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

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

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

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

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

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

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

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

fs/xfs/Makefile

@@ -51,6 +51,7 @@ xfs-y				+= $(addprefix libxfs/, \
 				   xfs_rmap_btree.o \
 				   xfs_refcount.o \
 				   xfs_refcount_btree.o \
+				   xfs_rtrmap_btree.o \
 				   xfs_sb.o \
 				   xfs_symlink_remote.o \
 				   xfs_trans_inode.o \
@@ -193,6 +194,7 @@ xfs-$(CONFIG_XFS_ONLINE_SCRUB_STATS) += scrub/stats.o
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
 				   rgsuper.o \
 				   rtbitmap.o \
+				   rtrmap.o \
 				   rtsummary.o \
 				   )
 
@@ -232,6 +234,7 @@ xfs-y				+= $(addprefix scrub/, \
 
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
 				   rtbitmap_repair.o \
+				   rtrmap_repair.o \
 				   rtsummary_repair.o \
 				   )
 

fs/xfs/libxfs/xfs_btree.c

@@ -30,6 +30,11 @@
 #include "xfs_health.h"
 #include "xfs_buf_mem.h"
 #include "xfs_btree_mem.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_bmap.h"
+#include "xfs_rmap.h"
+#include "xfs_quota.h"
+#include "xfs_metafile.h"
 
 /*
  * Btree magic numbers.
@@ -5525,6 +5530,9 @@ xfs_btree_init_cur_caches(void)
 	if (error)
 		goto err;
 	error = xfs_refcountbt_init_cur_cache();
+	if (error)
+		goto err;
+	error = xfs_rtrmapbt_init_cur_cache();
 	if (error)
 		goto err;
 
@@ -5543,6 +5551,7 @@ xfs_btree_destroy_cur_caches(void)
 	xfs_bmbt_destroy_cur_cache();
 	xfs_rmapbt_destroy_cur_cache();
 	xfs_refcountbt_destroy_cur_cache();
+	xfs_rtrmapbt_destroy_cur_cache();
 }
 
 /* Move the btree cursor before the first record. */
@@ -5571,3 +5580,67 @@ xfs_btree_goto_left_edge(
 
 	return 0;
 }
+
+/* Allocate a block for an inode-rooted metadata btree. */
+int
+xfs_btree_alloc_metafile_block(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*start,
+	union xfs_btree_ptr		*new,
+	int				*stat)
+{
+	struct xfs_alloc_arg		args = {
+		.mp			= cur->bc_mp,
+		.tp			= cur->bc_tp,
+		.resv			= XFS_AG_RESV_METAFILE,
+		.minlen			= 1,
+		.maxlen			= 1,
+		.prod			= 1,
+	};
+	struct xfs_inode		*ip = cur->bc_ino.ip;
+	int				error;
+
+	ASSERT(xfs_is_metadir_inode(ip));
+
+	xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, cur->bc_ino.whichfork);
+	error = xfs_alloc_vextent_start_ag(&args,
+			XFS_INO_TO_FSB(cur->bc_mp, ip->i_ino));
+	if (error)
+		return error;
+	if (args.fsbno == NULLFSBLOCK) {
+		*stat = 0;
+		return 0;
+	}
+	ASSERT(args.len == 1);
+
+	xfs_metafile_resv_alloc_space(ip, &args);
+
+	new->l = cpu_to_be64(args.fsbno);
+	*stat = 1;
+	return 0;
+}
+
+/* Free a block from an inode-rooted metadata btree. */
+int
+xfs_btree_free_metafile_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = cur->bc_mp;
+	struct xfs_inode	*ip = cur->bc_ino.ip;
+	struct xfs_trans	*tp = cur->bc_tp;
+	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
+	int			error;
+
+	ASSERT(xfs_is_metadir_inode(ip));
+
+	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
+	error = xfs_free_extent_later(tp, fsbno, 1, &oinfo, XFS_AG_RESV_METAFILE,
+			0);
+	if (error)
+		return error;
+
+	xfs_metafile_resv_free_space(ip, tp, 1);
+	return 0;
+}

fs/xfs/libxfs/xfs_btree.h

@@ -135,7 +135,7 @@ struct xfs_btree_ops {
 	/* offset of btree stats array */
 	unsigned int		statoff;
 
-	/* sick mask for health reporting (only for XFS_BTREE_TYPE_AG) */
+	/* sick mask for health reporting (not for bmap btrees) */
 	unsigned int		sick_mask;
 
 	/* cursor operations */
@@ -703,4 +703,10 @@ xfs_btree_at_iroot(
 	       level == cur->bc_nlevels - 1;
 }
 
+int xfs_btree_alloc_metafile_block(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *start, union xfs_btree_ptr *newp,
+		int *stat);
+int xfs_btree_free_metafile_block(struct xfs_btree_cur *cur,
+		struct xfs_buf *bp);
+
 #endif	/* __XFS_BTREE_H__ */

fs/xfs/libxfs/xfs_btree_mem.c

@@ -18,6 +18,7 @@
 #include "xfs_ag.h"
 #include "xfs_buf_item.h"
 #include "xfs_trace.h"
+#include "xfs_rtgroup.h"
 
 /* Set the root of an in-memory btree. */
 void

fs/xfs/libxfs/xfs_btree_staging.c

@@ -134,6 +134,7 @@ xfs_btree_stage_ifakeroot(
 	cur->bc_ino.ifake = ifake;
 	cur->bc_nlevels = ifake->if_levels;
 	cur->bc_ino.forksize = ifake->if_fork_size;
+	cur->bc_ino.whichfork = XFS_STAGING_FORK;
 	cur->bc_flags |= XFS_BTREE_STAGING;
 }
 

fs/xfs/libxfs/xfs_defer.h

@@ -69,6 +69,7 @@ struct xfs_defer_op_type {
 extern const struct xfs_defer_op_type xfs_bmap_update_defer_type;
 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_rtrmap_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;

fs/xfs/libxfs/xfs_exchmaps.c

@@ -662,7 +662,9 @@ xfs_exchmaps_rmapbt_blocks(
 	if (!xfs_has_rmapbt(mp))
 		return 0;
 	if (XFS_IS_REALTIME_INODE(req->ip1))
-		return 0;
+		return howmany_64(req->nr_exchanges,
+					XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) *
+			XFS_RTRMAPADD_SPACE_RES(mp);
 
 	return howmany_64(req->nr_exchanges,
 					XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) *

fs/xfs/libxfs/xfs_format.h

@@ -857,6 +857,7 @@ enum xfs_metafile_type {
 	XFS_METAFILE_PRJQUOTA,		/* project quota */
 	XFS_METAFILE_RTBITMAP,		/* rt bitmap */
 	XFS_METAFILE_RTSUMMARY,		/* rt summary */
+	XFS_METAFILE_RTRMAP,		/* rt rmap */
 
 	XFS_METAFILE_MAX
 } __packed;
@@ -868,7 +869,8 @@ enum xfs_metafile_type {
 	{ XFS_METAFILE_GRPQUOTA,	"grpquota" }, \
 	{ XFS_METAFILE_PRJQUOTA,	"prjquota" }, \
 	{ XFS_METAFILE_RTBITMAP,	"rtbitmap" }, \
-	{ XFS_METAFILE_RTSUMMARY,	"rtsummary" }
+	{ XFS_METAFILE_RTSUMMARY,	"rtsummary" }, \
+	{ XFS_METAFILE_RTRMAP,		"rtrmap" }
 
 /*
  * On-disk inode structure.
@@ -997,7 +999,8 @@ enum xfs_dinode_fmt {
 	XFS_DINODE_FMT_LOCAL,		/* bulk data */
 	XFS_DINODE_FMT_EXTENTS,		/* struct xfs_bmbt_rec */
 	XFS_DINODE_FMT_BTREE,		/* struct xfs_bmdr_block */
-	XFS_DINODE_FMT_UUID		/* added long ago, but never used */
+	XFS_DINODE_FMT_UUID,		/* added long ago, but never used */
+	XFS_DINODE_FMT_META_BTREE,	/* metadata btree */
 };
 
 #define XFS_INODE_FORMAT_STR \
@@ -1005,7 +1008,8 @@ enum xfs_dinode_fmt {
 	{ XFS_DINODE_FMT_LOCAL,		"local" }, \
 	{ XFS_DINODE_FMT_EXTENTS,	"extent" }, \
 	{ XFS_DINODE_FMT_BTREE,		"btree" }, \
-	{ XFS_DINODE_FMT_UUID,		"uuid" }
+	{ XFS_DINODE_FMT_UUID,		"uuid" }, \
+	{ XFS_DINODE_FMT_META_BTREE,	"meta_btree" }
 
 /*
  * Max values for extnum and aextnum.
@@ -1725,6 +1729,24 @@ typedef __be32 xfs_rmap_ptr_t;
 	 XFS_FIBT_BLOCK(mp) + 1 : \
 	 XFS_IBT_BLOCK(mp) + 1)
 
+/*
+ * Realtime Reverse mapping btree format definitions
+ *
+ * This is a btree for reverse mapping records for realtime volumes
+ */
+#define	XFS_RTRMAP_CRC_MAGIC	0x4d415052	/* 'MAPR' */
+
+/*
+ * rtrmap root header, on-disk form only.
+ */
+struct xfs_rtrmap_root {
+	__be16		bb_level;	/* 0 is a leaf */
+	__be16		bb_numrecs;	/* current # of data records */
+};
+
+/* inode-based btree pointer type */
+typedef __be64 xfs_rtrmap_ptr_t;
+
 /*
  * Reference Count Btree format definitions
  *

fs/xfs/libxfs/xfs_fs.h

@@ -737,9 +737,10 @@ struct xfs_scrub_metadata {
 #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 */
+#define XFS_SCRUB_TYPE_RTRMAPBT	31	/* rtgroup reverse mapping btree */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	31
+#define XFS_SCRUB_TYPE_NR	32
 
 /*
  * This special type code only applies to the vectored scrub implementation.
@@ -829,9 +830,10 @@ struct xfs_scrub_vec_head {
 #define XFS_SCRUB_METAPATH_USRQUOTA	(5)  /* user quota */
 #define XFS_SCRUB_METAPATH_GRPQUOTA	(6)  /* group quota */
 #define XFS_SCRUB_METAPATH_PRJQUOTA	(7)  /* project quota */
+#define XFS_SCRUB_METAPATH_RTRMAPBT	(8)  /* realtime reverse mapping */
 
 /* Number of metapath sm_ino values */
-#define XFS_SCRUB_METAPATH_NR		(8)
+#define XFS_SCRUB_METAPATH_NR		(9)
 
 /*
  * ioctl limits
@@ -993,6 +995,7 @@ struct xfs_rtgroup_geometry {
 #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 */
+#define XFS_RTGROUP_GEOM_SICK_RMAPBT	(1U << 3)  /* reverse mappings */
 
 /*
  * ioctl commands that are used by Linux filesystems

fs/xfs/libxfs/xfs_health.h

@@ -70,6 +70,7 @@ struct xfs_rtgroup;
 #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 */
+#define XFS_SICK_RG_RMAPBT	(1 << 3)  /* reverse mappings */
 
 /* Observable health issues for AG metadata. */
 #define XFS_SICK_AG_SB		(1 << 0)  /* superblock */
@@ -115,7 +116,8 @@ struct xfs_rtgroup;
 
