+xfs_rtblock_ops(
+	struct xfs_mount	*mp,
+	enum xfs_rtg_inodes	type)
+{
+	if (xfs_has_rtgroups(mp)) {
+		if (type == XFS_RTGI_SUMMARY)
+			return &xfs_rtsummary_buf_ops;
+		return &xfs_rtbitmap_buf_ops;
+	}
+	return &xfs_rtbuf_ops;
+}
+
 /*
  * Functions for walking free space rtextents in the realtime bitmap.
  */
@@ -324,6 +369,7 @@ int xfs_rtfree_extent(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
 int xfs_rtfree_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
 		xfs_fsblock_t rtbno, xfs_filblks_t rtlen);
 
+xfs_rtxnum_t xfs_rtbitmap_rtx_per_rbmblock(struct xfs_mount *mp);
 xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp);
 xfs_filblks_t xfs_rtbitmap_blockcount_len(struct xfs_mount *mp,
 		xfs_rtbxlen_t rtextents);
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index d5bf886e18ab9e..c55ccecaccbda4 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -246,11 +246,26 @@ xfs_extents_per_rbm(
 	return sbp->sb_rextents;
 }
 
+/*
+ * Return the payload size of a single rt bitmap block (without the metadata
+ * header if any).
+ */
+static inline unsigned int
+xfs_rtbmblock_size(
+	struct xfs_sb		*sbp)
+{
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR))
+		return sbp->sb_blocksize - sizeof(struct xfs_rtbuf_blkinfo);
+	return sbp->sb_blocksize;
+}
+
 static uint64_t
 xfs_expected_rbmblocks(
 	struct xfs_sb		*sbp)
 {
-	return howmany_64(xfs_extents_per_rbm(sbp), NBBY * sbp->sb_blocksize);
+	return howmany_64(xfs_extents_per_rbm(sbp),
+			  NBBY * xfs_rtbmblock_size(sbp));
 }
 
 /* Validate the realtime geometry */
@@ -1098,8 +1113,8 @@ xfs_sb_mount_common(
 	mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
 	mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
 	mp->m_blockmask = sbp->sb_blocksize - 1;
-	mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
-	mp->m_blockwmask = mp->m_blockwsize - 1;
+	mp->m_blockwsize = xfs_rtbmblock_size(sbp) >> XFS_WORDLOG;
+	mp->m_rtx_per_rbmblock = mp->m_blockwsize << XFS_NBWORDLOG;
 
 	ags->blocks = mp->m_sb.sb_agblocks;
 	ags->blklog = mp->m_sb.sb_agblklog;
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 552365d212ea26..9363f918675ac0 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -38,6 +38,8 @@ extern const struct xfs_buf_ops xfs_inode_buf_ops;
 extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_refcountbt_buf_ops;
 extern const struct xfs_buf_ops xfs_rmapbt_buf_ops;
+extern const struct xfs_buf_ops xfs_rtbitmap_buf_ops;
+extern const struct xfs_buf_ops xfs_rtsummary_buf_ops;
 extern const struct xfs_buf_ops xfs_rtbuf_ops;
 extern const struct xfs_buf_ops xfs_rtsb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_buf_ops;
diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c
index 1688380988007f..8198ea84ad70e5 100644
--- a/fs/xfs/scrub/rtsummary_repair.c
+++ b/fs/xfs/scrub/rtsummary_repair.c
@@ -83,12 +83,23 @@ xrep_rtsummary_prep_buf(
 	ondisk = xfs_rsumblock_infoptr(&rts->args, 0);
 	rts->args.sumbp = NULL;
 
-	bp->b_ops = &xfs_rtbuf_ops;
-
 	error = xfsum_copyout(sc, rts->prep_wordoff, ondisk, mp->m_blockwsize);
 	if (error)
 		return error;
 
+	if (xfs_has_rtgroups(sc->mp)) {
+		struct xfs_rtbuf_blkinfo	*hdr = bp->b_addr;
+
+		hdr->rt_magic = cpu_to_be32(XFS_RTSUMMARY_MAGIC);
+		hdr->rt_owner = cpu_to_be64(sc->ip->i_ino);
+		hdr->rt_blkno = cpu_to_be64(xfs_buf_daddr(bp));
+		hdr->rt_lsn = 0;
+		uuid_copy(&hdr->rt_uuid, &sc->mp->m_sb.sb_meta_uuid);
+		bp->b_ops = &xfs_rtsummary_buf_ops;
+	} else {
+		bp->b_ops = &xfs_rtbuf_ops;
+	}
+
 	rts->prep_wordoff += mp->m_blockwsize;
 	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_RTSUMMARY_BUF);
 	return 0;
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index feb3db2e891614..3d0c6402cb3634 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -26,6 +26,7 @@
 #include "xfs_ag.h"
 #include "xfs_sb.h"
 #include "xfs_rtgroup.h"
+#include "xfs_rtbitmap.h"
 
 /*
  * This is the number of entries in the l_buf_cancel_table used during
@@ -394,9 +395,18 @@ xlog_recover_validate_buf_type(
 		break;
 #ifdef CONFIG_XFS_RT
 	case XFS_BLFT_RTBITMAP_BUF:
+		if (xfs_has_rtgroups(mp) && magic32 != XFS_RTBITMAP_MAGIC) {
+			warnmsg = "Bad rtbitmap magic!";
+			break;
+		}
+		bp->b_ops = xfs_rtblock_ops(mp, XFS_RTGI_BITMAP);
+		break;
 	case XFS_BLFT_RTSUMMARY_BUF:
-		/* no magic numbers for verification of RT buffers */
-		bp->b_ops = &xfs_rtbuf_ops;
+		if (xfs_has_rtgroups(mp) && magic32 != XFS_RTSUMMARY_MAGIC) {
+			warnmsg = "Bad rtsummary magic!";
+			break;
+		}
+		bp->b_ops = xfs_rtblock_ops(mp, XFS_RTGI_SUMMARY);
 		break;
 #endif /* CONFIG_XFS_RT */
 	default:
@@ -815,11 +825,20 @@ xlog_recover_get_buf_lsn(
 	 * UUIDs, so we must recover them immediately.
 	 */
 	blft = xfs_blft_from_flags(buf_f);
-	if (blft == XFS_BLFT_RTBITMAP_BUF || blft == XFS_BLFT_RTSUMMARY_BUF)
+	if (!xfs_has_rtgroups(mp) && (blft == XFS_BLFT_RTBITMAP_BUF ||
+				      blft == XFS_BLFT_RTSUMMARY_BUF))
 		goto recover_immediately;
 
 	magic32 = be32_to_cpu(*(__be32 *)blk);
 	switch (magic32) {
+	case XFS_RTSUMMARY_MAGIC:
+	case XFS_RTBITMAP_MAGIC: {
+		struct xfs_rtbuf_blkinfo	*hdr = blk;
+
+		lsn = be64_to_cpu(hdr->rt_lsn);
+		uuid = &hdr->rt_uuid;
+		break;
+	}
 	case XFS_ABTB_CRC_MAGIC:
 	case XFS_ABTC_CRC_MAGIC:
 	case XFS_ABTB_MAGIC:
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 42b8b5e0e931b7..e71bd64685f900 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -572,7 +572,7 @@ xfs_trim_rtextents(
 	 * trims the extents returned.
 	 */
 	do {
-		tr.stop_rtx = low + (mp->m_sb.sb_blocksize * NBBY);
+		tr.stop_rtx = low + xfs_rtbitmap_rtx_per_rbmblock(mp);
 		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
 		error = xfs_rtalloc_query_range(rtg, tp, low, high,
 				xfs_trim_gather_rtextent, &tr);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 33fb03547c88ac..1f228047639587 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -150,7 +150,8 @@ typedef struct xfs_mount {
 	int8_t			m_rgblklog;	/* log2 of rt group sz if possible */
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
-	uint			m_blockwmask;	/* blockwsize-1 */
+	/* number of rt extents per rt bitmap block if rtgroups enabled */
+	unsigned int		m_rtx_per_rbmblock;
 	uint			m_alloc_mxr[2];	/* max alloc btree records */
 	uint			m_alloc_mnr[2];	/* min alloc btree records */
 	uint			m_bmap_dmxr[2];	/* max bmap btree records */
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index abeedc848b3bd2..2baa8bed42ff5b 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -776,7 +776,7 @@ xfs_growfs_rt_nrblocks(
 	struct xfs_mount	*mp = rtg_mount(rtg);
 	xfs_rfsblock_t		step;
 
-	step = (bmbno + 1) * NBBY * mp->m_sb.sb_blocksize * rextsize;
+	step = (bmbno + 1) * mp->m_rtx_per_rbmblock * rextsize;
 	if (xfs_has_rtgroups(mp)) {
 		xfs_rfsblock_t	rgblocks = mp->m_sb.sb_rgextents * rextsize;
 

[PATCH 12/34] xfs: encode the rtbitmap in big endian format

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, the ondisk realtime bitmap file is accessed in units of
32-bit words.  There's no endian translation of the contents of this
file, which means that the Bad Things Happen(tm) if you go from (say)
x86 to powerpc.  Since we have a new feature flag, let's take the
opportunity to enforce an endianness on the file.

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


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 016ee4ff537440..cd9457ed5873fe 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -709,10 +709,12 @@ struct xfs_agfl {
 
 /*
  * Realtime bitmap information is accessed by the word, which is currently
- * stored in host-endian format.
+ * stored in host-endian format.  Starting with the realtime groups feature,
+ * the words are stored in be32 ondisk.
  */
 union xfs_rtword_raw {
 	__u32		old;
+	__be32		rtg;
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 2286a98ecb32bb..f9c0d241590104 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -210,6 +210,8 @@ xfs_rtbitmap_getword(
 {
 	union xfs_rtword_raw	*word = xfs_rbmblock_wordptr(args, index);
 
+	if (xfs_has_rtgroups(args->mp))
+		return be32_to_cpu(word->rtg);
 	return word->old;
 }
 
@@ -222,7 +224,10 @@ xfs_rtbitmap_setword(
 {
 	union xfs_rtword_raw	*word = xfs_rbmblock_wordptr(args, index);
 
-	word->old = value;
+	if (xfs_has_rtgroups(args->mp))
+		word->rtg = cpu_to_be32(value);
+	else
+		word->old = value;
 }
 
 /*

[PATCH 13/34] xfs: encode the rtsummary in big endian format

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, the ondisk realtime summary file counters are accessed in
units of 32-bit words.  There's no endian translation of the contents of
this file, which means that the Bad Things Happen(tm) if you go from
(say) x86 to powerpc.  Since we have a new feature flag, let's take the
opportunity to enforce an endianness on the file.  Encode the summary
information in big endian format, like most of the rest of the
filesystem.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_format.h   |    4 +++-
 fs/xfs/libxfs/xfs_rtbitmap.h |    7 +++++++
 fs/xfs/scrub/rtsummary.c     |    5 +++++
 3 files changed, 15 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index cd9457ed5873fe..f56ff9f43c218f 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -719,10 +719,12 @@ union xfs_rtword_raw {
 
 /*
  * Realtime summary counts are accessed by the word, which is currently
- * stored in host-endian format.
+ * stored in host-endian format.  Starting with the realtime groups feature,
+ * the words are stored in be32 ondisk.
  */
 union xfs_suminfo_raw {
 	__u32		old;
+	__be32		rtg;
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index f9c0d241590104..7be76490a31879 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -300,6 +300,8 @@ xfs_suminfo_get(
 {
 	union xfs_suminfo_raw	*info = xfs_rsumblock_infoptr(args, index);
 
+	if (xfs_has_rtgroups(args->mp))
+		return be32_to_cpu(info->rtg);
 	return info->old;
 }
 
@@ -312,6 +314,11 @@ xfs_suminfo_add(
 {
 	union xfs_suminfo_raw	*info = xfs_rsumblock_infoptr(args, index);
 
+	if (xfs_has_rtgroups(args->mp)) {
+		be32_add_cpu(&info->rtg, delta);
+		return be32_to_cpu(info->rtg);
+	}
+
 	info->old += delta;
 	return info->old;
 }
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 8f3f69b26cad04..49fc6250bafcaa 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -151,6 +151,11 @@ xchk_rtsum_inc(
 	struct xfs_mount	*mp,
 	union xfs_suminfo_raw	*v)
 {
+	if (xfs_has_rtgroups(mp)) {
+		be32_add_cpu(&v->rtg, 1);
+		return be32_to_cpu(v->rtg);
+	}
+
 	v->old += 1;
 	return v->old;
 }

[PATCH 14/34] xfs: grow the realtime section when realtime groups are enabled

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Enable growing the rt section when realtime groups are enabled.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_shared.h |    1 
 fs/xfs/xfs_rtalloc.c       |  270 ++++++++++++++++++++++++++++++++++++++------
 fs/xfs/xfs_trans.c         |    9 +
 fs/xfs/xfs_trans.h         |    1 
 4 files changed, 244 insertions(+), 37 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 9363f918675ac0..e7efdb9ceaf382 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -160,6 +160,7 @@ void	xfs_log_get_max_trans_res(struct xfs_mount *mp,
 #define	XFS_TRANS_SB_RBLOCKS		0x00000800
 #define	XFS_TRANS_SB_REXTENTS		0x00001000
 #define	XFS_TRANS_SB_REXTSLOG		0x00002000
+#define XFS_TRANS_SB_RGCOUNT		0x00004000
 
 /*
  * Here we centralize the specification of XFS meta-data buffer reference count
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 2baa8bed42ff5b..1f53d5e07a91a0 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -766,6 +766,31 @@ xfs_growfs_rt_alloc_fake_mount(
 	return nmp;
 }
 
+/* Free all the new space and return the number of extents actually freed. */
+static int
+xfs_growfs_rt_free_new(
+	struct xfs_rtgroup	*rtg,
+	struct xfs_rtalloc_args	*nargs,
+	xfs_rtbxlen_t		*freed_rtx)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	xfs_rgnumber_t		rgno = rtg_rgno(rtg);
+	xfs_rtxnum_t		start_rtx = 0, end_rtx;
+
+	if (rgno < mp->m_sb.sb_rgcount)
+		start_rtx = xfs_rtgroup_extents(mp, rgno);
+	end_rtx = xfs_rtgroup_extents(nargs->mp, rgno);
+
+	/*
+	 * Compute the first new extent that we want to free, being careful to
+	 * skip past a realtime superblock at the start of the realtime volume.
+	 */
+	if (xfs_has_rtsb(nargs->mp) && rgno == 0 && start_rtx == 0)
+		start_rtx++;
+	*freed_rtx = end_rtx - start_rtx;
+	return xfs_rtfree_range(nargs, start_rtx, *freed_rtx);
+}
+
 static xfs_rfsblock_t
 xfs_growfs_rt_nrblocks(
 	struct xfs_rtgroup	*rtg,
@@ -786,6 +811,43 @@ xfs_growfs_rt_nrblocks(
 	return min(nrblocks, step);
 }
 
+/*
+ * If the post-grow filesystem will have an rtsb; we're initializing the first
+ * rtgroup; and the filesystem didn't have a realtime section, write the rtsb
+ * now, and attach the rtsb buffer to the real mount.
+ */
+static int
+xfs_growfs_rt_init_rtsb(
+	const struct xfs_rtalloc_args	*nargs,
+	const struct xfs_rtgroup	*rtg,
+	const struct xfs_rtalloc_args	*args)
+{
+	struct xfs_mount		*mp = args->mp;
+	struct xfs_buf			*rtsb_bp;
+	int				error;
+
+	if (!xfs_has_rtsb(nargs->mp))
+		return 0;
+	if (rtg_rgno(rtg) > 0)
+		return 0;
+	if (mp->m_sb.sb_rblocks)
+		return 0;
+
+	error = xfs_buf_get_uncached(mp->m_rtdev_targp, XFS_FSB_TO_BB(mp, 1),
+			0, &rtsb_bp);
+	if (error)
+		return error;
+
+	rtsb_bp->b_maps[0].bm_bn = XFS_RTSB_DADDR;
+	rtsb_bp->b_ops = &xfs_rtsb_buf_ops;
+
+	xfs_update_rtsb(rtsb_bp, mp->m_sb_bp);
+	mp->m_rtsb_bp = rtsb_bp;
+	error = xfs_bwrite(rtsb_bp);
+	xfs_buf_unlock(rtsb_bp);
+	return error;
+}
+
 static int
 xfs_growfs_rt_bmblock(
 	struct xfs_rtgroup	*rtg,
@@ -808,7 +870,8 @@ xfs_growfs_rt_bmblock(
 	int			error;
 
 	/*
-	 * Calculate new sb and mount fields for this round.
+	 * Calculate new sb and mount fields for this round.  Also ensure the
+	 * rtg_extents value is uptodate as the rtbitmap code relies on it.
 	 */
 	nmp = nargs.mp = xfs_growfs_rt_alloc_fake_mount(mp,
 			xfs_growfs_rt_nrblocks(rtg, nrblocks, rextsize, bmbno),
@@ -861,6 +924,10 @@ xfs_growfs_rt_bmblock(
 			goto out_cancel;
 	}
 
+	error = xfs_growfs_rt_init_rtsb(&nargs, rtg, &args);
+	if (error)
+		goto out_cancel;
+
 	/*
 	 * Update superblock fields.
 	 */
@@ -879,12 +946,14 @@ xfs_growfs_rt_bmblock(
 	if (nmp->m_sb.sb_rextslog != mp->m_sb.sb_rextslog)
 		xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTSLOG,
 			nmp->m_sb.sb_rextslog - mp->m_sb.sb_rextslog);
+	if (nmp->m_sb.sb_rgcount != mp->m_sb.sb_rgcount)
+		xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RGCOUNT,
+			nmp->m_sb.sb_rgcount - mp->m_sb.sb_rgcount);
 
 	/*
 	 * Free the new extent.
 	 */
-	freed_rtx = nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents;
-	error = xfs_rtfree_range(&nargs, mp->m_sb.sb_rextents, freed_rtx);
+	error = xfs_growfs_rt_free_new(rtg, &nargs, &freed_rtx);
 	xfs_rtbuf_cache_relse(&nargs);
 	if (error)
 		goto out_cancel;
@@ -925,6 +994,15 @@ xfs_growfs_rt_bmblock(
 	return error;
 }
 
+static xfs_rtxnum_t
+xfs_last_rtgroup_extents(
+	struct xfs_mount	*mp)
+{
+	return mp->m_sb.sb_rextents -
+		((xfs_rtxnum_t)(mp->m_sb.sb_rgcount - 1) *
+		 mp->m_sb.sb_rgextents);
+}
+
 /*
  * Calculate the last rbmblock currently used.
  *
@@ -935,11 +1013,20 @@ xfs_last_rt_bmblock(
 	struct xfs_rtgroup	*rtg)
 {
 	struct xfs_mount	*mp = rtg_mount(rtg);
-	xfs_fileoff_t		bmbno = mp->m_sb.sb_rbmblocks;
+	xfs_rgnumber_t		rgno = rtg_rgno(rtg);
+	xfs_fileoff_t		bmbno = 0;
+
+	ASSERT(!mp->m_sb.sb_rgcount || rgno >= mp->m_sb.sb_rgcount - 1);
+
+	if (mp->m_sb.sb_rgcount && rgno == mp->m_sb.sb_rgcount - 1) {
+		xfs_rtxnum_t	nrext = xfs_last_rtgroup_extents(mp);
+
+		/* Also fill up the previous block if not entirely full. */
+		bmbno = xfs_rtbitmap_blockcount_len(mp, nrext);
+		if (xfs_rtx_to_rbmword(mp, nrext) != 0)
+			bmbno--;
+	}
 
-	/* Skip the current block if it is exactly full. */
-	if (xfs_rtx_to_rbmword(mp, mp->m_sb.sb_rextents) != 0)
-		bmbno--;
 	return bmbno;
 }
 
@@ -956,38 +1043,56 @@ xfs_growfs_rt_alloc_blocks(
 	struct xfs_mount	*mp = rtg_mount(rtg);
 	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
 	struct xfs_inode	*rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
-	xfs_extlen_t		orbmblocks;
-	xfs_extlen_t		orsumblocks;
-	xfs_extlen_t		nrsumblocks;
+	xfs_extlen_t		orbmblocks = 0;
+	xfs_extlen_t		orsumblocks = 0;
 	struct xfs_mount	*nmp;
-	int			error;
-
-	/*
-	 * Get the old block counts for bitmap and summary inodes.
-	 * These can't change since other growfs callers are locked out.
-	 */
-	orbmblocks = XFS_B_TO_FSB(mp, rbmip->i_disk_size);
-	orsumblocks = XFS_B_TO_FSB(mp, rsumip->i_disk_size);
+	int			error = 0;
 
 	nmp = xfs_growfs_rt_alloc_fake_mount(mp, nrblocks, rextsize);
 	if (!nmp)
 		return -ENOMEM;
-
 	*nrbmblocks = nmp->m_sb.sb_rbmblocks;
-	nrsumblocks = nmp->m_rsumblocks;
-	kfree(nmp);
+
+	if (xfs_has_rtgroups(mp)) {
+		/*
+		 * For file systems with the rtgroups feature, the RT bitmap and
+		 * summary are always fully allocated, which means that we never
+		 * need to grow the existing files.
+		 *
+		 * But we have to be careful to only fill the bitmap until the
+		 * end of the actually used range.
+		 */
+		if (rtg_rgno(rtg) == nmp->m_sb.sb_rgcount - 1)
+			*nrbmblocks = xfs_rtbitmap_blockcount_len(nmp,
+					xfs_last_rtgroup_extents(nmp));
+
+		if (mp->m_sb.sb_rgcount &&
+		    rtg_rgno(rtg) == mp->m_sb.sb_rgcount - 1)
+			goto out_free;
+	} else {
+		/*
+		 * Get the old block counts for bitmap and summary inodes.
+		 * These can't change since other growfs callers are locked out.
+		 */
+		orbmblocks = XFS_B_TO_FSB(mp, rbmip->i_disk_size);
+		orsumblocks = XFS_B_TO_FSB(mp, rsumip->i_disk_size);
+	}
 
 	error = xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_BITMAP, orbmblocks,
-			*nrbmblocks, NULL);
+			nmp->m_sb.sb_rbmblocks, NULL);
 	if (error)
-		return error;
-	return xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_SUMMARY, orsumblocks,
-			nrsumblocks, NULL);
+		goto out_free;
+	error = xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_SUMMARY, orsumblocks,
+			nmp->m_rsumblocks, NULL);
+out_free:
+	kfree(nmp);
+	return error;
 }
 
 static int
 xfs_growfs_rtg(
 	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno,
 	xfs_rfsblock_t		nrblocks,
 	xfs_agblock_t		rextsize)
 {
@@ -998,7 +1103,7 @@ xfs_growfs_rtg(
 	unsigned int		i;
 	int			error;
 
-	rtg = xfs_rtgroup_grab(mp, 0);
+	rtg = xfs_rtgroup_grab(mp, rgno);
 	if (!rtg)
 		return -EINVAL;
 
@@ -1069,14 +1174,67 @@ xfs_growfs_check_rtgeom(
 	return error;
 }
 
+/*
+ * Compute the new number of rt groups and ensure that /rtgroups exists.
+ *
+ * Changing the rtgroup size is not allowed (even if the rt volume hasn't yet
+ * been initialized) because the userspace ABI doesn't support it.
+ */
+static int
+xfs_growfs_rt_prep_groups(
+	struct xfs_mount	*mp,
+	xfs_rfsblock_t		rblocks,
+	xfs_extlen_t		rextsize,
+	xfs_rgnumber_t		*new_rgcount)
+{
+	int			error;
+
+	*new_rgcount = howmany_64(rblocks, mp->m_sb.sb_rgextents * rextsize);
+	if (*new_rgcount > XFS_MAX_RGNUMBER)
+		return -EINVAL;
+
+	/* Make sure the /rtgroups dir has been created */
+	if (!mp->m_rtdirip) {
+		struct xfs_trans	*tp;
+
+		error = xfs_trans_alloc_empty(mp, &tp);
+		if (error)
+			return error;
+		error = xfs_rtginode_load_parent(tp);
+		xfs_trans_cancel(tp);
+
+		if (error == -ENOENT)
+			error = xfs_rtginode_mkdir_parent(mp);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+static bool
+xfs_grow_last_rtg(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_has_rtgroups(mp))
+		return true;
+	if (mp->m_sb.sb_rgcount == 0)
+		return false;
+	return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) <=
+			mp->m_sb.sb_rgextents;
+}
+
 /*
  * Grow the realtime area of the filesystem.
  */
 int
 xfs_growfs_rt(
-	xfs_mount_t	*mp,		/* mount point for filesystem */
-	xfs_growfs_rt_t	*in)		/* growfs rt input struct */
+	struct xfs_mount	*mp,
+	struct xfs_growfs_rt	*in)
 {
+	xfs_rgnumber_t		old_rgcount = mp->m_sb.sb_rgcount;
+	xfs_rgnumber_t		new_rgcount = 1;
+	xfs_rgnumber_t		rgno;
 	struct xfs_buf		*bp;
 	xfs_agblock_t		old_rextsize = mp->m_sb.sb_rextsize;
 	int			error;
@@ -1134,19 +1292,57 @@ xfs_growfs_rt(
 	if (error)
 		goto out_unlock;
 
-	error = xfs_growfs_rtg(mp, in->newblocks, in->extsize);
-	if (error)
-		goto out_unlock;
+	if (xfs_has_rtgroups(mp)) {
+		error = xfs_growfs_rt_prep_groups(mp, in->newblocks,
+				in->extsize, &new_rgcount);
+		if (error)
+			goto out_unlock;
+	}
 
-	if (old_rextsize != in->extsize) {
+	if (xfs_grow_last_rtg(mp)) {
+		error = xfs_growfs_rtg(mp, old_rgcount - 1, in->newblocks,
+				in->extsize);
+		if (error)
+			goto out_unlock;
+	}
+
+	for (rgno = old_rgcount; rgno < new_rgcount; rgno++) {
+		xfs_rtbxlen_t	rextents = div_u64(in->newblocks, in->extsize);
+
+		error = xfs_rtgroup_alloc(mp, rgno, new_rgcount, rextents);
+		if (error)
+			goto out_unlock;
+
+		error = xfs_growfs_rtg(mp, rgno, in->newblocks, in->extsize);
+		if (error) {
+			struct xfs_rtgroup	*rtg;
+
+			rtg = xfs_rtgroup_grab(mp, rgno);
+			if (!WARN_ON_ONCE(!rtg)) {
+				xfs_rtunmount_rtg(rtg);
+				xfs_rtgroup_rele(rtg);
+				xfs_rtgroup_free(mp, rgno);
+			}
+			break;
+		}
+	}
+
+	if (!error && old_rextsize != in->extsize)
 		error = xfs_growfs_rt_fixup_extsize(mp);
-		if (error)
-			goto out_unlock;
+
+	/*
+	 * Update secondary superblocks now the physical grow has completed.
+	 *
+	 * Also do this in case of an error as we might have already
+	 * successfully updated one or more RTGs and incremented sb_rgcount.
+	 */
+	if (!xfs_is_shutdown(mp)) {
+		int error2 = xfs_update_secondary_sbs(mp);
+
+		if (!error)
+			error = error2;
 	}
 
-	/* Update secondary superblocks now the physical grow has completed */
-	error = xfs_update_secondary_sbs(mp);
-
 out_unlock:
 	mutex_unlock(&mp->m_growlock);
 	return error;
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 01b5f5b32af467..a29a181e684041 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -460,6 +460,10 @@ xfs_trans_mod_sb(
 	case XFS_TRANS_SB_REXTSLOG:
 		tp->t_rextslog_delta += delta;
 		break;
+	case XFS_TRANS_SB_RGCOUNT:
+		ASSERT(delta > 0);
+		tp->t_rgcount_delta += delta;
+		break;
 	default:
 		ASSERT(0);
 		return;
@@ -561,6 +565,10 @@ xfs_trans_apply_sb_deltas(
 		sbp->sb_rextslog += tp->t_rextslog_delta;
 		whole = 1;
 	}
+	if (tp->t_rgcount_delta) {
+		be32_add_cpu(&sbp->sb_rgcount, tp->t_rgcount_delta);
+		whole = 1;
+	}
 
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
 	if (whole)
@@ -674,6 +682,7 @@ xfs_trans_unreserve_and_mod_sb(
 	mp->m_sb.sb_rblocks += tp->t_rblocks_delta;
 	mp->m_sb.sb_rextents += tp->t_rextents_delta;
 	mp->m_sb.sb_rextslog += tp->t_rextslog_delta;
+	mp->m_sb.sb_rgcount += tp->t_rgcount_delta;
 	spin_unlock(&mp->m_sb_lock);
 
 	/*
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index f97e5c416efad1..71c2e82e4dadff 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -148,6 +148,7 @@ typedef struct xfs_trans {
 	int64_t			t_rblocks_delta;/* superblock rblocks change */
 	int64_t			t_rextents_delta;/* superblocks rextents chg */
 	int64_t			t_rextslog_delta;/* superblocks rextslog chg */
+	int64_t			t_rgcount_delta; /* realtime group count */
 	struct list_head	t_items;	/* log item descriptors */
 	struct list_head	t_busy;		/* list of busy extents */
 	struct list_head	t_dfops;	/* deferred operations */

[PATCH 15/34] xfs: store rtgroup information with a bmap intent

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Make the bmap intent items take an active reference to the rtgroup
containing the space that is being mapped or unmapped.  We will need
this functionality once we start enabling rmap and reflink on the rt
volume.  Technically speaking we need it even for !rtgroups filesystems
to prevent the (dummy) rtgroup 0 from going away, even though this will
never happen.