 #define XFS_SICK_RG_PRIMARY	(XFS_SICK_RG_SUPER | \
 				 XFS_SICK_RG_BITMAP | \
-				 XFS_SICK_RG_SUMMARY)
+				 XFS_SICK_RG_SUMMARY | \
+				 XFS_SICK_RG_RMAPBT)
 
 #define XFS_SICK_AG_PRIMARY	(XFS_SICK_AG_SB | \
 				 XFS_SICK_AG_AGF | \

fs/xfs/libxfs/xfs_inode_buf.c

@@ -441,6 +441,25 @@ xfs_dinode_verify_fork(
 		if (di_nextents > max_extents)
 			return __this_address;
 		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		if (!xfs_has_metadir(mp))
+			return __this_address;
+		if (!(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA)))
+			return __this_address;
+		switch (be16_to_cpu(dip->di_metatype)) {
+		case XFS_METAFILE_RTRMAP:
+			/*
+			 * growfs must create the rtrmap inodes before adding a
+			 * realtime volume to the filesystem, so we cannot use
+			 * the rtrmapbt predicate here.
+			 */
+			if (!xfs_has_rmapbt(mp))
+				return __this_address;
+			break;
+		default:
+			return __this_address;
+		}
+		break;
 	default:
 		return __this_address;
 	}
@@ -460,6 +479,10 @@ xfs_dinode_verify_forkoff(
 		if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3))
 			return __this_address;
 		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		if (!xfs_has_metadir(mp) || !xfs_has_parent(mp))
+			return __this_address;
+		fallthrough;
 	case XFS_DINODE_FMT_LOCAL:	/* fall through ... */
 	case XFS_DINODE_FMT_EXTENTS:    /* fall through ... */
 	case XFS_DINODE_FMT_BTREE:
@@ -637,9 +660,6 @@ xfs_dinode_verify(
 	if (mode && nextents + naextents > nblocks)
 		return __this_address;
 
-	if (nextents + naextents == 0 && nblocks != 0)
-		return __this_address;
-
 	if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents)
 		return __this_address;
 
@@ -743,6 +763,12 @@ xfs_dinode_verify(
 			return fa;
 	}
 
+	/* metadata inodes containing btrees always have zero extent count */
+	if (XFS_DFORK_FORMAT(dip, XFS_DATA_FORK) != XFS_DINODE_FMT_META_BTREE) {
+		if (nextents + naextents == 0 && nblocks != 0)
+			return __this_address;
+	}
+
 	return NULL;
 }
 

fs/xfs/libxfs/xfs_inode_fork.c

@@ -27,6 +27,7 @@
 #include "xfs_errortag.h"
 #include "xfs_health.h"
 #include "xfs_symlink_remote.h"
+#include "xfs_rtrmap_btree.h"
 
 struct kmem_cache *xfs_ifork_cache;
 
@@ -267,6 +268,14 @@ xfs_iformat_data_fork(
 			return xfs_iformat_extents(ip, dip, XFS_DATA_FORK);
 		case XFS_DINODE_FMT_BTREE:
 			return xfs_iformat_btree(ip, dip, XFS_DATA_FORK);
+		case XFS_DINODE_FMT_META_BTREE:
+			switch (ip->i_metatype) {
+			case XFS_METAFILE_RTRMAP:
+				return xfs_iformat_rtrmap(ip, dip);
+			default:
+				break;
+			}
+			fallthrough;
 		default:
 			xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
 					dip, sizeof(*dip), __this_address);
@@ -601,6 +610,22 @@ xfs_iflush_fork(
 		}
 		break;
 
+	case XFS_DINODE_FMT_META_BTREE:
+		ASSERT(whichfork == XFS_DATA_FORK);
+
+		if (!(iip->ili_fields & brootflag[whichfork]))
+			break;
+
+		switch (ip->i_metatype) {
+		case XFS_METAFILE_RTRMAP:
+			xfs_iflush_rtrmap(ip, dip);
+			break;
+		default:
+			ASSERT(0);
+			break;
+		}
+		break;
+
 	default:
 		ASSERT(0);
 		break;

fs/xfs/libxfs/xfs_log_format.h

@@ -250,6 +250,8 @@ typedef struct xfs_trans_header {
 #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_RUI_RT		0x124c	/* realtime rmap update intent */
+#define	XFS_LI_RUD_RT		0x124d	/* realtime rmap update done */
 
 #define XFS_LI_TYPE_DESC \
 	{ XFS_LI_EFI,		"XFS_LI_EFI" }, \
@@ -271,7 +273,9 @@ typedef struct xfs_trans_header {
 	{ XFS_LI_XMI,		"XFS_LI_XMI" }, \
 	{ XFS_LI_XMD,		"XFS_LI_XMD" }, \
 	{ XFS_LI_EFI_RT,	"XFS_LI_EFI_RT" }, \
-	{ XFS_LI_EFD_RT,	"XFS_LI_EFD_RT" }
+	{ XFS_LI_EFD_RT,	"XFS_LI_EFD_RT" }, \
+	{ XFS_LI_RUI_RT,	"XFS_LI_RUI_RT" }, \
+	{ XFS_LI_RUD_RT,	"XFS_LI_RUD_RT" }
 
 /*
  * Inode Log Item Format definitions.

fs/xfs/libxfs/xfs_log_recover.h

@@ -79,6 +79,8 @@ 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;
+extern const struct xlog_recover_item_ops xlog_rtrui_item_ops;
+extern const struct xlog_recover_item_ops xlog_rtrud_item_ops;
 
 /*
  * Macros, structures, prototypes for internal log manager use.

fs/xfs/libxfs/xfs_metafile.c

@@ -22,6 +22,24 @@
 #include "xfs_error.h"
 #include "xfs_alloc.h"
 
+static const struct {
+	enum xfs_metafile_type	mtype;
+	const char		*name;
+} xfs_metafile_type_strs[] = { XFS_METAFILE_TYPE_STR };
+
+const char *
+xfs_metafile_type_str(enum xfs_metafile_type metatype)
+{
+	unsigned int	i;
+
+	for (i = 0; i < ARRAY_SIZE(xfs_metafile_type_strs); i++) {
+		if (xfs_metafile_type_strs[i].mtype == metatype)
+			return xfs_metafile_type_strs[i].name;
+	}
+
+	return NULL;
+}
+
 /* Set up an inode to be recognized as a metadata directory inode. */
 void
 xfs_metafile_set_iflag(

fs/xfs/libxfs/xfs_metafile.h

@@ -6,6 +6,8 @@
 #ifndef __XFS_METAFILE_H__
 #define __XFS_METAFILE_H__
 
+const char *xfs_metafile_type_str(enum xfs_metafile_type metatype);
+
 /* All metadata files must have these flags set. */
 #define XFS_METAFILE_DIFLAGS	(XFS_DIFLAG_IMMUTABLE | \
 				 XFS_DIFLAG_SYNC | \

fs/xfs/libxfs/xfs_ondisk.h

@@ -83,6 +83,8 @@ xfs_check_ondisk_structs(void)
 	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);
+	XFS_CHECK_STRUCT_SIZE(xfs_rtrmap_ptr_t,			8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rtrmap_root,		4);
 
 	/*
 	 * m68k has problems with struct xfs_attr_leaf_name_remote, but we pad

fs/xfs/libxfs/xfs_refcount.c

@@ -1831,8 +1831,7 @@ xfs_refcount_alloc_cow_extent(
 	__xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len);
 
 	/* Add rmap entry */
-	xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
-			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
+	xfs_rmap_alloc_extent(tp, false, fsb, len, XFS_RMAP_OWN_COW);
 }
 
 /* Forget a CoW staging event in the refcount btree. */
@@ -1848,8 +1847,7 @@ xfs_refcount_free_cow_extent(
 		return;
 
 	/* Remove rmap entry */
-	xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
-			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
+	xfs_rmap_free_extent(tp, false, fsb, len, XFS_RMAP_OWN_COW);
 	__xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len);
 }
 

fs/xfs/libxfs/xfs_rmap.c

@@ -25,6 +25,8 @@
 #include "xfs_ag.h"
 #include "xfs_health.h"
 #include "xfs_rmap_item.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
 
 struct kmem_cache	*xfs_rmap_intent_cache;
 
@@ -264,11 +266,70 @@ xfs_rmap_check_irec(
 	return NULL;
 }
 
+static xfs_failaddr_t
+xfs_rtrmap_check_meta_irec(
+	struct xfs_rtgroup		*rtg,
+	const struct xfs_rmap_irec	*irec)
+{
+	struct xfs_mount		*mp = rtg_mount(rtg);
+
+	if (irec->rm_offset != 0)
+		return __this_address;
+	if (irec->rm_flags & XFS_RMAP_UNWRITTEN)
+		return __this_address;
+
+	switch (irec->rm_owner) {
+	case XFS_RMAP_OWN_FS:
+		if (irec->rm_startblock != 0)
+			return __this_address;
+		if (irec->rm_blockcount != mp->m_sb.sb_rextsize)
+			return __this_address;
+		return NULL;
+	default:
+		return __this_address;
+	}
+
+	return NULL;
+}
+
+static xfs_failaddr_t
+xfs_rtrmap_check_inode_irec(
+	struct xfs_rtgroup		*rtg,
+	const struct xfs_rmap_irec	*irec)
+{
+	struct xfs_mount		*mp = rtg_mount(rtg);
+
+	if (!xfs_verify_ino(mp, irec->rm_owner))
+		return __this_address;
+	if (!xfs_verify_rgbext(rtg, irec->rm_startblock, irec->rm_blockcount))
+		return __this_address;
+	if (!xfs_verify_fileext(mp, irec->rm_offset, irec->rm_blockcount))
+		return __this_address;
+	return NULL;
+}
+
+xfs_failaddr_t
+xfs_rtrmap_check_irec(
+	struct xfs_rtgroup		*rtg,
+	const struct xfs_rmap_irec	*irec)
+{
+	if (irec->rm_blockcount == 0)
+		return __this_address;
+	if (irec->rm_flags & (XFS_RMAP_BMBT_BLOCK | XFS_RMAP_ATTR_FORK))
+		return __this_address;
+	if (XFS_RMAP_NON_INODE_OWNER(irec->rm_owner))
+		return xfs_rtrmap_check_meta_irec(rtg, irec);
+	return xfs_rtrmap_check_inode_irec(rtg, irec);
+}
+
 static inline xfs_failaddr_t
 xfs_rmap_check_btrec(
 	struct xfs_btree_cur		*cur,
 	const struct xfs_rmap_irec	*irec)
 {
+	if (xfs_btree_is_rtrmap(cur->bc_ops) ||
+	    xfs_btree_is_mem_rtrmap(cur->bc_ops))
+		return xfs_rtrmap_check_irec(to_rtg(cur->bc_group), irec);
 	return xfs_rmap_check_irec(to_perag(cur->bc_group), irec);
 }
 
@@ -283,6 +344,10 @@ xfs_rmap_complain_bad_rec(
 	if (xfs_btree_is_mem_rmap(cur->bc_ops))
 		xfs_warn(mp,
  "In-Memory Reverse Mapping BTree record corruption detected at %pS!", fa);
+	else if (xfs_btree_is_rtrmap(cur->bc_ops))
+		xfs_warn(mp,
+ "RT Reverse Mapping BTree record corruption in rtgroup %u detected at %pS!",
+				cur->bc_group->xg_gno, fa);
 	else
 		xfs_warn(mp,
  "Reverse Mapping BTree record corruption in AG %d detected at %pS!",
@@ -525,7 +590,7 @@ xfs_rmap_free_check_owner(
 	struct xfs_btree_cur	*cur,
 	uint64_t		ltoff,
 	struct xfs_rmap_irec	*rec,
-	xfs_filblks_t		len,
+	xfs_extlen_t		len,
 	uint64_t		owner,
 	uint64_t		offset,
 	unsigned int		flags)
@@ -2556,6 +2621,47 @@ __xfs_rmap_finish_intent(
 	}
 }
 
+static int
+xfs_rmap_finish_init_cursor(
+	struct xfs_trans		*tp,
+	struct xfs_rmap_intent		*ri,
+	struct xfs_btree_cur		**pcur)
+{
+	struct xfs_perag		*pag = to_perag(ri->ri_group);
+	struct xfs_buf			*agbp = NULL;
+	int				error;
+
+	/*
+	 * 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, pag, &agbp);
+	if (error) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
+		return error;
+	}
+	if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
+		return -EFSCORRUPTED;
+	}
+	*pcur = xfs_rmapbt_init_cursor(tp->t_mountp, tp, agbp, pag);
+	return 0;
+}
+
+static int
+xfs_rtrmap_finish_init_cursor(
+	struct xfs_trans		*tp,
+	struct xfs_rmap_intent		*ri,
+	struct xfs_btree_cur		**pcur)
+{
+	struct xfs_rtgroup		*rtg = to_rtg(ri->ri_group);
+
+	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+	xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP);
+	*pcur = xfs_rtrmapbt_init_cursor(tp, rtg);
+	return 0;
+}
+
 /*
  * Process one of the deferred rmap operations.  We pass back the
  * btree cursor to maintain our lock on the rmapbt between calls.
@@ -2571,8 +2677,6 @@ xfs_rmap_finish_one(
 {
 	struct xfs_owner_info		oinfo;
 	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_btree_cur		*rcur = *pcur;
-	struct xfs_buf			*agbp = NULL;
 	xfs_agblock_t			bno;
 	bool				unwritten;
 	int				error = 0;
@@ -2586,38 +2690,26 @@ 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_group != ri->ri_group) {
-		xfs_btree_del_cursor(rcur, 0);
-		rcur = NULL;
+	if (*pcur != NULL && (*pcur)->bc_group != ri->ri_group) {
+		xfs_btree_del_cursor(*pcur, 0);
 		*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, pag, &agbp);
-		if (error) {
-			xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
+	if (*pcur == NULL) {
+		if (ri->ri_group->xg_type == XG_TYPE_RTG)
+			error = xfs_rtrmap_finish_init_cursor(tp, ri, pcur);
+		else
+			error = xfs_rmap_finish_init_cursor(tp, ri, pcur);
+		if (error)
 			return error;
-		}
-		if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) {
-			xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
-			return -EFSCORRUPTED;
-		}
-
-		*pcur = rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
 	}
 
 	xfs_rmap_ino_owner(&oinfo, ri->ri_owner, ri->ri_whichfork,
 			ri->ri_bmap.br_startoff);
 	unwritten = ri->ri_bmap.br_state == XFS_EXT_UNWRITTEN;
-	bno = XFS_FSB_TO_AGBNO(rcur->bc_mp, ri->ri_bmap.br_startblock);
 
-	error = __xfs_rmap_finish_intent(rcur, ri->ri_type, bno,
+	bno = xfs_fsb_to_gbno(mp, ri->ri_bmap.br_startblock,
+			ri->ri_group->xg_type);
+	error = __xfs_rmap_finish_intent(*pcur, ri->ri_type, bno,
 			ri->ri_bmap.br_blockcount, &oinfo, unwritten);
 	if (error)
 		return error;
@@ -2647,6 +2739,7 @@ __xfs_rmap_add(
 	struct xfs_trans		*tp,
 	enum xfs_rmap_intent_type	type,
 	uint64_t			owner,
+	bool				isrt,
 	int				whichfork,
 	struct xfs_bmbt_irec		*bmap)
 {
@@ -2658,6 +2751,7 @@ __xfs_rmap_add(
 	ri->ri_owner = owner;
 	ri->ri_whichfork = whichfork;
 	ri->ri_bmap = *bmap;
+	ri->ri_realtime = isrt;
 
 	xfs_rmap_defer_add(tp, ri);
 }
@@ -2671,6 +2765,7 @@ xfs_rmap_map_extent(
 	struct xfs_bmbt_irec	*PREV)
 {
 	enum xfs_rmap_intent_type type = XFS_RMAP_MAP;
+	bool			isrt = xfs_ifork_is_realtime(ip, whichfork);
 
 	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return;
@@ -2678,7 +2773,7 @@ xfs_rmap_map_extent(
 	if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip))
 		type = XFS_RMAP_MAP_SHARED;
 
-	__xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV);
+	__xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV);
 }
 
 /* Unmap an extent out of a file. */
@@ -2690,6 +2785,7 @@ xfs_rmap_unmap_extent(
 	struct xfs_bmbt_irec	*PREV)
 {
 	enum xfs_rmap_intent_type type = XFS_RMAP_UNMAP;
+	bool			isrt = xfs_ifork_is_realtime(ip, whichfork);
 
 	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return;
@@ -2697,7 +2793,7 @@ xfs_rmap_unmap_extent(
 	if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip))
 		type = XFS_RMAP_UNMAP_SHARED;
 
-	__xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV);
+	__xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV);
 }
 
 /*
@@ -2715,6 +2811,7 @@ xfs_rmap_convert_extent(
 	struct xfs_bmbt_irec	*PREV)
 {
 	enum xfs_rmap_intent_type type = XFS_RMAP_CONVERT;
+	bool			isrt = xfs_ifork_is_realtime(ip, whichfork);
 
 	if (!xfs_rmap_update_is_needed(mp, whichfork))
 		return;
@@ -2722,15 +2819,15 @@ xfs_rmap_convert_extent(
 	if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip))
 		type = XFS_RMAP_CONVERT_SHARED;
 
-	__xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV);
+	__xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV);
 }
 
 /* Schedule the creation of an rmap for non-file data. */
 void
 xfs_rmap_alloc_extent(
 	struct xfs_trans	*tp,
-	xfs_agnumber_t		agno,
-	xfs_agblock_t		bno,
+	bool			isrt,
+	xfs_fsblock_t		fsbno,
 	xfs_extlen_t		len,
 	uint64_t		owner)
 {
@@ -2739,20 +2836,20 @@ xfs_rmap_alloc_extent(
 	if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK))
 		return;
 
-	bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno);
+	bmap.br_startblock = fsbno;
 	bmap.br_blockcount = len;
 	bmap.br_startoff = 0;
 	bmap.br_state = XFS_EXT_NORM;
 
-	__xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, XFS_DATA_FORK, &bmap);
+	__xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, isrt, XFS_DATA_FORK, &bmap);
 }
 
 /* Schedule the deletion of an rmap for non-file data. */
 void
 xfs_rmap_free_extent(
 	struct xfs_trans	*tp,
-	xfs_agnumber_t		agno,
-	xfs_agblock_t		bno,
+	bool			isrt,
+	xfs_fsblock_t		fsbno,
 	xfs_extlen_t		len,
 	uint64_t		owner)
 {
@@ -2761,12 +2858,12 @@ xfs_rmap_free_extent(
 	if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK))
 		return;
 
-	bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno);
+	bmap.br_startblock = fsbno;
 	bmap.br_blockcount = len;
 	bmap.br_startoff = 0;
 	bmap.br_state = XFS_EXT_NORM;
 
-	__xfs_rmap_add(tp, XFS_RMAP_FREE, owner, XFS_DATA_FORK, &bmap);
+	__xfs_rmap_add(tp, XFS_RMAP_FREE, owner, isrt, XFS_DATA_FORK, &bmap);
 }
 
 /* Compare rmap records.  Returns -1 if a < b, 1 if a > b, and 0 if equal. */

fs/xfs/libxfs/xfs_rmap.h

@@ -7,6 +7,7 @@
 #define __XFS_RMAP_H__
 
 struct xfs_perag;
+struct xfs_rtgroup;
 
 static inline void
 xfs_rmap_ino_bmbt_owner(
@@ -174,6 +175,7 @@ struct xfs_rmap_intent {
 	uint64_t				ri_owner;
 	struct xfs_bmbt_irec			ri_bmap;
 	struct xfs_group			*ri_group;
+	bool					ri_realtime;
 };
 
 /* functions for updating the rmapbt based on bmbt map/unmap operations */
@@ -184,10 +186,10 @@ void xfs_rmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 void xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_trans *tp,
 		struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *imap);
-void xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
-		xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner);
-void xfs_rmap_free_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
-		xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner);
+void xfs_rmap_alloc_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno,
+		xfs_extlen_t len, uint64_t owner);
+void xfs_rmap_free_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno,
+		xfs_extlen_t len, uint64_t owner);
 
 int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri,
 		struct xfs_btree_cur **pcur);
@@ -206,6 +208,8 @@ xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_rmap_irec *irec);
 xfs_failaddr_t xfs_rmap_check_irec(struct xfs_perag *pag,
 		const struct xfs_rmap_irec *irec);
+xfs_failaddr_t xfs_rtrmap_check_irec(struct xfs_rtgroup *rtg,
+		const struct xfs_rmap_irec *irec);
 
 int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		xfs_extlen_t len, enum xbtree_recpacking *outcome);

fs/xfs/libxfs/xfs_rtbitmap.c

@@ -1055,7 +1055,7 @@ xfs_rtfree_extent(
 	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_inode	*rbmip = rtg_bitmap(rtg);
 	struct xfs_rtalloc_args	args = {
 		.mp		= mp,
 		.tp		= tp,

fs/xfs/libxfs/xfs_rtbitmap.h

@@ -135,6 +135,15 @@ xfs_rtb_to_rtx(
 	return div_u64(rtbno, mp->m_sb.sb_rextsize);
 }
 
+/* Return the offset of a rtgroup block number within an rt extent. */
+static inline xfs_extlen_t
+xfs_rgbno_to_rtxoff(
+	struct xfs_mount	*mp,
+	xfs_rgblock_t		rgbno)
+{
+	return rgbno % mp->m_sb.sb_rextsize;
+}
+
 /* Return the offset of an rt block number within an rt extent. */
 static inline xfs_extlen_t
 xfs_rtb_to_rtxoff(

fs/xfs/libxfs/xfs_rtgroup.c

@@ -33,6 +33,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_metafile.h"
 #include "xfs_metadir.h"
+#include "xfs_rtrmap_btree.h"
 
 /* Find the first usable fsblock in this rtgroup. */
 static inline uint32_t
@@ -197,11 +198,14 @@ xfs_rtgroup_lock(
 		 * 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);
+		xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
+		xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL);
 	} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
-		xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED);
+		xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
 	}
+
+	if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg))
+		xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_EXCL);
 }
 
 /* Unlock metadata inodes associated with this rt group. */
@@ -214,11 +218,14 @@ xfs_rtgroup_unlock(
 	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
 	       !(rtglock_flags & XFS_RTGLOCK_BITMAP));
 
+	if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg))
+		xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_EXCL);
+
 	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);
+		xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL);
+		xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
 	} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
-		xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED);
+		xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
 	}
 }
 
@@ -236,11 +243,12 @@ xfs_rtgroup_trans_join(
 	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED));
 