As a bonus, we can rework the xfs_bmap_deferred_class tracepoint to use
the xfs_group object to figure out the type and group number, widen the
group block number field to fit 64-bit quantities, and get rid of the
now redundant opdev and rtblock fields.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_bmap_item.c |   25 ++++++++-----------------
 fs/xfs/xfs_trace.h     |   41 ++++++++++++++++++++++-------------------
 2 files changed, 30 insertions(+), 36 deletions(-)


diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 37dab184c2dfc2..3d52e9d7ad571a 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -318,14 +318,16 @@ xfs_bmap_update_create_done(
 	return &budp->bud_item;
 }
 
-/* Take a passive ref to the AG containing the space we're mapping. */
+/* Take a passive ref to the group containing the space we're mapping. */
 static inline void
 xfs_bmap_update_get_group(
 	struct xfs_mount	*mp,
 	struct xfs_bmap_intent	*bi)
 {
+	enum xfs_group_type	type = XG_TYPE_AG;
+
 	if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
-		return;
+		type = XG_TYPE_RTG;
 
 	/*
 	 * Bump the intent count on behalf of the deferred rmap and refcount
@@ -335,7 +337,7 @@ xfs_bmap_update_get_group(
 	 * remains nonzero across the transaction roll.
 	 */
 	bi->bi_group = xfs_group_intent_get(mp, bi->bi_bmap.br_startblock,
-			XG_TYPE_AG);
+				type);
 }
 
 /* Add this deferred BUI to the transaction. */
@@ -344,8 +346,6 @@ xfs_bmap_defer_add(
 	struct xfs_trans	*tp,
 	struct xfs_bmap_intent	*bi)
 {
-	trace_xfs_bmap_defer(bi);
-
 	xfs_bmap_update_get_group(tp->t_mountp, bi);
 
 	/*
@@ -358,20 +358,11 @@ xfs_bmap_defer_add(
 	 */
 	if (bi->bi_type == XFS_BMAP_MAP)
 		bi->bi_owner->i_delayed_blks += bi->bi_bmap.br_blockcount;
+
+	trace_xfs_bmap_defer(bi);
 	xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
 }
 
-/* Release a passive AG ref after finishing mapping work. */
-static inline void
-xfs_bmap_update_put_group(
-	struct xfs_bmap_intent	*bi)
-{
-	if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
-		return;
-
-	xfs_group_intent_put(bi->bi_group);
-}
-
 /* Cancel a deferred bmap update. */
 STATIC void
 xfs_bmap_update_cancel_item(
@@ -382,7 +373,7 @@ xfs_bmap_update_cancel_item(
 	if (bi->bi_type == XFS_BMAP_MAP)
 		bi->bi_owner->i_delayed_blks -= bi->bi_bmap.br_blockcount;
 
-	xfs_bmap_update_put_group(bi);
+	xfs_group_intent_put(bi->bi_group);
 	kmem_cache_free(xfs_bmap_intent_cache, bi);
 }
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 62169c2ec38789..a9392eaaf6f581 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3081,11 +3081,10 @@ DECLARE_EVENT_CLASS(xfs_bmap_deferred_class,
 	TP_ARGS(bi),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(dev_t, opdev)
+		__field(enum xfs_group_type, type)
 		__field(xfs_agnumber_t, agno)
 		__field(xfs_ino_t, ino)
-		__field(xfs_agblock_t, agbno)
-		__field(xfs_fsblock_t, rtbno)
+		__field(unsigned long long, gbno)
 		__field(int, whichfork)
 		__field(xfs_fileoff_t, l_loff)
 		__field(xfs_filblks_t, l_len)
@@ -3094,20 +3093,25 @@ DECLARE_EVENT_CLASS(xfs_bmap_deferred_class,
 	),
 	TP_fast_assign(
 		struct xfs_inode	*ip = bi->bi_owner;
+		struct xfs_mount	*mp = ip->i_mount;
 
-		__entry->dev = ip->i_mount->m_super->s_dev;
-		if (xfs_ifork_is_realtime(ip, bi->bi_whichfork)) {
-			__entry->agno = 0;
-			__entry->agbno = 0;
-			__entry->rtbno = bi->bi_bmap.br_startblock;
-			__entry->opdev = ip->i_mount->m_rtdev_targp->bt_dev;
+		__entry->dev = mp->m_super->s_dev;
+		__entry->type = bi->bi_group->xg_type;
+		__entry->agno = bi->bi_group->xg_gno;
+		if (bi->bi_group->xg_type == XG_TYPE_RTG &&
+		    !xfs_has_rtgroups(mp)) {
+			/*
+			 * Legacy rt filesystems do not have allocation groups
+			 * ondisk.  We emulate this incore with one gigantic
+			 * rtgroup whose size can exceed a 32-bit block number.
+			 * For this tracepoint, we report group 0 and a 64-bit
+			 * group block number.
+			 */
+			__entry->gbno = bi->bi_bmap.br_startblock;
 		} else {
-			__entry->agno = XFS_FSB_TO_AGNO(ip->i_mount,
-						bi->bi_bmap.br_startblock);
-			__entry->agbno = XFS_FSB_TO_AGBNO(ip->i_mount,
-						bi->bi_bmap.br_startblock);
-			__entry->rtbno = 0;
-			__entry->opdev = __entry->dev;
+			__entry->gbno = xfs_fsb_to_gbno(mp,
+						bi->bi_bmap.br_startblock,
+						bi->bi_group->xg_type);
 		}
 		__entry->ino = ip->i_ino;
 		__entry->whichfork = bi->bi_whichfork;
@@ -3116,14 +3120,13 @@ DECLARE_EVENT_CLASS(xfs_bmap_deferred_class,
 		__entry->l_state = bi->bi_bmap.br_state;
 		__entry->op = bi->bi_type;
 	),
-	TP_printk("dev %d:%d op %s opdev %d:%d ino 0x%llx agno 0x%x agbno 0x%x rtbno 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d",
+	TP_printk("dev %d:%d op %s ino 0x%llx %sno 0x%x gbno 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __print_symbolic(__entry->op, XFS_BMAP_INTENT_STRINGS),
-		  MAJOR(__entry->opdev), MINOR(__entry->opdev),
 		  __entry->ino,
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
-		  __entry->agbno,
-		  __entry->rtbno,
+		  __entry->gbno,
 		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
 		  __entry->l_loff,
 		  __entry->l_len,

[PATCH 16/34] xfs: force swapext to a realtime file to use the file content exchange ioctl

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

xfs_swap_extent_rmap does not use log items to track the overall
progress of an attempt to swap the extent mappings between two files.
If the system crashes in the middle of swapping a partially written
realtime extent, the mapping will be left in an inconsistent state
wherein a file can point to multiple extents on the rt volume.

The new file range exchange functionality handles this correctly, so all
callers must upgrade to that.

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


diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 1ac0b0facb7fd3..bc53f5c7357c7a 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1532,6 +1532,18 @@ xfs_swap_extents(
 		goto out_unlock;
 	}
 
+	/*
+	 * The rmapbt implementation is unable to resume a swapext operation
+	 * after a crash if the allocation unit size is larger than a block.
+	 * This (deprecated) interface will not be upgraded to handle this
+	 * situation.  Defragmentation must be performed with the commit range
+	 * ioctl.
+	 */
+	if (XFS_IS_REALTIME_INODE(ip) && xfs_has_rtgroups(ip->i_mount)) {
+		error = -EOPNOTSUPP;
+		goto out_unlock;
+	}
+
 	error = xfs_qm_dqattach(ip);
 	if (error)
 		goto out_unlock;

[PATCH 17/34] xfs: support logging EFIs for realtime extents

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Teach the EFI mechanism how to free realtime extents.  We're going to
need this to enforce proper ordering of operations when we enable
realtime rmap.

Declare a new log intent item type (XFS_LI_EFI_RT) and a separate defer
ops for rt extents.  This keeps the ondisk artifacts and processing code
completely separate between the rt and non-rt cases.  Hopefully this
will make it easier to debug filesystem problems.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_alloc.c       |   15 ++
 fs/xfs/libxfs/xfs_alloc.h       |   12 ++
 fs/xfs/libxfs/xfs_defer.c       |    6 +
 fs/xfs/libxfs/xfs_defer.h       |    1 
 fs/xfs/libxfs/xfs_log_format.h  |    6 +
 fs/xfs/libxfs/xfs_log_recover.h |    2 
 fs/xfs/xfs_extfree_item.c       |  270 +++++++++++++++++++++++++++++++++++----
 fs/xfs/xfs_log_recover.c        |    2 
 fs/xfs/xfs_trace.h              |   11 +-
 9 files changed, 286 insertions(+), 39 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index d33c2fdaf4f2c9..ff4a1dc9f6beb9 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2648,8 +2648,17 @@ xfs_defer_extent_free(
 	ASSERT(!isnullstartblock(bno));
 	ASSERT(!(free_flags & ~XFS_FREE_EXTENT_ALL_FLAGS));
 
-	if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
-		return -EFSCORRUPTED;
+	if (free_flags & XFS_FREE_EXTENT_REALTIME) {
+		if (type != XFS_AG_RESV_NONE) {
+			ASSERT(type == XFS_AG_RESV_NONE);
+			return -EFSCORRUPTED;
+		}
+		if (XFS_IS_CORRUPT(mp, !xfs_verify_rtbext(mp, bno, len)))
+			return -EFSCORRUPTED;
+	} else {
+		if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
+			return -EFSCORRUPTED;
+	}
 
 	xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
 			       GFP_KERNEL | __GFP_NOFAIL);
@@ -2658,6 +2667,8 @@ xfs_defer_extent_free(
 	xefi->xefi_agresv = type;
 	if (free_flags & XFS_FREE_EXTENT_SKIP_DISCARD)
 		xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD;
+	if (free_flags & XFS_FREE_EXTENT_REALTIME)
+		xefi->xefi_flags |= XFS_EFI_REALTIME;
 	if (oinfo) {
 		ASSERT(oinfo->oi_offset == 0);
 
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index efbde04fbbb15f..50ef79a1ed41a1 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -237,7 +237,11 @@ int xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
 /* Don't issue a discard for the blocks freed. */
 #define XFS_FREE_EXTENT_SKIP_DISCARD	(1U << 0)
 
-#define XFS_FREE_EXTENT_ALL_FLAGS	(XFS_FREE_EXTENT_SKIP_DISCARD)
+/* Free blocks on the realtime device. */
+#define XFS_FREE_EXTENT_REALTIME	(1U << 1)
+
+#define XFS_FREE_EXTENT_ALL_FLAGS	(XFS_FREE_EXTENT_SKIP_DISCARD | \
+					 XFS_FREE_EXTENT_REALTIME)
 
 /*
  * List of extents to be free "later".
@@ -257,6 +261,12 @@ struct xfs_extent_free_item {
 #define XFS_EFI_ATTR_FORK	(1U << 1) /* freeing attr fork block */
 #define XFS_EFI_BMBT_BLOCK	(1U << 2) /* freeing bmap btree block */
 #define XFS_EFI_CANCELLED	(1U << 3) /* dont actually free the space */
+#define XFS_EFI_REALTIME	(1U << 4) /* freeing realtime extent */
+
+static inline bool xfs_efi_is_realtime(const struct xfs_extent_free_item *xefi)
+{
+	return xefi->xefi_flags & XFS_EFI_REALTIME;
+}
 
 struct xfs_alloc_autoreap {
 	struct xfs_defer_pending	*dfp;
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 2cd212ad2c1d98..5b377cbbb1f7e0 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -846,6 +846,12 @@ xfs_defer_add(
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 
+	if (!ops->finish_item) {
+		ASSERT(ops->finish_item != NULL);
+		xfs_force_shutdown(tp->t_mountp, SHUTDOWN_CORRUPT_INCORE);
+		return NULL;
+	}
+
 	dfp = xfs_defer_find_last(tp, ops);
 	if (!dfp || !xfs_defer_can_append(dfp, ops))
 		dfp = xfs_defer_alloc(&tp->t_dfops, ops);
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 8b338031e487c4..ec51b8465e61cb 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -71,6 +71,7 @@ extern const struct xfs_defer_op_type xfs_refcount_update_defer_type;
 extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
 extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
 extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
+extern const struct xfs_defer_op_type xfs_rtextent_free_defer_type;
 extern const struct xfs_defer_op_type xfs_attr_defer_type;
 extern const struct xfs_defer_op_type xfs_exchmaps_defer_type;
 
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index ace7384a275bfb..15dec19b6c32ad 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -248,6 +248,8 @@ typedef struct xfs_trans_header {
 #define	XFS_LI_ATTRD		0x1247  /* attr set/remove done */
 #define	XFS_LI_XMI		0x1248  /* mapping exchange intent */
 #define	XFS_LI_XMD		0x1249  /* mapping exchange done */
+#define	XFS_LI_EFI_RT		0x124a	/* realtime extent free intent */
+#define	XFS_LI_EFD_RT		0x124b	/* realtime extent free done */
 
 #define XFS_LI_TYPE_DESC \
 	{ XFS_LI_EFI,		"XFS_LI_EFI" }, \
@@ -267,7 +269,9 @@ typedef struct xfs_trans_header {
 	{ XFS_LI_ATTRI,		"XFS_LI_ATTRI" }, \
 	{ XFS_LI_ATTRD,		"XFS_LI_ATTRD" }, \
 	{ XFS_LI_XMI,		"XFS_LI_XMI" }, \
-	{ XFS_LI_XMD,		"XFS_LI_XMD" }
+	{ XFS_LI_XMD,		"XFS_LI_XMD" }, \
+	{ XFS_LI_EFI_RT,	"XFS_LI_EFI_RT" }, \
+	{ XFS_LI_EFD_RT,	"XFS_LI_EFD_RT" }
 
 /*
  * Inode Log Item Format definitions.
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index 521d327e4c89ed..5397a8ff004df8 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -77,6 +77,8 @@ extern const struct xlog_recover_item_ops xlog_attri_item_ops;
 extern const struct xlog_recover_item_ops xlog_attrd_item_ops;
 extern const struct xlog_recover_item_ops xlog_xmi_item_ops;
 extern const struct xlog_recover_item_ops xlog_xmd_item_ops;
+extern const struct xlog_recover_item_ops xlog_rtefi_item_ops;
+extern const struct xlog_recover_item_ops xlog_rtefd_item_ops;
 
 /*
  * Macros, structures, prototypes for internal log manager use.
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index e469510986e8d0..a25c713ff888c7 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -25,6 +25,10 @@
 #include "xfs_error.h"
 #include "xfs_log_priv.h"
 #include "xfs_log_recover.h"
+#include "xfs_rtalloc.h"
+#include "xfs_inode.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
 
 struct kmem_cache	*xfs_efi_cache;
 struct kmem_cache	*xfs_efd_cache;
@@ -95,16 +99,15 @@ xfs_efi_item_format(
 
 	ASSERT(atomic_read(&efip->efi_next_extent) ==
 				efip->efi_format.efi_nextents);
+	ASSERT(lip->li_type == XFS_LI_EFI || lip->li_type == XFS_LI_EFI_RT);
 
-	efip->efi_format.efi_type = XFS_LI_EFI;
+	efip->efi_format.efi_type = lip->li_type;
 	efip->efi_format.efi_size = 1;
 
-	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFI_FORMAT,
-			&efip->efi_format,
+	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFI_FORMAT, &efip->efi_format,
 			xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents));
 }
 
-
 /*
  * The unpin operation is the last place an EFI is manipulated in the log. It is
  * either inserted in the AIL or aborted in the event of a log I/O error. In
@@ -140,12 +143,14 @@ xfs_efi_item_release(
 STATIC struct xfs_efi_log_item *
 xfs_efi_init(
 	struct xfs_mount	*mp,
+	unsigned short		item_type,
 	uint			nextents)
-
 {
 	struct xfs_efi_log_item	*efip;
 
+	ASSERT(item_type == XFS_LI_EFI || item_type == XFS_LI_EFI_RT);
 	ASSERT(nextents > 0);
+
 	if (nextents > XFS_EFI_MAX_FAST_EXTENTS) {
 		efip = kzalloc(xfs_efi_log_item_sizeof(nextents),
 				GFP_KERNEL | __GFP_NOFAIL);
@@ -154,7 +159,7 @@ xfs_efi_init(
 					 GFP_KERNEL | __GFP_NOFAIL);
 	}
 
-	xfs_log_item_init(mp, &efip->efi_item, XFS_LI_EFI, &xfs_efi_item_ops);
+	xfs_log_item_init(mp, &efip->efi_item, item_type, &xfs_efi_item_ops);
 	efip->efi_format.efi_nextents = nextents;
 	efip->efi_format.efi_id = (uintptr_t)(void *)efip;
 	atomic_set(&efip->efi_next_extent, 0);
@@ -264,12 +269,12 @@ xfs_efd_item_format(
 	struct xfs_log_iovec	*vecp = NULL;
 
 	ASSERT(efdp->efd_next_extent == efdp->efd_format.efd_nextents);
+	ASSERT(lip->li_type == XFS_LI_EFD || lip->li_type == XFS_LI_EFD_RT);
 
-	efdp->efd_format.efd_type = XFS_LI_EFD;
+	efdp->efd_format.efd_type = lip->li_type;
 	efdp->efd_format.efd_size = 1;
 
-	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFD_FORMAT,
-			&efdp->efd_format,
+	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFD_FORMAT, &efdp->efd_format,
 			xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents));
 }
 
@@ -308,6 +313,14 @@ static inline struct xfs_extent_free_item *xefi_entry(const struct list_head *e)
 	return list_entry(e, struct xfs_extent_free_item, xefi_list);
 }
 
+static inline bool
+xfs_efi_item_isrt(const struct xfs_log_item *lip)
+{
+	ASSERT(lip->li_type == XFS_LI_EFI || lip->li_type == XFS_LI_EFI_RT);
+
+	return lip->li_type == XFS_LI_EFI_RT;
+}
+
 /*
  * Fill the EFD with all extents from the EFI when we need to roll the
  * transaction and continue with a new EFI.
@@ -388,18 +401,20 @@ xfs_extent_free_log_item(
 }
 
 static struct xfs_log_item *
-xfs_extent_free_create_intent(
+__xfs_extent_free_create_intent(
 	struct xfs_trans		*tp,
 	struct list_head		*items,
 	unsigned int			count,
-	bool				sort)
+	bool				sort,
+	unsigned short			item_type)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_efi_log_item		*efip = xfs_efi_init(mp, count);
+	struct xfs_efi_log_item		*efip;
 	struct xfs_extent_free_item	*xefi;
 
 	ASSERT(count > 0);
 
+	efip = xfs_efi_init(mp, item_type, count);
 	if (sort)
 		list_sort(mp, items, xfs_extent_free_diff_items);
 	list_for_each_entry(xefi, items, xefi_list)
@@ -407,6 +422,23 @@ xfs_extent_free_create_intent(
 	return &efip->efi_item;
 }
 
+static struct xfs_log_item *
+xfs_extent_free_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	return __xfs_extent_free_create_intent(tp, items, count, sort,
+			XFS_LI_EFI);
+}
+
+static inline unsigned short
+xfs_efd_type_from_efi(const struct xfs_efi_log_item *efip)
+{
+	return xfs_efi_item_isrt(&efip->efi_item) ?  XFS_LI_EFD_RT : XFS_LI_EFD;
+}
+
 /* Get an EFD so we can process all the free extents. */
 static struct xfs_log_item *
 xfs_extent_free_create_done(
@@ -427,8 +459,8 @@ xfs_extent_free_create_done(
 					GFP_KERNEL | __GFP_NOFAIL);
 	}
 
-	xfs_log_item_init(tp->t_mountp, &efdp->efd_item, XFS_LI_EFD,
-			  &xfs_efd_item_ops);
+	xfs_log_item_init(tp->t_mountp, &efdp->efd_item,
+			xfs_efd_type_from_efi(efip), &xfs_efd_item_ops);
 	efdp->efd_efip = efip;
 	efdp->efd_format.efd_nextents = count;
 	efdp->efd_format.efd_efi_id = efip->efi_format.efi_id;
@@ -436,6 +468,17 @@ xfs_extent_free_create_done(
 	return &efdp->efd_item;
 }
 
+static inline const struct xfs_defer_op_type *
+xefi_ops(
+	struct xfs_extent_free_item	*xefi)
+{
+	if (xfs_efi_is_realtime(xefi))
+		return &xfs_rtextent_free_defer_type;
+	if (xefi->xefi_agresv == XFS_AG_RESV_AGFL)
+		return &xfs_agfl_free_defer_type;
+	return &xfs_extent_free_defer_type;
+}
+
 /* Add this deferred EFI to the transaction. */
 void
 xfs_extent_free_defer_add(
@@ -445,16 +488,11 @@ xfs_extent_free_defer_add(
 {
 	struct xfs_mount		*mp = tp->t_mountp;
 
-	trace_xfs_extent_free_defer(mp, xefi);
-
 	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);
-	else
-		*dfpp = xfs_defer_add(tp, &xefi->xefi_list,
-				&xfs_extent_free_defer_type);
+			xfs_efi_is_realtime(xefi) ? XG_TYPE_RTG : XG_TYPE_AG);
+
+	trace_xfs_extent_free_defer(mp, xefi);
+	*dfpp = xfs_defer_add(tp, &xefi->xefi_list, xefi_ops(xefi));
 }
 
 /* Cancel a free extent. */
@@ -560,8 +598,12 @@ xfs_agfl_free_finish_item(
 static inline bool
 xfs_efi_validate_ext(
 	struct xfs_mount		*mp,
+	bool				isrt,
 	struct xfs_extent		*extp)
 {
+	if (isrt)
+		return xfs_verify_rtbext(mp, extp->ext_start, extp->ext_len);
+
 	return xfs_verify_fsbext(mp, extp->ext_start, extp->ext_len);
 }
 
@@ -569,6 +611,7 @@ static inline void
 xfs_efi_recover_work(
 	struct xfs_mount		*mp,
 	struct xfs_defer_pending	*dfp,
+	bool				isrt,
 	struct xfs_extent		*extp)
 {
 	struct xfs_extent_free_item	*xefi;
@@ -580,7 +623,9 @@ xfs_efi_recover_work(
 	xefi->xefi_agresv = XFS_AG_RESV_NONE;
 	xefi->xefi_owner = XFS_RMAP_OWN_UNKNOWN;
 	xefi->xefi_group = xfs_group_intent_get(mp, extp->ext_start,
-			XG_TYPE_AG);
+			isrt ? XG_TYPE_RTG : XG_TYPE_AG);
+	if (isrt)
+		xefi->xefi_flags |= XFS_EFI_REALTIME;
 
 	xfs_defer_add_item(dfp, &xefi->xefi_list);
 }
@@ -601,14 +646,15 @@ xfs_extent_free_recover_work(
 	struct xfs_trans		*tp;
 	int				i;
 	int				error = 0;
+	bool				isrt = xfs_efi_item_isrt(lip);
 
 	/*
-	 * First check the validity of the extents described by the
-	 * EFI.  If any are bad, then assume that all are bad and
-	 * just toss the EFI.
+	 * First check the validity of the extents described by the EFI.  If
+	 * any are bad, then assume that all are bad and just toss the EFI.
+	 * Mixing RT and non-RT extents in the same EFI item is not allowed.
 	 */
 	for (i = 0; i < efip->efi_format.efi_nextents; i++) {
-		if (!xfs_efi_validate_ext(mp,
+		if (!xfs_efi_validate_ext(mp, isrt,
 					&efip->efi_format.efi_extents[i])) {
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 					&efip->efi_format,
@@ -616,7 +662,8 @@ xfs_extent_free_recover_work(
 			return -EFSCORRUPTED;
 		}
 
-		xfs_efi_recover_work(mp, dfp, &efip->efi_format.efi_extents[i]);
+		xfs_efi_recover_work(mp, dfp, isrt,
+				&efip->efi_format.efi_extents[i]);
 	}
 
 	resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
@@ -654,10 +701,12 @@ xfs_extent_free_relog_intent(
 	count = EFI_ITEM(intent)->efi_format.efi_nextents;
 	extp = EFI_ITEM(intent)->efi_format.efi_extents;
 
+	ASSERT(intent->li_type == XFS_LI_EFI || intent->li_type == XFS_LI_EFI_RT);
+
 	efdp->efd_next_extent = count;
 	memcpy(efdp->efd_format.efd_extents, extp, count * sizeof(*extp));
 
-	efip = xfs_efi_init(tp->t_mountp, count);
+	efip = xfs_efi_init(tp->t_mountp, intent->li_type, count);
 	memcpy(efip->efi_format.efi_extents, extp, count * sizeof(*extp));
 	atomic_set(&efip->efi_next_extent, count);
 
@@ -689,6 +738,72 @@ const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
 	.relog_intent	= xfs_extent_free_relog_intent,
 };
 
+#ifdef CONFIG_XFS_RT
+/* Create a realtime extent freeing */
+static struct xfs_log_item *
+xfs_rtextent_free_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	return __xfs_extent_free_create_intent(tp, items, count, sort,
+			XFS_LI_EFI_RT);
+}
+
+/* Process a free realtime extent. */
+STATIC int
+xfs_rtextent_free_finish_item(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*done,
+	struct list_head		*item,
+	struct xfs_btree_cur		**state)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_extent_free_item	*xefi = xefi_entry(item);
+	struct xfs_efd_log_item		*efdp = EFD_ITEM(done);
+	struct xfs_rtgroup		**rtgp = (struct xfs_rtgroup **)state;
+	int				error = 0;
+
+	trace_xfs_extent_free_deferred(mp, xefi);
+
+	if (!(xefi->xefi_flags & XFS_EFI_CANCELLED)) {
+		if (*rtgp != to_rtg(xefi->xefi_group)) {
+			*rtgp = to_rtg(xefi->xefi_group);
+			xfs_rtgroup_lock(*rtgp, XFS_RTGLOCK_BITMAP);
+			xfs_rtgroup_trans_join(tp, *rtgp,
+					XFS_RTGLOCK_BITMAP);
+		}
+		error = xfs_rtfree_blocks(tp, *rtgp,
+				xefi->xefi_startblock, xefi->xefi_blockcount);
+	}
+	if (error == -EAGAIN) {
+		xfs_efd_from_efi(efdp);
+		return error;
+	}
+
+	xfs_efd_add_extent(efdp, xefi);
+	xfs_extent_free_cancel_item(item);
+	return error;
+}
+
+const struct xfs_defer_op_type xfs_rtextent_free_defer_type = {
+	.name		= "rtextent_free",
+	.max_items	= XFS_EFI_MAX_FAST_EXTENTS,
+	.create_intent	= xfs_rtextent_free_create_intent,
+	.abort_intent	= xfs_extent_free_abort_intent,
+	.create_done	= xfs_extent_free_create_done,
+	.finish_item	= xfs_rtextent_free_finish_item,
+	.cancel_item	= xfs_extent_free_cancel_item,
+	.recover_work	= xfs_extent_free_recover_work,
+	.relog_intent	= xfs_extent_free_relog_intent,
+};
+#else
+const struct xfs_defer_op_type xfs_rtextent_free_defer_type = {
+	.name		= "rtextent_free",
+};
+#endif /* CONFIG_XFS_RT */
+
 STATIC bool
 xfs_efi_item_match(
 	struct xfs_log_item	*lip,
@@ -733,7 +848,7 @@ xlog_recover_efi_commit_pass2(
 		return -EFSCORRUPTED;
 	}
 
-	efip = xfs_efi_init(mp, efi_formatp->efi_nextents);
+	efip = xfs_efi_init(mp, ITEM_TYPE(item), efi_formatp->efi_nextents);
 	error = xfs_efi_copy_format(&item->ri_buf[0], &efip->efi_format);
 	if (error) {
 		xfs_efi_item_free(efip);
@@ -751,6 +866,58 @@ const struct xlog_recover_item_ops xlog_efi_item_ops = {
 	.commit_pass2		= xlog_recover_efi_commit_pass2,
 };
 
+#ifdef CONFIG_XFS_RT
+STATIC int
+xlog_recover_rtefi_commit_pass2(
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
+{
+	struct xfs_mount		*mp = log->l_mp;
+	struct xfs_efi_log_item		*efip;
+	struct xfs_efi_log_format	*efi_formatp;
+	int				error;
+
+	efi_formatp = item->ri_buf[0].i_addr;
+
+	if (item->ri_buf[0].i_len < xfs_efi_log_format_sizeof(0)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
+	efip = xfs_efi_init(mp, ITEM_TYPE(item), efi_formatp->efi_nextents);
+	error = xfs_efi_copy_format(&item->ri_buf[0], &efip->efi_format);
+	if (error) {
+		xfs_efi_item_free(efip);
+		return error;
+	}
+	atomic_set(&efip->efi_next_extent, efi_formatp->efi_nextents);
+
+	xlog_recover_intent_item(log, &efip->efi_item, lsn,
+			&xfs_rtextent_free_defer_type);
+	return 0;
+}
+#else
+STATIC int
+xlog_recover_rtefi_commit_pass2(
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
+{
+	XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+			item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+	return -EFSCORRUPTED;
+}
+#endif
+
+const struct xlog_recover_item_ops xlog_rtefi_item_ops = {
+	.item_type		= XFS_LI_EFI_RT,
+	.commit_pass2		= xlog_recover_rtefi_commit_pass2,
+};
+
 /*
  * This routine is called when an EFD format structure is found in a committed
  * transaction in the log. Its purpose is to cancel the corresponding EFI if it
@@ -793,3 +960,44 @@ const struct xlog_recover_item_ops xlog_efd_item_ops = {
 	.item_type		= XFS_LI_EFD,
 	.commit_pass2		= xlog_recover_efd_commit_pass2,
 };
+
+#ifdef CONFIG_XFS_RT
+STATIC int
+xlog_recover_rtefd_commit_pass2(
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
+{
+	struct xfs_efd_log_format	*efd_formatp;
+	int				buflen = item->ri_buf[0].i_len;
+
+	efd_formatp = item->ri_buf[0].i_addr;
+
+	if (buflen < sizeof(struct xfs_efd_log_format)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				efd_formatp, buflen);
+		return -EFSCORRUPTED;
+	}
+
+	if (item->ri_buf[0].i_len != xfs_efd_log_format32_sizeof(
+						efd_formatp->efd_nextents) &&
+	    item->ri_buf[0].i_len != xfs_efd_log_format64_sizeof(
+						efd_formatp->efd_nextents)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				efd_formatp, buflen);
+		return -EFSCORRUPTED;
+	}
+
+	xlog_recover_release_intent(log, XFS_LI_EFI_RT,
+			efd_formatp->efd_efi_id);
+	return 0;
+}
+#else
+# define xlog_recover_rtefd_commit_pass2	xlog_recover_rtefi_commit_pass2
+#endif
+
+const struct xlog_recover_item_ops xlog_rtefd_item_ops = {
+	.item_type		= XFS_LI_EFD_RT,
+	.commit_pass2		= xlog_recover_rtefd_commit_pass2,
+};
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 55e412a821483e..0af3d477197b24 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1818,6 +1818,8 @@ static const struct xlog_recover_item_ops *xlog_recover_item_ops[] = {
 	&xlog_attrd_item_ops,
 	&xlog_xmi_item_ops,
 	&xlog_xmd_item_ops,
+	&xlog_rtefi_item_ops,
+	&xlog_rtefd_item_ops,
 };
 
 static const struct xlog_recover_item_ops *
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index a9392eaaf6f581..b07790d74d351f 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2761,6 +2761,7 @@ DECLARE_EVENT_CLASS(xfs_free_extent_deferred_class,
 	TP_ARGS(mp, free),
 	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)
@@ -2768,13 +2769,16 @@ DECLARE_EVENT_CLASS(xfs_free_extent_deferred_class,
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock);
-		__entry->agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock);
+		__entry->type = free->xefi_group->xg_type;
+		__entry->agno = free->xefi_group->xg_gno;
+		__entry->agbno = xfs_fsb_to_gbno(mp, free->xefi_startblock,
+						free->xefi_group->xg_type);
 		__entry->len = free->xefi_blockcount;
 		__entry->flags = free->xefi_flags;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x flags 0x%x",
+	TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x flags 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
 		  __entry->agbno,
 		  __entry->len,
@@ -2784,7 +2788,6 @@ DECLARE_EVENT_CLASS(xfs_free_extent_deferred_class,
 DEFINE_EVENT(xfs_free_extent_deferred_class, name, \
 	TP_PROTO(struct xfs_mount *mp, struct xfs_extent_free_item *free), \
 	TP_ARGS(mp, free))
-DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_agfl_free_defer);
 DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_agfl_free_deferred);
 DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_extent_free_defer);
 DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_extent_free_deferred);

[PATCH 18/34] xfs: support error injection when freeing rt extents

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

A handful of fstests expect to be able to test what happens when extent
free intents fail to actually free the extent.  Now that we're
supporting EFIs for realtime extents, add to xfs_rtfree_extent the same
injection point that exists in the regular extent freeing code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_rtbitmap.c |    4 ++++
 1 file changed, 4 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index cae0b22397d007..c73826aa4425af 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -21,6 +21,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_health.h"
 #include "xfs_sb.h"
+#include "xfs_errortag.h"
 #include "xfs_log.h"
 #include "xfs_buf_item.h"
 
@@ -1065,6 +1066,9 @@ xfs_rtfree_extent(
 	ASSERT(rbmip->i_itemp != NULL);
 	xfs_assert_ilocked(rbmip, XFS_ILOCK_EXCL);
 
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_FREE_EXTENT))
+		return -EIO;
+
 	error = xfs_rtcheck_alloc_range(&args, start, len);
 	if (error)
 		return error;

[PATCH 19/34] xfs: use realtime EFI to free extents when rtgroups are enabled

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When rmap is enabled, XFS expects a certain order of operations, which
is: 1) remove the file mapping, 2) remove the reverse mapping, and then
3) free the blocks.  When reflink is enabled, XFS replaces (3) with a
deferred refcount decrement operation that can schedule freeing the
blocks if that was the last refcount.

For realtime files, xfs_bmap_del_extent_real tries to do 1 and 3 in the
same transaction, which will break both rmap and reflink unless we
switch it to use realtime EFIs.  Both rmap and reflink depend on the
rtgroups feature, so let's turn on EFIs for all rtgroups filesystems.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_bmap.c |   17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 482b4c0cd6b193..b15a43c18b0a57 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5383,9 +5383,11 @@ xfs_bmap_del_extent_real(
 	 * If we need to, add to list of extents to delete.
 	 */
 	if (!(bflags & XFS_BMAPI_REMAP)) {
+		bool	isrt = xfs_ifork_is_realtime(ip, whichfork);
+
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
 			xfs_refcount_decrease_extent(tp, del);
-		} else if (xfs_ifork_is_realtime(ip, whichfork)) {
+		} else if (isrt && !xfs_has_rtgroups(mp)) {
 			error = xfs_bmap_free_rtblocks(tp, del);
 		} else {
 			unsigned int	efi_flags = 0;
@@ -5394,6 +5396,19 @@ xfs_bmap_del_extent_real(
 			    del->br_state == XFS_EXT_UNWRITTEN)
 				efi_flags |= XFS_FREE_EXTENT_SKIP_DISCARD;
 
+			/*
+			 * Historically, we did not use EFIs to free realtime
+			 * extents.  However, when reverse mapping is enabled,
+			 * we must maintain the same order of operations as the
+			 * data device, which is: Remove the file mapping,
+			 * remove the reverse mapping, and then free the
+			 * blocks.  Reflink for realtime volumes requires the
+			 * same sort of ordering.  Both features rely on
+			 * rtgroups, so let's gate rt EFI usage on rtgroups.
+			 */
+			if (isrt)
+				efi_flags |= XFS_FREE_EXTENT_REALTIME;
+
 			error = xfs_free_extent_later(tp, del->br_startblock,
 					del->br_blockcount, NULL,
 					XFS_AG_RESV_NONE, efi_flags);

[PATCH 20/34] xfs: don't merge ioends across RTGs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Unlike AGs, RTGs don't always have metadata in their first blocks, and
thus we don't get automatic protection from merging I/O completions
across RTG boundaries.  Add code to set the IOMAP_F_BOUNDARY flag for
ioends that start at the first block of a RTG so that they never get
merged into the previous ioend.

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_rtgroup.h |    9 +++++++++
 fs/xfs/xfs_iomap.c          |   13 ++++++++++++-
 2 files changed, 21 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 026f34f984b32f..2ddfac9a0182f9 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -188,6 +188,15 @@ xfs_rtb_to_rgbno(
 	return __xfs_rtb_to_rgbno(mp, rtbno);
 }
 
+/* Is rtbno the start of a RT group? */
+static inline bool
+xfs_rtbno_is_group_start(
+	struct xfs_mount	*mp,
+	xfs_rtblock_t		rtbno)
+{
+	return (rtbno & mp->m_rgblkmask) == 0;
+}
+
 static inline xfs_daddr_t
 xfs_rtb_to_daddr(
 	struct xfs_mount	*mp,
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index e810e901cd3576..17e5c273e28c45 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -24,6 +24,7 @@
 #include "xfs_iomap.h"
 #include "xfs_trace.h"
 #include "xfs_quota.h"
+#include "xfs_rtgroup.h"
 #include "xfs_dquot_item.h"
 #include "xfs_dquot.h"
 #include "xfs_reflink.h"
@@ -115,7 +116,9 @@ xfs_bmbt_to_iomap(
 		iomap->addr = IOMAP_NULL_ADDR;
 		iomap->type = IOMAP_DELALLOC;
 	} else {
-		iomap->addr = BBTOB(xfs_fsb_to_db(ip, imap->br_startblock));
+		xfs_daddr_t	daddr = xfs_fsb_to_db(ip, imap->br_startblock);
+
+		iomap->addr = BBTOB(daddr);
 		if (mapping_flags & IOMAP_DAX)
 			iomap->addr += target->bt_dax_part_off;
 
@@ -124,6 +127,14 @@ xfs_bmbt_to_iomap(
 		else
 			iomap->type = IOMAP_MAPPED;
 
+		/*
+		 * Mark iomaps starting at the first sector of a RTG as merge
+		 * boundary so that each I/O completions is contained to a
+		 * single RTG.
+		 */
+		if (XFS_IS_REALTIME_INODE(ip) && xfs_has_rtgroups(mp) &&
+		    xfs_rtbno_is_group_start(mp, imap->br_startblock))
+			iomap->flags |= IOMAP_F_BOUNDARY;
 	}
 	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
 	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);

[PATCH 21/34] xfs: make the RT allocator rtgroup aware

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Make the allocator rtgroup aware by either picking a specific group if
there is a hint, or loop over all groups otherwise.  A simple rotor is
provided to pick the placement for initial allocations.

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_bmap.c     |   13 +++++-
 fs/xfs/libxfs/xfs_rtbitmap.c |    6 ++-
 fs/xfs/xfs_mount.h           |    1 
 fs/xfs/xfs_rtalloc.c         |   98 ++++++++++++++++++++++++++++++++++++++----
 4 files changed, 105 insertions(+), 13 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index b15a43c18b0a57..3498d7b4fbc54e 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3151,8 +3151,17 @@ xfs_bmap_adjacent_valid(
 	struct xfs_mount	*mp = ap->ip->i_mount;
 
 	if (XFS_IS_REALTIME_INODE(ap->ip) &&
-	    (ap->datatype & XFS_ALLOC_USERDATA))
-		return x < mp->m_sb.sb_rblocks;
+	    (ap->datatype & XFS_ALLOC_USERDATA)) {
+		if (x >= mp->m_sb.sb_rblocks)
+			return false;
+		if (!xfs_has_rtgroups(mp))
+			return true;
+
+		return xfs_rtb_to_rgno(mp, x) == xfs_rtb_to_rgno(mp, y) &&
+			xfs_rtb_to_rgno(mp, x) < mp->m_sb.sb_rgcount &&
+			xfs_rtb_to_rtx(mp, x) < mp->m_sb.sb_rgextents;
+
+	}
 
 	return XFS_FSB_TO_AGNO(mp, x) == XFS_FSB_TO_AGNO(mp, y) &&
 		XFS_FSB_TO_AGNO(mp, x) < mp->m_sb.sb_agcount &&
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index c73826aa4425af..5abfd84852ce3b 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1084,11 +1084,13 @@ xfs_rtfree_extent(
 	 * Mark more blocks free in the superblock.
 	 */
 	xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, (long)len);
+
 	/*
 	 * If we've now freed all the blocks, reset the file sequence
-	 * number to 0.
+	 * number to 0 for pre-RTG file systems.
 	 */
-	if (tp->t_frextents_delta + mp->m_sb.sb_frextents ==
+	if (!xfs_has_rtgroups(mp) &&
+	    tp->t_frextents_delta + mp->m_sb.sb_frextents ==
 	    mp->m_sb.sb_rextents) {
 		if (!(rbmip->i_diflags & XFS_DIFLAG_NEWRTBM))
 			rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 1f228047639587..62c251b3a385d4 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -255,6 +255,7 @@ typedef struct xfs_mount {
 #endif
 	xfs_agnumber_t		m_agfrotor;	/* last ag where space found */
 	atomic_t		m_agirotor;	/* last ag dir inode alloced */
+	atomic_t		m_rtgrotor;	/* last rtgroup rtpicked */
 
 	/* Memory shrinker to throttle and reprioritize inodegc */
 	struct shrinker		*m_inodegc_shrinker;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 1f53d5e07a91a0..b27d23bcc06418 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1662,8 +1662,9 @@ xfs_rtalloc_align_minmax(
 }
 
 static int
-xfs_rtallocate(
+xfs_rtallocate_rtg(
 	struct xfs_trans	*tp,
+	xfs_rgnumber_t		rgno,
 	xfs_rtblock_t		bno_hint,
 	xfs_rtxlen_t		minlen,
 	xfs_rtxlen_t		maxlen,
@@ -1683,16 +1684,33 @@ xfs_rtallocate(
 	xfs_rtxlen_t		len = 0;
 	int			error = 0;
 
-	args.rtg = xfs_rtgroup_grab(args.mp, 0);
+	args.rtg = xfs_rtgroup_grab(args.mp, rgno);
 	if (!args.rtg)
 		return -ENOSPC;
 
 	/*
-	 * Lock out modifications to both the RT bitmap and summary inodes.
+	 * We need to lock out modifications to both the RT bitmap and summary
+	 * inodes for finding free space in xfs_rtallocate_extent_{near,size}
+	 * and join the bitmap and summary inodes for the actual allocation
+	 * down in xfs_rtallocate_range.
+	 *
+	 * For RTG-enabled file system we don't want to join the inodes to the
+	 * transaction until we are committed to allocate to allocate from this
+	 * RTG so that only one inode of each type is locked at a time.
+	 *
+	 * But for pre-RTG file systems we need to already to join the bitmap
+	 * inode to the transaction for xfs_rtpick_extent, which bumps the
+	 * sequence number in it, so we'll have to join the inode to the
+	 * transaction early here.
+	 *
+	 * This is all a bit messy, but at least the mess is contained in
+	 * this function.
 	 */
 	if (!*rtlocked) {
 		xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP);
-		xfs_rtgroup_trans_join(tp, args.rtg, XFS_RTGLOCK_BITMAP);
+		if (!xfs_has_rtgroups(args.mp))
+			xfs_rtgroup_trans_join(tp, args.rtg,
+					XFS_RTGLOCK_BITMAP);
 		*rtlocked = true;
 	}
 
@@ -1702,7 +1720,7 @@ xfs_rtallocate(
 	 */
 	if (bno_hint)
 		start = xfs_rtb_to_rtx(args.mp, bno_hint);
-	else if (initial_user_data)
+	else if (!xfs_has_rtgroups(args.mp) && initial_user_data)
 		start = xfs_rtpick_extent(args.rtg, tp, maxlen);
 
 	if (start) {
@@ -1723,8 +1741,16 @@ xfs_rtallocate(
 				prod, &rtx);
 	}
 
-	if (error)
+	if (error) {
+		if (xfs_has_rtgroups(args.mp)) {
+			xfs_rtgroup_unlock(args.rtg, XFS_RTGLOCK_BITMAP);
+			*rtlocked = false;
+		}
 		goto out_release;
+	}
+
+	if (xfs_has_rtgroups(args.mp))
+		xfs_rtgroup_trans_join(tp, args.rtg, XFS_RTGLOCK_BITMAP);
 
 	error = xfs_rtallocate_range(&args, rtx, len);
 	if (error)
@@ -1742,6 +1768,53 @@ xfs_rtallocate(
 	return error;
 }
 
+static int
+xfs_rtallocate_rtgs(
+	struct xfs_trans	*tp,
+	xfs_fsblock_t		bno_hint,
+	xfs_rtxlen_t		minlen,
+	xfs_rtxlen_t		maxlen,
+	xfs_rtxlen_t		prod,
+	bool			wasdel,
+	bool			initial_user_data,
+	xfs_rtblock_t		*bno,
+	xfs_extlen_t		*blen)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	xfs_rgnumber_t		start_rgno, rgno;
+	int			error;
+
+	/*
+	 * For now this just blindly iterates over the RTGs for an initial
+	 * allocation.  We could try to keep an in-memory rtg_longest member
+	 * to avoid the locking when just looking for big enough free space,
+	 * but for now this keeps things simple.
+	 */
+	if (bno_hint != NULLFSBLOCK)
+		start_rgno = xfs_rtb_to_rgno(mp, bno_hint);
+	else
+		start_rgno = (atomic_inc_return(&mp->m_rtgrotor) - 1) %
+				mp->m_sb.sb_rgcount;
+
+	rgno = start_rgno;
+	do {
+		bool		rtlocked = false;
+
+		error = xfs_rtallocate_rtg(tp, rgno, bno_hint, minlen, maxlen,
+				prod, wasdel, initial_user_data, &rtlocked,
+				bno, blen);
+		if (error != -ENOSPC)
+			return error;
+		ASSERT(!rtlocked);
+
+		if (++rgno == mp->m_sb.sb_rgcount)
+			rgno = 0;
+		bno_hint = NULLFSBLOCK;
+	} while (rgno != start_rgno);
+
+	return -ENOSPC;
+}
+
 static int
 xfs_rtallocate_align(
 	struct xfs_bmalloca	*ap,
@@ -1836,9 +1909,16 @@ xfs_bmap_rtalloc(
 	if (xfs_bmap_adjacent(ap))
 		bno_hint = ap->blkno;
 
-	error = xfs_rtallocate(ap->tp, bno_hint, raminlen, ralen, prod,
-			ap->wasdel, initial_user_data, &rtlocked,
-			&ap->blkno, &ap->length);
+	if (xfs_has_rtgroups(ap->ip->i_mount)) {
+		error = xfs_rtallocate_rtgs(ap->tp, bno_hint, raminlen, ralen,
+				prod, ap->wasdel, initial_user_data,
+				&ap->blkno, &ap->length);
+	} else {
+		error = xfs_rtallocate_rtg(ap->tp, 0, bno_hint, raminlen, ralen,
+				prod, ap->wasdel, initial_user_data,
+				&rtlocked, &ap->blkno, &ap->length);
+	}
+
 	if (error == -ENOSPC) {
 		if (!noalign) {
 			/*

[PATCH 22/34] xfs: don't coalesce file mappings that cross rtgroup boundaries in scrub

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The bmbt scrubber will combine file mappings if they are mergeable to
reduce the number of cross-referencing checks.  However, we shouldn't
combine mappings that cross rt group boundaries because that will cause
verifiers to trip incorrectly.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/bmap.c |   16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 008630b2b75263..7e00312225ed10 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -834,9 +834,12 @@ xchk_bmap_iext_mapping(
 /* Are these two mappings contiguous with each other? */
 static inline bool
 xchk_are_bmaps_contiguous(
+	const struct xchk_bmap_info	*info,
 	const struct xfs_bmbt_irec	*b1,
 	const struct xfs_bmbt_irec	*b2)
 {
+	struct xfs_mount		*mp = info->sc->mp;
+
 	/* Don't try to combine unallocated mappings. */
 	if (!xfs_bmap_is_real_extent(b1))
 		return false;
@@ -850,6 +853,17 @@ xchk_are_bmaps_contiguous(
 		return false;
 	if (b1->br_state != b2->br_state)
 		return false;
+
+	/*
+	 * Don't combine bmaps that would cross rtgroup boundaries.  This is a
+	 * valid state, but if combined they will fail rtb extent checks.
+	 */
+	if (info->is_rt && xfs_has_rtgroups(mp)) {
+		if (xfs_rtb_to_rgno(mp, b1->br_startblock) !=
+		    xfs_rtb_to_rgno(mp, b2->br_startblock))
+			return false;
+	}
+
 	return true;
 }
 
@@ -887,7 +901,7 @@ xchk_bmap_iext_iter(
 	 * that we just read, if possible.
 	 */
 	while (xfs_iext_peek_next_extent(ifp, &info->icur, &got)) {
-		if (!xchk_are_bmaps_contiguous(irec, &got))
+		if (!xchk_are_bmaps_contiguous(info, irec, &got))
 			break;
 
 		if (!xchk_bmap_iext_mapping(info, &got)) {

[PATCH 23/34] xfs: scrub the realtime group superblock

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Enable scrubbing of realtime group superblocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/Makefile        |    1 +
 fs/xfs/libxfs/xfs_fs.h |    3 +-
 fs/xfs/scrub/common.h  |    2 +
 fs/xfs/scrub/health.c  |    1 +
 fs/xfs/scrub/rgsuper.c |   68 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/scrub.c   |    7 +++++
 fs/xfs/scrub/scrub.h   |    2 +
 fs/xfs/scrub/stats.c   |    1 +
 fs/xfs/scrub/trace.h   |    4 ++-
 9 files changed, 87 insertions(+), 2 deletions(-)
 create mode 100644 fs/xfs/scrub/rgsuper.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 6814debac29929..ed9b0dabc1f11d 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -191,6 +191,7 @@ xfs-y				+= $(addprefix scrub/, \
 xfs-$(CONFIG_XFS_ONLINE_SCRUB_STATS) += scrub/stats.o
 
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
+				   rgsuper.o \
 				   rtbitmap.o \
 				   rtsummary.o \
 				   )
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 4c0682173d6144..50de6ad88dbe45 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -736,9 +736,10 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_HEALTHY	27	/* everything checked out ok */
 #define XFS_SCRUB_TYPE_DIRTREE	28	/* directory tree structure */
 #define XFS_SCRUB_TYPE_METAPATH	29	/* metadata directory tree paths */
+#define XFS_SCRUB_TYPE_RGSUPER	30	/* realtime superblock */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	30
+#define XFS_SCRUB_TYPE_NR	31
 
 /*
  * This special type code only applies to the vectored scrub implementation.
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 672ed48d4a9fc3..9ff3cafd867962 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -79,9 +79,11 @@ int xchk_setup_metapath(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
 int xchk_setup_rtbitmap(struct xfs_scrub *sc);
 int xchk_setup_rtsummary(struct xfs_scrub *sc);
+int xchk_setup_rgsuperblock(struct xfs_scrub *sc);
 #else
 # define xchk_setup_rtbitmap		xchk_setup_nothing
 # define xchk_setup_rtsummary		xchk_setup_nothing
+# define xchk_setup_rgsuperblock	xchk_setup_nothing
 #endif
 #ifdef CONFIG_XFS_QUOTA
 int xchk_ino_dqattach(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 7547fb5bcd7272..ce86bdad37fa42 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -111,6 +111,7 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_NLINKS]		= { XHG_FS,  XFS_SICK_FS_NLINKS },
 	[XFS_SCRUB_TYPE_DIRTREE]	= { XHG_INO, XFS_SICK_INO_DIRTREE },
 	[XFS_SCRUB_TYPE_METAPATH]	= { XHG_FS,  XFS_SICK_FS_METAPATH },
+	[XFS_SCRUB_TYPE_RGSUPER]	= { XHG_RTGROUP, XFS_SICK_RG_SUPER },
 };
 
 /* Return the health status mask for this scrub type. */
diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c
new file mode 100644
index 00000000000000..00dfe043dfea7f
--- /dev/null
+++ b/fs/xfs/scrub/rgsuper.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_rtgroup.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+
+/* Set us up with a transaction and an empty context. */
+int
+xchk_setup_rgsuperblock(
+	struct xfs_scrub	*sc)
+{
+	return xchk_trans_alloc(sc, 0);
+}
+
+/* Cross-reference with the other rt metadata. */
+STATIC void
+xchk_rgsuperblock_xref(
+	struct xfs_scrub	*sc)
+{
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return;
+
+	xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), 1);
+}
+
+int
+xchk_rgsuperblock(
+	struct xfs_scrub	*sc)
+{
+	xfs_rgnumber_t		rgno = sc->sm->sm_agno;
+	int			error;
+
+	/*
+	 * Only rtgroup 0 has a superblock.  We may someday want to use higher
+	 * rgno for other functions, similar to what we do with the primary
+	 * super scrub function.
+	 */
+	if (rgno != 0)
+		return -ENOENT;
+
+	/*
+	 * Grab an active reference to the rtgroup structure.  If we can't get
+	 * it, we're racing with something that's tearing down the group, so
+	 * signal that the group no longer exists.  Take the rtbitmap in shared
+	 * mode so that the group can't change while we're doing things.
+	 */
+	error = xchk_rtgroup_init_existing(sc, rgno, &sc->sr);
+	if (!xchk_xref_process_error(sc, 0, 0, &error))
+		return error;
+
+	xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP_SHARED);
+
+	/*
+	 * Since we already validated the rt superblock at mount time, we don't
+	 * need to check its contents again.  All we need is to cross-reference.
+	 */
+	xchk_rgsuperblock_xref(sc);
+	return 0;
+}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 8cd7e36c09990e..ceb22c722d8f52 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -451,6 +451,13 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.has	= xfs_has_metadir,
 		.repair	= xrep_metapath,
 	},
+	[XFS_SCRUB_TYPE_RGSUPER] = {	/* realtime group superblock */
+		.type	= ST_RTGROUP,
+		.setup	= xchk_setup_rgsuperblock,
+		.scrub	= xchk_rgsuperblock,
+		.has	= xfs_has_rtsb,
+		.repair = xrep_notsupported,
+	},
 };
 
 static int
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index f73c6d0d90a11a..a7fda3e2b01377 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -273,9 +273,11 @@ int xchk_metapath(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
 int xchk_rtbitmap(struct xfs_scrub *sc);
 int xchk_rtsummary(struct xfs_scrub *sc);
+int xchk_rgsuperblock(struct xfs_scrub *sc);
 #else
 # define xchk_rtbitmap		xchk_nothing
 # define xchk_rtsummary		xchk_nothing
+# define xchk_rgsuperblock	xchk_nothing
 #endif
 #ifdef CONFIG_XFS_QUOTA
 int xchk_quota(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c
index edcd02dc2e62c0..a476c7b2ab7597 100644
--- a/fs/xfs/scrub/stats.c
+++ b/fs/xfs/scrub/stats.c
@@ -81,6 +81,7 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_NLINKS]		= "nlinks",
 	[XFS_SCRUB_TYPE_DIRTREE]	= "dirtree",
 	[XFS_SCRUB_TYPE_METAPATH]	= "metapath",
+	[XFS_SCRUB_TYPE_RGSUPER]	= "rgsuper",
 };
 
 /* Format the scrub stats into a text buffer, similar to pcp style. */
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index b6c8d0944fa453..9b38f5ad1eaf07 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -71,6 +71,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_HEALTHY);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_DIRTREE);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_BARRIER);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_METAPATH);
+TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RGSUPER);
 
 #define XFS_SCRUB_TYPE_STRINGS \
 	{ XFS_SCRUB_TYPE_PROBE,		"probe" }, \
@@ -103,7 +104,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_METAPATH);
 	{ XFS_SCRUB_TYPE_HEALTHY,	"healthy" }, \
 	{ XFS_SCRUB_TYPE_DIRTREE,	"dirtree" }, \
 	{ XFS_SCRUB_TYPE_BARRIER,	"barrier" }, \
-	{ XFS_SCRUB_TYPE_METAPATH,	"metapath" }
+	{ XFS_SCRUB_TYPE_METAPATH,	"metapath" }, \
+	{ XFS_SCRUB_TYPE_RGSUPER,	"rgsuper" }
 
 #define XFS_SCRUB_FLAG_STRINGS \
 	{ XFS_SCRUB_IFLAG_REPAIR,		"repair" }, \

[PATCH 24/34] xfs: repair realtime group superblock

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Repair the realtime superblock if it has become out of date with the
primary superblock.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/repair.h  |    3 +++
 fs/xfs/scrub/rgsuper.c |   16 ++++++++++++++++
 fs/xfs/scrub/scrub.c   |    2 +-
 3 files changed, 20 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 4052185743910d..b649da1a93eb8c 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -146,9 +146,11 @@ int xrep_metapath(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
 int xrep_rtbitmap(struct xfs_scrub *sc);
 int xrep_rtsummary(struct xfs_scrub *sc);
+int xrep_rgsuperblock(struct xfs_scrub *sc);
 #else
 # define xrep_rtbitmap			xrep_notsupported
 # define xrep_rtsummary			xrep_notsupported
+# define xrep_rgsuperblock		xrep_notsupported
 #endif /* CONFIG_XFS_RT */
 
 #ifdef CONFIG_XFS_QUOTA
@@ -253,6 +255,7 @@ static inline int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *x)
 #define xrep_symlink			xrep_notsupported
 #define xrep_dirtree			xrep_notsupported
 #define xrep_metapath			xrep_notsupported
+#define xrep_rgsuperblock		xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c
index 00dfe043dfea7f..463b3573bb761b 100644
--- a/fs/xfs/scrub/rgsuper.c
+++ b/fs/xfs/scrub/rgsuper.c
@@ -10,8 +10,12 @@
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
 #include "xfs_rtgroup.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
+#include "scrub/repair.h"
 
 /* Set us up with a transaction and an empty context. */
 int
@@ -66,3 +70,15 @@ xchk_rgsuperblock(
 	xchk_rgsuperblock_xref(sc);
 	return 0;
 }
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int
+xrep_rgsuperblock(
+	struct xfs_scrub	*sc)
+{
+	ASSERT(rtg_rgno(sc->sr.rtg) == 0);
+
+	xfs_log_sb(sc->tp);
+	return 0;
+}
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index ceb22c722d8f52..950f5a58dcd967 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -456,7 +456,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.setup	= xchk_setup_rgsuperblock,
 		.scrub	= xchk_rgsuperblock,
 		.has	= xfs_has_rtsb,
-		.repair = xrep_notsupported,
+		.repair = xrep_rgsuperblock,
 	},
 };
 

[PATCH 25/34] xfs: scrub metadir paths for rtgroup metadata

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add the code we need to scan the metadata directory paths of rt group
metadata files.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_fs.h  |    5 ++-
 fs/xfs/scrub/metapath.c |   92 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 96 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 50de6ad88dbe45..96f7d3c95fb4bc 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -822,9 +822,12 @@ struct xfs_scrub_vec_head {
  * path checking.
  */
 #define XFS_SCRUB_METAPATH_PROBE	(0)  /* do we have a metapath scrubber? */
+#define XFS_SCRUB_METAPATH_RTDIR	(1)  /* rtrgroups metadir */
+#define XFS_SCRUB_METAPATH_RTBITMAP	(2)  /* per-rtg bitmap */
+#define XFS_SCRUB_METAPATH_RTSUMMARY	(3)  /* per-rtg summary */
 
 /* Number of metapath sm_ino values */
-#define XFS_SCRUB_METAPATH_NR		(1)
+#define XFS_SCRUB_METAPATH_NR		(4)
 
 /*
  * ioctl limits
diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c
index edc1a395c4015a..b8e427fd7fa73e 100644
--- a/fs/xfs/scrub/metapath.c
+++ b/fs/xfs/scrub/metapath.c
@@ -20,6 +20,7 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_trans_space.h"
 #include "xfs_attr.h"
+#include "xfs_rtgroup.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -79,6 +80,91 @@ xchk_metapath_cleanup(
 	kfree(mpath->path);
 }
 
+/* Set up a metadir path scan.  @path must be dynamically allocated. */
+static inline int
+xchk_setup_metapath_scan(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*dp,
+	const char		*path,
+	struct xfs_inode	*ip)
+{
+	struct xchk_metapath	*mpath;
+	int			error;
+
+	if (!path)
+		return -ENOMEM;
+
+	error = xchk_install_live_inode(sc, ip);
+	if (error) {
+		kfree(path);
+		return error;
+	}
+
+	mpath = kzalloc(sizeof(struct xchk_metapath), XCHK_GFP_FLAGS);
+	if (!mpath) {
+		kfree(path);
+		return -ENOMEM;
+	}
+
+	mpath->sc = sc;
+	sc->buf = mpath;
+	sc->buf_cleanup = xchk_metapath_cleanup;
+
+	mpath->dp = dp;
+	mpath->path = path; /* path is now owned by mpath */
+
+	mpath->xname.name = mpath->path;
+	mpath->xname.len = strlen(mpath->path);
+	mpath->xname.type = xfs_mode_to_ftype(VFS_I(ip)->i_mode);
+
+	return 0;
+}
+
+#ifdef CONFIG_XFS_RT
+/* Scan the /rtgroups directory itself. */
+static int
+xchk_setup_metapath_rtdir(
+	struct xfs_scrub	*sc)
+{
+	if (!sc->mp->m_rtdirip)
+		return -ENOENT;
+
+	return xchk_setup_metapath_scan(sc, sc->mp->m_metadirip,
+			kasprintf(GFP_KERNEL, "rtgroups"), sc->mp->m_rtdirip);
+}
+
+/* Scan a rtgroup inode under the /rtgroups directory. */
+static int
+xchk_setup_metapath_rtginode(
+	struct xfs_scrub	*sc,
+	enum xfs_rtg_inodes	type)
+{
+	struct xfs_rtgroup	*rtg;
+	struct xfs_inode	*ip;
+	int			error;
+
+	rtg = xfs_rtgroup_get(sc->mp, sc->sm->sm_agno);
+	if (!rtg)
+		return -ENOENT;
+
+	ip = rtg->rtg_inodes[type];
+	if (!ip) {
+		error = -ENOENT;
+		goto out_put_rtg;
+	}
+
+	error = xchk_setup_metapath_scan(sc, sc->mp->m_rtdirip,
+			xfs_rtginode_path(rtg_rgno(rtg), type), ip);
+
+out_put_rtg:
+	xfs_rtgroup_put(rtg);
+	return error;
+}
+#else
+# define xchk_setup_metapath_rtdir(...)		(-ENOENT)
+# define xchk_setup_metapath_rtginode(...)	(-ENOENT)
+#endif /* CONFIG_XFS_RT */
+
 int
 xchk_setup_metapath(
 	struct xfs_scrub	*sc)
@@ -94,6 +180,12 @@ xchk_setup_metapath(
 		if (sc->sm->sm_agno)
 			return -EINVAL;
 		return 0;
+	case XFS_SCRUB_METAPATH_RTDIR:
+		return xchk_setup_metapath_rtdir(sc);
+	case XFS_SCRUB_METAPATH_RTBITMAP:
+		return xchk_setup_metapath_rtginode(sc, XFS_RTGI_BITMAP);
+	case XFS_SCRUB_METAPATH_RTSUMMARY:
+		return xchk_setup_metapath_rtginode(sc, XFS_RTGI_SUMMARY);
 	default:
 		return -ENOENT;
 	}

[PATCH 26/34] xfs: mask off the rtbitmap and summary inodes when metadir in use

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Set the rtbitmap and summary file inumbers to NULLFSINO in the
superblock and make sure they're zeroed whenever we write the superblock
to disk, to mimic mkfs behavior.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_sb.c |   20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index c55ccecaccbda4..1af7029753ea15 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -655,6 +655,14 @@ xfs_validate_sb_common(
 void
 xfs_sb_quota_from_disk(struct xfs_sb *sbp)
 {
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
+		sbp->sb_uquotino = NULLFSINO;
+		sbp->sb_gquotino = NULLFSINO;
+		sbp->sb_pquotino = NULLFSINO;
+		return;
+	}
+
 	/*
 	 * older mkfs doesn't initialize quota inodes to NULLFSINO. This
 	 * leads to in-core values having two different values for a quota
@@ -783,6 +791,8 @@ __xfs_sb_from_disk(
 		to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
 		to->sb_rgcount = be32_to_cpu(from->sb_rgcount);
 		to->sb_rgextents = be32_to_cpu(from->sb_rgextents);
+		to->sb_rbmino = NULLFSINO;
+		to->sb_rsumino = NULLFSINO;
 	} else {
 		to->sb_metadirino = NULLFSINO;
 		to->sb_rgcount = 1;
@@ -805,6 +815,14 @@ xfs_sb_quota_to_disk(
 {
 	uint16_t	qflags = from->sb_qflags;
 
+	if (xfs_sb_is_v5(from) &&
+	    (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
+		to->sb_uquotino = cpu_to_be64(0);
+		to->sb_gquotino = cpu_to_be64(0);
+		to->sb_pquotino = cpu_to_be64(0);
+		return;
+	}
+
 	to->sb_uquotino = cpu_to_be64(from->sb_uquotino);
 
 	/*
@@ -940,6 +958,8 @@ xfs_sb_to_disk(
 		to->sb_metadirino = cpu_to_be64(from->sb_metadirino);
 		to->sb_rgcount = cpu_to_be32(from->sb_rgcount);
 		to->sb_rgextents = cpu_to_be32(from->sb_rgextents);
+		to->sb_rbmino = cpu_to_be64(0);
+		to->sb_rsumino = cpu_to_be64(0);
 	}
 }
 

[PATCH 27/34] xfs: create helpers to deal with rounding xfs_fileoff_t to rtx boundaries

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

We're about to segment xfs_rtblock_t addresses, so we must create
type-specific helpers to do rt extent rounding of file block offsets
because the rtb helpers soon will not do the right thing there.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_rtbitmap.h |   17 +++++++++++++----
 fs/xfs/xfs_bmap_util.c       |    6 +++---
 2 files changed, 16 insertions(+), 7 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 7be76490a31879..dc2b8beadfc331 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -135,13 +135,22 @@ xfs_rtb_roundup_rtx(
 	return roundup_64(rtbno, mp->m_sb.sb_rextsize);
 }
 
-/* Round this rtblock down to the nearest rt extent size. */
+/* Round this file block offset up to the nearest rt extent size. */
 static inline xfs_rtblock_t
-xfs_rtb_rounddown_rtx(
+xfs_fileoff_roundup_rtx(
 	struct xfs_mount	*mp,
-	xfs_rtblock_t		rtbno)
+	xfs_fileoff_t		off)
 {
-	return rounddown_64(rtbno, mp->m_sb.sb_rextsize);
+	return roundup_64(off, mp->m_sb.sb_rextsize);
+}
+
+/* Round this file block offset down to the nearest rt extent size. */
+static inline xfs_rtblock_t
+xfs_fileoff_rounddown_rtx(
+	struct xfs_mount	*mp,
+	xfs_fileoff_t		off)
+{
+	return rounddown_64(off, mp->m_sb.sb_rextsize);
 }
 
 /* Convert an rt extent number to a file block offset in the rt bitmap file. */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index bc53f5c7357c7a..1fe676710394e1 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -541,7 +541,7 @@ xfs_can_free_eofblocks(
 	 */
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
 	if (xfs_inode_has_bigrtalloc(ip))
-		end_fsb = xfs_rtb_roundup_rtx(mp, end_fsb);
+		end_fsb = xfs_fileoff_roundup_rtx(mp, end_fsb);
 	last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	if (last_fsb <= end_fsb)
 		return false;
@@ -863,8 +863,8 @@ xfs_free_file_space(
 
 	/* We can only free complete realtime extents. */
 	if (xfs_inode_has_bigrtalloc(ip)) {
-		startoffset_fsb = xfs_rtb_roundup_rtx(mp, startoffset_fsb);
-		endoffset_fsb = xfs_rtb_rounddown_rtx(mp, endoffset_fsb);
+		startoffset_fsb = xfs_fileoff_roundup_rtx(mp, startoffset_fsb);
+		endoffset_fsb = xfs_fileoff_rounddown_rtx(mp, endoffset_fsb);
 	}
 
 	/*

[PATCH 28/34] xfs: create helpers to deal with rounding xfs_filblks_t to rtx boundaries

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

We're about to segment xfs_rtblock_t addresses, so we must create
type-specific helpers to do rt extent rounding of file mapping block
lengths because the rtb helpers soon will not do the right thing there.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_rtbitmap.c |    2 +-
 fs/xfs/libxfs/xfs_rtbitmap.h |   30 +++++++++++++++++++++---------
 fs/xfs/xfs_exchrange.c       |    2 +-
 3 files changed, 23 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 5abfd84852ce3b..30220bf8c3f430 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1123,7 +1123,7 @@ xfs_rtfree_blocks(
 
 	ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN);
 
-	mod = xfs_rtb_to_rtxoff(mp, rtlen);
+	mod = xfs_blen_to_rtxoff(mp, rtlen);
 	if (mod) {
 		ASSERT(mod == 0);
 		return -EIO;
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index dc2b8beadfc331..e0fb36f181cc9e 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -101,6 +101,27 @@ xfs_blen_to_rtbxlen(
 	return div_u64(blen, mp->m_sb.sb_rextsize);
 }
 
+/* Return the offset of a file block length within an rt extent. */
+static inline xfs_extlen_t
+xfs_blen_to_rtxoff(
+	struct xfs_mount	*mp,
+	xfs_filblks_t		blen)
+{
+	if (likely(mp->m_rtxblklog >= 0))
+		return blen & mp->m_rtxblkmask;
+
+	return do_div(blen, mp->m_sb.sb_rextsize);
+}
+
+/* Round this block count up to the nearest rt extent size. */
+static inline xfs_filblks_t
+xfs_blen_roundup_rtx(
+	struct xfs_mount	*mp,
+	xfs_filblks_t		blen)
+{
+	return roundup_64(blen, mp->m_sb.sb_rextsize);
+}
+
 /* Convert an rt block number into an rt extent number. */
 static inline xfs_rtxnum_t
 xfs_rtb_to_rtx(
@@ -126,15 +147,6 @@ xfs_rtb_to_rtxoff(
 	return do_div(rtbno, mp->m_sb.sb_rextsize);
 }
 
-/* Round this rtblock up to the nearest rt extent size. */
-static inline xfs_rtblock_t
-xfs_rtb_roundup_rtx(
-	struct xfs_mount	*mp,
-	xfs_rtblock_t		rtbno)
-{
-	return roundup_64(rtbno, mp->m_sb.sb_rextsize);
-}
-
 /* Round this file block offset up to the nearest rt extent size. */
 static inline xfs_rtblock_t
 xfs_fileoff_roundup_rtx(
diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c
index 75cb53f090d1f7..f644c4cc77fac1 100644
--- a/fs/xfs/xfs_exchrange.c
+++ b/fs/xfs/xfs_exchrange.c
@@ -217,7 +217,7 @@ xfs_exchrange_mappings(
 	 * length in @fxr are safe to round up.
 	 */
 	if (xfs_inode_has_bigrtalloc(ip2))
-		req.blockcount = xfs_rtb_roundup_rtx(mp, req.blockcount);
+		req.blockcount = xfs_blen_roundup_rtx(mp, req.blockcount);
 
 	error = xfs_exchrange_estimate(&req);
 	if (error)

[PATCH 29/34] xfs: make xfs_rtblock_t a segmented address like xfs_fsblock_t

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we've finished adding allocation groups to the realtime volume,
let's make the file block mapping address (xfs_rtblock_t) a segmented
value just like we do on the data device.  This means that group number
and block number conversions can be done with shifting and masking
instead of integer division.