 	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
-		xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_BITMAP],
-				XFS_ILOCK_EXCL);
-		xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_SUMMARY],
-				XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, rtg_bitmap(rtg), XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, rtg_summary(rtg), XFS_ILOCK_EXCL);
 	}
+
+	if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg))
+		xfs_trans_ijoin(tp, rtg_rmap(rtg), XFS_ILOCK_EXCL);
 }
 
 /* Retrieve rt group geometry. */
@@ -284,7 +292,8 @@ xfs_rtginode_ilock_print_fn(
 	const struct xfs_inode *ip =
 		container_of(m, struct xfs_inode, i_lock.dep_map);
 
-	printk(KERN_CONT " rgno=%u", ip->i_projid);
+	printk(KERN_CONT " rgno=%u metatype=%s", ip->i_projid,
+			xfs_metafile_type_str(ip->i_metatype));
 }
 
 /*
@@ -316,6 +325,8 @@ struct xfs_rtginode_ops {
 
 	unsigned int		sick;	/* rtgroup sickness flag */
 
+	unsigned int		fmt_mask; /* all valid data fork formats */
+
 	/* Does the fs have this feature? */
 	bool			(*enabled)(struct xfs_mount *mp);
 
@@ -331,14 +342,31 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
 		.name		= "bitmap",
 		.metafile_type	= XFS_METAFILE_RTBITMAP,
 		.sick		= XFS_SICK_RG_BITMAP,
+		.fmt_mask	= (1U << XFS_DINODE_FMT_EXTENTS) |
+				  (1U << XFS_DINODE_FMT_BTREE),
 		.create		= xfs_rtbitmap_create,
 	},
 	[XFS_RTGI_SUMMARY] = {
 		.name		= "summary",
 		.metafile_type	= XFS_METAFILE_RTSUMMARY,
 		.sick		= XFS_SICK_RG_SUMMARY,
+		.fmt_mask	= (1U << XFS_DINODE_FMT_EXTENTS) |
+				  (1U << XFS_DINODE_FMT_BTREE),
 		.create		= xfs_rtsummary_create,
 	},
+	[XFS_RTGI_RMAP] = {
+		.name		= "rmap",
+		.metafile_type	= XFS_METAFILE_RTRMAP,
+		.sick		= XFS_SICK_RG_RMAPBT,
+		.fmt_mask	= 1U << XFS_DINODE_FMT_META_BTREE,
+		/*
+		 * growfs must create the rtrmap inodes before adding a
+		 * realtime volume to the filesystem, so we cannot use the
+		 * rtrmapbt predicate here.
+		 */
+		.enabled	= xfs_has_rmapbt,
+		.create		= xfs_rtrmapbt_create,
+	},
 };
 
 /* Return the shortname of this rtgroup inode. */
@@ -435,8 +463,7 @@ xfs_rtginode_load(
 		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)) {
+	if (XFS_IS_CORRUPT(mp, !((1U << ip->i_df.if_format) & ops->fmt_mask))) {
 		xfs_irele(ip);
 		xfs_rtginode_mark_sick(rtg, type);
 		return -EFSCORRUPTED;

fs/xfs/libxfs/xfs_rtgroup.h

@@ -14,6 +14,7 @@ struct xfs_trans;
 enum xfs_rtg_inodes {
 	XFS_RTGI_BITMAP,	/* allocation bitmap */
 	XFS_RTGI_SUMMARY,	/* allocation summary */
+	XFS_RTGI_RMAP,		/* rmap btree inode */
 
 	XFS_RTGI_MAX,
 };
@@ -64,6 +65,21 @@ static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg)
 	return rtg->rtg_group.xg_gno;
 }
 
+static inline struct xfs_inode *rtg_bitmap(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_inodes[XFS_RTGI_BITMAP];
+}
+
+static inline struct xfs_inode *rtg_summary(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_inodes[XFS_RTGI_SUMMARY];
+}
+
+static inline struct xfs_inode *rtg_rmap(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_inodes[XFS_RTGI_RMAP];
+}
+
 /* Passive rtgroup references */
 static inline struct xfs_rtgroup *
 xfs_rtgroup_get(
@@ -122,6 +138,32 @@ xfs_rtgroup_next(
 	return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1);
 }
 
+static inline bool
+xfs_verify_rgbno(
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		rgbno)
+{
+	ASSERT(xfs_has_rtgroups(rtg_mount(rtg)));
+
+	return xfs_verify_gbno(rtg_group(rtg), rgbno);
+}
+
+/*
+ * Check that [@rgbno,@len] is a valid extent range in @rtg.
+ *
+ * Must only be used for RTG-enabled file systems.
+ */
+static inline bool
+xfs_verify_rgbext(
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		rgbno,
+	xfs_extlen_t		len)
+{
+	ASSERT(xfs_has_rtgroups(rtg_mount(rtg)));
+
+	return xfs_verify_gbext(rtg_group(rtg), rgbno, len);
+}
+
 static inline xfs_rtblock_t
 xfs_rgbno_to_rtb(
 	struct xfs_rtgroup	*rtg,
@@ -223,9 +265,12 @@ int xfs_update_last_rtgroup_size(struct xfs_mount *mp,
 #define XFS_RTGLOCK_BITMAP		(1U << 0)
 /* Lock the rt bitmap inode in shared mode */
 #define XFS_RTGLOCK_BITMAP_SHARED	(1U << 1)
+/* Lock the rt rmap inode in exclusive mode */
+#define XFS_RTGLOCK_RMAP		(1U << 2)
 
 #define XFS_RTGLOCK_ALL_FLAGS	(XFS_RTGLOCK_BITMAP | \
-				 XFS_RTGLOCK_BITMAP_SHARED)
+				 XFS_RTGLOCK_BITMAP_SHARED | \
+				 XFS_RTGLOCK_RMAP)
 
 void xfs_rtgroup_lock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
 void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags);
@@ -248,6 +293,8 @@ int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
 		bool init);
 void xfs_rtginode_irele(struct xfs_inode **ipp);
 
+void xfs_rtginode_irele(struct xfs_inode **ipp);
+
 static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno,
 		enum xfs_rtg_inodes type)
 {

fs/xfs/libxfs/xfs_rtrmap_btree.h

@@ -0,0 +1,210 @@
+/* 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_RTRMAP_BTREE_H__
+#define __XFS_RTRMAP_BTREE_H__
+
+struct xfs_buf;
+struct xfs_btree_cur;
+struct xfs_mount;
+struct xbtree_ifakeroot;
+struct xfs_rtgroup;
+struct xfbtree;
+
+/* rmaps only exist on crc enabled filesystems */
+#define XFS_RTRMAP_BLOCK_LEN	XFS_BTREE_LBLOCK_CRC_LEN
+
+struct xfs_btree_cur *xfs_rtrmapbt_init_cursor(struct xfs_trans *tp,
+		struct xfs_rtgroup *rtg);
+struct xfs_btree_cur *xfs_rtrmapbt_stage_cursor(struct xfs_mount *mp,
+		struct xfs_rtgroup *rtg, struct xfs_inode *ip,
+		struct xbtree_ifakeroot *ifake);
+void xfs_rtrmapbt_commit_staged_btree(struct xfs_btree_cur *cur,
+		struct xfs_trans *tp);
+unsigned int xfs_rtrmapbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen,
+		bool leaf);
+void xfs_rtrmapbt_compute_maxlevels(struct xfs_mount *mp);
+unsigned int xfs_rtrmapbt_droot_maxrecs(unsigned int blocklen, bool leaf);
+
+/*
+ * Addresses of records, keys, and pointers within an incore rtrmapbt block.
+ *
+ * (note that some of these may appear unused, but they are used in userspace)
+ */
+static inline struct xfs_rmap_rec *
+xfs_rtrmap_rec_addr(
+	struct xfs_btree_block	*block,
+	unsigned int		index)
+{
+	return (struct xfs_rmap_rec *)
+		((char *)block + XFS_RTRMAP_BLOCK_LEN +
+		 (index - 1) * sizeof(struct xfs_rmap_rec));
+}
+
+static inline struct xfs_rmap_key *
+xfs_rtrmap_key_addr(
+	struct xfs_btree_block	*block,
+	unsigned int		index)
+{
+	return (struct xfs_rmap_key *)
+		((char *)block + XFS_RTRMAP_BLOCK_LEN +
+		 (index - 1) * 2 * sizeof(struct xfs_rmap_key));
+}
+
+static inline struct xfs_rmap_key *
+xfs_rtrmap_high_key_addr(
+	struct xfs_btree_block	*block,
+	unsigned int		index)
+{
+	return (struct xfs_rmap_key *)
+		((char *)block + XFS_RTRMAP_BLOCK_LEN +
+		 sizeof(struct xfs_rmap_key) +
+		 (index - 1) * 2 * sizeof(struct xfs_rmap_key));
+}
+
+static inline xfs_rtrmap_ptr_t *
+xfs_rtrmap_ptr_addr(
+	struct xfs_btree_block	*block,
+	unsigned int		index,
+	unsigned int		maxrecs)
+{
+	return (xfs_rtrmap_ptr_t *)
+		((char *)block + XFS_RTRMAP_BLOCK_LEN +
+		 maxrecs * 2 * sizeof(struct xfs_rmap_key) +
+		 (index - 1) * sizeof(xfs_rtrmap_ptr_t));
+}
+
+unsigned int xfs_rtrmapbt_maxlevels_ondisk(void);
+
+int __init xfs_rtrmapbt_init_cur_cache(void);
+void xfs_rtrmapbt_destroy_cur_cache(void);
+
+xfs_filblks_t xfs_rtrmapbt_calc_reserves(struct xfs_mount *mp);
+
+/* Addresses of key, pointers, and records within an ondisk rtrmapbt block. */
+
+static inline struct xfs_rmap_rec *
+xfs_rtrmap_droot_rec_addr(
+	struct xfs_rtrmap_root	*block,
+	unsigned int		index)
+{
+	return (struct xfs_rmap_rec *)
+		((char *)(block + 1) +
+		 (index - 1) * sizeof(struct xfs_rmap_rec));
+}
+
+static inline struct xfs_rmap_key *
+xfs_rtrmap_droot_key_addr(
+	struct xfs_rtrmap_root	*block,
+	unsigned int		index)
+{
+	return (struct xfs_rmap_key *)
+		((char *)(block + 1) +
+		 (index - 1) * 2 * sizeof(struct xfs_rmap_key));
+}
+
+static inline xfs_rtrmap_ptr_t *
+xfs_rtrmap_droot_ptr_addr(
+	struct xfs_rtrmap_root	*block,
+	unsigned int		index,
+	unsigned int		maxrecs)
+{
+	return (xfs_rtrmap_ptr_t *)
+		((char *)(block + 1) +
+		 maxrecs * 2 * sizeof(struct xfs_rmap_key) +
+		 (index - 1) * sizeof(xfs_rtrmap_ptr_t));
+}
+
+/*
+ * Address of pointers within the incore btree root.
+ *
+ * These are to be used when we know the size of the block and
+ * we don't have a cursor.
+ */
+static inline xfs_rtrmap_ptr_t *
+xfs_rtrmap_broot_ptr_addr(
+	struct xfs_mount	*mp,
+	struct xfs_btree_block	*bb,
+	unsigned int		index,
+	unsigned int		block_size)
+{
+	return xfs_rtrmap_ptr_addr(bb, index,
+			xfs_rtrmapbt_maxrecs(mp, block_size, false));
+}
+
+/*
+ * Compute the space required for the incore btree root containing the given
+ * number of records.
+ */
+static inline size_t
+xfs_rtrmap_broot_space_calc(
+	struct xfs_mount	*mp,
+	unsigned int		level,
+	unsigned int		nrecs)
+{
+	size_t			sz = XFS_RTRMAP_BLOCK_LEN;
+
+	if (level > 0)
+		return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) +
+					 sizeof(xfs_rtrmap_ptr_t));
+	return sz + nrecs * sizeof(struct xfs_rmap_rec);
+}
+
+/*
+ * Compute the space required for the incore btree root given the ondisk
+ * btree root block.
+ */
+static inline size_t
+xfs_rtrmap_broot_space(struct xfs_mount *mp, struct xfs_rtrmap_root *bb)
+{
+	return xfs_rtrmap_broot_space_calc(mp, be16_to_cpu(bb->bb_level),
+			be16_to_cpu(bb->bb_numrecs));
+}
+
+/* Compute the space required for the ondisk root block. */
+static inline size_t
+xfs_rtrmap_droot_space_calc(
+	unsigned int		level,
+	unsigned int		nrecs)
+{
+	size_t			sz = sizeof(struct xfs_rtrmap_root);
+
+	if (level > 0)
+		return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) +
+					 sizeof(xfs_rtrmap_ptr_t));
+	return sz + nrecs * sizeof(struct xfs_rmap_rec);
+}
+
+/*
+ * Compute the space required for the ondisk root block given an incore root
+ * block.
+ */
+static inline size_t
+xfs_rtrmap_droot_space(struct xfs_btree_block *bb)
+{
+	return xfs_rtrmap_droot_space_calc(be16_to_cpu(bb->bb_level),
+			be16_to_cpu(bb->bb_numrecs));
+}
+
+int xfs_iformat_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip);
+void xfs_rtrmapbt_to_disk(struct xfs_mount *mp, struct xfs_btree_block *rblock,
+		unsigned int rblocklen, struct xfs_rtrmap_root *dblock,
+		unsigned int dblocklen);
+void xfs_iflush_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip);
+
+int xfs_rtrmapbt_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip,
+		struct xfs_trans *tp, bool init);
+int xfs_rtrmapbt_init_rtsb(struct xfs_mount *mp, struct xfs_rtgroup *rtg,
+		struct xfs_trans *tp);
+
+unsigned long long xfs_rtrmapbt_calc_size(struct xfs_mount *mp,
+		unsigned long long len);
+
+struct xfs_btree_cur *xfs_rtrmapbt_mem_cursor(struct xfs_rtgroup *rtg,
+		struct xfs_trans *tp, struct xfbtree *xfbtree);
+int xfs_rtrmapbt_mem_init(struct xfs_mount *mp, struct xfbtree *xfbtree,
+		struct xfs_buftarg *btp, xfs_rgnumber_t rgno);
+
+#endif /* __XFS_RTRMAP_BTREE_H__ */