While in theory we could continue caching the rgno shift value in
m_rgblklog, the fact that we now always use the shift value means that
we have an opportunity to increase the redundancy of the rt geometry by
storing it in the ondisk superblock and adding more sb verifier code.
Extend the sueprblock to store the rgblklog value.

Now that we have segmented addresses, set the correct values in
m_groups[XG_TYPE_RTG] so that the xfs_group helpers work correctly.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_bmap.c     |    4 +-
 fs/xfs/libxfs/xfs_format.h   |    6 ++++
 fs/xfs/libxfs/xfs_ondisk.h   |    2 +
 fs/xfs/libxfs/xfs_rtbitmap.h |   13 ++++----
 fs/xfs/libxfs/xfs_rtgroup.h  |   69 +++++++++++++-----------------------------
 fs/xfs/libxfs/xfs_sb.c       |   65 +++++++++++++++++++++++++++++++++++-----
 fs/xfs/libxfs/xfs_sb.h       |    4 ++
 fs/xfs/libxfs/xfs_types.c    |    7 ++--
 fs/xfs/scrub/agheader.c      |   11 +++++--
 fs/xfs/xfs_mount.h           |    4 +-
 fs/xfs/xfs_rtalloc.c         |    4 +-
 fs/xfs/xfs_trans.c           |   21 ++++++++++---
 12 files changed, 126 insertions(+), 84 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 3498d7b4fbc54e..9052839305e2ca 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3152,10 +3152,8 @@ xfs_bmap_adjacent_valid(
 
 	if (XFS_IS_REALTIME_INODE(ap->ip) &&
 	    (ap->datatype & XFS_ALLOC_USERDATA)) {
-		if (x >= mp->m_sb.sb_rblocks)
-			return false;
 		if (!xfs_has_rtgroups(mp))
-			return true;
+			return x < mp->m_sb.sb_rblocks;
 
 		return xfs_rtb_to_rgno(mp, x) == xfs_rtb_to_rgno(mp, y) &&
 			xfs_rtb_to_rgno(mp, x) < mp->m_sb.sb_rgcount &&
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index f56ff9f43c218f..d6c10855ab023b 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -179,6 +179,9 @@ typedef struct xfs_sb {
 	xfs_rgnumber_t	sb_rgcount;	/* number of realtime groups */
 	xfs_rtxlen_t	sb_rgextents;	/* size of a realtime group in rtx */
 
+	uint8_t		sb_rgblklog;    /* rt group number shift */
+	uint8_t		sb_pad[7];	/* zeroes */
+
 	/* must be padded to 64 bit alignment */
 } xfs_sb_t;
 
@@ -268,6 +271,9 @@ struct xfs_dsb {
 	__be32		sb_rgcount;	/* # of realtime groups */
 	__be32		sb_rgextents;	/* size of rtgroup in rtx */
 
+	__u8		sb_rgblklog;    /* rt group number shift */
+	__u8		sb_pad[7];	/* zeroes */
+
 	/*
 	 * The size of this structure must be padded to 64 bit alignment.
 	 *
diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 6a2bcbc392842c..99eae7f67e961b 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -37,7 +37,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dinode,		176);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot,		104);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk,			136);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			280);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			288);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr,		56);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key,		4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec,		16);
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index e0fb36f181cc9e..16563a44bd138a 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -26,7 +26,7 @@ xfs_rtx_to_rtb(
 	xfs_rtxnum_t		rtx)
 {
 	struct xfs_mount	*mp = rtg_mount(rtg);
-	xfs_rtblock_t		start = xfs_rgno_start_rtb(mp, rtg_rgno(rtg));
+	xfs_rtblock_t		start = xfs_group_start_fsb(rtg_group(rtg));
 
 	if (mp->m_rtxblklog >= 0)
 		return start + (rtx << mp->m_rtxblklog);
@@ -128,11 +128,11 @@ xfs_rtb_to_rtx(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
-	uint64_t		__rgbno = __xfs_rtb_to_rgbno(mp, rtbno);
-
+	/* open-coded 64-bit masking operation */
+	rtbno &= mp->m_groups[XG_TYPE_RTG].blkmask;
 	if (likely(mp->m_rtxblklog >= 0))
-		return __rgbno >> mp->m_rtxblklog;
-	return div_u64(__rgbno, mp->m_sb.sb_rextsize);
+		return rtbno >> mp->m_rtxblklog;
+	return div_u64(rtbno, mp->m_sb.sb_rextsize);
 }
 
 /* Return the offset of an rt block number within an rt extent. */
@@ -141,9 +141,10 @@ xfs_rtb_to_rtxoff(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
+	/* open-coded 64-bit masking operation */
+	rtbno &= mp->m_groups[XG_TYPE_RTG].blkmask;
 	if (likely(mp->m_rtxblklog >= 0))
 		return rtbno & mp->m_rtxblkmask;
-
 	return do_div(rtbno, mp->m_sb.sb_rextsize);
 }
 
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 2ddfac9a0182f9..c15b232e1f8e77 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -122,31 +122,12 @@ xfs_rtgroup_next(
 	return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1);
 }
 
-static inline xfs_rtblock_t
-xfs_rgno_start_rtb(
-	struct xfs_mount	*mp,
-	xfs_rgnumber_t		rgno)
-{
-	if (mp->m_rgblklog >= 0)
-		return ((xfs_rtblock_t)rgno << mp->m_rgblklog);
-	return ((xfs_rtblock_t)rgno * mp->m_rgblocks);
-}
-
-static inline xfs_rtblock_t
-__xfs_rgbno_to_rtb(
-	struct xfs_mount	*mp,
-	xfs_rgnumber_t		rgno,
-	xfs_rgblock_t		rgbno)
-{
-	return xfs_rgno_start_rtb(mp, rgno) + rgbno;
-}
-
 static inline xfs_rtblock_t
 xfs_rgbno_to_rtb(
 	struct xfs_rtgroup	*rtg,
 	xfs_rgblock_t		rgbno)
 {
-	return __xfs_rgbno_to_rtb(rtg_mount(rtg), rtg_rgno(rtg), rgbno);
+	return xfs_gbno_to_fsb(rtg_group(rtg), rgbno);
 }
 
 static inline xfs_rgnumber_t
@@ -154,30 +135,7 @@ xfs_rtb_to_rgno(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
-	if (!xfs_has_rtgroups(mp))
-		return 0;
-
-	if (mp->m_rgblklog >= 0)
-		return rtbno >> mp->m_rgblklog;
-
-	return div_u64(rtbno, mp->m_rgblocks);
-}
-
-static inline uint64_t
-__xfs_rtb_to_rgbno(
-	struct xfs_mount	*mp,
-	xfs_rtblock_t		rtbno)
-{
-	uint32_t		rem;
-
-	if (!xfs_has_rtgroups(mp))
-		return rtbno;
-
-	if (mp->m_rgblklog >= 0)
-		return rtbno & mp->m_rgblkmask;
-
-	div_u64_rem(rtbno, mp->m_rgblocks, &rem);
-	return rem;
+	return xfs_fsb_to_gno(mp, rtbno, XG_TYPE_RTG);
 }
 
 static inline xfs_rgblock_t
@@ -185,7 +143,7 @@ xfs_rtb_to_rgbno(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
-	return __xfs_rtb_to_rgbno(mp, rtbno);
+	return xfs_fsb_to_gbno(mp, rtbno, XG_TYPE_RTG);
 }
 
 /* Is rtbno the start of a RT group? */
@@ -194,7 +152,7 @@ xfs_rtbno_is_group_start(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
-	return (rtbno & mp->m_rgblkmask) == 0;
+	return (rtbno & mp->m_groups[XG_TYPE_RTG].blkmask) == 0;
 }
 
 static inline xfs_daddr_t
@@ -202,7 +160,11 @@ xfs_rtb_to_daddr(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
-	return rtbno << mp->m_blkbb_log;
+	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
+	xfs_rgnumber_t		rgno = xfs_rtb_to_rgno(mp, rtbno);
+	uint64_t		start_bno = (xfs_rtblock_t)rgno * g->blocks;
+
+	return XFS_FSB_TO_BB(mp, start_bno + (rtbno & g->blkmask));
 }
 
 static inline xfs_rtblock_t
@@ -210,7 +172,18 @@ xfs_daddr_to_rtb(
 	struct xfs_mount	*mp,
 	xfs_daddr_t		daddr)
 {
-	return daddr >> mp->m_blkbb_log;
+	xfs_rfsblock_t		bno = XFS_BB_TO_FSBT(mp, daddr);
+
+	if (xfs_has_rtgroups(mp)) {
+		struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG];
+		xfs_rgnumber_t	rgno;
+		uint32_t	rgbno;
+
+		rgno = div_u64_rem(bno, g->blocks, &rgbno);
+		return ((xfs_rtblock_t)rgno << g->blklog) + rgbno;
+	}
+
+	return bno;
 }
 
 #ifdef CONFIG_XFS_RT
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 1af7029753ea15..6a31f48a2c5424 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -368,12 +368,23 @@ xfs_validate_sb_write(
 	return 0;
 }
 
+int
+xfs_compute_rgblklog(
+	xfs_rtxlen_t	rgextents,
+	xfs_rgblock_t	rextsize)
+{
+	uint64_t	rgblocks = (uint64_t)rgextents * rextsize;
+
+	return xfs_highbit64(rgblocks - 1) + 1;
+}
+
 static int
 xfs_validate_sb_rtgroups(
 	struct xfs_mount	*mp,
 	struct xfs_sb		*sbp)
 {
 	uint64_t		groups;
+	int			rgblklog;
 
 	if (sbp->sb_rextsize == 0) {
 		xfs_warn(mp,
@@ -418,6 +429,14 @@ xfs_validate_sb_rtgroups(
 		return -EINVAL;
 	}
 
+	rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents, sbp->sb_rextsize);
+	if (sbp->sb_rgblklog != rgblklog) {
+		xfs_warn(mp,
+"Realtime group log (%d) does not match expected value (%d).",
+				sbp->sb_rgblklog, rgblklog);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -484,6 +503,12 @@ xfs_validate_sb_common(
 		}
 
 		if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
+			if (memchr_inv(sbp->sb_pad, 0, sizeof(sbp->sb_pad))) {
+				xfs_warn(mp,
+"Metadir superblock padding fields must be zero.");
+				return -EINVAL;
+			}
+
 			error = xfs_validate_sb_rtgroups(mp, sbp);
 			if (error)
 				return error;
@@ -789,6 +814,8 @@ __xfs_sb_from_disk(
 
 	if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
 		to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
+		to->sb_rgblklog = from->sb_rgblklog;
+		memcpy(to->sb_pad, from->sb_pad, sizeof(to->sb_pad));
 		to->sb_rgcount = be32_to_cpu(from->sb_rgcount);
 		to->sb_rgextents = be32_to_cpu(from->sb_rgextents);
 		to->sb_rbmino = NULLFSINO;
@@ -956,6 +983,8 @@ xfs_sb_to_disk(
 
 	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
 		to->sb_metadirino = cpu_to_be64(from->sb_metadirino);
+		to->sb_rgblklog = from->sb_rgblklog;
+		memset(to->sb_pad, 0, sizeof(to->sb_pad));
 		to->sb_rgcount = cpu_to_be32(from->sb_rgcount);
 		to->sb_rgextents = cpu_to_be32(from->sb_rgextents);
 		to->sb_rbmino = cpu_to_be64(0);
@@ -1090,8 +1119,9 @@ const struct xfs_buf_ops xfs_sb_quiet_buf_ops = {
 	.verify_write = xfs_sb_write_verify,
 };
 
+/* Compute cached rt geometry from the incore sb. */
 void
-xfs_mount_sb_set_rextsize(
+xfs_sb_mount_rextsize(
 	struct xfs_mount	*mp,
 	struct xfs_sb		*sbp)
 {
@@ -1100,13 +1130,32 @@ xfs_mount_sb_set_rextsize(
 	mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize);
 	mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize);
 
-	mp->m_rgblocks = sbp->sb_rgextents * sbp->sb_rextsize;
-	mp->m_rgblklog = log2_if_power2(mp->m_rgblocks);
-	mp->m_rgblkmask = mask64_if_power2(mp->m_rgblocks);
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
+		rgs->blocks = sbp->sb_rgextents * sbp->sb_rextsize;
+		rgs->blklog = mp->m_sb.sb_rgblklog;
+		rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog);
+	} else {
+		rgs->blocks = 0;
+		rgs->blklog = 0;
+		rgs->blkmask = (uint64_t)-1;
+	}
+}
 
-	rgs->blocks = 0;
-	rgs->blklog = 0;
-	rgs->blkmask = (uint64_t)-1;
+/* Update incore sb rt extent size, then recompute the cached rt geometry. */
+void
+xfs_mount_sb_set_rextsize(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp,
+	xfs_agblock_t		rextsize)
+{
+	sbp->sb_rextsize = rextsize;
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR))
+		sbp->sb_rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents,
+							rextsize);
+
+	xfs_sb_mount_rextsize(mp, sbp);
 }
 
 /*
@@ -1140,7 +1189,7 @@ xfs_sb_mount_common(
 	ags->blklog = mp->m_sb.sb_agblklog;
 	ags->blkmask = xfs_mask32lo(mp->m_sb.sb_agblklog);
 
-	xfs_mount_sb_set_rextsize(mp, sbp);
+	xfs_sb_mount_rextsize(mp, sbp);
 
 	mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, true);
 	mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, false);
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 999dcfccdaf960..34d0dd374e9b0b 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -17,8 +17,9 @@ extern void	xfs_log_sb(struct xfs_trans *tp);
 extern int	xfs_sync_sb(struct xfs_mount *mp, bool wait);
 extern int	xfs_sync_sb_buf(struct xfs_mount *mp, bool update_rtsb);
 extern void	xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp);
+void		xfs_sb_mount_rextsize(struct xfs_mount *mp, struct xfs_sb *sbp);
 void		xfs_mount_sb_set_rextsize(struct xfs_mount *mp,
-			struct xfs_sb *sbp);
+			struct xfs_sb *sbp, xfs_agblock_t rextsize);
 extern void	xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from);
 extern void	xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from);
 extern void	xfs_sb_quota_from_disk(struct xfs_sb *sbp);
@@ -43,5 +44,6 @@ bool	xfs_validate_stripe_geometry(struct xfs_mount *mp,
 bool	xfs_validate_rt_geometry(struct xfs_sb *sbp);
 
 uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
+int xfs_compute_rgblklog(xfs_rtxlen_t rgextents, xfs_rgblock_t rextsize);
 
 #endif	/* __XFS_SB_H__ */
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index a4c30844d42be1..1faf04204c5ddc 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -146,9 +146,6 @@ xfs_verify_rtbno(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
 {
-	if (rtbno >= mp->m_sb.sb_rblocks)
-		return false;
-
 	if (xfs_has_rtgroups(mp)) {
 		xfs_rgnumber_t	rgno = xfs_rtb_to_rgno(mp, rtbno);
 		xfs_rtxnum_t	rtx = xfs_rtb_to_rtx(mp, rtbno);
@@ -159,8 +156,10 @@ xfs_verify_rtbno(
 			return false;
 		if (xfs_has_rtsb(mp) && rgno == 0 && rtx == 0)
 			return false;
+		return true;
 	}
-	return true;
+
+	return rtbno < mp->m_sb.sb_rblocks;
 }
 
 /*
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index cad997f38a424c..05f5e94b99382b 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -279,8 +279,15 @@ xchk_superblock(
 		if (!!(sb->sb_features2 & cpu_to_be32(~v2_ok)))
 			xchk_block_set_corrupt(sc, bp);
 
-		if (sb->sb_features2 != sb->sb_bad_features2)
-			xchk_block_set_preen(sc, bp);
+		if (xfs_has_metadir(mp)) {
+			if (sb->sb_rgblklog != mp->m_sb.sb_rgblklog)
+				xchk_block_set_corrupt(sc, bp);
+			if (memchr_inv(sb->sb_pad, 0, sizeof(sb->sb_pad)))
+				xchk_block_set_preen(sc, bp);
+		} else {
+			if (sb->sb_features2 != sb->sb_bad_features2)
+				xchk_block_set_preen(sc, bp);
+		}
 	}
 
 	/* Check sb_features2 flags that are set at mkfs time. */
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 62c251b3a385d4..ee1c3eb53d9f2b 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -147,7 +147,7 @@ typedef struct xfs_mount {
 	uint8_t			m_agno_log;	/* log #ag's */
 	uint8_t			m_sectbb_log;	/* sectlog - BBSHIFT */
 	int8_t			m_rtxblklog;	/* log2 of rextsize, if possible */
-	int8_t			m_rgblklog;	/* log2 of rt group sz if possible */
+
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
 	/* number of rt extents per rt bitmap block if rtgroups enabled */
@@ -177,14 +177,12 @@ typedef struct xfs_mount {
 	int			m_logbsize;	/* size of each log buffer */
 	unsigned int		m_rsumlevels;	/* rt summary levels */
 	xfs_filblks_t		m_rsumblocks;	/* size of rt summary, FSBs */
-	uint32_t		m_rgblocks;	/* size of rtgroup in rtblocks */
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_qflags;	/* quota status flags */
 	uint64_t		m_features;	/* active filesystem features */
 	uint64_t		m_low_space[XFS_LOWSP_MAX];
 	uint64_t		m_low_rtexts[XFS_LOWSP_MAX];
 	uint64_t		m_rtxblkmask;	/* rt extent block mask */
-	uint64_t		m_rgblkmask;	/* rt group block mask */
 	struct xfs_ino_geometry	m_ino_geo;	/* inode geometry */
 	struct xfs_trans_resv	m_resv;		/* precomputed res values */
 						/* low free space thresholds */
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index b27d23bcc06418..42070587e856ef 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -745,8 +745,7 @@ xfs_growfs_rt_alloc_fake_mount(
 	nmp = kmemdup(mp, sizeof(*mp), GFP_KERNEL);
 	if (!nmp)
 		return NULL;
-	nmp->m_sb.sb_rextsize = rextsize;
-	xfs_mount_sb_set_rextsize(nmp, &nmp->m_sb);
+	xfs_mount_sb_set_rextsize(nmp, &nmp->m_sb, rextsize);
 	nmp->m_sb.sb_rblocks = rblocks;
 	nmp->m_sb.sb_rextents = xfs_blen_to_rtbxlen(nmp, nmp->m_sb.sb_rblocks);
 	nmp->m_sb.sb_rbmblocks = xfs_rtbitmap_blockcount(nmp);
@@ -968,7 +967,6 @@ xfs_growfs_rt_bmblock(
 	 */
 	mp->m_rsumlevels = nmp->m_rsumlevels;
 	mp->m_rsumblocks = nmp->m_rsumblocks;
-	xfs_mount_sb_set_rextsize(mp, &mp->m_sb);
 
 	/*
 	 * Recompute the growfsrt reservation from the new rsumsize.
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index a29a181e684041..4db022c189e134 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -26,6 +26,7 @@
 #include "xfs_icache.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_rtgroup.h"
+#include "xfs_sb.h"
 
 struct kmem_cache	*xfs_trans_cache;
 
@@ -547,6 +548,18 @@ xfs_trans_apply_sb_deltas(
 	}
 	if (tp->t_rextsize_delta) {
 		be32_add_cpu(&sbp->sb_rextsize, tp->t_rextsize_delta);
+
+		/*
+		 * Because the ondisk sb records rtgroup size in units of rt
+		 * extents, any time we update the rt extent size we have to
+		 * recompute the ondisk rtgroup block log.  The incore values
+		 * will be recomputed in xfs_trans_unreserve_and_mod_sb.
+		 */
+		if (xfs_has_rtgroups(tp->t_mountp)) {
+			sbp->sb_rgblklog = xfs_compute_rgblklog(
+						be32_to_cpu(sbp->sb_rgextents),
+						be32_to_cpu(sbp->sb_rextsize));
+		}
 		whole = 1;
 	}
 	if (tp->t_rbmblocks_delta) {
@@ -673,11 +686,9 @@ xfs_trans_unreserve_and_mod_sb(
 	mp->m_sb.sb_dblocks += tp->t_dblocks_delta;
 	mp->m_sb.sb_agcount += tp->t_agcount_delta;
 	mp->m_sb.sb_imax_pct += tp->t_imaxpct_delta;
-	mp->m_sb.sb_rextsize += tp->t_rextsize_delta;
-	if (tp->t_rextsize_delta) {
-		mp->m_rtxblklog = log2_if_power2(mp->m_sb.sb_rextsize);
-		mp->m_rtxblkmask = mask64_if_power2(mp->m_sb.sb_rextsize);
-	}
+	if (tp->t_rextsize_delta)
+		xfs_mount_sb_set_rextsize(mp, &mp->m_sb,
+				mp->m_sb.sb_rextsize + tp->t_rextsize_delta);
 	mp->m_sb.sb_rbmblocks += tp->t_rbmblocks_delta;
 	mp->m_sb.sb_rblocks += tp->t_rblocks_delta;
 	mp->m_sb.sb_rextents += tp->t_rextents_delta;

[PATCH 30/34] xfs: adjust min_block usage in xfs_verify_agbno

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

There's some weird logic in xfs_verify_agbno -- min_block ought to be
the first agblock number in the AG that can be used by non-static
metadata.  However, we initialize it to the last agblock of the static
metadata, which works due to the <= check, even though this isn't
technically correct.

Change the check to < and set min_block to the next agblock past the
static metadata.  This hasn't been an issue up to now, but we're going
to move these things into the generic group struct, and this will cause
problems with rtgroups, where min_block can be zero for an rtgroup that
doesn't have a rt superblock.

Note that there's no user-visible impact with the old logic, so this
isn't a bug fix.

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


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 47e90dbb852bba..8fe96a9e047205 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -242,7 +242,7 @@ xfs_perag_alloc(
 	 * Pre-calculated geometry
 	 */
 	pag->block_count = __xfs_ag_block_count(mp, index, agcount, dblocks);
-	pag->min_block = XFS_AGFL_BLOCK(mp);
+	pag->min_block = XFS_AGFL_BLOCK(mp) + 1;
 	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
 			&pag->agino_max);
 
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 7290148fa6e6aa..9c22a76d58cfc2 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -222,7 +222,7 @@ xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno)
 {
 	if (agbno >= pag->block_count)
 		return false;
-	if (agbno <= pag->min_block)
+	if (agbno < pag->min_block)
 		return false;
 	return true;
 }

[PATCH 31/34] xfs: move the min and max group block numbers to xfs_group

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move the min and max agblock numbers to the generic xfs_group structure
so that we can start building validators for extents within an rtgroup.
While we're at it, use check_add_overflow for the extent length
computation because that has much better overflow checking.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_ag.c           |   22 ++++++++++++----------
 fs/xfs/libxfs/xfs_ag.h           |   16 ++--------------
 fs/xfs/libxfs/xfs_group.h        |   33 +++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_ialloc_btree.c |    2 +-
 fs/xfs/libxfs/xfs_rtgroup.c      |   31 ++++++++++++++++++++++++++++++-
 fs/xfs/libxfs/xfs_rtgroup.h      |    3 +++
 fs/xfs/scrub/agheader.c          |    4 ++--
 fs/xfs/scrub/agheader_repair.c   |    4 ++--
 fs/xfs/scrub/repair.c            |    6 +++---
 fs/xfs/xfs_discard.c             |    4 ++--
 fs/xfs/xfs_rtalloc.c             |    8 ++++----
 11 files changed, 94 insertions(+), 39 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 8fe96a9e047205..b59cb461e096ea 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -205,9 +205,10 @@ xfs_update_last_ag_size(
 
 	if (!pag)
 		return -EFSCORRUPTED;
-	pag->block_count = __xfs_ag_block_count(mp, prev_agcount - 1,
-			mp->m_sb.sb_agcount, mp->m_sb.sb_dblocks);
-	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+	pag_group(pag)->xg_block_count = __xfs_ag_block_count(mp,
+			prev_agcount - 1, mp->m_sb.sb_agcount,
+			mp->m_sb.sb_dblocks);
+	__xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min,
 			&pag->agino_max);
 	xfs_perag_rele(pag);
 	return 0;
@@ -241,9 +242,10 @@ xfs_perag_alloc(
 	/*
 	 * Pre-calculated geometry
 	 */
-	pag->block_count = __xfs_ag_block_count(mp, index, agcount, dblocks);
-	pag->min_block = XFS_AGFL_BLOCK(mp) + 1;
-	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+	pag_group(pag)->xg_block_count = __xfs_ag_block_count(mp, index, agcount,
+				dblocks);
+	pag_group(pag)->xg_min_gbno = XFS_AGFL_BLOCK(mp) + 1;
+	__xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min,
 			&pag->agino_max);
 
 	error = xfs_group_insert(mp, pag_group(pag), index, XG_TYPE_AG);
@@ -852,8 +854,8 @@ xfs_ag_shrink_space(
 	}
 
 	/* Update perag geometry */
-	pag->block_count -= delta;
-	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+	pag_group(pag)->xg_block_count -= delta;
+	__xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min,
 			&pag->agino_max);
 
 	xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH);
@@ -924,8 +926,8 @@ xfs_ag_extend_space(
 		return error;
 
 	/* Update perag geometry */
-	pag->block_count = be32_to_cpu(agf->agf_length);
-	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+	pag_group(pag)->xg_block_count = be32_to_cpu(agf->agf_length);
+	__xfs_agino_range(mp, pag_group(pag)->xg_block_count, &pag->agino_min,
 			&pag->agino_max);
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 9c22a76d58cfc2..1f24cfa2732172 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -61,8 +61,6 @@ struct xfs_perag {
 	struct xfs_ag_resv	pag_rmapbt_resv;
 
 	/* Precalculated geometry info */
-	xfs_agblock_t		block_count;
-	xfs_agblock_t		min_block;
 	xfs_agino_t		agino_min;
 	xfs_agino_t		agino_max;
 
@@ -220,11 +218,7 @@ void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno,
 static inline bool
 xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno)
 {
-	if (agbno >= pag->block_count)
-		return false;
-	if (agbno < pag->min_block)
-		return false;
-	return true;
+	return xfs_verify_gbno(pag_group(pag), agbno);
 }
 
 static inline bool
@@ -233,13 +227,7 @@ xfs_verify_agbext(
 	xfs_agblock_t		agbno,
 	xfs_agblock_t		len)
 {
-	if (agbno + len <= agbno)
-		return false;
-
-	if (!xfs_verify_agbno(pag, agbno))
-		return false;
-
-	return xfs_verify_agbno(pag, agbno + len - 1);
+	return xfs_verify_gbext(pag_group(pag), agbno, len);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index 5b7362277c3f7a..242b05627c7a6e 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -12,6 +12,10 @@ struct xfs_group {
 	atomic_t		xg_ref;		/* passive reference count */
 	atomic_t		xg_active_ref;	/* active reference count */
 
+	/* Precalculated geometry info */
+	uint32_t		xg_block_count;	/* max usable gbno */
+	uint32_t		xg_min_gbno;	/* min usable gbno */
+
 #ifdef __KERNEL__
 	/* -- kernel only structures below this line -- */
 
@@ -128,4 +132,33 @@ xfs_fsb_to_gbno(
 	return fsbno & mp->m_groups[type].blkmask;
 }
 
+static inline bool
+xfs_verify_gbno(
+	struct xfs_group	*xg,
+	uint32_t		gbno)
+{
+	if (gbno >= xg->xg_block_count)
+		return false;
+	if (gbno < xg->xg_min_gbno)
+		return false;
+	return true;
+}
+
+static inline bool
+xfs_verify_gbext(
+	struct xfs_group	*xg,
+	uint32_t		gbno,
+	uint32_t		glen)
+{
+	uint32_t		end;
+
+	if (!xfs_verify_gbno(xg, gbno))
+		return false;
+	if (glen == 0 || check_add_overflow(gbno, glen - 1, &end))
+		return false;
+	if (!xfs_verify_gbno(xg, end))
+		return false;
+	return true;
+}
+
 #endif /* __LIBXFS_GROUP_H */
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 4c28deb3e9881d..9b34896dd1a32f 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -717,7 +717,7 @@ xfs_inobt_max_size(
 	struct xfs_perag	*pag)
 {
 	struct xfs_mount	*mp = pag_mount(pag);
-	xfs_agblock_t		agblocks = pag->block_count;
+	xfs_agblock_t		agblocks = pag_group(pag)->xg_block_count;
 