fs/xfs/libxfs/xfs_sb.c

@@ -28,6 +28,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_exchrange.h"
 #include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -1215,6 +1216,11 @@ xfs_sb_mount_common(
 	mp->m_rmap_mnr[0] = mp->m_rmap_mxr[0] / 2;
 	mp->m_rmap_mnr[1] = mp->m_rmap_mxr[1] / 2;
 
+	mp->m_rtrmap_mxr[0] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, true);
+	mp->m_rtrmap_mxr[1] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, false);
+	mp->m_rtrmap_mnr[0] = mp->m_rtrmap_mxr[0] / 2;
+	mp->m_rtrmap_mnr[1] = mp->m_rtrmap_mxr[1] / 2;
+
 	mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, true);
 	mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, false);
 	mp->m_refc_mnr[0] = mp->m_refc_mxr[0] / 2;

fs/xfs/libxfs/xfs_shared.h

@@ -42,6 +42,7 @@ 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_rtrmapbt_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;
@@ -55,6 +56,8 @@ extern const struct xfs_btree_ops xfs_bmbt_ops;
 extern const struct xfs_btree_ops xfs_refcountbt_ops;
 extern const struct xfs_btree_ops xfs_rmapbt_ops;
 extern const struct xfs_btree_ops xfs_rmapbt_mem_ops;
+extern const struct xfs_btree_ops xfs_rtrmapbt_ops;
+extern const struct xfs_btree_ops xfs_rtrmapbt_mem_ops;
 
 static inline bool xfs_btree_is_bno(const struct xfs_btree_ops *ops)
 {
@@ -96,10 +99,21 @@ static inline bool xfs_btree_is_mem_rmap(const struct xfs_btree_ops *ops)
 {
 	return ops == &xfs_rmapbt_mem_ops;
 }
+
+static inline bool xfs_btree_is_mem_rtrmap(const struct xfs_btree_ops *ops)
+{
+	return ops == &xfs_rtrmapbt_mem_ops;
+}
 #else
 # define xfs_btree_is_mem_rmap(...)	(false)
+# define xfs_btree_is_mem_rtrmap(...)	(false)
 #endif
 
+static inline bool xfs_btree_is_rtrmap(const struct xfs_btree_ops *ops)
+{
+	return ops == &xfs_rtrmapbt_ops;
+}
+
 /* log size calculation functions */
 int	xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
 int	xfs_log_calc_minimum_size(struct xfs_mount *);

fs/xfs/libxfs/xfs_trans_resv.c

@@ -213,7 +213,9 @@ xfs_calc_inode_chunk_res(
  * Per-extent log reservation for the btree changes involved in freeing or
  * allocating a realtime extent.  We have to be able to log as many rtbitmap
  * blocks as needed to mark inuse XFS_BMBT_MAX_EXTLEN blocks' worth of realtime
- * extents, as well as the realtime summary block.
+ * extents, as well as the realtime summary block (t1).  Realtime rmap btree
+ * operations happen in a second transaction, so factor in a couple of rtrmapbt
+ * splits (t2).
  */
 static unsigned int
 xfs_rtalloc_block_count(
@@ -222,10 +224,16 @@ xfs_rtalloc_block_count(
 {
 	unsigned int		rtbmp_blocks;
 	xfs_rtxlen_t		rtxlen;
+	unsigned int		t1, t2 = 0;
 
 	rtxlen = xfs_extlen_to_rtxlen(mp, XFS_MAX_BMBT_EXTLEN);
 	rtbmp_blocks = xfs_rtbitmap_blockcount_len(mp, rtxlen);
-	return (rtbmp_blocks + 1) * num_ops;
+	t1 = (rtbmp_blocks + 1) * num_ops;
+
+	if (xfs_has_rmapbt(mp))
+		t2 = num_ops * (2 * mp->m_rtrmap_maxlevels - 1);
+
+	return max(t1, t2);
 }
 
 /*

fs/xfs/libxfs/xfs_trans_space.h

@@ -14,6 +14,19 @@
 #define XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp)    \
 		(((mp)->m_bmap_dmxr[0]) - ((mp)->m_bmap_dmnr[0]))
 
+/* Worst case number of realtime rmaps that can be held in a block. */
+#define XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)    \
+		(((mp)->m_rtrmap_mxr[0]) - ((mp)->m_rtrmap_mnr[0]))
+
+/* Adding one realtime rmap could split every level to the top of the tree. */
+#define XFS_RTRMAPADD_SPACE_RES(mp) ((mp)->m_rtrmap_maxlevels)
+
+/* Blocks we might need to add "b" realtime rmaps to a tree. */
+#define XFS_NRTRMAPADD_SPACE_RES(mp, b) \
+	((((b) + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp) - 1) / \
+	  XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) * \
+	  XFS_RTRMAPADD_SPACE_RES(mp))
+
 /* Worst case number of rmaps that can be held in a block. */
 #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)    \
 		(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))

fs/xfs/scrub/alloc_repair.c

@@ -542,8 +542,9 @@ xrep_abt_dispose_one(
 
 	/* Add a deferred rmap for each extent we used. */
 	if (resv->used > 0)
-		xfs_rmap_alloc_extent(sc->tp, pag_agno(pag), resv->agbno,
-				resv->used, XFS_RMAP_OWN_AG);
+		xfs_rmap_alloc_extent(sc->tp, false,
+				xfs_agbno_to_fsb(pag, resv->agbno), resv->used,
+				XFS_RMAP_OWN_AG);
 
 	/*
 	 * For each reserved btree block we didn't use, add it to the free

fs/xfs/scrub/bmap.c

@@ -21,6 +21,8 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_rtgroup.h"
 #include "xfs_health.h"
+#include "xfs_rtalloc.h"
+#include "xfs_rtrmap_btree.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/btree.h"
@@ -143,15 +145,22 @@ static inline bool
 xchk_bmap_get_rmap(
 	struct xchk_bmap_info	*info,
 	struct xfs_bmbt_irec	*irec,
-	xfs_agblock_t		agbno,
+	xfs_agblock_t		bno,
 	uint64_t		owner,
 	struct xfs_rmap_irec	*rmap)
 {
+	struct xfs_btree_cur	**curp = &info->sc->sa.rmap_cur;
 	xfs_fileoff_t		offset;
 	unsigned int		rflags = 0;
 	int			has_rmap;
 	int			error;
 
+	if (xfs_ifork_is_realtime(info->sc->ip, info->whichfork))
+		curp = &info->sc->sr.rmap_cur;
+
+	if (*curp == NULL)
+		return false;
+
 	if (info->whichfork == XFS_ATTR_FORK)
 		rflags |= XFS_RMAP_ATTR_FORK;
 	if (irec->br_state == XFS_EXT_UNWRITTEN)
@@ -172,13 +181,13 @@ xchk_bmap_get_rmap(
 	 * range rmap lookup to make sure we get the correct owner/offset.
 	 */
 	if (info->is_shared) {
-		error = xfs_rmap_lookup_le_range(info->sc->sa.rmap_cur, agbno,
-				owner, offset, rflags, rmap, &has_rmap);
+		error = xfs_rmap_lookup_le_range(*curp, bno, owner, offset,
+				rflags, rmap, &has_rmap);
 	} else {
-		error = xfs_rmap_lookup_le(info->sc->sa.rmap_cur, agbno,
-				owner, offset, rflags, rmap, &has_rmap);
+		error = xfs_rmap_lookup_le(*curp, bno, owner, offset,
+				rflags, rmap, &has_rmap);
 	}
-	if (!xchk_should_check_xref(info->sc, &error, &info->sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(info->sc, &error, curp))
 		return false;
 
 	if (!has_rmap)
@@ -192,29 +201,29 @@ STATIC void
 xchk_bmap_xref_rmap(
 	struct xchk_bmap_info	*info,
 	struct xfs_bmbt_irec	*irec,
-	xfs_agblock_t		agbno)
+	xfs_agblock_t		bno)
 {
 	struct xfs_rmap_irec	rmap;
 	unsigned long long	rmap_end;
 	uint64_t		owner = info->sc->ip->i_ino;
 
-	if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm))
+	if (xchk_skip_xref(info->sc->sm))
 		return;
 
 	/* Find the rmap record for this irec. */
-	if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap))
+	if (!xchk_bmap_get_rmap(info, irec, bno, owner, &rmap))
 		return;
 
 	/*
 	 * The rmap must be an exact match for this incore file mapping record,
 	 * which may have arisen from multiple ondisk records.
 	 */
-	if (rmap.rm_startblock != agbno)
+	if (rmap.rm_startblock != bno)
 		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount;
-	if (rmap_end != agbno + irec->br_blockcount)
+	if (rmap_end != bno + irec->br_blockcount)
 		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
@@ -259,7 +268,7 @@ STATIC void
 xchk_bmap_xref_rmap_cow(
 	struct xchk_bmap_info	*info,
 	struct xfs_bmbt_irec	*irec,
-	xfs_agblock_t		agbno)
+	xfs_agblock_t		bno)
 {
 	struct xfs_rmap_irec	rmap;
 	unsigned long long	rmap_end;
@@ -269,7 +278,7 @@ xchk_bmap_xref_rmap_cow(
 		return;
 
 	/* Find the rmap record for this irec. */
-	if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap))
+	if (!xchk_bmap_get_rmap(info, irec, bno, owner, &rmap))
 		return;
 
 	/*
@@ -277,12 +286,12 @@ xchk_bmap_xref_rmap_cow(
 	 * can start before and end after the physical space allocated to this
 	 * mapping.  There are no offsets to check.
 	 */
-	if (rmap.rm_startblock > agbno)
+	if (rmap.rm_startblock > bno)
 		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount;
-	if (rmap_end < agbno + irec->br_blockcount)
+	if (rmap_end < bno + irec->br_blockcount)
 		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
@@ -315,6 +324,8 @@ xchk_bmap_rt_iextent_xref(
 	struct xchk_bmap_info	*info,
 	struct xfs_bmbt_irec	*irec)
 {
+	struct xfs_owner_info	oinfo;
+	xfs_rgblock_t		rgbno;
 	int			error;
 
 	error = xchk_rtgroup_init_existing(info->sc,
@@ -324,10 +335,28 @@ xchk_bmap_rt_iextent_xref(
 			irec->br_startoff, &error))
 		return;
 
-	xchk_rtgroup_lock(&info->sc->sr, XCHK_RTGLOCK_ALL);
+	error = xchk_rtgroup_lock(info->sc, &info->sc->sr, XCHK_RTGLOCK_ALL);
+	if (!xchk_fblock_process_error(info->sc, info->whichfork,
+			irec->br_startoff, &error))
+		goto out_free;
+
 	xchk_xref_is_used_rt_space(info->sc, irec->br_startblock,
 			irec->br_blockcount);
 
+	if (!xfs_has_rtrmapbt(info->sc->mp))
+		goto out_cur;
+
+	rgbno = xfs_rtb_to_rgbno(info->sc->mp, irec->br_startblock);
+	xchk_bmap_xref_rmap(info, irec, rgbno);
+
+	xfs_rmap_ino_owner(&oinfo, info->sc->ip->i_ino, info->whichfork,
+			irec->br_startoff);
+	xchk_xref_is_only_rt_owned_by(info->sc, rgbno,
+			irec->br_blockcount, &oinfo);
+
+out_cur:
+	xchk_rtgroup_btcur_free(&info->sc->sr);
+out_free:
 	xchk_rtgroup_free(info->sc, &info->sc->sr);
 }
 
@@ -614,8 +643,7 @@ xchk_bmap_check_rmap(
 			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					check_rec.rm_offset);
 		if (irec.br_startblock !=
-		    xfs_agbno_to_fsb(to_perag(cur->bc_group),
-				check_rec.rm_startblock))
+		    xfs_gbno_to_fsb(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)
@@ -669,6 +697,30 @@ xchk_bmap_check_ag_rmaps(
 	return error;
 }
 
+/* Make sure each rt rmap has a corresponding bmbt entry. */
+STATIC int
+xchk_bmap_check_rt_rmaps(
+	struct xfs_scrub		*sc,
+	struct xfs_rtgroup		*rtg)
+{
+	struct xchk_bmap_check_rmap_info sbcri;
+	struct xfs_btree_cur		*cur;
+	int				error;
+
+	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+	cur = xfs_rtrmapbt_init_cursor(sc->tp, rtg);
+
+	sbcri.sc = sc;
+	sbcri.whichfork = XFS_DATA_FORK;
+	error = xfs_rmap_query_all(cur, xchk_bmap_check_rmap, &sbcri);
+	if (error == -ECANCELED)
+		error = 0;
+
+	xfs_btree_del_cursor(cur, error);
+	xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
+	return error;
+}
+
 /*
  * Decide if we want to scan the reverse mappings to determine if the attr
  * fork /really/ has zero space mappings.
@@ -723,10 +775,6 @@ xchk_bmap_check_empty_datafork(
 {
 	struct xfs_ifork	*ifp = &ip->i_df;
 
-	/* Don't support realtime rmap checks yet. */
-	if (XFS_IS_REALTIME_INODE(ip))
-		return false;
-
 	/*
 	 * If the dinode repair found a bad data fork, it will reset the fork
 	 * to extents format with zero records and wait for the this scrubber
@@ -777,6 +825,21 @@ xchk_bmap_check_rmaps(
 	struct xfs_perag	*pag = NULL;
 	int			error;
 
+	if (xfs_ifork_is_realtime(sc->ip, whichfork)) {
+		struct xfs_rtgroup	*rtg = NULL;
+
+		while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) {
+			error = xchk_bmap_check_rt_rmaps(sc, rtg);
+			if (error ||
+			    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
+				xfs_rtgroup_rele(rtg);
+				return error;
+			}
+		}
+
+		return 0;
+	}
+
 	while ((pag = xfs_perag_next(sc->mp, pag))) {
 		error = xchk_bmap_check_ag_rmaps(sc, whichfork, pag);
 		if (error ||
@@ -983,6 +1046,7 @@ xchk_bmap(
 	case XFS_DINODE_FMT_UUID:
 	case XFS_DINODE_FMT_DEV:
 	case XFS_DINODE_FMT_LOCAL:
+	case XFS_DINODE_FMT_META_BTREE:
 		/* No mappings to check. */
 		if (whichfork == XFS_COW_FORK)
 			xchk_fblock_set_corrupt(sc, whichfork, 0);

fs/xfs/scrub/bmap_repair.c

@@ -25,11 +25,13 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_rmap.h"
 #include "xfs_rmap_btree.h"
+#include "xfs_rtrmap_btree.h"
 #include "xfs_refcount.h"
 #include "xfs_quota.h"
 #include "xfs_ialloc.h"
 #include "xfs_ag.h"
 #include "xfs_reflink.h"
+#include "xfs_rtgroup.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -359,6 +361,112 @@ xrep_bmap_scan_ag(
 	return error;
 }
 
+#ifdef CONFIG_XFS_RT
+/* Check for any obvious errors or conflicts in the file mapping. */
+STATIC int
+xrep_bmap_check_rtfork_rmap(
+	struct xfs_scrub		*sc,
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec)
+{
+	/* xattr extents are never stored on realtime devices */
+	if (rec->rm_flags & XFS_RMAP_ATTR_FORK)
+		return -EFSCORRUPTED;
+
+	/* bmbt blocks are never stored on realtime devices */
+	if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK)
+		return -EFSCORRUPTED;
+
+	/* Data extents for non-rt files are never stored on the rt device. */
+	if (!XFS_IS_REALTIME_INODE(sc->ip))
+		return -EFSCORRUPTED;
+
+	/* Check the file offsets and physical extents. */
+	if (!xfs_verify_fileext(sc->mp, rec->rm_offset, rec->rm_blockcount))
+		return -EFSCORRUPTED;
+
+	/* Check that this is within the rtgroup. */
+	if (!xfs_verify_rgbext(to_rtg(cur->bc_group), rec->rm_startblock,
+				rec->rm_blockcount))
+		return -EFSCORRUPTED;
+
+	/* Make sure this isn't free space. */
+	return xrep_require_rtext_inuse(sc, rec->rm_startblock,
+			rec->rm_blockcount);
+}
+
+/* Record realtime extents that belong to this inode's fork. */
+STATIC int
+xrep_bmap_walk_rtrmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_bmap		*rb = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(rb->sc, &error))
+		return error;
+
+	/* Skip extents which are not owned by this inode and fork. */
+	if (rec->rm_owner != rb->sc->ip->i_ino)
+		return 0;
+
+	error = xrep_bmap_check_rtfork_rmap(rb->sc, cur, rec);
+	if (error)
+		return error;
+
+	/*
+	 * Record all blocks allocated to this file even if the extent isn't
+	 * for the fork we're rebuilding so that we can reset di_nblocks later.
+	 */
+	rb->nblocks += rec->rm_blockcount;
+
+	/* If this rmap isn't for the fork we want, we're done. */
+	if (rb->whichfork == XFS_DATA_FORK &&
+	    (rec->rm_flags & XFS_RMAP_ATTR_FORK))
+		return 0;
+	if (rb->whichfork == XFS_ATTR_FORK &&
+	    !(rec->rm_flags & XFS_RMAP_ATTR_FORK))
+		return 0;
+
+	return xrep_bmap_from_rmap(rb, rec->rm_offset,
+			xfs_rgbno_to_rtb(to_rtg(cur->bc_group),
+				rec->rm_startblock),
+			rec->rm_blockcount,
+			rec->rm_flags & XFS_RMAP_UNWRITTEN);
+}
+
+/* Scan the realtime reverse mappings to build the new extent map. */
+STATIC int
+xrep_bmap_scan_rtgroup(
+	struct xrep_bmap	*rb,
+	struct xfs_rtgroup	*rtg)
+{
+	struct xfs_scrub	*sc = rb->sc;
+	int			error;
+
+	if (!xfs_has_rtrmapbt(sc->mp))
+		return 0;
+
+	error = xrep_rtgroup_init(sc, rtg, &sc->sr,
+			XFS_RTGLOCK_RMAP | XFS_RTGLOCK_BITMAP_SHARED);
+	if (error)
+		return error;
+
+	error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_bmap_walk_rtrmap, rb);
+	xchk_rtgroup_btcur_free(&sc->sr);
+	xchk_rtgroup_free(sc, &sc->sr);
+	return error;
+}
+#else
+static inline int
+xrep_bmap_scan_rtgroup(struct xrep_bmap *rb, struct xfs_rtgroup *rtg)
+{
+	return -EFSCORRUPTED;
+}
+#endif
+
 /* Find the delalloc extents from the old incore extent tree. */
 STATIC int
 xrep_bmap_find_delalloc(
@@ -410,6 +518,22 @@ xrep_bmap_find_mappings(
 	struct xfs_perag	*pag = NULL;
 	int			error = 0;
 
+	/*
+	 * Iterate the rtrmaps for extents.  Metadata files never have content
+	 * on the realtime device, so there's no need to scan them.
+	 */
+	if (!xfs_is_metadir_inode(sc->ip)) {
+		struct xfs_rtgroup	*rtg = NULL;
+
+		while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) {
+			error = xrep_bmap_scan_rtgroup(rb, rtg);
+			if (error) {
+				xfs_rtgroup_rele(rtg);
+				return error;
+			}
+		}
+	}
+
 	/* Iterate the rmaps for extents. */
 	while ((pag = xfs_perag_next(sc->mp, pag))) {
 		error = xrep_bmap_scan_ag(rb, pag);
@@ -731,6 +855,7 @@ xrep_bmap_check_inputs(
 	case XFS_DINODE_FMT_DEV:
 	case XFS_DINODE_FMT_LOCAL:
 	case XFS_DINODE_FMT_UUID:
+	case XFS_DINODE_FMT_META_BTREE:
 		return -ECANCELED;
 	case XFS_DINODE_FMT_EXTENTS:
 	case XFS_DINODE_FMT_BTREE:
@@ -753,10 +878,6 @@ xrep_bmap_check_inputs(
 		return -EINVAL;
 	}
 