 	/* Bail out if we're uninitialized, which can happen in mkfs. */
 	if (M_IGEO(mp)->inobt_mxr[0] == 0)
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index 624d8b25eba0ec..e74bb059f24fa1 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -34,6 +34,32 @@
 #include "xfs_metafile.h"
 #include "xfs_metadir.h"
 
+/* Find the first usable fsblock in this rtgroup. */
+static inline uint32_t
+xfs_rtgroup_min_block(
+	struct xfs_mount	*mp,
+	xfs_rgnumber_t		rgno)
+{
+	if (xfs_has_rtsb(mp) && rgno == 0)
+		return mp->m_sb.sb_rextsize;
+
+	return 0;
+}
+
+/* Precompute this group's geometry */
+void
+xfs_rtgroup_calc_geometry(
+	struct xfs_mount	*mp,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgnumber_t		rgno,
+	xfs_rgnumber_t		rgcount,
+	xfs_rtbxlen_t		rextents)
+{
+	rtg->rtg_extents = __xfs_rtgroup_extents(mp, rgno, rgcount, rextents);
+	rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize;
+	rtg_group(rtg)->xg_min_gbno = xfs_rtgroup_min_block(mp, rgno);
+}
+
 int
 xfs_rtgroup_alloc(
 	struct xfs_mount	*mp,
@@ -48,6 +74,8 @@ xfs_rtgroup_alloc(
 	if (!rtg)
 		return -ENOMEM;
 
+	xfs_rtgroup_calc_geometry(mp, rtg, rgno, rgcount, rextents);
+
 	error = xfs_group_insert(mp, rtg_group(rtg), rgno, XG_TYPE_RTG);
 	if (error)
 		goto out_free_rtg;
@@ -149,6 +177,7 @@ xfs_update_last_rtgroup_size(
 		return -EFSCORRUPTED;
 	rtg->rtg_extents = __xfs_rtgroup_extents(mp, prev_rgcount - 1,
 			mp->m_sb.sb_rgcount, mp->m_sb.sb_rextents);
+	rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize;
 	xfs_rtgroup_rele(rtg);
 	return 0;
 }
@@ -223,7 +252,7 @@ xfs_rtgroup_get_geometry(
 	/* Fill out form. */
 	memset(rgeo, 0, sizeof(*rgeo));
 	rgeo->rg_number = rtg_rgno(rtg);
-	rgeo->rg_length = rtg->rtg_extents * rtg_mount(rtg)->m_sb.sb_rextsize;
+	rgeo->rg_length = rtg_group(rtg)->xg_block_count;
 	xfs_rtgroup_geom_health(rtg, rgeo);
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index c15b232e1f8e77..1e51dc62d1143e 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -199,6 +199,9 @@ int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
 xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno,
 		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
 xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno);
+void xfs_rtgroup_calc_geometry(struct xfs_mount *mp, struct xfs_rtgroup *rtg,
+		xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount,
+		xfs_rtbxlen_t rextents);
 
 int xfs_update_last_rtgroup_size(struct xfs_mount *mp,
 		xfs_rgnumber_t prev_rgcount);
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 05f5e94b99382b..d037de6dd821d2 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -564,7 +564,7 @@ xchk_agf(
 
 	/* Check the AG length */
 	eoag = be32_to_cpu(agf->agf_length);
-	if (eoag != pag->block_count)
+	if (eoag != pag_group(pag)->xg_block_count)
 		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	/* Check the AGF btree roots and levels */
@@ -944,7 +944,7 @@ xchk_agi(
 
 	/* Check the AG length */
 	eoag = be32_to_cpu(agi->agi_length);
-	if (eoag != pag->block_count)
+	if (eoag != pag_group(pag)->xg_block_count)
 		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check btree roots and levels */
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 0ea04d6e21cd83..0fad0baaba2f69 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -209,7 +209,7 @@ xrep_agf_init_header(
 	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_agno(pag));
-	agf->agf_length = cpu_to_be32(pag->block_count);
+	agf->agf_length = cpu_to_be32(pag_group(pag)->xg_block_count);
 	agf->agf_flfirst = old_agf->agf_flfirst;
 	agf->agf_fllast = old_agf->agf_fllast;
 	agf->agf_flcount = old_agf->agf_flcount;
@@ -898,7 +898,7 @@ xrep_agi_init_header(
 	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_agno(pag));
-	agi->agi_length = cpu_to_be32(pag->block_count);
+	agi->agi_length = cpu_to_be32(pag_group(pag)->xg_block_count);
 	agi->agi_newino = cpu_to_be32(NULLAGINO);
 	agi->agi_dirino = cpu_to_be32(NULLAGINO);
 	if (xfs_has_crc(mp))
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 3fa009126170e6..91c8bc055a4fd7 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -306,7 +306,7 @@ xrep_calc_ag_resblks(
 	/* Now grab the block counters from the AGF. */
 	error = xfs_alloc_read_agf(pag, NULL, 0, &bp);
 	if (error) {
-		aglen = pag->block_count;
+		aglen = pag_group(pag)->xg_block_count;
 		freelen = aglen;
 		usedlen = aglen;
 	} else {
@@ -326,9 +326,9 @@ xrep_calc_ag_resblks(
 
 	/* If the block counts are impossible, make worst-case assumptions. */
 	if (aglen == NULLAGBLOCK ||
-	    aglen != pag->block_count ||
+	    aglen != pag_group(pag)->xg_block_count ||
 	    freelen >= aglen) {
-		aglen = pag->block_count;
+		aglen = pag_group(pag)->xg_block_count;
 		freelen = aglen;
 		usedlen = aglen;
 	}
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index e71bd64685f900..a7635962448911 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -337,7 +337,7 @@ xfs_trim_perag_extents(
 	};
 	int			error = 0;
 
-	if (start != 0 || end != pag->block_count)
+	if (start != 0 || end != pag_group(pag)->xg_block_count)
 		tcur.by_bno = true;
 
 	do {
@@ -403,7 +403,7 @@ xfs_trim_datadev_extents(
 	end_agbno = xfs_daddr_to_agbno(mp, ddev_end);
 
 	while ((pag = xfs_perag_next_range(mp, pag, start_agno, end_agno))) {
-		xfs_agblock_t	agend = pag->block_count;
+		xfs_agblock_t	agend = pag_group(pag)->xg_block_count;
 
 		if (pag_agno(pag) == end_agno)
 			agend = end_agbno;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 42070587e856ef..8520d72afac0d9 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -878,7 +878,8 @@ xfs_growfs_rt_bmblock(
 	if (!nmp)
 		return -ENOMEM;
 
-	rtg->rtg_extents = xfs_rtgroup_extents(nmp, rtg_rgno(rtg));
+	xfs_rtgroup_calc_geometry(nmp, rtg, rtg_rgno(rtg),
+			nmp->m_sb.sb_rgcount, nmp->m_sb.sb_rextents);
 
 	/*
 	 * Recompute the growfsrt reservation from the new rsumsize, so that the
@@ -1137,7 +1138,8 @@ xfs_growfs_rtg(
 	/*
 	 * Reset rtg_extents to the old value if adding more blocks failed.
 	 */
-	rtg->rtg_extents = xfs_rtgroup_extents(rtg_mount(rtg), rtg_rgno(rtg));
+	xfs_rtgroup_calc_geometry(mp, rtg, rtg_rgno(rtg), mp->m_sb.sb_rgcount,
+			mp->m_sb.sb_rextents);
 	if (old_rsum_cache) {
 		kvfree(rtg->rtg_rsum_cache);
 		rtg->rtg_rsum_cache = old_rsum_cache;
@@ -1519,8 +1521,6 @@ xfs_rtmount_rtg(
 {
 	int			error, i;
 
-	rtg->rtg_extents = xfs_rtgroup_extents(mp, rtg_rgno(rtg));
-
 	for (i = 0; i < XFS_RTGI_MAX; i++) {
 		error = xfs_rtginode_load(rtg, i, tp);
 		if (error)

[PATCH 32/34] xfs: port the perag discard code to handle generic groups

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port xfs_discard_extents and its tracepoints to handle generic groups
instead of just perags.  This is needed to enable busy extent tracking
for rtgroups.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_discard.c |   35 ++++++++++++++++++++++++++---------
 fs/xfs/xfs_trace.h   |   19 +++++++++++--------
 2 files changed, 37 insertions(+), 17 deletions(-)


diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index a7635962448911..b7c1e09e9afefc 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -101,6 +101,24 @@ xfs_discard_endio(
 	bio_put(bio);
 }
 
+static inline struct block_device *
+xfs_group_bdev(
+	const struct xfs_group	*xg)
+{
+	struct xfs_mount	*mp = xg->xg_mount;
+
+	switch (xg->xg_type) {
+	case XG_TYPE_AG:
+		return mp->m_ddev_targp->bt_bdev;
+	case XG_TYPE_RTG:
+		return mp->m_rtdev_targp->bt_bdev;
+	default:
+		ASSERT(0);
+		break;
+	}
+	return NULL;
+}
+
 /*
  * Walk the discard list and issue discards on all the busy extents in the
  * list. We plug and chain the bios so that we only need a single completion
@@ -118,12 +136,11 @@ xfs_discard_extents(
 
 	blk_start_plug(&plug);
 	list_for_each_entry(busyp, &extents->extent_list, list) {
-		struct xfs_perag	*pag = to_perag(busyp->group);
+		trace_xfs_discard_extent(busyp->group, busyp->bno,
+				busyp->length);
 
-		trace_xfs_discard_extent(pag, busyp->bno, busyp->length);
-
-		error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
-				xfs_agbno_to_daddr(pag, busyp->bno),
+		error = __blkdev_issue_discard(xfs_group_bdev(busyp->group),
+				xfs_gbno_to_daddr(busyp->group, busyp->bno),
 				XFS_FSB_TO_BB(mp, busyp->length),
 				GFP_KERNEL, &bio);
 		if (error && error != -EOPNOTSUPP) {
@@ -241,11 +258,11 @@ xfs_trim_gather_extents(
 		 * overlapping ranges for now.
 		 */
 		if (fbno + flen < tcur->start) {
-			trace_xfs_discard_exclude(pag, fbno, flen);
+			trace_xfs_discard_exclude(pag_group(pag), fbno, flen);
 			goto next_extent;
 		}
 		if (fbno > tcur->end) {
-			trace_xfs_discard_exclude(pag, fbno, flen);
+			trace_xfs_discard_exclude(pag_group(pag), fbno, flen);
 			if (tcur->by_bno) {
 				tcur->count = 0;
 				break;
@@ -263,7 +280,7 @@ xfs_trim_gather_extents(
 
 		/* Too small?  Give up. */
 		if (flen < tcur->minlen) {
-			trace_xfs_discard_toosmall(pag, fbno, flen);
+			trace_xfs_discard_toosmall(pag_group(pag), fbno, flen);
 			if (tcur->by_bno)
 				goto next_extent;
 			tcur->count = 0;
@@ -275,7 +292,7 @@ xfs_trim_gather_extents(
 		 * discard and try again the next time.
 		 */
 		if (xfs_extent_busy_search(pag_group(pag), fbno, flen)) {
-			trace_xfs_discard_busy(pag, fbno, flen);
+			trace_xfs_discard_busy(pag_group(pag), fbno, flen);
 			goto next_extent;
 		}
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index b07790d74d351f..5f7b461286ab67 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2475,23 +2475,26 @@ DEFINE_LOG_RECOVER_ICREATE_ITEM(xfs_log_recover_icreate_cancel);
 DEFINE_LOG_RECOVER_ICREATE_ITEM(xfs_log_recover_icreate_recover);
 
 DECLARE_EVENT_CLASS(xfs_discard_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 gbno 0x%x fsbcount 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
 		  __entry->agbno,
 		  __entry->len)
@@ -2499,9 +2502,9 @@ DECLARE_EVENT_CLASS(xfs_discard_class,
 
 #define DEFINE_DISCARD_EVENT(name) \
 DEFINE_EVENT(xfs_discard_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_DISCARD_EVENT(xfs_discard_extent);
 DEFINE_DISCARD_EVENT(xfs_discard_toosmall);
 DEFINE_DISCARD_EVENT(xfs_discard_exclude);

[PATCH 33/34] xfs: implement busy extent tracking for rtgroups

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

For rtgroups filesystems, track newly freed (rt) space through the log
until the rt EFIs have been committed to disk.  This way we ensure that
space cannot be reused until all traces of the old owner are gone.

As a fringe benefit, we now support -o discard on the realtime device.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_rtbitmap.c |   12 ++++
 fs/xfs/libxfs/xfs_rtgroup.h  |   13 ++++
 fs/xfs/xfs_extent_busy.c     |    6 ++
 fs/xfs/xfs_rtalloc.c         |  127 ++++++++++++++++++++++++++++++++++++++++--
 fs/xfs/xfs_trace.h           |   75 +++++++++++++++++++++++++
 5 files changed, 227 insertions(+), 6 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 30220bf8c3f430..4ddfb7e395b38a 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -24,6 +24,7 @@
 #include "xfs_errortag.h"
 #include "xfs_log.h"
 #include "xfs_buf_item.h"
+#include "xfs_extent_busy.h"
 
 /*
  * Realtime allocator bitmap functions shared with userspace.
@@ -1120,6 +1121,7 @@ xfs_rtfree_blocks(
 {
 	struct xfs_mount	*mp = tp->t_mountp;
 	xfs_extlen_t		mod;
+	int			error;
 
 	ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN);
 
@@ -1135,8 +1137,16 @@ xfs_rtfree_blocks(
 		return -EIO;
 	}
 
-	return xfs_rtfree_extent(tp, rtg, xfs_rtb_to_rtx(mp, rtbno),
+	error = xfs_rtfree_extent(tp, rtg, xfs_rtb_to_rtx(mp, rtbno),
 			xfs_extlen_to_rtxlen(mp, rtlen));
+	if (error)
+		return error;
+
+	if (xfs_has_rtgroups(mp))
+		xfs_extent_busy_insert(tp, rtg_group(rtg),
+				xfs_rtb_to_rgbno(mp, rtbno), rtlen, 0);
+
+	return 0;
 }
 
 /* Find all the free records within a given range. */
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 1e51dc62d1143e..7e7e491ff06fa5 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -155,6 +155,19 @@ xfs_rtbno_is_group_start(
 	return (rtbno & mp->m_groups[XG_TYPE_RTG].blkmask) == 0;
 }
 
+/* Convert an rtgroups rt extent number into an rgbno. */
+static inline xfs_rgblock_t
+xfs_rtx_to_rgbno(
+	struct xfs_rtgroup	*rtg,
+	xfs_rtxnum_t		rtx)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	if (likely(mp->m_rtxblklog >= 0))
+		return rtx << mp->m_rtxblklog;
+	return rtx * mp->m_sb.sb_rextsize;
+}
+
 static inline xfs_daddr_t
 xfs_rtb_to_daddr(
 	struct xfs_mount	*mp,
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 457a27ab837599..ea43c9a6e54c12 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -18,6 +18,7 @@
 #include "xfs_trans.h"
 #include "xfs_log.h"
 #include "xfs_ag.h"
+#include "xfs_rtgroup.h"
 
 struct xfs_extent_busy_tree {
 	spinlock_t		eb_lock;
@@ -665,9 +666,14 @@ xfs_extent_busy_wait_all(
 	struct xfs_mount	*mp)
 {
 	struct xfs_perag	*pag = NULL;
+	struct xfs_rtgroup	*rtg = NULL;
 
 	while ((pag = xfs_perag_next(mp, pag)))
 		xfs_extent_busy_wait_group(pag_group(pag));
+
+	if (xfs_has_rtgroups(mp))
+		while ((rtg = xfs_rtgroup_next(mp, rtg)))
+			xfs_extent_busy_wait_group(rtg_group(rtg));
 }
 
 /*
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 8520d72afac0d9..7ecea7623a151a 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -29,6 +29,7 @@
 #include "xfs_metafile.h"
 #include "xfs_rtgroup.h"
 #include "xfs_error.h"
+#include "xfs_trace.h"
 
 /*
  * Return whether there are any free extents in the size range given
@@ -1659,6 +1660,114 @@ xfs_rtalloc_align_minmax(
 	*raminlen = newminlen;
 }
 
+/* Given a free extent, find any part of it that isn't busy, if possible. */
+STATIC bool
+xfs_rtalloc_check_busy(
+	struct xfs_rtalloc_args	*args,
+	xfs_rtxnum_t		start,
+	xfs_rtxlen_t		minlen_rtx,
+	xfs_rtxlen_t		maxlen_rtx,
+	xfs_rtxlen_t		len_rtx,
+	xfs_rtxlen_t		prod,
+	xfs_rtxnum_t		rtx,
+	xfs_rtxlen_t		*reslen,
+	xfs_rtxnum_t		*resrtx,
+	unsigned		*busy_gen)
+{
+	struct xfs_rtgroup	*rtg = args->rtg;
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	xfs_agblock_t		rgbno = xfs_rtx_to_rgbno(rtg, rtx);
+	xfs_rgblock_t		min_rgbno = xfs_rtx_to_rgbno(rtg, start);
+	xfs_extlen_t		minlen = xfs_rtxlen_to_extlen(mp, minlen_rtx);
+	xfs_extlen_t		len = xfs_rtxlen_to_extlen(mp, len_rtx);
+	xfs_extlen_t		diff;
+	bool			busy;
+
+	busy = xfs_extent_busy_trim(rtg_group(rtg), minlen,
+			xfs_rtxlen_to_extlen(mp, maxlen_rtx), &rgbno, &len,
+			busy_gen);
+
+	/*
+	 * If we have a largish extent that happens to start before min_rgbno,
+	 * see if we can shift it into range...
+	 */
+	if (rgbno < min_rgbno && rgbno + len > min_rgbno) {
+		diff = min_rgbno - rgbno;
+		if (len > diff) {
+			rgbno += diff;
+			len -= diff;
+		}
+	}
+
+	if (prod > 1 && len >= minlen) {
+		xfs_rgblock_t	aligned_rgbno = roundup(rgbno, prod);
+
+		diff = aligned_rgbno - rgbno;
+
+		*resrtx = xfs_rgbno_to_rtx(mp, aligned_rgbno);
+		*reslen = xfs_extlen_to_rtxlen(mp,
+				diff >= len ? 0 : len - diff);
+	} else {
+		*resrtx = xfs_rgbno_to_rtx(mp, rgbno);
+		*reslen = xfs_extlen_to_rtxlen(mp, len);
+	}
+
+	return busy;
+}
+
+/*
+ * Adjust the given free extent so that it isn't busy, or flush the log and
+ * wait for the space to become unbusy.  Only needed for rtgroups.
+ */
+STATIC int
+xfs_rtallocate_adjust_for_busy(
+	struct xfs_rtalloc_args	*args,
+	xfs_rtxnum_t		start,
+	xfs_rtxlen_t		minlen,
+	xfs_rtxlen_t		maxlen,
+	xfs_rtxlen_t		*len,
+	xfs_rtxlen_t		prod,
+	xfs_rtxnum_t		*rtx)
+{
+	xfs_rtxnum_t		resrtx;
+	xfs_rtxlen_t		reslen;
+	unsigned		busy_gen;
+	bool			busy;
+	int			error;
+
+again:
+	busy = xfs_rtalloc_check_busy(args, start, minlen, maxlen, *len, prod,
+			*rtx, &reslen, &resrtx, &busy_gen);
+	if (!busy)
+		return 0;
+
+	if (reslen < minlen || (start != 0 && resrtx != *rtx)) {
+		/*
+		 * Enough of the extent was busy that we cannot satisfy the
+		 * allocation, or this is a near allocation and the start of
+		 * the extent is busy.  Flush the log and wait for the busy
+		 * situation to resolve.
+		 */
+		trace_xfs_rtalloc_extent_busy(args->rtg, start, minlen, maxlen,
+				*len, prod, *rtx, busy_gen);
+
+		error = xfs_extent_busy_flush(args->tp, rtg_group(args->rtg),
+				busy_gen, 0);
+		if (error)
+			return error;
+
+		goto again;
+	}
+
+	/* Some of the free space wasn't busy, hand that back to the caller. */
+	trace_xfs_rtalloc_extent_busy_trim(args->rtg, *rtx, *len, resrtx,
+			reslen);
+	*len = reslen;
+	*rtx = resrtx;
+
+	return 0;
+}
+
 static int
 xfs_rtallocate_rtg(
 	struct xfs_trans	*tp,
@@ -1740,15 +1849,19 @@ xfs_rtallocate_rtg(
 	}
 
 	if (error) {
-		if (xfs_has_rtgroups(args.mp)) {
-			xfs_rtgroup_unlock(args.rtg, XFS_RTGLOCK_BITMAP);
-			*rtlocked = false;
-		}
+		if (xfs_has_rtgroups(args.mp))
+			goto out_unlock;
 		goto out_release;
 	}
 
-	if (xfs_has_rtgroups(args.mp))
+	if (xfs_has_rtgroups(args.mp)) {
+		error = xfs_rtallocate_adjust_for_busy(&args, start, minlen,
+				maxlen, &len, prod, &rtx);
+		if (error)
+			goto out_unlock;
+
 		xfs_rtgroup_trans_join(tp, args.rtg, XFS_RTGLOCK_BITMAP);
+	}
 
 	error = xfs_rtallocate_range(&args, rtx, len);
 	if (error)
@@ -1764,6 +1877,10 @@ xfs_rtallocate_rtg(
 	xfs_rtgroup_rele(args.rtg);
 	xfs_rtbuf_cache_relse(&args);
 	return error;
+out_unlock:
+	xfs_rtgroup_unlock(args.rtg, XFS_RTGLOCK_BITMAP);
+	*rtlocked = false;
+	goto out_release;
 }
 
 static int
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 5f7b461286ab67..d81b5b69a6f3b8 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -97,6 +97,7 @@ struct xfs_extent_free_item;
 struct xfs_rmap_intent;
 struct xfs_refcount_intent;
 struct xfs_metadir_update;
+struct xfs_rtgroup;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
@@ -1744,6 +1745,80 @@ TRACE_EVENT(xfs_extent_busy_trim,
 		  __entry->tlen)
 );
 
+#ifdef CONFIG_XFS_RT
+TRACE_EVENT(xfs_rtalloc_extent_busy,
+	TP_PROTO(struct xfs_rtgroup *rtg, xfs_rtxnum_t start,
+		 xfs_rtxlen_t minlen, xfs_rtxlen_t maxlen,
+		 xfs_rtxlen_t len, xfs_rtxlen_t prod, xfs_rtxnum_t rtx,
+		 unsigned busy_gen),
+	TP_ARGS(rtg, start, minlen, maxlen, len, prod, rtx, busy_gen),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rtxnum_t, start)
+		__field(xfs_rtxlen_t, minlen)
+		__field(xfs_rtxlen_t, maxlen)
+		__field(xfs_rtxlen_t, mod)
+		__field(xfs_rtxlen_t, prod)
+		__field(xfs_rtxlen_t, len)
+		__field(xfs_rtxnum_t, rtx)
+		__field(unsigned, busy_gen)
+	),
+	TP_fast_assign(
+		__entry->dev = rtg_mount(rtg)->m_super->s_dev;
+		__entry->rgno = rtg_rgno(rtg);
+		__entry->start = start;
+		__entry->minlen = minlen;
+		__entry->maxlen = maxlen;
+		__entry->prod = prod;
+		__entry->len = len;
+		__entry->rtx = rtx;
+		__entry->busy_gen = busy_gen;
+	),
+	TP_printk("dev %d:%d rgno 0x%x startrtx 0x%llx minlen %u maxlen %u "
+		  "prod %u len %u rtx 0%llx busy_gen 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->start,
+		  __entry->minlen,
+		  __entry->maxlen,
+		  __entry->prod,
+		  __entry->len,
+		  __entry->rtx,
+		  __entry->busy_gen)
+)
+
+TRACE_EVENT(xfs_rtalloc_extent_busy_trim,
+	TP_PROTO(struct xfs_rtgroup *rtg, xfs_rtxnum_t old_rtx,
+		 xfs_rtxlen_t old_len, xfs_rtxnum_t new_rtx,
+		 xfs_rtxlen_t new_len),
+	TP_ARGS(rtg, old_rtx, old_len, new_rtx, new_len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rtxnum_t, old_rtx)
+		__field(xfs_rtxnum_t, new_rtx)
+		__field(xfs_rtxlen_t, old_len)
+		__field(xfs_rtxlen_t, new_len)
+	),
+	TP_fast_assign(
+		__entry->dev = rtg_mount(rtg)->m_super->s_dev;
+		__entry->rgno = rtg_rgno(rtg);
+		__entry->old_rtx = old_rtx;
+		__entry->old_len = old_len;
+		__entry->new_rtx = new_rtx;
+		__entry->new_len = new_len;
+	),
+	TP_printk("dev %d:%d rgno 0x%x rtx 0x%llx rtxcount 0x%x -> rtx 0x%llx rtxcount 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->old_rtx,
+		  __entry->old_len,
+		  __entry->new_rtx,
+		  __entry->new_len)
+);
+#endif /* CONFIG_XFS_RT */
+
 DECLARE_EVENT_CLASS(xfs_agf_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags,
 		 unsigned long caller_ip),

[PATCH 34/34] xfs: use rtgroup busy extent list for FITRIM

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

For filesystems that have rtgroups and hence use the busy extent list
for freed rt space, use that busy extent list so that FITRIM can issue
discard commands asynchronously without worrying about other callers
accidentally allocating and using space that is being discarded.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_discard.c |  146 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 144 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index b7c1e09e9afefc..c4bd145f5ec1bf 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -73,6 +73,8 @@
  * extent search so that it overlaps in flight discard IO.
  */
 
+#define XFS_DISCARD_MAX_EXAMINE	(100)
+
 struct workqueue_struct *xfs_discard_wq;
 
 static void
@@ -185,7 +187,7 @@ xfs_trim_gather_extents(
 	struct xfs_buf		*agbp;
 	int			error;
 	int			i;
-	int			batch = 100;
+	int			batch = XFS_DISCARD_MAX_EXAMINE;
 
 	/*
 	 * Force out the log.  This means any transactions that might have freed
@@ -565,6 +567,7 @@ xfs_trim_gather_rtextent(
 	return 0;
 }
 
+/* Trim extents on an !rtgroups realtime device */
 static int
 xfs_trim_rtextents(
 	struct xfs_rtgroup	*rtg,
@@ -619,6 +622,140 @@ xfs_trim_rtextents(
 	return error;
 }
 
+struct xfs_trim_rtgroup {
+	/* list of rtgroup extents to free */
+	struct xfs_busy_extents	*extents;
+
+	/* minimum length that caller allows us to trim */
+	xfs_rtblock_t		minlen_fsb;
+
+	/* restart point for the rtbitmap walk */
+	xfs_rtxnum_t		restart_rtx;
+
+	/* number of extents to examine before stopping to issue discard ios */
+	int			batch;
+
+	/* number of extents queued for discard */
+	int			queued;
+};
+
+static int
+xfs_trim_gather_rtgroup_extent(
+	struct xfs_rtgroup		*rtg,
+	struct xfs_trans		*tp,
+	const struct xfs_rtalloc_rec	*rec,
+	void				*priv)
+{
+	struct xfs_trim_rtgroup		*tr = priv;
+	xfs_rgblock_t			rgbno;
+	xfs_extlen_t			len;
+
+	if (--tr->batch <= 0) {
+		/*
+		 * If we've checked a large number of extents, update the
+		 * cursor to point at this extent so we restart the next batch
+		 * from this extent.
+		 */
+		tr->restart_rtx = rec->ar_startext;
+		return -ECANCELED;
+	}
+
+	rgbno = xfs_rtx_to_rgbno(rtg, rec->ar_startext);
+	len = xfs_rtxlen_to_extlen(rtg_mount(rtg), rec->ar_extcount);
+
+	/* Ignore too small. */
+	if (len < tr->minlen_fsb) {
+		trace_xfs_discard_toosmall(rtg_group(rtg), rgbno, len);
+		return 0;
+	}
+
+	/*
+	 * If any blocks in the range are still busy, skip the discard and try
+	 * again the next time.
+	 */
+	if (xfs_extent_busy_search(rtg_group(rtg), rgbno, len)) {
+		trace_xfs_discard_busy(rtg_group(rtg), rgbno, len);
+		return 0;
+	}
+
+	xfs_extent_busy_insert_discard(rtg_group(rtg), rgbno, len,
+			&tr->extents->extent_list);
+
+	tr->queued++;
+	tr->restart_rtx = rec->ar_startext + rec->ar_extcount;
+	return 0;
+}
+
+/* Trim extents in this rtgroup using the busy extent machinery. */
+static int
+xfs_trim_rtgroup_extents(
+	struct xfs_rtgroup	*rtg,
+	xfs_rtxnum_t		low,
+	xfs_rtxnum_t		high,
+	xfs_daddr_t		minlen)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_trim_rtgroup	tr = {
+		.minlen_fsb	= XFS_BB_TO_FSB(mp, minlen),
+	};
+	struct xfs_trans	*tp;
+	int			error;
+
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	/*
+	 * Walk the free ranges between low and high.  The query_range function
+	 * trims the extents returned.
+	 */
+	do {
+		tr.extents = kzalloc(sizeof(*tr.extents), GFP_KERNEL);
+		if (!tr.extents) {
+			error = -ENOMEM;
+			break;
+		}
+
+		tr.queued = 0;
+		tr.batch = XFS_DISCARD_MAX_EXAMINE;
+		tr.extents->owner = tr.extents;
+		INIT_LIST_HEAD(&tr.extents->extent_list);
+
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+		error = xfs_rtalloc_query_range(rtg, tp, low, high,
+				xfs_trim_gather_rtgroup_extent, &tr);
+		xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+		if (error == -ECANCELED)
+			error = 0;
+		if (error) {
+			kfree(tr.extents);
+			break;
+		}
+
+		if (!tr.queued)
+			break;
+
+		/*
+		 * We hand the extent list to the discard function here so the
+		 * discarded extents can be removed from the busy extent list.
+		 * This allows the discards to run asynchronously with
+		 * gathering the next round of extents to discard.
+		 *
+		 * However, we must ensure that we do not reference the extent
+		 * list  after this function call, as it may have been freed by
+		 * the time control returns to us.
+		 */
+		error = xfs_discard_extents(rtg_mount(rtg), tr.extents);
+		if (error)
+			break;
+
+		low = tr.restart_rtx;
+	} while (!xfs_trim_should_stop() && low <= high);
+
+	xfs_trans_cancel(tp);
+	return error;
+}
+
 static int
 xfs_trim_rtdev_extents(
 	struct xfs_mount	*mp,
@@ -657,7 +794,12 @@ xfs_trim_rtdev_extents(
 		if (rtg_rgno(rtg) == end_rgno)
 			rtg_end = min(rtg_end, end_rtx);
 
-		error = xfs_trim_rtextents(rtg, start_rtx, rtg_end, minlen);
+		if (xfs_has_rtgroups(mp))
+			error = xfs_trim_rtgroup_extents(rtg, start_rtx,
+					rtg_end, minlen);
+		else
+			error = xfs_trim_rtextents(rtg, start_rtx, rtg_end,
+					minlen);
 		if (error)
 			last_error = error;
 

[PATCH 1/4] xfs: refactor xfs_qm_destroy_quotainos

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Reuse this function instead of open-coding the logic.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_qm.c |   53 ++++++++++++++++++++---------------------------------
 1 file changed, 20 insertions(+), 33 deletions(-)


diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 28b1420bac1dd2..b37e80fe7e86a6 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -40,7 +40,6 @@
 STATIC int	xfs_qm_init_quotainos(struct xfs_mount *mp);
 STATIC int	xfs_qm_init_quotainfo(struct xfs_mount *mp);
 