-	/* Don't know how to rebuild realtime data forks. */
-	if (XFS_IS_REALTIME_INODE(sc->ip))
-		return -EOPNOTSUPP;
-
 	return 0;
 }
 

fs/xfs/scrub/common.c

@@ -35,6 +35,8 @@
 #include "xfs_exchmaps.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_bmap_util.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -719,20 +721,105 @@ xchk_rtgroup_init(
 	return 0;
 }
 
-void
+/* Lock all the rt group metadata inode ILOCKs and wait for intents. */
+int
 xchk_rtgroup_lock(
+	struct xfs_scrub	*sc,
 	struct xchk_rt		*sr,
 	unsigned int		rtglock_flags)
 {
-	xfs_rtgroup_lock(sr->rtg, rtglock_flags);
+	int			error = 0;
+
+	ASSERT(sr->rtg != NULL);
+
+	/*
+	 * If we're /only/ locking the rtbitmap in shared mode, then we're
+	 * obviously not trying to compare records in two metadata inodes.
+	 * There's no need to drain intents here because the caller (most
+	 * likely the rgsuper scanner) doesn't need that level of consistency.
+	 */
+	if (rtglock_flags == XFS_RTGLOCK_BITMAP_SHARED) {
+		xfs_rtgroup_lock(sr->rtg, rtglock_flags);
+		sr->rtlock_flags = rtglock_flags;
+		return 0;
+	}
+
+	do {
+		if (xchk_should_terminate(sc, &error))
+			return error;
+
+		xfs_rtgroup_lock(sr->rtg, rtglock_flags);
+
+		/*
+		 * If we've grabbed a non-metadata file for scrubbing, we
+		 * assume that holding its ILOCK will suffice to coordinate
+		 * with any rt intent chains involving this inode.
+		 */
+		if (sc->ip && !xfs_is_internal_inode(sc->ip))
+			break;
+
+		/*
+		 * Decide if the rt group is quiet enough for all metadata to
+		 * be consistent with each other.  Regular file IO doesn't get
+		 * to lock all the rt inodes at the same time, which means that
+		 * there could be other threads in the middle of processing a
+		 * chain of deferred ops.
+		 *
+		 * We just locked all the metadata inodes for this rt group;
+		 * now take a look to see if there are any intents in progress.
+		 * If there are, drop the rt group inode locks and wait for the
+		 * intents to drain.  Since we hold the rt group inode locks
+		 * for the duration of the scrub, this is the only time we have
+		 * to sample the intents counter; any threads increasing it
+		 * after this point can't possibly be in the middle of a chain
+		 * of rt metadata updates.
+		 *
+		 * Obviously, this should be slanted against scrub and in favor
+		 * of runtime threads.
+		 */
+		if (!xfs_group_intent_busy(rtg_group(sr->rtg)))
+			break;
+
+		xfs_rtgroup_unlock(sr->rtg, rtglock_flags);
+
+		if (!(sc->flags & XCHK_FSGATES_DRAIN))
+			return -ECHRNG;
+		error = xfs_group_intent_drain(rtg_group(sr->rtg));
+		if (error) {
+			if (error == -ERESTARTSYS)
+				error = -EINTR;
+			return error;
+		}
+	} while (1);
+
 	sr->rtlock_flags = rtglock_flags;
+
+	if (xfs_has_rtrmapbt(sc->mp) && (rtglock_flags & XFS_RTGLOCK_RMAP))
+		sr->rmap_cur = xfs_rtrmapbt_init_cursor(sc->tp, sr->rtg);
+
+	return 0;
+}
+
+/*
+ * Free all the btree cursors and other incore data relating to the realtime
+ * group.  This has to be done /before/ committing (or cancelling) the scrub
+ * transaction.
+ */
+void
+xchk_rtgroup_btcur_free(
+	struct xchk_rt		*sr)
+{
+	if (sr->rmap_cur)
+		xfs_btree_del_cursor(sr->rmap_cur, XFS_BTREE_ERROR);
+
+	sr->rmap_cur = NULL;
 }
 
 /*
  * Unlock the realtime group.  This must be done /after/ committing (or
  * cancelling) the scrub transaction.
  */
-static void
+void
 xchk_rtgroup_unlock(
 	struct xchk_rt		*sr)
 {
@@ -812,6 +899,14 @@ xchk_setup_fs(
 	return xchk_trans_alloc(sc, resblks);
 }
 
+/* Set us up with a transaction and an empty context to repair rt metadata. */
+int
+xchk_setup_rt(
+	struct xfs_scrub	*sc)
+{
+	return xchk_trans_alloc(sc, xrep_calc_rtgroup_resblks(sc));
+}
+
 /* Set us up with AG headers and btree cursors. */
 int
 xchk_setup_ag_btree(
@@ -1379,7 +1474,7 @@ xchk_fsgates_enable(
 	trace_xchk_fsgates_enable(sc, scrub_fsgates);
 
 	if (scrub_fsgates & XCHK_FSGATES_DRAIN)
-		xfs_drain_wait_enable();
+		xfs_defer_drain_wait_enable();
 
 	if (scrub_fsgates & XCHK_FSGATES_QUOTA)
 		xfs_dqtrx_hook_enable();
@@ -1573,3 +1668,60 @@ xchk_inode_rootdir_inum(const struct xfs_inode *ip)
 		return mp->m_metadirip->i_ino;
 	return mp->m_rootip->i_ino;
 }
+
+static int
+xchk_meta_btree_count_blocks(
+	struct xfs_scrub	*sc,
+	xfs_extnum_t		*nextents,
+	xfs_filblks_t		*count)
+{
+	struct xfs_btree_cur	*cur;
+	int			error;
+
+	if (!sc->sr.rtg) {
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	switch (sc->ip->i_metatype) {
+	case XFS_METAFILE_RTRMAP:
+		cur = xfs_rtrmapbt_init_cursor(sc->tp, sc->sr.rtg);
+		break;
+	default:
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	error = xfs_btree_count_blocks(cur, count);
+	xfs_btree_del_cursor(cur, error);
+	if (!error) {
+		*nextents = 0;
+		(*count)--;	/* don't count the btree iroot */
+	}
+	return error;
+}
+
+/* Count the blocks used by a file, even if it's a metadata inode. */
+int
+xchk_inode_count_blocks(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_extnum_t		*nextents,
+	xfs_filblks_t		*count)
+{
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(sc->ip, whichfork);
+
+	if (!ifp) {
+		*nextents = 0;
+		*count = 0;
+		return 0;
+	}
+
+	if (ifp->if_format == XFS_DINODE_FMT_META_BTREE) {
+		ASSERT(whichfork == XFS_DATA_FORK);
+		return xchk_meta_btree_count_blocks(sc, nextents, count);
+	}
+
+	return xfs_bmap_count_blocks(sc->tp, sc->ip, whichfork, nextents,
+			count);
+}

fs/xfs/scrub/common.h

@@ -63,6 +63,7 @@ static inline int xchk_setup_nothing(struct xfs_scrub *sc)
 /* Setup functions */
 int xchk_setup_agheader(struct xfs_scrub *sc);
 int xchk_setup_fs(struct xfs_scrub *sc);
+int xchk_setup_rt(struct xfs_scrub *sc);
 int xchk_setup_ag_allocbt(struct xfs_scrub *sc);
 int xchk_setup_ag_iallocbt(struct xfs_scrub *sc);
 int xchk_setup_ag_rmapbt(struct xfs_scrub *sc);
@@ -80,10 +81,12 @@ int xchk_setup_metapath(struct xfs_scrub *sc);
 int xchk_setup_rtbitmap(struct xfs_scrub *sc);
 int xchk_setup_rtsummary(struct xfs_scrub *sc);
 int xchk_setup_rgsuperblock(struct xfs_scrub *sc);
+int xchk_setup_rtrmapbt(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
+# define xchk_setup_rtrmapbt		xchk_setup_nothing
 #endif
 #ifdef CONFIG_XFS_QUOTA
 int xchk_ino_dqattach(struct xfs_scrub *sc);
@@ -125,7 +128,8 @@ xchk_ag_init_existing(
 #ifdef CONFIG_XFS_RT
 
 /* All the locks we need to check an rtgroup. */
-#define XCHK_RTGLOCK_ALL	(XFS_RTGLOCK_BITMAP)
+#define XCHK_RTGLOCK_ALL	(XFS_RTGLOCK_BITMAP | \
+				 XFS_RTGLOCK_RMAP)
 
 int xchk_rtgroup_init(struct xfs_scrub *sc, xfs_rgnumber_t rgno,
 		struct xchk_rt *sr);
@@ -141,12 +145,17 @@ xchk_rtgroup_init_existing(
 	return error == -ENOENT ? -EFSCORRUPTED : error;
 }
 
-void xchk_rtgroup_lock(struct xchk_rt *sr, unsigned int rtglock_flags);
+int xchk_rtgroup_lock(struct xfs_scrub *sc, struct xchk_rt *sr,
+		unsigned int rtglock_flags);
+void xchk_rtgroup_unlock(struct xchk_rt *sr);
+void xchk_rtgroup_btcur_free(struct xchk_rt *sr);
 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_lock(sc, sr, lockflags)		(-EFSCORRUPTED)
+# define xchk_rtgroup_unlock(sr)			do { } while (0)
+# define xchk_rtgroup_btcur_free(sr)			do { } while (0)
 # define xchk_rtgroup_free(sc, sr)			do { } while (0)
 #endif /* CONFIG_XFS_RT */
 
@@ -257,6 +266,12 @@ int xchk_metadata_inode_forks(struct xfs_scrub *sc);
 			(sc)->mp->m_super->s_id, \
 			(sc)->ip ? (sc)->ip->i_ino : (sc)->sm->sm_ino, \
 			##__VA_ARGS__)
+#define xchk_xfile_rtgroup_descr(sc, fmt, ...) \
+	kasprintf(XCHK_GFP_FLAGS, "XFS (%s): rtgroup 0x%x " fmt, \
+			(sc)->mp->m_super->s_id, \
+			(sc)->sa.pag ? \
+				rtg_rgno((sc)->sr.rtg) : (sc)->sm->sm_agno, \
+			##__VA_ARGS__)
 
 /*
  * Setting up a hook to wait for intents to drain is costly -- we have to take
@@ -274,6 +289,8 @@ 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);
+int xchk_inode_count_blocks(struct xfs_scrub *sc, int whichfork,
+		xfs_extnum_t *nextents, xfs_filblks_t *count);
 
 bool xchk_inode_is_dirtree_root(const struct xfs_inode *ip);
 bool xchk_inode_is_sb_rooted(const struct xfs_inode *ip);

fs/xfs/scrub/health.c

@@ -114,6 +114,7 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
 	[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 },
+	[XFS_SCRUB_TYPE_RTRMAPBT]	= { XHG_RTGROUP, XFS_SICK_RG_RMAPBT },
 };
 
 /* Return the health status mask for this scrub type. */

fs/xfs/scrub/inode.c

@@ -502,6 +502,10 @@ xchk_dinode(
 		if (!S_ISREG(mode) && !S_ISDIR(mode))
 			xchk_ino_set_corrupt(sc, ino);
 		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		if (!S_ISREG(mode))
+			xchk_ino_set_corrupt(sc, ino);
+		break;
 	case XFS_DINODE_FMT_UUID:
 	default:
 		xchk_ino_set_corrupt(sc, ino);
@@ -686,15 +690,13 @@ xchk_inode_xref_bmap(
 		return;
 