-STATIC void	xfs_qm_destroy_quotainos(struct xfs_quotainfo *qi);
 STATIC void	xfs_qm_dqfree_one(struct xfs_dquot *dqp);
 /*
  * We use the batch lookup interface to iterate over the dquots as it
@@ -226,6 +225,24 @@ xfs_qm_unmount_rt(
 	xfs_rtgroup_rele(rtg);
 }
 
+STATIC void
+xfs_qm_destroy_quotainos(
+	struct xfs_quotainfo	*qi)
+{
+	if (qi->qi_uquotaip) {
+		xfs_irele(qi->qi_uquotaip);
+		qi->qi_uquotaip = NULL; /* paranoia */
+	}
+	if (qi->qi_gquotaip) {
+		xfs_irele(qi->qi_gquotaip);
+		qi->qi_gquotaip = NULL;
+	}
+	if (qi->qi_pquotaip) {
+		xfs_irele(qi->qi_pquotaip);
+		qi->qi_pquotaip = NULL;
+	}
+}
+
 /*
  * Called from the vfsops layer.
  */
@@ -250,20 +267,8 @@ xfs_qm_unmount_quotas(
 	/*
 	 * Release the quota inodes.
 	 */
-	if (mp->m_quotainfo) {
-		if (mp->m_quotainfo->qi_uquotaip) {
-			xfs_irele(mp->m_quotainfo->qi_uquotaip);
-			mp->m_quotainfo->qi_uquotaip = NULL;
-		}
-		if (mp->m_quotainfo->qi_gquotaip) {
-			xfs_irele(mp->m_quotainfo->qi_gquotaip);
-			mp->m_quotainfo->qi_gquotaip = NULL;
-		}
-		if (mp->m_quotainfo->qi_pquotaip) {
-			xfs_irele(mp->m_quotainfo->qi_pquotaip);
-			mp->m_quotainfo->qi_pquotaip = NULL;
-		}
-	}
+	if (mp->m_quotainfo)
+		xfs_qm_destroy_quotainos(mp->m_quotainfo);
 }
 
 STATIC int
@@ -1712,24 +1717,6 @@ xfs_qm_init_quotainos(
 	return error;
 }
 
-STATIC void
-xfs_qm_destroy_quotainos(
-	struct xfs_quotainfo	*qi)
-{
-	if (qi->qi_uquotaip) {
-		xfs_irele(qi->qi_uquotaip);
-		qi->qi_uquotaip = NULL; /* paranoia */
-	}
-	if (qi->qi_gquotaip) {
-		xfs_irele(qi->qi_gquotaip);
-		qi->qi_gquotaip = NULL;
-	}
-	if (qi->qi_pquotaip) {
-		xfs_irele(qi->qi_pquotaip);
-		qi->qi_pquotaip = NULL;
-	}
-}
-
 STATIC void
 xfs_qm_dqfree_one(
 	struct xfs_dquot	*dqp)

[PATCH 2/4] xfs: use metadir for quota inodes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Store the quota inodes in the /quota metadata directory if metadir is
enabled.  This enables us to stop using the sb_[ugp]uotino fields in the
superblock.  From this point on, all metadata files will be children of
the metadata directory tree root.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_dquot_buf.c  |  190 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_quota_defs.h |   43 +++++++++
 fs/xfs/libxfs/xfs_sb.c         |    1 
 fs/xfs/xfs_qm.c                |  197 +++++++++++++++++++++++++++++++++++-----
 4 files changed, 407 insertions(+), 24 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 15a362e2f5ea70..dceef2abd4e2a3 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -16,6 +16,9 @@
 #include "xfs_trans.h"
 #include "xfs_qm.h"
 #include "xfs_error.h"
+#include "xfs_health.h"
+#include "xfs_metadir.h"
+#include "xfs_metafile.h"
 
 int
 xfs_calc_dquots_per_chunk(
@@ -323,3 +326,190 @@ xfs_dquot_to_disk_ts(
 
 	return cpu_to_be32(t);
 }
+
+inline unsigned int
+xfs_dqinode_sick_mask(xfs_dqtype_t type)
+{
+	switch (type) {
+	case XFS_DQTYPE_USER:
+		return XFS_SICK_FS_UQUOTA;
+	case XFS_DQTYPE_GROUP:
+		return XFS_SICK_FS_GQUOTA;
+	case XFS_DQTYPE_PROJ:
+		return XFS_SICK_FS_PQUOTA;
+	}
+
+	ASSERT(0);
+	return 0;
+}
+
+/*
+ * Load the inode for a given type of quota, assuming that the sb fields have
+ * been sorted out.  This is not true when switching quota types on a V4
+ * filesystem, so do not use this function for that.  If metadir is enabled,
+ * @dp must be the /quota metadir.
+ *
+ * Returns -ENOENT if the quota inode field is NULLFSINO; 0 and an inode on
+ * success; or a negative errno.
+ */
+int
+xfs_dqinode_load(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	xfs_dqtype_t		type,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_inode	*ip;
+	enum xfs_metafile_type	metafile_type = xfs_dqinode_metafile_type(type);
+	int			error;
+
+	if (!xfs_has_metadir(mp)) {
+		xfs_ino_t	ino;
+
+		switch (type) {
+		case XFS_DQTYPE_USER:
+			ino = mp->m_sb.sb_uquotino;
+			break;
+		case XFS_DQTYPE_GROUP:
+			ino = mp->m_sb.sb_gquotino;
+			break;
+		case XFS_DQTYPE_PROJ:
+			ino = mp->m_sb.sb_pquotino;
+			break;
+		default:
+			ASSERT(0);
+			return -EFSCORRUPTED;
+		}
+
+		/* Should have set 0 to NULLFSINO when loading superblock */
+		if (ino == NULLFSINO)
+			return -ENOENT;
+
+		error = xfs_trans_metafile_iget(tp, ino, metafile_type, &ip);
+	} else {
+		error = xfs_metadir_load(tp, dp, xfs_dqinode_path(type),
+				metafile_type, &ip);
+		if (error == -ENOENT)
+			return error;
+	}
+	if (error) {
+		if (xfs_metadata_is_sick(error))
+			xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type));
+		return error;
+	}
+
+	if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
+			       ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) {
+		xfs_irele(ip);
+		xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type));
+		return -EFSCORRUPTED;
+	}
+
+	if (XFS_IS_CORRUPT(mp, ip->i_projid != 0)) {
+		xfs_irele(ip);
+		xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type));
+		return -EFSCORRUPTED;
+	}
+
+	*ipp = ip;
+	return 0;
+}
+
+/* Create a metadata directory quota inode. */
+int
+xfs_dqinode_metadir_create(
+	struct xfs_inode		*dp,
+	xfs_dqtype_t			type,
+	struct xfs_inode		**ipp)
+{
+	struct xfs_metadir_update	upd = {
+		.dp			= dp,
+		.metafile_type		= xfs_dqinode_metafile_type(type),
+		.path			= xfs_dqinode_path(type),
+	};
+	int				error;
+
+	error = xfs_metadir_start_create(&upd);
+	if (error)
+		return error;
+
+	error = xfs_metadir_create(&upd, S_IFREG);
+	if (error)
+		return error;
+
+	xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE);
+
+	error = xfs_metadir_commit(&upd);
+	if (error)
+		return error;
+
+	xfs_finish_inode_setup(upd.ip);
+	*ipp = upd.ip;
+	return 0;
+}
+
+#ifndef __KERNEL__
+/* Link a metadata directory quota inode. */
+int
+xfs_dqinode_metadir_link(
+	struct xfs_inode		*dp,
+	xfs_dqtype_t			type,
+	struct xfs_inode		*ip)
+{
+	struct xfs_metadir_update	upd = {
+		.dp			= dp,
+		.metafile_type		= xfs_dqinode_metafile_type(type),
+		.path			= xfs_dqinode_path(type),
+		.ip			= ip,
+	};
+	int				error;
+
+	error = xfs_metadir_start_link(&upd);
+	if (error)
+		return error;
+
+	error = xfs_metadir_link(&upd);
+	if (error)
+		return error;
+
+	xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE);
+
+	return xfs_metadir_commit(&upd);
+}
+#endif /* __KERNEL__ */
+
+/* Create the parent directory for all quota inodes and load it. */
+int
+xfs_dqinode_mkdir_parent(
+	struct xfs_mount	*mp,
+	struct xfs_inode	**dpp)
+{
+	if (!mp->m_metadirip) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
+		return -EFSCORRUPTED;
+	}
+
+	return xfs_metadir_mkdir(mp->m_metadirip, "quota", dpp);
+}
+
+/*
+ * Load the parent directory of all quota inodes.  Pass the inode to the caller
+ * because quota functions (e.g. QUOTARM) can be called on the quota files even
+ * if quotas are not enabled.
+ */
+int
+xfs_dqinode_load_parent(
+	struct xfs_trans	*tp,
+	struct xfs_inode	**dpp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+
+	if (!mp->m_metadirip) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
+		return -EFSCORRUPTED;
+	}
+
+	return xfs_metadir_load(tp, mp->m_metadirip, "quota", XFS_METAFILE_DIR,
+			dpp);
+}
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index fb05f44f6c754a..763d941a8420c5 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -143,4 +143,47 @@ time64_t xfs_dquot_from_disk_ts(struct xfs_disk_dquot *ddq,
 		__be32 dtimer);
 __be32 xfs_dquot_to_disk_ts(struct xfs_dquot *ddq, time64_t timer);
 
+static inline const char *
+xfs_dqinode_path(xfs_dqtype_t type)
+{
+	switch (type) {
+	case XFS_DQTYPE_USER:
+		return "user";
+	case XFS_DQTYPE_GROUP:
+		return "group";
+	case XFS_DQTYPE_PROJ:
+		return "project";
+	}
+
+	ASSERT(0);
+	return NULL;
+}
+
+static inline enum xfs_metafile_type
+xfs_dqinode_metafile_type(xfs_dqtype_t type)
+{
+	switch (type) {
+	case XFS_DQTYPE_USER:
+		return XFS_METAFILE_USRQUOTA;
+	case XFS_DQTYPE_GROUP:
+		return XFS_METAFILE_GRPQUOTA;
+	case XFS_DQTYPE_PROJ:
+		return XFS_METAFILE_PRJQUOTA;
+	}
+
+	ASSERT(0);
+	return XFS_METAFILE_UNKNOWN;
+}
+
+unsigned int xfs_dqinode_sick_mask(xfs_dqtype_t type);
+
+int xfs_dqinode_load(struct xfs_trans *tp, struct xfs_inode *dp,
+		xfs_dqtype_t type, struct xfs_inode **ipp);
+int xfs_dqinode_metadir_create(struct xfs_inode *dp, xfs_dqtype_t type,
+		struct xfs_inode **ipp);
+int xfs_dqinode_metadir_link(struct xfs_inode *dp, xfs_dqtype_t type,
+		struct xfs_inode *ip);
+int xfs_dqinode_mkdir_parent(struct xfs_mount *mp, struct xfs_inode **dpp);
+int xfs_dqinode_load_parent(struct xfs_trans *tp, struct xfs_inode **dpp);
+
 #endif	/* __XFS_QUOTA_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 6a31f48a2c5424..30c7c5238437bc 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -844,6 +844,7 @@ xfs_sb_quota_to_disk(
 
 	if (xfs_sb_is_v5(from) &&
 	    (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
+		to->sb_qflags = cpu_to_be16(from->sb_qflags);
 		to->sb_uquotino = cpu_to_be64(0);
 		to->sb_gquotino = cpu_to_be64(0);
 		to->sb_pquotino = cpu_to_be64(0);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index b37e80fe7e86a6..d9d09195eabb0d 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -645,6 +645,157 @@ xfs_qm_init_timelimits(
 	xfs_qm_dqdestroy(dqp);
 }
 
+static int
+xfs_qm_load_metadir_qinos(
+	struct xfs_mount	*mp,
+	struct xfs_quotainfo	*qi,
+	struct xfs_inode	**dpp)
+{
+	struct xfs_trans	*tp;
+	int			error;
+
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	error = xfs_dqinode_load_parent(tp, dpp);
+	if (error == -ENOENT) {
+		/* no quota dir directory, but we'll create one later */
+		error = 0;
+		goto out_trans;
+	}
+	if (error)
+		goto out_trans;
+
+	if (XFS_IS_UQUOTA_ON(mp)) {
+		error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_USER,
+				&qi->qi_uquotaip);
+		if (error && error != -ENOENT)
+			goto out_trans;
+	}
+
+	if (XFS_IS_GQUOTA_ON(mp)) {
+		error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_GROUP,
+				&qi->qi_gquotaip);
+		if (error && error != -ENOENT)
+			goto out_trans;
+	}
+
+	if (XFS_IS_PQUOTA_ON(mp)) {
+		error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_PROJ,
+				&qi->qi_pquotaip);
+		if (error && error != -ENOENT)
+			goto out_trans;
+	}
+
+	error = 0;
+out_trans:
+	xfs_trans_cancel(tp);
+	return error;
+}
+
+/* Create quota inodes in the metadata directory tree. */
+STATIC int
+xfs_qm_create_metadir_qinos(
+	struct xfs_mount	*mp,
+	struct xfs_quotainfo	*qi,
+	struct xfs_inode	**dpp)
+{
+	int			error;
+
+	if (!*dpp) {
+		error = xfs_dqinode_mkdir_parent(mp, dpp);
+		if (error && error != -EEXIST)
+			return error;
+	}
+
+	if (XFS_IS_UQUOTA_ON(mp) && !qi->qi_uquotaip) {
+		error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_USER,
+				&qi->qi_uquotaip);
+		if (error)
+			return error;
+	}
+
+	if (XFS_IS_GQUOTA_ON(mp) && !qi->qi_gquotaip) {
+		error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_GROUP,
+				&qi->qi_gquotaip);
+		if (error)
+			return error;
+	}
+
+	if (XFS_IS_PQUOTA_ON(mp) && !qi->qi_pquotaip) {
+		error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_PROJ,
+				&qi->qi_pquotaip);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/*
+ * Add QUOTABIT to sb_versionnum and initialize qflags in preparation for
+ * creating quota files on a metadir filesystem.
+ */
+STATIC int
+xfs_qm_prep_metadir_sb(
+	struct xfs_mount	*mp)
+{
+	struct xfs_trans	*tp;
+	int			error;
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp);
+	if (error)
+		return error;
+
+	spin_lock(&mp->m_sb_lock);
+
+	xfs_add_quota(mp);
+
+	/* qflags will get updated fully _after_ quotacheck */
+	mp->m_sb.sb_qflags = mp->m_qflags & XFS_ALL_QUOTA_ACCT;
+
+	spin_unlock(&mp->m_sb_lock);
+	xfs_log_sb(tp);
+
+	return xfs_trans_commit(tp);
+}
+
+/*
+ * Load existing quota inodes or create them.  Since this is a V5 filesystem,
+ * we don't have to deal with the grp/prjquota switcheroo thing from V4.
+ */
+STATIC int
+xfs_qm_init_metadir_qinos(
+	struct xfs_mount	*mp)
+{
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	struct xfs_inode	*dp = NULL;
+	int			error;
+
+	if (!xfs_has_quota(mp)) {
+		error = xfs_qm_prep_metadir_sb(mp);
+		if (error)
+			return error;
+	}
+
+	error = xfs_qm_load_metadir_qinos(mp, qi, &dp);
+	if (error)
+		goto out_err;
+
+	error = xfs_qm_create_metadir_qinos(mp, qi, &dp);
+	if (error)
+		goto out_err;
+
+	xfs_irele(dp);
+	return 0;
+out_err:
+	xfs_qm_destroy_quotainos(mp->m_quotainfo);
+	if (dp)
+		xfs_irele(dp);
+	return error;
+}
+
 /*
  * This initializes all the quota information that's kept in the
  * mount structure
@@ -669,7 +820,10 @@ xfs_qm_init_quotainfo(
 	 * See if quotainodes are setup, and if not, allocate them,
 	 * and change the superblock accordingly.
 	 */
-	error = xfs_qm_init_quotainos(mp);
+	if (xfs_has_metadir(mp))
+		error = xfs_qm_init_metadir_qinos(mp);
+	else
+		error = xfs_qm_init_quotainos(mp);
 	if (error)
 		goto out_free_lru;
 
@@ -1581,7 +1735,7 @@ xfs_qm_mount_quotas(
 	}
 
 	if (error) {
-		xfs_warn(mp, "Failed to initialize disk quotas.");
+		xfs_warn(mp, "Failed to initialize disk quotas, err %d.", error);
 		return;
 	}
 }
@@ -1600,31 +1754,26 @@ xfs_qm_qino_load(
 	xfs_dqtype_t		type,
 	struct xfs_inode	**ipp)
 {
-	xfs_ino_t		ino = NULLFSINO;
-	enum xfs_metafile_type	metafile_type = XFS_METAFILE_UNKNOWN;
+	struct xfs_trans	*tp;
+	struct xfs_inode	*dp = NULL;
+	int			error;
 
-	switch (type) {
-	case XFS_DQTYPE_USER:
-		ino = mp->m_sb.sb_uquotino;
-		metafile_type = XFS_METAFILE_USRQUOTA;
-		break;
-	case XFS_DQTYPE_GROUP:
-		ino = mp->m_sb.sb_gquotino;
-		metafile_type = XFS_METAFILE_GRPQUOTA;
-		break;
-	case XFS_DQTYPE_PROJ:
-		ino = mp->m_sb.sb_pquotino;
-		metafile_type = XFS_METAFILE_PRJQUOTA;
-		break;
-	default:
-		ASSERT(0);
-		return -EFSCORRUPTED;
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	if (xfs_has_metadir(mp)) {
+		error = xfs_dqinode_load_parent(tp, &dp);
+		if (error)
+			goto out_cancel;
 	}
 
-	if (ino == NULLFSINO)
-		return -ENOENT;
-
-	return xfs_metafile_iget(mp, ino, metafile_type, ipp);
+	error = xfs_dqinode_load(tp, dp, type, ipp);
+	if (dp)
+		xfs_irele(dp);
+out_cancel:
+	xfs_trans_cancel(tp);
+	return error;
 }
 
 /*

[PATCH 3/4] xfs: scrub quota file metapaths

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Enable online fsck for quota file metadata directory paths.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_fs.h  |    6 +++-
 fs/xfs/scrub/metapath.c |   76 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 96f7d3c95fb4bc..41ce4d3d650ec7 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -825,9 +825,13 @@ struct xfs_scrub_vec_head {
 #define XFS_SCRUB_METAPATH_RTDIR	(1)  /* rtrgroups metadir */
 #define XFS_SCRUB_METAPATH_RTBITMAP	(2)  /* per-rtg bitmap */
 #define XFS_SCRUB_METAPATH_RTSUMMARY	(3)  /* per-rtg summary */
+#define XFS_SCRUB_METAPATH_QUOTADIR	(4)  /* quota metadir */
+#define XFS_SCRUB_METAPATH_USRQUOTA	(5)  /* user quota */
+#define XFS_SCRUB_METAPATH_GRPQUOTA	(6)  /* group quota */
+#define XFS_SCRUB_METAPATH_PRJQUOTA	(7)  /* project quota */
 
 /* Number of metapath sm_ino values */
-#define XFS_SCRUB_METAPATH_NR		(4)
+#define XFS_SCRUB_METAPATH_NR		(8)
 
 /*
  * ioctl limits
diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c
index b8e427fd7fa73e..b78db651346518 100644
--- a/fs/xfs/scrub/metapath.c
+++ b/fs/xfs/scrub/metapath.c
@@ -165,6 +165,74 @@ xchk_setup_metapath_rtginode(
 # define xchk_setup_metapath_rtginode(...)	(-ENOENT)
 #endif /* CONFIG_XFS_RT */
 
+#ifdef CONFIG_XFS_QUOTA
+/* Scan the /quota directory itself. */
+static int
+xchk_setup_metapath_quotadir(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_trans	*tp;
+	struct xfs_inode	*dp = NULL;
+	int			error;
+
+	error = xfs_trans_alloc_empty(sc->mp, &tp);
+	if (error)
+		return error;
+
+	error = xfs_dqinode_load_parent(tp, &dp);
+	xfs_trans_cancel(tp);
+	if (error)
+		return error;
+
+	error = xchk_setup_metapath_scan(sc, sc->mp->m_metadirip,
+			kasprintf(GFP_KERNEL, "quota"), dp);
+	xfs_irele(dp);
+	return error;
+}
+
+/* Scan a quota inode under the /quota directory. */
+static int
+xchk_setup_metapath_dqinode(
+	struct xfs_scrub	*sc,
+	xfs_dqtype_t		type)
+{
+	struct xfs_trans	*tp = NULL;
+	struct xfs_inode	*dp = NULL;
+	struct xfs_inode	*ip = NULL;
+	const char		*path;
+	int			error;
+
+	error = xfs_trans_alloc_empty(sc->mp, &tp);
+	if (error)
+		return error;
+
+	error = xfs_dqinode_load_parent(tp, &dp);
+	if (error)
+		goto out_cancel;
+
+	error = xfs_dqinode_load(tp, dp, type, &ip);
+	if (error)
+		goto out_dp;
+
+	xfs_trans_cancel(tp);
+	tp = NULL;
+
+	path = kasprintf(GFP_KERNEL, "%s", xfs_dqinode_path(type));
+	error = xchk_setup_metapath_scan(sc, dp, path, ip);
+
+	xfs_irele(ip);
+out_dp:
+	xfs_irele(dp);
+out_cancel:
+	if (tp)
+		xfs_trans_cancel(tp);
+	return error;
+}
+#else
+# define xchk_setup_metapath_quotadir(...)	(-ENOENT)
+# define xchk_setup_metapath_dqinode(...)	(-ENOENT)
+#endif /* CONFIG_XFS_QUOTA */
+
 int
 xchk_setup_metapath(
 	struct xfs_scrub	*sc)
@@ -186,6 +254,14 @@ xchk_setup_metapath(
 		return xchk_setup_metapath_rtginode(sc, XFS_RTGI_BITMAP);
 	case XFS_SCRUB_METAPATH_RTSUMMARY:
 		return xchk_setup_metapath_rtginode(sc, XFS_RTGI_SUMMARY);
+	case XFS_SCRUB_METAPATH_QUOTADIR:
+		return xchk_setup_metapath_quotadir(sc);
+	case XFS_SCRUB_METAPATH_USRQUOTA:
+		return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_USER);
+	case XFS_SCRUB_METAPATH_GRPQUOTA:
+		return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_GROUP);
+	case XFS_SCRUB_METAPATH_PRJQUOTA:
+		return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_PROJ);
 	default:
 		return -ENOENT;
 	}

[PATCH 4/4] xfs: persist quota flags with metadir

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

It's annoying that one has to keep reminding XFS about what quota
options it should mount with, since the quota flags recording the
previous state are sitting right there in the primary superblock.  Even
more strangely, there exists a noquota option to disable quotas
completely, so it's odder still that providing no options is the same as
noquota.

Starting with metadir, let's change the behavior so that if the user
does not specify any quota-related mount options at all, the ondisk
quota flags will be used to bring up quota.  In other words, the
filesystem will mount in the same state and with the same functionality
as it had during the last mount.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_mount.c  |   15 +++++++++++++++
 fs/xfs/xfs_mount.h  |   21 +++++++++++++++++++--
 fs/xfs/xfs_qm_bhv.c |   18 ++++++++++++++++++
 fs/xfs/xfs_quota.h  |    2 ++
 fs/xfs/xfs_super.c  |   25 ++++++++++++++++++++++++-
 5 files changed, 78 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index dba1f6fc688166..5918f433dba754 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -852,6 +852,13 @@ xfs_mountfs(
 	if (error)
 		goto out_fail_wait;
 
+	/*
+	 * If we're resuming quota status, pick up the preliminary qflags from
+	 * the ondisk superblock so that we know if we should recover dquots.
+	 */
+	if (xfs_is_resuming_quotaon(mp))
+		xfs_qm_resume_quotaon(mp);
+
 	/*
 	 * Log's mount-time initialization. The first part of recovery can place
 	 * some items on the AIL, to be handled when recovery is finished or
@@ -865,6 +872,14 @@ xfs_mountfs(
 		goto out_inodegc_shrinker;
 	}
 
+	/*
+	 * If we're resuming quota status and recovered the log, re-sample the
+	 * qflags from the ondisk superblock now that we've recovered it, just
+	 * in case someone shut down enforcement just before a crash.
+	 */
+	if (xfs_clear_resuming_quotaon(mp) && xlog_recovery_needed(mp->m_log))
+		xfs_qm_resume_quotaon(mp);
+
 	/*
 	 * If logged xattrs are still enabled after log recovery finishes, then
 	 * they'll be available until unmount.  Otherwise, turn them off.
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index ee1c3eb53d9f2b..db9dade7d22a19 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -499,6 +499,8 @@ __XFS_HAS_FEAT(nouuid, NOUUID)
 #define XFS_OPSTATE_WARNED_PPTR		16
 /* Kernel has logged a warning about metadata dirs being used on this fs. */
 #define XFS_OPSTATE_WARNED_METADIR	17
+/* Filesystem should use qflags to determine quotaon status */
+#define XFS_OPSTATE_RESUMING_QUOTAON	18
 
 #define __XFS_IS_OPSTATE(name, NAME) \
 static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
@@ -523,9 +525,24 @@ __XFS_IS_OPSTATE(inodegc_enabled, INODEGC_ENABLED)
 __XFS_IS_OPSTATE(blockgc_enabled, BLOCKGC_ENABLED)
 #ifdef CONFIG_XFS_QUOTA
 __XFS_IS_OPSTATE(quotacheck_running, QUOTACHECK_RUNNING)
+__XFS_IS_OPSTATE(resuming_quotaon, RESUMING_QUOTAON)
 #else
-# define xfs_is_quotacheck_running(mp)	(false)
-#endif
+static inline bool xfs_is_quotacheck_running(struct xfs_mount *mp)
+{
+	return false;
+}
+static inline bool xfs_is_resuming_quotaon(struct xfs_mount *mp)
+{
+	return false;
+}
+static inline void xfs_set_resuming_quotaon(struct xfs_mount *m)
+{
+}
+static inline bool xfs_clear_resuming_quotaon(struct xfs_mount *mp)
+{
+	return false;
+}
+#endif /* CONFIG_XFS_QUOTA */
 __XFS_IS_OPSTATE(done_with_log_incompat, UNSET_LOG_INCOMPAT)
 __XFS_IS_OPSTATE(using_logged_xattrs, USE_LARP)
 
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index a11436579877d5..79a96558f739e3 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -135,3 +135,21 @@ xfs_qm_newmount(
 
 	return 0;
 }
+
+/*
+ * If the sysadmin didn't provide any quota mount options, restore the quota
+ * accounting and enforcement state from the ondisk superblock.  Only do this
+ * for metadir filesystems because this is a behavior change.
+ */
+void
+xfs_qm_resume_quotaon(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_has_metadir(mp))
+		return;
+	if (xfs_has_norecovery(mp))
+		return;
+
+	mp->m_qflags = mp->m_sb.sb_qflags & (XFS_ALL_QUOTA_ACCT |
+					     XFS_ALL_QUOTA_ENFD);
+}
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index 645761997bf2d9..2d36d967380e7c 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -125,6 +125,7 @@ extern void xfs_qm_dqdetach(struct xfs_inode *);
 extern void xfs_qm_dqrele(struct xfs_dquot *);
 extern void xfs_qm_statvfs(struct xfs_inode *, struct kstatfs *);
 extern int xfs_qm_newmount(struct xfs_mount *, uint *, uint *);
+void xfs_qm_resume_quotaon(struct xfs_mount *mp);
 extern void xfs_qm_mount_quotas(struct xfs_mount *);
 extern void xfs_qm_unmount(struct xfs_mount *);
 extern void xfs_qm_unmount_quotas(struct xfs_mount *);
@@ -202,6 +203,7 @@ xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, struct xfs_dquot *udqp,
 #define xfs_qm_dqrele(d)			do { (d) = (d); } while(0)
 #define xfs_qm_statvfs(ip, s)			do { } while(0)
 #define xfs_qm_newmount(mp, a, b)					(0)
+#define xfs_qm_resume_quotaon(mp)		((void)0)
 #define xfs_qm_mount_quotas(mp)
 #define xfs_qm_unmount(mp)
 #define xfs_qm_unmount_quotas(mp)
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 3afeab6844680a..20fde2442768c4 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -67,6 +67,9 @@ enum xfs_dax_mode {
 	XFS_DAX_NEVER = 2,
 };
 
+/* Were quota mount options provided?  Must use the upper 16 bits of qflags. */
+#define XFS_QFLAGS_MNTOPTS	(1U << 31)
+
 static void
 xfs_mount_set_dax_mode(
 	struct xfs_mount	*mp,
@@ -1264,6 +1267,8 @@ xfs_fs_parse_param(
 	int			size = 0;
 	int			opt;
 
+	BUILD_BUG_ON(XFS_QFLAGS_MNTOPTS & XFS_MOUNT_QUOTA_ALL);
+
 	opt = fs_parse(fc, xfs_fs_parameters, param, &result);
 	if (opt < 0)
 		return opt;
@@ -1341,32 +1346,39 @@ xfs_fs_parse_param(
 	case Opt_noquota:
 		parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
 		parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
+		parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS;
 		return 0;
 	case Opt_quota:
 	case Opt_uquota:
 	case Opt_usrquota:
 		parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ENFD);
+		parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS;
 		return 0;
 	case Opt_qnoenforce:
 	case Opt_uqnoenforce:
 		parsing_mp->m_qflags |= XFS_UQUOTA_ACCT;
 		parsing_mp->m_qflags &= ~XFS_UQUOTA_ENFD;
+		parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS;
 		return 0;
 	case Opt_pquota:
 	case Opt_prjquota:
 		parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ENFD);
+		parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS;
 		return 0;
 	case Opt_pqnoenforce:
 		parsing_mp->m_qflags |= XFS_PQUOTA_ACCT;
 		parsing_mp->m_qflags &= ~XFS_PQUOTA_ENFD;
+		parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS;
 		return 0;
 	case Opt_gquota:
 	case Opt_grpquota:
 		parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ENFD);
+		parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS;
 		return 0;
 	case Opt_gqnoenforce:
 		parsing_mp->m_qflags |= XFS_GQUOTA_ACCT;
 		parsing_mp->m_qflags &= ~XFS_GQUOTA_ENFD;
+		parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS;
 		return 0;
 	case Opt_discard:
 		parsing_mp->m_features |= XFS_FEAT_DISCARD;
@@ -1433,7 +1445,8 @@ xfs_fs_validate_params(
 		return -EINVAL;
 	}
 
-	if (!IS_ENABLED(CONFIG_XFS_QUOTA) && mp->m_qflags != 0) {
+	if (!IS_ENABLED(CONFIG_XFS_QUOTA) &&
+	    (mp->m_qflags & ~XFS_QFLAGS_MNTOPTS)) {
 		xfs_warn(mp, "quota support not available in this kernel.");
 		return -EINVAL;
 	}
@@ -1768,6 +1781,14 @@ xfs_fs_fill_super(
 	if (xfs_has_parent(mp))
 		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_PPTR);
 
+	/*
+	 * If no quota mount options were provided, maybe we'll try to pick
+	 * up the quota accounting and enforcement flags from the ondisk sb.
+	 */
+	if (!(mp->m_qflags & XFS_QFLAGS_MNTOPTS))
+		xfs_set_resuming_quotaon(mp);
+	mp->m_qflags &= ~XFS_QFLAGS_MNTOPTS;
+
 	error = xfs_mountfs(mp);
 	if (error)
 		goto out_filestream_unmount;
@@ -1954,6 +1975,8 @@ xfs_fs_reconfigure(
 	int			flags = fc->sb_flags;
 	int			error;
 
+	new_mp->m_qflags &= ~XFS_QFLAGS_MNTOPTS;
+
 	/* version 5 superblocks always support version counters. */
 	if (xfs_has_crc(mp))
 		fc->sb_flags |= SB_I_VERSION;

[PATCH 1/6] xfs: fix chown with rt quota

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Make chown's quota adjustments work with realtime files.  This is mostly
a matter of calling xfs_inode_count_blocks on a given file to figure out
the number of blocks allocated to the data device and to the realtime
device, and using those quantities to update the quota accounting when
the id changes.  Delayed allocation reservations are moved from the old
dquot's incore reservation to the new dquot's incore reservation.

Note that there was a missing ILOCK bug in xfs_qm_dqusage_adjust that we
must fix before calling xfs_iread_extents.  Prior to 2.6.37 the locking
was correct, but then someone removed the ILOCK as part of a cleanup.
Nobody noticed because nowhere in the git history have we ever supported
rt+quota so nobody can use this.

I'm leaving git breadcrumbs in case anyone is desperate enough to try to
backport the rtquota code to old kernels.

Not-Cc: <stable@vger.kernel.org> # v2.6.37
Fixes: 52fda114249578 ("xfs: simplify xfs_qm_dqusage_adjust")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_qm.c    |   44 +++++++++++++++++++++++++++-----------------
 fs/xfs/xfs_trans.c |   31 +++++++++++++++++++++++++++++--
 2 files changed, 56 insertions(+), 19 deletions(-)


diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index d9d09195eabb0d..1c7d861dfbeceb 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1351,8 +1351,8 @@ xfs_qm_dqusage_adjust(
 	void			*data)
 {
 	struct xfs_inode	*ip;
-	xfs_qcnt_t		nblks;
-	xfs_filblks_t		rtblks = 0;	/* total rt blks */
+	xfs_filblks_t		nblks, rtblks;
+	unsigned int		lock_mode;
 	int			error;
 
 	ASSERT(XFS_IS_QUOTA_ON(mp));
@@ -1393,18 +1393,17 @@ xfs_qm_dqusage_adjust(
 
 	ASSERT(ip->i_delayed_blks == 0);
 
+	lock_mode = xfs_ilock_data_map_shared(ip);
 	if (XFS_IS_REALTIME_INODE(ip)) {
-		struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
-
 		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
-		if (error)
+		if (error) {
+			xfs_iunlock(ip, lock_mode);
 			goto error0;
-
-		xfs_bmap_count_leaves(ifp, &rtblks);
+		}
 	}
-
-	nblks = (xfs_qcnt_t)ip->i_nblocks - rtblks;
+	xfs_inode_count_blocks(tp, ip, &nblks, &rtblks);
 	xfs_iflags_clear(ip, XFS_IQUOTAUNCHECKED);
+	xfs_iunlock(ip, lock_mode);
 
 	/*
 	 * Add the (disk blocks and inode) resources occupied by this
@@ -2043,9 +2042,8 @@ xfs_qm_vop_chown(
 	struct xfs_dquot	*newdq)
 {
 	struct xfs_dquot	*prevdq;
-	uint		bfield = XFS_IS_REALTIME_INODE(ip) ?
-				 XFS_TRANS_DQ_RTBCOUNT : XFS_TRANS_DQ_BCOUNT;
-
+	xfs_filblks_t		dblocks, rblocks;
+	bool			isrt = XFS_IS_REALTIME_INODE(ip);
 
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
 	ASSERT(XFS_IS_QUOTA_ON(ip->i_mount));
@@ -2056,11 +2054,17 @@ xfs_qm_vop_chown(
 	ASSERT(prevdq);
 	ASSERT(prevdq != newdq);
 
-	xfs_trans_mod_ino_dquot(tp, ip, prevdq, bfield, -(ip->i_nblocks));
+	xfs_inode_count_blocks(tp, ip, &dblocks, &rblocks);
+
+	xfs_trans_mod_ino_dquot(tp, ip, prevdq, XFS_TRANS_DQ_BCOUNT,
+			-(xfs_qcnt_t)dblocks);
+	xfs_trans_mod_ino_dquot(tp, ip, prevdq, XFS_TRANS_DQ_RTBCOUNT,
+			-(xfs_qcnt_t)rblocks);
 	xfs_trans_mod_ino_dquot(tp, ip, prevdq, XFS_TRANS_DQ_ICOUNT, -1);
 
 	/* the sparkling new dquot */
-	xfs_trans_mod_ino_dquot(tp, ip, newdq, bfield, ip->i_nblocks);
+	xfs_trans_mod_ino_dquot(tp, ip, newdq, XFS_TRANS_DQ_BCOUNT, dblocks);
+	xfs_trans_mod_ino_dquot(tp, ip, newdq, XFS_TRANS_DQ_RTBCOUNT, rblocks);
 	xfs_trans_mod_ino_dquot(tp, ip, newdq, XFS_TRANS_DQ_ICOUNT, 1);
 
 	/*
@@ -2070,7 +2074,8 @@ xfs_qm_vop_chown(
 	 * (having already bumped up the real counter) so that we don't have
 	 * any reservation to give back when we commit.
 	 */
-	xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_RES_BLKS,
+	xfs_trans_mod_dquot(tp, newdq,
+			isrt ? XFS_TRANS_DQ_RES_RTBLKS : XFS_TRANS_DQ_RES_BLKS,
 			-ip->i_delayed_blks);
 
 	/*
@@ -2082,8 +2087,13 @@ xfs_qm_vop_chown(
 	 */
 	tp->t_flags |= XFS_TRANS_DIRTY;
 	xfs_dqlock(prevdq);
-	ASSERT(prevdq->q_blk.reserved >= ip->i_delayed_blks);
-	prevdq->q_blk.reserved -= ip->i_delayed_blks;
+	if (isrt) {
+		ASSERT(prevdq->q_rtb.reserved >= ip->i_delayed_blks);
+		prevdq->q_rtb.reserved -= ip->i_delayed_blks;
+	} else {
+		ASSERT(prevdq->q_blk.reserved >= ip->i_delayed_blks);
+		prevdq->q_blk.reserved -= ip->i_delayed_blks;
+	}
 	xfs_dqunlock(prevdq);
 
 	/*
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 4db022c189e134..30fbed27cf05cc 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1288,11 +1288,26 @@ xfs_trans_alloc_ichange(
 	gdqp = (new_gdqp != ip->i_gdquot) ? new_gdqp : NULL;
 	pdqp = (new_pdqp != ip->i_pdquot) ? new_pdqp : NULL;
 	if (udqp || gdqp || pdqp) {
+		xfs_filblks_t	dblocks, rblocks;
 		unsigned int	qflags = XFS_QMOPT_RES_REGBLKS;
+		bool		isrt = XFS_IS_REALTIME_INODE(ip);
 
 		if (force)
 			qflags |= XFS_QMOPT_FORCE_RES;
 
+		if (isrt) {
+			error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
+			if (error)
+				goto out_cancel;
+		}
+
+		xfs_inode_count_blocks(tp, ip, &dblocks, &rblocks);
+
+		if (isrt)
+			rblocks += ip->i_delayed_blks;
+		else
+			dblocks += ip->i_delayed_blks;
+
 		/*
 		 * Reserve enough quota to handle blocks on disk and reserved
 		 * for a delayed allocation.  We'll actually transfer the
@@ -1300,8 +1315,20 @@ xfs_trans_alloc_ichange(
 		 * though that part is only semi-transactional.
 		 */
 		error = xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp,
-				pdqp, ip->i_nblocks + ip->i_delayed_blks,
-				1, qflags);
+				pdqp, dblocks, 1, qflags);
+		if ((error == -EDQUOT || error == -ENOSPC) && !retried) {
+			xfs_trans_cancel(tp);
+			xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0);
+			retried = true;
+			goto retry;
+		}
+		if (error)
+			goto out_cancel;
+
+		/* Do the same for realtime. */
+		qflags = XFS_QMOPT_RES_RTBLKS | (qflags & XFS_QMOPT_FORCE_RES);
+		error = xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp,
+				pdqp, rblocks, 0, qflags);
 		if ((error == -EDQUOT || error == -ENOSPC) && !retried) {
 			xfs_trans_cancel(tp);
 			xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0);

[PATCH 2/6] xfs: advertise realtime quota support in the xqm stat files

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a fifth column to this (really old) stat file to advertise that the
kernel supports quota for realtime volumes.  This will be used by
fstests to detect kernel support.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_stats.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index ed97d72caa6652..ffb52725c2a8e8 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -115,10 +115,11 @@ void xfs_stats_clearall(struct xfsstats __percpu *stats)
 
 static int xqm_proc_show(struct seq_file *m, void *v)
 {
-	/* maximum; incore; ratio free to inuse; freelist */
-	seq_printf(m, "%d\t%d\t%d\t%u\n",
+	/* maximum; incore; ratio free to inuse; freelist; rtquota */
+	seq_printf(m, "%d\t%d\t%d\t%u\t%s\n",
 		   0, counter_val(xfsstats.xs_stats, XFSSTAT_END_XQMSTAT),
-		   0, counter_val(xfsstats.xs_stats, XFSSTAT_END_XQMSTAT + 1));
+		   0, counter_val(xfsstats.xs_stats, XFSSTAT_END_XQMSTAT + 1),
+		   IS_ENABLED(CONFIG_XFS_RT) ? "rtquota" : "quota");
 	return 0;
 }
 

[PATCH 3/6] xfs: report realtime block quota limits on realtime directories

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

On the data device, calling statvfs on a projinherit directory results
in the block and avail counts being curtailed to the project quota block
limits, if any are set.  Do the same for realtime files or directories,
only use the project quota rt block limits.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_qm_bhv.c |   18 ++++++++++++------
 fs/xfs/xfs_super.c  |   11 +++++------
 2 files changed, 17 insertions(+), 12 deletions(-)


diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 79a96558f739e3..847ba29630e9d8 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -19,18 +19,24 @@
 STATIC void
 xfs_fill_statvfs_from_dquot(
 	struct kstatfs		*statp,
+	struct xfs_inode	*ip,
 	struct xfs_dquot	*dqp)
 {
+	struct xfs_dquot_res	*blkres = &dqp->q_blk;
 	uint64_t		limit;
 
-	limit = dqp->q_blk.softlimit ?
-		dqp->q_blk.softlimit :
-		dqp->q_blk.hardlimit;
+	if (XFS_IS_REALTIME_MOUNT(ip->i_mount) &&
+	    (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME)))
+		blkres = &dqp->q_rtb;
+
+	limit = blkres->softlimit ?
+		blkres->softlimit :
+		blkres->hardlimit;
 	if (limit && statp->f_blocks > limit) {
 		statp->f_blocks = limit;
 		statp->f_bfree = statp->f_bavail =
-			(statp->f_blocks > dqp->q_blk.reserved) ?
-			 (statp->f_blocks - dqp->q_blk.reserved) : 0;
+			(statp->f_blocks > blkres->reserved) ?
+			 (statp->f_blocks - blkres->reserved) : 0;
 	}
 
 	limit = dqp->q_ino.softlimit ?
@@ -61,7 +67,7 @@ xfs_qm_statvfs(
 	struct xfs_dquot	*dqp;
 
 	if (!xfs_qm_dqget(mp, ip->i_projid, XFS_DQTYPE_PROJ, false, &dqp)) {
-		xfs_fill_statvfs_from_dquot(statp, dqp);
+		xfs_fill_statvfs_from_dquot(statp, ip, dqp);
 		xfs_qm_dqput(dqp);
 	}
 }
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 20fde2442768c4..f8d59081950a72 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -877,12 +877,6 @@ xfs_fs_statfs(
 	ffree = statp->f_files - (icount - ifree);
 	statp->f_ffree = max_t(int64_t, ffree, 0);
 
-
-	if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
-	    ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) ==
-			      (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))
-		xfs_qm_statvfs(ip, statp);
-
 	if (XFS_IS_REALTIME_MOUNT(mp) &&
 	    (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) {
 		s64	freertx;
@@ -893,6 +887,11 @@ xfs_fs_statfs(
 			xfs_rtbxlen_to_blen(mp, freertx);
 	}
 
+	if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
+	    ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) ==
+			      (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))
+		xfs_qm_statvfs(ip, statp);
+
 	return 0;
 }
 

[PATCH 4/6] xfs: create quota preallocation watermarks for realtime quota

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Refactor the quota preallocation watermarking code so that it'll work
for realtime quota too.  Convert the do_div calls into div_u64 for
compactness.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_dquot.c |   37 +++++++++++++++++++++----------------
 fs/xfs/xfs_dquot.h |   18 ++++++++++++++----
 fs/xfs/xfs_iomap.c |   37 ++++++++++++++++++++++++++++++-------
 fs/xfs/xfs_qm.c    |   21 ++++++++++++++++-----
 4 files changed, 81 insertions(+), 32 deletions(-)


diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 3bf47458c517af..ff982d983989b0 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -277,6 +277,25 @@ xfs_qm_init_dquot_blk(
 		xfs_trans_log_buf(tp, bp, 0, BBTOB(q->qi_dqchunklen) - 1);
 }
 
+static void
+xfs_dquot_set_prealloc(
+	struct xfs_dquot_pre		*pre,
+	const struct xfs_dquot_res	*res)
+{
+	xfs_qcnt_t			space;
+
+	pre->q_prealloc_hi_wmark = res->hardlimit;
+	pre->q_prealloc_lo_wmark = res->softlimit;
+
+	space = div_u64(pre->q_prealloc_hi_wmark, 100);
+	if (!pre->q_prealloc_lo_wmark)
+		pre->q_prealloc_lo_wmark = space * 95;
+
+	pre->q_low_space[XFS_QLOWSP_1_PCNT] = space;
+	pre->q_low_space[XFS_QLOWSP_3_PCNT] = space * 3;
+	pre->q_low_space[XFS_QLOWSP_5_PCNT] = space * 5;
+}
+
 /*
  * Initialize the dynamic speculative preallocation thresholds. The lo/hi
  * watermarks correspond to the soft and hard limits by default. If a soft limit
@@ -285,22 +304,8 @@ xfs_qm_init_dquot_blk(
 void
 xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp)
 {
-	uint64_t space;
-
-	dqp->q_prealloc_hi_wmark = dqp->q_blk.hardlimit;
-	dqp->q_prealloc_lo_wmark = dqp->q_blk.softlimit;
-	if (!dqp->q_prealloc_lo_wmark) {
-		dqp->q_prealloc_lo_wmark = dqp->q_prealloc_hi_wmark;
-		do_div(dqp->q_prealloc_lo_wmark, 100);
-		dqp->q_prealloc_lo_wmark *= 95;
-	}
-
-	space = dqp->q_prealloc_hi_wmark;
-
-	do_div(space, 100);
-	dqp->q_low_space[XFS_QLOWSP_1_PCNT] = space;
-	dqp->q_low_space[XFS_QLOWSP_3_PCNT] = space * 3;
-	dqp->q_low_space[XFS_QLOWSP_5_PCNT] = space * 5;
+	xfs_dquot_set_prealloc(&dqp->q_blk_prealloc, &dqp->q_blk);
+	xfs_dquot_set_prealloc(&dqp->q_rtb_prealloc, &dqp->q_rtb);
 }
 
 /*
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index 677bb2dc9ac913..d73d179df00958 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -56,6 +56,12 @@ xfs_dquot_res_over_limits(
 	return false;
 }
 
+struct xfs_dquot_pre {
+	xfs_qcnt_t		q_prealloc_lo_wmark;
+	xfs_qcnt_t		q_prealloc_hi_wmark;
+	int64_t			q_low_space[XFS_QLOWSP_MAX];
+};
+
 /*
  * The incore dquot structure
  */
@@ -76,9 +82,9 @@ struct xfs_dquot {
 
 	struct xfs_dq_logitem	q_logitem;
 
-	xfs_qcnt_t		q_prealloc_lo_wmark;
-	xfs_qcnt_t		q_prealloc_hi_wmark;
-	int64_t			q_low_space[XFS_QLOWSP_MAX];
+	struct xfs_dquot_pre	q_blk_prealloc;
+	struct xfs_dquot_pre	q_rtb_prealloc;
+
 	struct mutex		q_qlock;
 	struct completion	q_flush;
 	atomic_t		q_pincount;
@@ -192,7 +198,11 @@ static inline bool xfs_dquot_lowsp(struct xfs_dquot *dqp)
 	int64_t freesp;
 
 	freesp = dqp->q_blk.hardlimit - dqp->q_blk.reserved;
-	if (freesp < dqp->q_low_space[XFS_QLOWSP_1_PCNT])
+	if (freesp < dqp->q_blk_prealloc.q_low_space[XFS_QLOWSP_1_PCNT])
+		return true;
+
+	freesp = dqp->q_rtb.hardlimit - dqp->q_rtb.reserved;
+	if (freesp < dqp->q_rtb_prealloc.q_low_space[XFS_QLOWSP_1_PCNT])
 		return true;
 
 	return false;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 17e5c273e28c45..a6fc5acbb6f2c7 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -353,16 +353,26 @@ xfs_quota_need_throttle(
 	xfs_fsblock_t		alloc_blocks)
 {
 	struct xfs_dquot	*dq = xfs_inode_dquot(ip, type);
+	struct xfs_dquot_res	*res;
+	struct xfs_dquot_pre	*pre;
 
 	if (!dq || !xfs_this_quota_on(ip->i_mount, type))
 		return false;
 
+	if (XFS_IS_REALTIME_INODE(ip)) {
+		res = &dq->q_rtb;
+		pre = &dq->q_rtb_prealloc;
+	} else {
+		res = &dq->q_blk;
+		pre = &dq->q_blk_prealloc;
+	}
+
 	/* no hi watermark, no throttle */
-	if (!dq->q_prealloc_hi_wmark)
+	if (!pre->q_prealloc_hi_wmark)
 		return false;
 
 	/* under the lo watermark, no throttle */
-	if (dq->q_blk.reserved + alloc_blocks < dq->q_prealloc_lo_wmark)
+	if (res->reserved + alloc_blocks < pre->q_prealloc_lo_wmark)
 		return false;
 
 	return true;
@@ -377,22 +387,35 @@ xfs_quota_calc_throttle(
 	int64_t			*qfreesp)
 {
 	struct xfs_dquot	*dq = xfs_inode_dquot(ip, type);
+	struct xfs_dquot_res	*res;
+	struct xfs_dquot_pre	*pre;
 	int64_t			freesp;
 	int			shift = 0;
 
+	if (!dq) {
+		res = NULL;
+		pre = NULL;
+	} else if (XFS_IS_REALTIME_INODE(ip)) {
+		res = &dq->q_rtb;
+		pre = &dq->q_rtb_prealloc;
+	} else {
+		res = &dq->q_blk;
+		pre = &dq->q_blk_prealloc;
+	}
+
 	/* no dq, or over hi wmark, squash the prealloc completely */
-	if (!dq || dq->q_blk.reserved >= dq->q_prealloc_hi_wmark) {
+	if (!res || res->reserved >= pre->q_prealloc_hi_wmark) {
 		*qblocks = 0;
 		*qfreesp = 0;
 		return;
 	}
 
-	freesp = dq->q_prealloc_hi_wmark - dq->q_blk.reserved;
-	if (freesp < dq->q_low_space[XFS_QLOWSP_5_PCNT]) {
+	freesp = pre->q_prealloc_hi_wmark - res->reserved;
+	if (freesp < pre->q_low_space[XFS_QLOWSP_5_PCNT]) {
 		shift = 2;
-		if (freesp < dq->q_low_space[XFS_QLOWSP_3_PCNT])
+		if (freesp < pre->q_low_space[XFS_QLOWSP_3_PCNT])
 			shift += 2;
-		if (freesp < dq->q_low_space[XFS_QLOWSP_1_PCNT])
+		if (freesp < pre->q_low_space[XFS_QLOWSP_1_PCNT])
 			shift += 2;
 	}
 
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 1c7d861dfbeceb..90d45aae5cb891 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -2178,6 +2178,8 @@ xfs_inode_near_dquot_enforcement(
 	xfs_dqtype_t		type)
 {
 	struct xfs_dquot	*dqp;
+	struct xfs_dquot_res	*res;
+	struct xfs_dquot_pre	*pre;
 	int64_t			freesp;
 
 	/* We only care for quotas that are enabled and enforced. */
@@ -2186,21 +2188,30 @@ xfs_inode_near_dquot_enforcement(
 		return false;
 
 	if (xfs_dquot_res_over_limits(&dqp->q_ino) ||
+	    xfs_dquot_res_over_limits(&dqp->q_blk) ||
 	    xfs_dquot_res_over_limits(&dqp->q_rtb))
 		return true;
 
+	if (XFS_IS_REALTIME_INODE(ip)) {
+		res = &dqp->q_rtb;
+		pre = &dqp->q_rtb_prealloc;
+	} else {
+		res = &dqp->q_blk;
+		pre = &dqp->q_blk_prealloc;
+	}
+
 	/* For space on the data device, check the various thresholds. */
-	if (!dqp->q_prealloc_hi_wmark)
+	if (!pre->q_prealloc_hi_wmark)
 		return false;
 
-	if (dqp->q_blk.reserved < dqp->q_prealloc_lo_wmark)
+	if (res->reserved < pre->q_prealloc_lo_wmark)
 		return false;
 
-	if (dqp->q_blk.reserved >= dqp->q_prealloc_hi_wmark)
+	if (res->reserved >= pre->q_prealloc_hi_wmark)
 		return true;
 
-	freesp = dqp->q_prealloc_hi_wmark - dqp->q_blk.reserved;
-	if (freesp < dqp->q_low_space[XFS_QLOWSP_5_PCNT])
+	freesp = pre->q_prealloc_hi_wmark - res->reserved;
+	if (freesp < pre->q_low_space[XFS_QLOWSP_5_PCNT])
 		return true;
 
 	return false;

[PATCH 5/6] xfs: reserve quota for realtime files correctly

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Fix xfs_quota_reserve_blkres to reserve rt block quota whenever we're
dealing with a realtime file.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_quota.h       |   12 ++++++------
 fs/xfs/xfs_trans_dquot.c |   11 +++++++++++
 2 files changed, 17 insertions(+), 6 deletions(-)


diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index 2d36d967380e7c..fa1317cc396c96 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -130,6 +130,7 @@ extern void xfs_qm_mount_quotas(struct xfs_mount *);
 extern void xfs_qm_unmount(struct xfs_mount *);
 extern void xfs_qm_unmount_quotas(struct xfs_mount *);
 bool xfs_inode_near_dquot_enforcement(struct xfs_inode *ip, xfs_dqtype_t type);
+int xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t blocks);
 
 # ifdef CONFIG_XFS_LIVE_HOOKS
 void xfs_trans_mod_ino_dquot(struct xfs_trans *tp, struct xfs_inode *ip,
@@ -209,6 +210,11 @@ xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, struct xfs_dquot *udqp,
 #define xfs_qm_unmount_quotas(mp)
 #define xfs_inode_near_dquot_enforcement(ip, type)			(false)
 
+static inline int xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t blocks)
+{
+	return 0;
+}
+
 # ifdef CONFIG_XFS_LIVE_HOOKS
 #  define xfs_dqtrx_hook_enable()		((void)0)
 #  define xfs_dqtrx_hook_disable()		((void)0)
@@ -216,12 +222,6 @@ xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, struct xfs_dquot *udqp,
 
 #endif /* CONFIG_XFS_QUOTA */
 
-static inline int
-xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t blocks)
-{
-	return xfs_trans_reserve_quota_nblks(NULL, ip, blocks, 0, false);
-}
-
 static inline void
 xfs_quota_unreserve_blkres(struct xfs_inode *ip, uint64_t blocks)
 {
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index ca7df018290e0e..481ba3dc9f190d 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -1031,3 +1031,14 @@ xfs_trans_free_dqinfo(
 	kmem_cache_free(xfs_dqtrx_cache, tp->t_dqinfo);
 	tp->t_dqinfo = NULL;
 }
+
+int
+xfs_quota_reserve_blkres(
+	struct xfs_inode	*ip,
+	int64_t			blocks)
+{
+	if (XFS_IS_REALTIME_INODE(ip))
+		return xfs_trans_reserve_quota_nblks(NULL, ip, 0, blocks,
+				false);
+	return xfs_trans_reserve_quota_nblks(NULL, ip, blocks, 0, false);
+}

[PATCH 6/6] xfs: enable realtime quota again

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Enable quotas for the realtime device.

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


diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 90d45aae5cb891..b928b036990bc3 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1663,10 +1663,11 @@ xfs_qm_mount_quotas(
 	uint			sbf;
 
 	/*
-	 * If quotas on realtime volumes is not supported, we disable
-	 * quotas immediately.
+	 * If quotas on realtime volumes is not supported, disable quotas
+	 * immediately.  We only support rtquota if rtgroups are enabled to
+	 * avoid problems with older kernels.
 	 */
-	if (mp->m_sb.sb_rextents) {
+	if (mp->m_sb.sb_rextents && !xfs_has_rtgroups(mp)) {
 		xfs_notice(mp, "Cannot turn on quotas for realtime filesystem");
 		mp->m_qflags = 0;
 		goto write_changes;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 7ecea7623a151a..0cb534d71119a5 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1265,7 +1265,9 @@ xfs_growfs_rt(
 
 	/* Unsupported realtime features. */
 	error = -EOPNOTSUPP;
-	if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp) || xfs_has_quota(mp))
+	if (xfs_has_quota(mp) && !xfs_has_rtgroups(mp))
+		goto out_unlock;
+	if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp))
 		goto out_unlock;
 
 	error = xfs_sb_validate_fsb_count(&mp->m_sb, in->newblocks);

[PATCH 1/2] xfs: update sb field checks when metadir is turned on

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When metadir is enabled, we want to check the two new rtgroups fields,
and we don't want to check the old inumbers that are now in the metadir.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/scrub/agheader.c |   36 ++++++++++++++++++++++++------------
 1 file changed, 24 insertions(+), 12 deletions(-)


diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index d037de6dd821d2..61f80a6410c738 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -147,14 +147,14 @@ xchk_superblock(
 	if (xfs_has_metadir(sc->mp)) {
 		if (sb->sb_metadirino != cpu_to_be64(mp->m_sb.sb_metadirino))
 			xchk_block_set_preen(sc, bp);
+	} else {
+		if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino))
+			xchk_block_set_preen(sc, bp);
+
+		if (sb->sb_rsumino != cpu_to_be64(mp->m_sb.sb_rsumino))
+			xchk_block_set_preen(sc, bp);
 	}
 
-	if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino))
-		xchk_block_set_preen(sc, bp);
-
-	if (sb->sb_rsumino != cpu_to_be64(mp->m_sb.sb_rsumino))
-		xchk_block_set_preen(sc, bp);
-
 	if (sb->sb_rextsize != cpu_to_be32(mp->m_sb.sb_rextsize))
 		xchk_block_set_corrupt(sc, bp);
 
@@ -229,11 +229,13 @@ xchk_superblock(
 	 * sb_icount, sb_ifree, sb_fdblocks, sb_frexents
 	 */
 
-	if (sb->sb_uquotino != cpu_to_be64(mp->m_sb.sb_uquotino))
-		xchk_block_set_preen(sc, bp);
+	if (!xfs_has_metadir(mp)) {
+		if (sb->sb_uquotino != cpu_to_be64(mp->m_sb.sb_uquotino))
+			xchk_block_set_preen(sc, bp);
 
-	if (sb->sb_gquotino != cpu_to_be64(mp->m_sb.sb_gquotino))
-		xchk_block_set_preen(sc, bp);
+		if (sb->sb_gquotino != cpu_to_be64(mp->m_sb.sb_gquotino))
+			xchk_block_set_preen(sc, bp);
+	}
 
 	/*
 	 * Skip the quota flags since repair will force quotacheck.
@@ -349,8 +351,10 @@ xchk_superblock(
 		if (sb->sb_spino_align != cpu_to_be32(mp->m_sb.sb_spino_align))
 			xchk_block_set_corrupt(sc, bp);
 
-		if (sb->sb_pquotino != cpu_to_be64(mp->m_sb.sb_pquotino))
-			xchk_block_set_preen(sc, bp);
+		if (!xfs_has_metadir(mp)) {
+			if (sb->sb_pquotino != cpu_to_be64(mp->m_sb.sb_pquotino))
+				xchk_block_set_preen(sc, bp);
+		}
 
 		/* Don't care about sb_lsn */
 	}
@@ -361,6 +365,14 @@ xchk_superblock(
 			xchk_block_set_corrupt(sc, bp);
 	}
 
+	if (xfs_has_metadir(mp)) {
+		if (sb->sb_rgcount != cpu_to_be32(mp->m_sb.sb_rgcount))
+			xchk_block_set_corrupt(sc, bp);
+
+		if (sb->sb_rgextents != cpu_to_be32(mp->m_sb.sb_rgextents))
+			xchk_block_set_corrupt(sc, bp);
+	}
+
 	/* Everything else must be zero. */
 	if (memchr_inv(sb + 1, 0,
 			BBTOB(bp->b_length) - sizeof(struct xfs_dsb)))

[PATCH 2/2] xfs: enable metadata directory feature

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Enable the metadata directory feature.  With this feature, all metadata
inodes are placed in the metadata directory, and the only inumbers in
the superblock are the roots of the two directory trees.

The RT device is now sharded into a number of rtgroups, where 0 rtgroups
mean that no RT extents are supported, and the traditional XFS stub RT
bitmap and summary inodes don't exist.  A single rtgroup gives roughly
identical behavior to the traditional RT setup, but now with checksummed
and self identifying free space metadata.

For quota, the quota options are read from the superblock unless
explicitly overridden via mount options.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_format.h |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index d6c10855ab023b..4d47a3e723aa13 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -403,7 +403,8 @@ xfs_sb_has_ro_compat_feature(
 		 XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR | \
 		 XFS_SB_FEAT_INCOMPAT_NREXT64 | \
 		 XFS_SB_FEAT_INCOMPAT_EXCHRANGE | \
-		 XFS_SB_FEAT_INCOMPAT_PARENT)
+		 XFS_SB_FEAT_INCOMPAT_PARENT | \
+		 XFS_SB_FEAT_INCOMPAT_METADIR)
 
 #define XFS_SB_FEAT_INCOMPAT_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_ALL
 static inline bool

[PATCH 1/3] xfs: convert struct typedefs in xfs_ondisk.h

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Replace xfs_foo_t with struct xfs_foo where appropriate.  The next patch
will import more checks from xfs/122, and it's easier to automate
deduplication if we don't have to reason about typedefs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_ondisk.h |   74 ++++++++++++++++++++++----------------------
 1 file changed, 37 insertions(+), 37 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 99eae7f67e961b..98208c8a0d9ed0 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -49,7 +49,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_timestamp,	8);
 	XFS_CHECK_STRUCT_SIZE(xfs_alloc_key_t,			8);
 	XFS_CHECK_STRUCT_SIZE(xfs_alloc_ptr_t,			4);
-	XFS_CHECK_STRUCT_SIZE(xfs_alloc_rec_t,			8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_alloc_rec,		8);
 	XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t,			4);
 	XFS_CHECK_STRUCT_SIZE(xfs_refcount_ptr_t,		4);
 	XFS_CHECK_STRUCT_SIZE(xfs_rmap_ptr_t,			4);
@@ -68,10 +68,10 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free_hdr,		64);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf,		64);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf_hdr,		64);
-	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_entry_t,		8);
-	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_hdr_t,		32);
-	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_map_t,		4);
-	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_local_t,	4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_entry,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_hdr,		32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_map,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_local,	4);
 
 	/* realtime structures */
 	XFS_CHECK_STRUCT_SIZE(union xfs_rtword_raw,		4);
@@ -79,23 +79,23 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_rtbuf_blkinfo,		48);
 
 	/*
-	 * m68k has problems with xfs_attr_leaf_name_remote_t, but we pad it to
-	 * 4 bytes anyway so it's not obviously a problem.  Hence for the moment
-	 * we don't check this structure. This can be re-instated when the attr
-	 * definitions are updated to use c99 VLA definitions.
+	 * m68k has problems with struct xfs_attr_leaf_name_remote, but we pad
+	 * it to 4 bytes anyway so it's not obviously a problem.  Hence for the
+	 * moment we don't check this structure. This can be re-instated when
+	 * the attr definitions are updated to use c99 VLA definitions.
 	 *
-	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_remote_t,	12);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_remote,	12);
 	 */
 
 	XFS_CHECK_OFFSET(struct xfs_dsb, sb_crc,		224);
-	XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, valuelen,	0);
-	XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, namelen,	2);
-	XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, nameval,	3);
-	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, valueblk,	0);
-	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, valuelen,	4);
-	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, namelen,	8);
-	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, name,	9);
-	XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t,		32);
+	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, valuelen,	0);
+	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, namelen,	2);
+	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, nameval,	3);
+	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, valueblk,	0);
+	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, valuelen,	4);
+	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, namelen,	8);
+	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_remote, name,	9);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leafblock,		32);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_hdr,		4);
 	XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, totsize,	0);
 	XFS_CHECK_OFFSET(struct xfs_attr_sf_hdr, count,		2);
@@ -103,25 +103,25 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, valuelen,	1);
 	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, flags,	2);
 	XFS_CHECK_OFFSET(struct xfs_attr_sf_entry, nameval,	3);
-	XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t,			12);
-	XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t,			16);
-	XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t,		8);
-	XFS_CHECK_STRUCT_SIZE(xfs_da_node_hdr_t,		16);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_free_t,		4);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_hdr_t,		16);
-	XFS_CHECK_OFFSET(xfs_dir2_data_unused_t, freetag,	0);
-	XFS_CHECK_OFFSET(xfs_dir2_data_unused_t, length,	2);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_hdr_t,		16);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_t,			16);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_entry_t,		8);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_hdr_t,		16);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_t,			16);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_tail_t,		4);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_entry_t,		3);
-	XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, namelen,		0);
-	XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, offset,		1);
-	XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, name,		3);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t,		10);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da_blkinfo,		12);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da_intnode,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_entry,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_hdr,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr,		16);
+	XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, freetag,	0);
+	XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, length,	2);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free_hdr,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_entry,	8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_hdr,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_tail,	4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_entry,		3);
+	XFS_CHECK_OFFSET(struct xfs_dir2_sf_entry, namelen,	0);
+	XFS_CHECK_OFFSET(struct xfs_dir2_sf_entry, offset,	1);
+	XFS_CHECK_OFFSET(struct xfs_dir2_sf_entry, name,	3);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr,		10);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_parent_rec,		12);
 
 	/* log structures */

[PATCH 2/3] xfs: separate space btree structures in xfs_ondisk.h

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a separate section for space management btrees so that they're
not mixed in with file structures.  Ignore the dsb stuff sprinkled
around for now, because we'll deal with that in a subsequent patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_ondisk.h |   24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 98208c8a0d9ed0..7b7c3d6d0d62d9 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -22,38 +22,39 @@
 static inline void __init
 xfs_check_ondisk_structs(void)
 {
-	/* ag/file structures */
+	/* file structures */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_acl,			4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_acl_entry,		12);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_agf,			224);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_agfl,			36);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_agi,			344);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_key,		8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_rec,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bmdr_block,		4);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_shdr,	48);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_lhdr,	64);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block,		72);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dinode,		176);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot,		104);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk,			136);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			288);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr,		56);
+	XFS_CHECK_STRUCT_SIZE(xfs_timestamp_t,			8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_timestamp,	8);
+
+	/* space btrees */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agf,			224);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agfl,			36);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agi,			344);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_alloc_rec,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block,		72);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_lhdr,	64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_shdr,	48);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key,		4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_refcount_key,		4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_refcount_rec,		12);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_key,		20);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_rec,		24);
-	XFS_CHECK_STRUCT_SIZE(xfs_timestamp_t,			8);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_timestamp,	8);
 	XFS_CHECK_STRUCT_SIZE(xfs_alloc_key_t,			8);
 	XFS_CHECK_STRUCT_SIZE(xfs_alloc_ptr_t,			4);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_alloc_rec,		8);
 	XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t,			4);
 	XFS_CHECK_STRUCT_SIZE(xfs_refcount_ptr_t,		4);
 	XFS_CHECK_STRUCT_SIZE(xfs_rmap_ptr_t,			4);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_rtsb,			56);
 
 	/* dir/attr trees */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr,	80);
@@ -74,6 +75,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_local,	4);
 
 	/* realtime structures */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rtsb,			56);
 	XFS_CHECK_STRUCT_SIZE(union xfs_rtword_raw,		4);
 	XFS_CHECK_STRUCT_SIZE(union xfs_suminfo_raw,		4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_rtbuf_blkinfo,		48);

[PATCH 3/3] xfs: port ondisk structure checks from xfs/122 to the kernel

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check this with every kernel and userspace build, so we can drop the
nonsense in xfs/122.  Roughly drafted with:

sed -e 's/^offsetof/\tXFS_CHECK_OFFSET/g' \
	-e 's/^sizeof/\tXFS_CHECK_STRUCT_SIZE/g' \
	-e 's/ = \([0-9]*\)/,\t\t\t\1);/g' \
	-e 's/xfs_sb_t/struct xfs_dsb/g' \
	-e 's/),/,/g' \
	-e 's/xfs_\([a-z0-9_]*\)_t,/struct xfs_\1,/g' \
	< tests/xfs/122.out | sort

and then manual fixups.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_ondisk.h |   90 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 88 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 7b7c3d6d0d62d9..ad0dedf00f1898 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -19,6 +19,10 @@
 	static_assert((value) == (expected), \
 		"XFS: value of " #value " is wrong, expected " #expected)
 
+#define XFS_CHECK_SB_OFFSET(field, offset) \
+	XFS_CHECK_OFFSET(struct xfs_dsb, field, offset); \
+	XFS_CHECK_OFFSET(struct xfs_sb, field, offset);
+
 static inline void __init
 xfs_check_ondisk_structs(void)
 {
@@ -31,7 +35,6 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dinode,		176);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot,		104);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk,			136);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			288);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr,		56);
 	XFS_CHECK_STRUCT_SIZE(xfs_timestamp_t,			8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_timestamp,	8);
@@ -55,6 +58,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t,			4);
 	XFS_CHECK_STRUCT_SIZE(xfs_refcount_ptr_t,		4);
 	XFS_CHECK_STRUCT_SIZE(xfs_rmap_ptr_t,			4);
+	XFS_CHECK_STRUCT_SIZE(xfs_bmdr_key_t,			8);
 
 	/* dir/attr trees */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr,	80);
@@ -89,7 +93,6 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_remote,	12);
 	 */
 
-	XFS_CHECK_OFFSET(struct xfs_dsb, sb_crc,		224);
 	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, valuelen,	0);
 	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, namelen,	2);
 	XFS_CHECK_OFFSET(struct xfs_attr_leaf_name_local, nameval,	3);
@@ -126,6 +129,20 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr,		10);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_parent_rec,		12);
 
+	/* ondisk dir/attr structures from xfs/122 */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_entry,		3);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free,	4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_unused,	6);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free_hdr,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_entry,	8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_hdr,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_tail,	4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_entry,		3);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr,		10);
+
 	/* log structures */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format,	88);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat,		24);
@@ -161,6 +178,11 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents,	16);
 	XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents,	16);
 
+	/* ondisk log structures from xfs/122 */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_unmount_log_format,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_xmd_log_format,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_xmi_log_format,		88);
+
 	/* parent pointer ioctls */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_getparents_rec,	32);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_getparents,		40);
@@ -205,6 +227,70 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MIN << XFS_DQ_BIGTIME_SHIFT, 4);
 	XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MAX << XFS_DQ_BIGTIME_SHIFT,
 			16299260424LL);
+
+	/* superblock field checks we got from xfs/122 */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,		288);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_sb,		288);
+	XFS_CHECK_SB_OFFSET(sb_magicnum,		0);
+	XFS_CHECK_SB_OFFSET(sb_blocksize,		4);
+	XFS_CHECK_SB_OFFSET(sb_dblocks,			8);
+	XFS_CHECK_SB_OFFSET(sb_rblocks,			16);
+	XFS_CHECK_SB_OFFSET(sb_rextents,		24);
+	XFS_CHECK_SB_OFFSET(sb_uuid,			32);
+	XFS_CHECK_SB_OFFSET(sb_logstart,		48);
+	XFS_CHECK_SB_OFFSET(sb_rootino,			56);
+	XFS_CHECK_SB_OFFSET(sb_rbmino,			64);
+	XFS_CHECK_SB_OFFSET(sb_rsumino,			72);
+	XFS_CHECK_SB_OFFSET(sb_rextsize,		80);
+	XFS_CHECK_SB_OFFSET(sb_agblocks,		84);
+	XFS_CHECK_SB_OFFSET(sb_agcount,			88);
+	XFS_CHECK_SB_OFFSET(sb_rbmblocks,		92);
+	XFS_CHECK_SB_OFFSET(sb_logblocks,		96);
+	XFS_CHECK_SB_OFFSET(sb_versionnum,		100);
+	XFS_CHECK_SB_OFFSET(sb_sectsize,		102);
+	XFS_CHECK_SB_OFFSET(sb_inodesize,		104);
+	XFS_CHECK_SB_OFFSET(sb_inopblock,		106);
+	XFS_CHECK_SB_OFFSET(sb_blocklog,		120);
+	XFS_CHECK_SB_OFFSET(sb_fname[12],		120);
+	XFS_CHECK_SB_OFFSET(sb_sectlog,			121);
+	XFS_CHECK_SB_OFFSET(sb_inodelog,		122);
+	XFS_CHECK_SB_OFFSET(sb_inopblog,		123);
+	XFS_CHECK_SB_OFFSET(sb_agblklog,		124);
+	XFS_CHECK_SB_OFFSET(sb_rextslog,		125);
+	XFS_CHECK_SB_OFFSET(sb_inprogress,		126);
+	XFS_CHECK_SB_OFFSET(sb_imax_pct,		127);
+	XFS_CHECK_SB_OFFSET(sb_icount,			128);
+	XFS_CHECK_SB_OFFSET(sb_ifree,			136);
+	XFS_CHECK_SB_OFFSET(sb_fdblocks,		144);
+	XFS_CHECK_SB_OFFSET(sb_frextents,		152);
+	XFS_CHECK_SB_OFFSET(sb_uquotino,		160);
+	XFS_CHECK_SB_OFFSET(sb_gquotino,		168);
+	XFS_CHECK_SB_OFFSET(sb_qflags,			176);
+	XFS_CHECK_SB_OFFSET(sb_flags,			178);
+	XFS_CHECK_SB_OFFSET(sb_shared_vn,		179);
+	XFS_CHECK_SB_OFFSET(sb_inoalignmt,		180);
+	XFS_CHECK_SB_OFFSET(sb_unit,			184);
+	XFS_CHECK_SB_OFFSET(sb_width,			188);
+	XFS_CHECK_SB_OFFSET(sb_dirblklog,		192);
+	XFS_CHECK_SB_OFFSET(sb_logsectlog,		193);
+	XFS_CHECK_SB_OFFSET(sb_logsectsize,		194);
+	XFS_CHECK_SB_OFFSET(sb_logsunit,		196);
+	XFS_CHECK_SB_OFFSET(sb_features2,		200);
+	XFS_CHECK_SB_OFFSET(sb_bad_features2,		204);
+	XFS_CHECK_SB_OFFSET(sb_features_compat,		208);
+	XFS_CHECK_SB_OFFSET(sb_features_ro_compat,	212);
+	XFS_CHECK_SB_OFFSET(sb_features_incompat,	216);
+	XFS_CHECK_SB_OFFSET(sb_features_log_incompat,	220);
+	XFS_CHECK_SB_OFFSET(sb_crc,			224);
+	XFS_CHECK_SB_OFFSET(sb_spino_align,		228);
+	XFS_CHECK_SB_OFFSET(sb_pquotino,		232);
+	XFS_CHECK_SB_OFFSET(sb_lsn,			240);
+	XFS_CHECK_SB_OFFSET(sb_meta_uuid,		248);
+	XFS_CHECK_SB_OFFSET(sb_metadirino,		264);
+	XFS_CHECK_SB_OFFSET(sb_rgcount,			272);
+	XFS_CHECK_SB_OFFSET(sb_rgextents,		276);
+	XFS_CHECK_SB_OFFSET(sb_rgblklog,		280);
+	XFS_CHECK_SB_OFFSET(sb_pad,			281);
 }
 
 #endif /* __XFS_ONDISK_H */

Re: [PATCH 02/21] xfs: create incore realtime group structures

[Brian Foster]

On Tue, Nov 05, 2024 at 02:24:26PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Create an incore object that will contain information about a realtime
> allocation group.  This will eventually enable us to shard the realtime
> section in a similar manner to how we shard the data section, but for
> now just a single object for the entire RT subvolume is created.
> 
> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
>  fs/xfs/Makefile               |    1 
>  fs/xfs/libxfs/xfs_format.h    |    3 +
>  fs/xfs/libxfs/xfs_rtgroup.c   |  151 +++++++++++++++++++++++++++++
>  fs/xfs/libxfs/xfs_rtgroup.h   |  217 +++++++++++++++++++++++++++++++++++++++++
>  fs/xfs/libxfs/xfs_sb.c        |   13 ++
>  fs/xfs/libxfs/xfs_types.h     |    8 +-
>  fs/xfs/xfs_bmap_util.c        |    3 -
>  fs/xfs/xfs_buf_item_recover.c |   25 +++++
>  fs/xfs/xfs_fsmap.c            |    5 +
>  fs/xfs/xfs_mount.c            |   13 ++
>  fs/xfs/xfs_mount.h            |   13 ++
>  fs/xfs/xfs_rtalloc.c          |    5 +
>  fs/xfs/xfs_trace.c            |    1 
>  fs/xfs/xfs_trace.h            |    1 
>  14 files changed, 454 insertions(+), 5 deletions(-)
>  create mode 100644 fs/xfs/libxfs/xfs_rtgroup.c
>  create mode 100644 fs/xfs/libxfs/xfs_rtgroup.h
> 
> 
...
> diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
> new file mode 100644
> index 00000000000000..8872c27a9585fd
> --- /dev/null
> +++ b/fs/xfs/libxfs/xfs_rtgroup.h
> @@ -0,0 +1,217 @@
...
> +#ifdef CONFIG_XFS_RT
> +int xfs_rtgroup_alloc(struct xfs_mount *mp, xfs_rgnumber_t rgno,
> +		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
> +void xfs_rtgroup_free(struct xfs_mount *mp, xfs_rgnumber_t rgno);
> +
> +void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
> +		xfs_rgnumber_t end_rgno);
> +int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno,
> +		xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents);
> +
> +xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno,
> +		xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents);
> +xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno);
> +
> +int xfs_update_last_rtgroup_size(struct xfs_mount *mp,
> +		xfs_rgnumber_t prev_rgcount);
> +#else
> +static inline void xfs_free_rtgroups(struct xfs_mount *mp,
> +		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno)
> +{
> +}
> +
> +static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
> +		xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno,
> +		xfs_rtbxlen_t rextents)
> +{
> +	return 0;
> +}
> +
> +# define xfs_rtgroup_extents(mp, rgno)		(0)
> +# define xfs_update_last_rtgroup_size(mp, rgno)	(-EOPNOTSUPP)
> +#endif /* CONFIG_XFS_RT */

This patch appears to cause a regression with CONFIG_XFS_RT disabled. On
generic/034 or generic/039, I see a mount failure and hang with the
following in dmesg:

[  522.627881] XFS (dm-2): Mounting V5 Filesystem c984a654-8653-430a-9042-b59f26132eb6
[  522.676496] XFS (dm-2): Starting recovery (logdev: internal)
[  522.693551] XFS (dm-2): log mount/recovery failed: error -95
[  522.701508] XFS (dm-2): log mount failed

It seems to be related to the xfs_update_last_rtgroup_size() definition
above in that the issue goes away if I replace the error code with zero,
but I've not looked further into it than that. I'm also not clear on if
the hang behavior is related or just a separate, latent issue triggered
by the injected error.

Brian

> +
> +#endif /* __LIBXFS_RTGROUP_H */
> diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
> index 4516824e3b9994..21891aa10ada02 100644
> --- a/fs/xfs/libxfs/xfs_sb.c
> +++ b/fs/xfs/libxfs/xfs_sb.c
> @@ -696,6 +696,9 @@ __xfs_sb_from_disk(
>  		to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
>  	else
>  		to->sb_metadirino = NULLFSINO;
> +
> +	to->sb_rgcount = 1;
> +	to->sb_rgextents = 0;
>  }
>  
>  void
> @@ -980,8 +983,18 @@ xfs_mount_sb_set_rextsize(
>  	struct xfs_mount	*mp,
>  	struct xfs_sb		*sbp)
>  {
> +	struct xfs_groups	*rgs = &mp->m_groups[XG_TYPE_RTG];
> +
>  	mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize);
>  	mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize);
> +
> +	mp->m_rgblocks = 0;
> +	mp->m_rgblklog = 0;
> +	mp->m_rgblkmask = (uint64_t)-1;
> +
> +	rgs->blocks = 0;
> +	rgs->blklog = 0;
> +	rgs->blkmask = (uint64_t)-1;
>  }
>  
>  /*
> diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
> index 25053a66c225ed..bf33c2b1e43e5f 100644
> --- a/fs/xfs/libxfs/xfs_types.h
> +++ b/fs/xfs/libxfs/xfs_types.h
> @@ -9,10 +9,12 @@
>  typedef uint32_t	prid_t;		/* project ID */
>  
>  typedef uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
> +typedef uint32_t	xfs_rgblock_t;	/* blockno in realtime group */
>  typedef uint32_t	xfs_agino_t;	/* inode # within allocation grp */
>  typedef uint32_t	xfs_extlen_t;	/* extent length in blocks */
>  typedef uint32_t	xfs_rtxlen_t;	/* file extent length in rtextents */
>  typedef uint32_t	xfs_agnumber_t;	/* allocation group number */
> +typedef uint32_t	xfs_rgnumber_t;	/* realtime group number */
>  typedef uint64_t	xfs_extnum_t;	/* # of extents in a file */
>  typedef uint32_t	xfs_aextnum_t;	/* # extents in an attribute fork */
>  typedef int64_t		xfs_fsize_t;	/* bytes in a file */
> @@ -53,7 +55,9 @@ typedef void *		xfs_failaddr_t;
>  #define	NULLFILEOFF	((xfs_fileoff_t)-1)
>  
>  #define	NULLAGBLOCK	((xfs_agblock_t)-1)
> +#define NULLRGBLOCK	((xfs_rgblock_t)-1)
>  #define	NULLAGNUMBER	((xfs_agnumber_t)-1)
> +#define	NULLRGNUMBER	((xfs_rgnumber_t)-1)
>  
>  #define NULLCOMMITLSN	((xfs_lsn_t)-1)
>  
> @@ -214,11 +218,13 @@ enum xbtree_recpacking {
>  
>  enum xfs_group_type {
>  	XG_TYPE_AG,
> +	XG_TYPE_RTG,
>  	XG_TYPE_MAX,
>  } __packed;
>  
>  #define XG_TYPE_STRINGS \
> -	{ XG_TYPE_AG,	"ag" }
> +	{ XG_TYPE_AG,	"ag" }, \
> +	{ XG_TYPE_RTG,	"rtg" }
>  
>  /*
>   * Type verifier functions
> diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
> index edaf193dbd5ccc..1ac0b0facb7fd3 100644
> --- a/fs/xfs/xfs_bmap_util.c
> +++ b/fs/xfs/xfs_bmap_util.c
> @@ -29,6 +29,7 @@
>  #include "xfs_iomap.h"
>  #include "xfs_reflink.h"
>  #include "xfs_rtbitmap.h"
> +#include "xfs_rtgroup.h"
>  
>  /* Kernel only BMAP related definitions and functions */
>  
> @@ -41,7 +42,7 @@ xfs_daddr_t
>  xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
>  {
>  	if (XFS_IS_REALTIME_INODE(ip))
> -		return XFS_FSB_TO_BB(ip->i_mount, fsb);
> +		return xfs_rtb_to_daddr(ip->i_mount, fsb);
>  	return XFS_FSB_TO_DADDR(ip->i_mount, fsb);
>  }
>  
> diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
> index c627ad3a3bbbfd..c8259ee482fd86 100644
> --- a/fs/xfs/xfs_buf_item_recover.c
> +++ b/fs/xfs/xfs_buf_item_recover.c
> @@ -25,6 +25,7 @@
>  #include "xfs_alloc.h"
>  #include "xfs_ag.h"
>  #include "xfs_sb.h"
> +#include "xfs_rtgroup.h"
>  
>  /*
>   * This is the number of entries in the l_buf_cancel_table used during
> @@ -704,6 +705,7 @@ xlog_recover_do_primary_sb_buffer(
>  {
>  	struct xfs_dsb			*dsb = bp->b_addr;
>  	xfs_agnumber_t			orig_agcount = mp->m_sb.sb_agcount;
> +	xfs_rgnumber_t			orig_rgcount = mp->m_sb.sb_rgcount;
>  	int				error;
>  
>  	xlog_recover_do_reg_buffer(mp, item, bp, buf_f, current_lsn);
> @@ -722,6 +724,11 @@ xlog_recover_do_primary_sb_buffer(
>  		xfs_alert(mp, "Shrinking AG count in log recovery not supported");
>  		return -EFSCORRUPTED;
>  	}
> +	if (mp->m_sb.sb_rgcount < orig_rgcount) {
> +		xfs_warn(mp,
> + "Shrinking rtgroup count in log recovery not supported");
> +		return -EFSCORRUPTED;
> +	}
>  
>  	/*
>  	 * If the last AG was grown or shrunk, we also need to update the
> @@ -731,6 +738,17 @@ xlog_recover_do_primary_sb_buffer(
>  	if (error)
>  		return error;
>  
> +	/*
> +	 * If the last rtgroup was grown or shrunk, we also need to update the
> +	 * length in the in-core rtgroup structure and values depending on it.
> +	 * Ignore this on any filesystem with zero rtgroups.
> +	 */
> +	if (orig_rgcount > 0) {
> +		error = xfs_update_last_rtgroup_size(mp, orig_rgcount);
> +		if (error)
> +			return error;
> +	}
> +
>  	/*
>  	 * Initialize the new perags, and also update various block and inode
>  	 * allocator setting based off the number of AGs or total blocks.
> @@ -744,6 +762,13 @@ xlog_recover_do_primary_sb_buffer(
>  		return error;
>  	}
>  	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
> +
> +	error = xfs_initialize_rtgroups(mp, orig_rgcount, mp->m_sb.sb_rgcount,
> +			mp->m_sb.sb_rextents);
> +	if (error) {
> +		xfs_warn(mp, "Failed recovery rtgroup init: %d", error);
> +		return error;
> +	}
>  	return 0;
>  }
>  
> diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
> index 6cf4f00636a2d6..40beb8d75f26b1 100644
> --- a/fs/xfs/xfs_fsmap.c
> +++ b/fs/xfs/xfs_fsmap.c
> @@ -25,6 +25,7 @@
>  #include "xfs_alloc_btree.h"
>  #include "xfs_rtbitmap.h"
>  #include "xfs_ag.h"
> +#include "xfs_rtgroup.h"
>  
>  /* Convert an xfs_fsmap to an fsmap. */
>  static void
> @@ -735,7 +736,7 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
>  		frec.start_daddr = info->end_daddr;
>  	} else {
>  		rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
> -		frec.start_daddr = XFS_FSB_TO_BB(mp, rtbno);
> +		frec.start_daddr = xfs_rtb_to_daddr(mp, rtbno);
>  	}
>  
>  	rtbno = xfs_rtx_to_rtb(mp, rec->ar_extcount);
> @@ -770,7 +771,7 @@ xfs_getfsmap_rtdev_rtbitmap(
>  
>  	/* Adjust the low key if we are continuing from where we left off. */
>  	if (keys[0].fmr_length > 0) {
> -		info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb);
> +		info->low_daddr = xfs_rtb_to_daddr(mp, start_rtb);
>  		if (info->low_daddr >= eofs)
>  			return 0;
>  	}
> diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
> index 2dd2606fc7e3e4..9464eddf9212e9 100644
> --- a/fs/xfs/xfs_mount.c
> +++ b/fs/xfs/xfs_mount.c
> @@ -36,6 +36,7 @@
>  #include "xfs_ag.h"
>  #include "xfs_rtbitmap.h"
>  #include "xfs_metafile.h"
> +#include "xfs_rtgroup.h"
>  #include "scrub/stats.h"
>  
>  static DEFINE_MUTEX(xfs_uuid_table_mutex);
> @@ -834,10 +835,17 @@ xfs_mountfs(
>  		goto out_free_dir;
>  	}
>  
> +	error = xfs_initialize_rtgroups(mp, 0, sbp->sb_rgcount,
> +			mp->m_sb.sb_rextents);
> +	if (error) {
> +		xfs_warn(mp, "Failed rtgroup init: %d", error);
> +		goto out_free_perag;
> +	}
> +
>  	if (XFS_IS_CORRUPT(mp, !sbp->sb_logblocks)) {
>  		xfs_warn(mp, "no log defined");
>  		error = -EFSCORRUPTED;
> -		goto out_free_perag;
> +		goto out_free_rtgroup;
>  	}
>  
>  	error = xfs_inodegc_register_shrinker(mp);
> @@ -1072,6 +1080,8 @@ xfs_mountfs(
>  	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
>  		xfs_buftarg_drain(mp->m_logdev_targp);
>  	xfs_buftarg_drain(mp->m_ddev_targp);
> + out_free_rtgroup:
> +	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
>   out_free_perag:
>  	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
>   out_free_dir:
> @@ -1156,6 +1166,7 @@ xfs_unmountfs(
>  	xfs_errortag_clearall(mp);
>  #endif
>  	shrinker_free(mp->m_inodegc_shrinker);
> +	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
>  	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
>  	xfs_errortag_del(mp);
>  	xfs_error_sysfs_del(mp);
> diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
> index 71ed04ddd737de..d491e31d33aac3 100644
> --- a/fs/xfs/xfs_mount.h
> +++ b/fs/xfs/xfs_mount.h
> @@ -155,6 +155,7 @@ typedef struct xfs_mount {
>  	uint8_t			m_agno_log;	/* log #ag's */
>  	uint8_t			m_sectbb_log;	/* sectlog - BBSHIFT */
>  	int8_t			m_rtxblklog;	/* log2 of rextsize, if possible */
> +	int8_t			m_rgblklog;	/* log2 of rt group sz if possible */
>  	uint			m_blockmask;	/* sb_blocksize-1 */
>  	uint			m_blockwsize;	/* sb_blocksize in words */
>  	uint			m_blockwmask;	/* blockwsize-1 */
> @@ -183,12 +184,14 @@ typedef struct xfs_mount {
>  	int			m_logbsize;	/* size of each log buffer */
>  	uint			m_rsumlevels;	/* rt summary levels */
>  	xfs_filblks_t		m_rsumblocks;	/* size of rt summary, FSBs */
> +	uint32_t		m_rgblocks;	/* size of rtgroup in rtblocks */
>  	int			m_fixedfsid[2];	/* unchanged for life of FS */
>  	uint			m_qflags;	/* quota status flags */
>  	uint64_t		m_features;	/* active filesystem features */
>  	uint64_t		m_low_space[XFS_LOWSP_MAX];
>  	uint64_t		m_low_rtexts[XFS_LOWSP_MAX];
>  	uint64_t		m_rtxblkmask;	/* rt extent block mask */
> +	uint64_t		m_rgblkmask;	/* rt group block mask */
>  	struct xfs_ino_geometry	m_ino_geo;	/* inode geometry */
>  	struct xfs_trans_resv	m_resv;		/* precomputed res values */
>  						/* low free space thresholds */
> @@ -391,6 +394,16 @@ __XFS_HAS_FEAT(large_extent_counts, NREXT64)
>  __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE)
>  __XFS_HAS_FEAT(metadir, METADIR)
>  
> +static inline bool xfs_has_rtgroups(struct xfs_mount *mp)
> +{
> +	return false;
> +}
> +
> +static inline bool xfs_has_rtsb(struct xfs_mount *mp)
> +{
> +	return false;
> +}
> +
>  /*
>   * Some features are always on for v5 file systems, allow the compiler to
>   * eliminiate dead code when building without v4 support.
> diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
> index 46a920b192d191..917c1a5e8f3180 100644
> --- a/fs/xfs/xfs_rtalloc.c
> +++ b/fs/xfs/xfs_rtalloc.c
> @@ -27,6 +27,7 @@
>  #include "xfs_health.h"
>  #include "xfs_da_format.h"
>  #include "xfs_metafile.h"
> +#include "xfs_rtgroup.h"
>  
>  /*
>   * Return whether there are any free extents in the size range given
> @@ -1136,6 +1137,7 @@ xfs_rtmount_inodes(
>  {
>  	struct xfs_trans	*tp;
>  	struct xfs_sb		*sbp = &mp->m_sb;
> +	struct xfs_rtgroup	*rtg = NULL;
>  	int			error;
>  
>  	error = xfs_trans_alloc_empty(mp, &tp);
> @@ -1166,6 +1168,9 @@ xfs_rtmount_inodes(
>  	if (error)
>  		goto out_rele_summary;
>  
> +	while ((rtg = xfs_rtgroup_next(mp, rtg)))
> +		rtg->rtg_extents = xfs_rtgroup_extents(mp, rtg_rgno(rtg));
> +
>  	error = xfs_alloc_rsum_cache(mp, sbp->sb_rbmblocks);
>  	if (error)
>  		goto out_rele_summary;
> diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
> index 1b9d75a54c5ea2..8f530e69c18ae7 100644
> --- a/fs/xfs/xfs_trace.c
> +++ b/fs/xfs/xfs_trace.c
> @@ -48,6 +48,7 @@
>  #include "xfs_refcount.h"
>  #include "xfs_metafile.h"
>  #include "xfs_metadir.h"
> +#include "xfs_rtgroup.h"
>  
>  /*
>   * We include this last to have the helpers above available for the trace
> diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
> index 0f3704f3c2e4e3..f66e5b590d7597 100644
> --- a/fs/xfs/xfs_trace.h
> +++ b/fs/xfs/xfs_trace.h
> @@ -219,6 +219,7 @@ DEFINE_PERAG_REF_EVENT(xfs_perag_clear_inode_tag);
>  DEFINE_PERAG_REF_EVENT(xfs_reclaim_inodes_count);
>  
>  TRACE_DEFINE_ENUM(XG_TYPE_AG);
> +TRACE_DEFINE_ENUM(XG_TYPE_RTG);
>  
>  DECLARE_EVENT_CLASS(xfs_group_class,
>  	TP_PROTO(struct xfs_group *xg, unsigned long caller_ip),
> 
> 

Re: [PATCH 02/21] xfs: create incore realtime group structures

[Christoph Hellwig]

On Tue, Dec 10, 2024 at 07:29:39AM -0500, Brian Foster wrote:
> This patch appears to cause a regression with CONFIG_XFS_RT disabled. On
> generic/034 or generic/039, I see a mount failure and hang with the
> following in dmesg:
> 
> [  522.627881] XFS (dm-2): Mounting V5 Filesystem c984a654-8653-430a-9042-b59f26132eb6
> [  522.676496] XFS (dm-2): Starting recovery (logdev: internal)
> [  522.693551] XFS (dm-2): log mount/recovery failed: error -95
> [  522.701508] XFS (dm-2): log mount failed
> 
> It seems to be related to the xfs_update_last_rtgroup_size() definition
> above in that the issue goes away if I replace the error code with zero,
> but I've not looked further into it than that. I'm also not clear on if
> the hang behavior is related or just a separate, latent issue triggered
> by the injected error.

So without CONFIG_XFS_RT we obviously should not update rgcounts,
but should also fail the mount earlier if there are RGs.  Turns out
that non-rtg file systems have a fake RTG if they have a rt subvolume,
and the count is always set to 1.  So yes, this should just return 0
and your fix is correct.

Re: [PATCH 02/21] xfs: create incore realtime group structures

[Christoph Hellwig]

On Tue, Dec 10, 2024 at 07:51:32PM -0800, Christoph Hellwig wrote:
> So without CONFIG_XFS_RT we obviously should not update rgcounts,
> but should also fail the mount earlier if there are RGs.  Turns out
> that non-rtg file systems have a fake RTG if they have a rt subvolume,
> and the count is always set to 1.  So yes, this should just return 0
> and your fix is correct.

Are you going to send this fix formally?  Or should I?

Re: [PATCH 02/21] xfs: create incore realtime group structures

[Brian Foster]

On Sun, Dec 15, 2024 at 10:38:52PM -0800, Christoph Hellwig wrote:
> On Tue, Dec 10, 2024 at 07:51:32PM -0800, Christoph Hellwig wrote:
> > So without CONFIG_XFS_RT we obviously should not update rgcounts,
> > but should also fail the mount earlier if there are RGs.  Turns out
> > that non-rtg file systems have a fake RTG if they have a rt subvolume,
> > and the count is always set to 1.  So yes, this should just return 0
> > and your fix is correct.
> 
> Are you going to send this fix formally?  Or should I?
> 
> 

I don't really have a patch to send. I was just trying to provide enough
debug analysis to hopefully be useful to somebody who knows this code
better than I do..

Brian