 	/* Walk all the extents to check nextents/naextents/nblocks. */
-	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
-			&nextents, &count);
+	error = xchk_inode_count_blocks(sc, XFS_DATA_FORK, &nextents, &count);
 	if (!xchk_should_check_xref(sc, &error, NULL))
 		return;
 	if (nextents < xfs_dfork_data_extents(dip))
 		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 
-	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
-			&nextents, &acount);
+	error = xchk_inode_count_blocks(sc, XFS_ATTR_FORK, &nextents, &acount);
 	if (!xchk_should_check_xref(sc, &error, NULL))
 		return;
 	if (nextents != xfs_dfork_attr_extents(dip))

fs/xfs/scrub/inode_repair.c

@@ -38,6 +38,8 @@
 #include "xfs_log_priv.h"
 #include "xfs_health.h"
 #include "xfs_symlink_remote.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -773,17 +775,71 @@ xrep_dinode_count_ag_rmaps(
 	return error;
 }
 
+/* Count extents and blocks for an inode given an rt rmap. */
+STATIC int
+xrep_dinode_walk_rtrmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_inode		*ri = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(ri->sc, &error))
+		return error;
+
+	/* We only care about this inode. */
+	if (rec->rm_owner != ri->sc->sm->sm_ino)
+		return 0;
+
+	if (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))
+		return -EFSCORRUPTED;
+
+	ri->rt_blocks += rec->rm_blockcount;
+	ri->rt_extents++;
+	return 0;
+}
+
+/* Count extents and blocks for an inode from all realtime rmap data. */
+STATIC int
+xrep_dinode_count_rtgroup_rmaps(
+	struct xrep_inode	*ri,
+	struct xfs_rtgroup	*rtg)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	int			error;
+
+	error = xrep_rtgroup_init(sc, rtg, &sc->sr, XFS_RTGLOCK_RMAP);
+	if (error)
+		return error;
+
+	error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_dinode_walk_rtrmap,
+			ri);
+	xchk_rtgroup_btcur_free(&sc->sr);
+	xchk_rtgroup_free(sc, &sc->sr);
+	return error;
+}
+
 /* Count extents and blocks for a given inode from all rmap data. */
 STATIC int
 xrep_dinode_count_rmaps(
 	struct xrep_inode	*ri)
 {
 	struct xfs_perag	*pag = NULL;
+	struct xfs_rtgroup	*rtg = NULL;
 	int			error;
 
-	if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp))
+	if (!xfs_has_rmapbt(ri->sc->mp))
 		return -EOPNOTSUPP;
 
+	while ((rtg = xfs_rtgroup_next(ri->sc->mp, rtg))) {
+		error = xrep_dinode_count_rtgroup_rmaps(ri, rtg);
+		if (error) {
+			xfs_rtgroup_rele(rtg);
+			return error;
+		}
+	}
+
 	while ((pag = xfs_perag_next(ri->sc->mp, pag))) {
 		error = xrep_dinode_count_ag_rmaps(ri, pag);
 		if (error) {
@@ -888,6 +944,55 @@ xrep_dinode_bad_bmbt_fork(
 	return false;
 }
 
+/* Return true if this rmap-format ifork looks like garbage. */
+STATIC bool
+xrep_dinode_bad_rtrmapbt_fork(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	unsigned int		dfork_size)
+{
+	struct xfs_rtrmap_root	*dfp;
+	unsigned int		nrecs;
+	unsigned int		level;
+
+	if (dfork_size < sizeof(struct xfs_rtrmap_root))
+		return true;
+
+	dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+	nrecs = be16_to_cpu(dfp->bb_numrecs);
+	level = be16_to_cpu(dfp->bb_level);
+
+	if (level > sc->mp->m_rtrmap_maxlevels)
+		return true;
+	if (xfs_rtrmap_droot_space_calc(level, nrecs) > dfork_size)
+		return true;
+	if (level > 0 && nrecs == 0)
+		return true;
+
+	return false;
+}
+
+/* Check a metadata-btree fork. */
+STATIC bool
+xrep_dinode_bad_metabt_fork(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	unsigned int		dfork_size,
+	int			whichfork)
+{
+	if (whichfork != XFS_DATA_FORK)
+		return true;
+
+	switch (be16_to_cpu(dip->di_metatype)) {
+	case XFS_METAFILE_RTRMAP:
+		return xrep_dinode_bad_rtrmapbt_fork(sc, dip, dfork_size);
+	default:
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Check the data fork for things that will fail the ifork verifiers or the
  * ifork formatters.
@@ -968,6 +1073,11 @@ xrep_dinode_check_dfork(
 				XFS_DATA_FORK))
 			return true;
 		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		if (xrep_dinode_bad_metabt_fork(sc, dip, dfork_size,
+				XFS_DATA_FORK))
+			return true;
+		break;
 	default:
 		return true;
 	}
@@ -1088,6 +1198,11 @@ xrep_dinode_check_afork(
 					XFS_ATTR_FORK))
 			return true;
 		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		if (xrep_dinode_bad_metabt_fork(sc, dip, afork_size,
+					XFS_ATTR_FORK))
+			return true;
+		break;
 	default:
 		return true;
 	}
@@ -1135,6 +1250,7 @@ xrep_dinode_ensure_forkoff(
 	uint16_t		mode)
 {
 	struct xfs_bmdr_block	*bmdr;
+	struct xfs_rtrmap_root	*rmdr;
 	struct xfs_scrub	*sc = ri->sc;
 	xfs_extnum_t		attr_extents, data_extents;
 	size_t			bmdr_minsz = xfs_bmdr_space_calc(1);
@@ -1241,6 +1357,17 @@ xrep_dinode_ensure_forkoff(
 		bmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
 		dfork_min = xfs_bmap_broot_space(sc->mp, bmdr);
 		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		switch (be16_to_cpu(dip->di_metatype)) {
+		case XFS_METAFILE_RTRMAP:
+			rmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
+			dfork_min = xfs_rtrmap_broot_space(sc->mp, rmdr);
+			break;
+		default:
+			dfork_min = 0;
+			break;
+		}
+		break;
 	default:
 		dfork_min = 0;
 		break;
@@ -1500,8 +1627,7 @@ xrep_inode_blockcounts(
 	trace_xrep_inode_blockcounts(sc);
 
 	/* Set data fork counters from the data fork mappings. */
-	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
-			&nextents, &count);
+	error = xchk_inode_count_blocks(sc, XFS_DATA_FORK, &nextents, &count);
 	if (error)
 		return error;
 	if (xfs_is_reflink_inode(sc->ip)) {
@@ -1525,8 +1651,8 @@ xrep_inode_blockcounts(
 	/* Set attr fork counters from the attr fork mappings. */
 	ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
 	if (ifp) {
-		error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
-				&nextents, &acount);
+		error = xchk_inode_count_blocks(sc, XFS_ATTR_FORK, &nextents,
+				&acount);
 		if (error)
 			return error;
 		if (count >= sc->mp->m_sb.sb_dblocks)

fs/xfs/scrub/metapath.c

@@ -21,6 +21,7 @@
 #include "xfs_trans_space.h"
 #include "xfs_attr.h"
 #include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -246,6 +247,8 @@ xchk_setup_metapath(
 		return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_GROUP);
 	case XFS_SCRUB_METAPATH_PRJQUOTA:
 		return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_PROJ);
+	case XFS_SCRUB_METAPATH_RTRMAPBT:
+		return xchk_setup_metapath_rtginode(sc, XFS_RTGI_RMAP);
 	default:
 		return -ENOENT;
 	}

fs/xfs/scrub/newbt.c

@@ -19,6 +19,8 @@
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
 #include "xfs_defer.h"
+#include "xfs_metafile.h"
+#include "xfs_quota.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -120,6 +122,43 @@ xrep_newbt_init_inode(
 	return 0;
 }
 
+/*
+ * Initialize accounting resources for staging a new metadata inode btree.
+ * If the metadata file has a space reservation, the caller must adjust that
+ * reservation when committing the new ondisk btree.
+ */
+int
+xrep_newbt_init_metadir_inode(
+	struct xrep_newbt		*xnr,
+	struct xfs_scrub		*sc)
+{
+	struct xfs_owner_info		oinfo;
+	struct xfs_ifork		*ifp;
+
+	ASSERT(xfs_is_metadir_inode(sc->ip));
+
+	xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, XFS_DATA_FORK);
+
+	ifp = kmem_cache_zalloc(xfs_ifork_cache, XCHK_GFP_FLAGS);
+	if (!ifp)
+		return -ENOMEM;
+
+	/*
+	 * Allocate new metadir btree blocks with XFS_AG_RESV_NONE because the
+	 * inode metadata space reservations can only account allocated space
+	 * to the i_nblocks.  We do not want to change the inode core fields
+	 * until we're ready to commit the new tree, so we allocate the blocks
+	 * as if they were regular file blocks.  This exposes us to a higher
+	 * risk of the repair being cancelled due to ENOSPC.
+	 */
+	xrep_newbt_init_ag(xnr, sc, &oinfo,
+			XFS_INO_TO_FSB(sc->mp, sc->ip->i_ino),
+			XFS_AG_RESV_NONE);
+	xnr->ifake.if_fork = ifp;
+	xnr->ifake.if_fork_size = xfs_inode_fork_size(sc->ip, XFS_DATA_FORK);
+	return 0;
+}
+
 /*
  * Initialize accounting resources for staging a new btree.  Callers are
  * expected to add their own reservations (and clean them up) manually.
@@ -224,6 +263,7 @@ xrep_newbt_alloc_ag_blocks(
 	int			error = 0;
 
 	ASSERT(sc->sa.pag != NULL);
+	ASSERT(xnr->resv != XFS_AG_RESV_METAFILE);
 
 	while (nr_blocks > 0) {
 		struct xfs_alloc_arg	args = {
@@ -297,6 +337,8 @@ xrep_newbt_alloc_file_blocks(
 	struct xfs_mount	*mp = sc->mp;
 	int			error = 0;
 
+	ASSERT(xnr->resv != XFS_AG_RESV_METAFILE);
+
 	while (nr_blocks > 0) {
 		struct xfs_alloc_arg	args = {
 			.tp		= sc->tp,

fs/xfs/scrub/newbt.h

@@ -63,6 +63,7 @@ void xrep_newbt_init_ag(struct xrep_newbt *xnr, struct xfs_scrub *sc,
 		enum xfs_ag_resv_type resv);
 int xrep_newbt_init_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc,
 		int whichfork, const struct xfs_owner_info *oinfo);
+int xrep_newbt_init_metadir_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc);
 int xrep_newbt_alloc_blocks(struct xrep_newbt *xnr, uint64_t nr_blocks);
 int xrep_newbt_add_extent(struct xrep_newbt *xnr, struct xfs_perag *pag,
 		xfs_agblock_t agbno, xfs_extlen_t len);

fs/xfs/scrub/reap.c

@@ -33,6 +33,7 @@
 #include "xfs_attr.h"
 #include "xfs_attr_remote.h"
 #include "xfs_defer.h"
+#include "xfs_metafile.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -390,6 +391,8 @@ xreap_agextent_iter(
 	xfs_fsblock_t		fsbno;
 	int			error = 0;
 
+	ASSERT(rs->resv != XFS_AG_RESV_METAFILE);
+
 	fsbno = xfs_agbno_to_fsb(sc->sa.pag, agbno);
 
 	/*
@@ -675,6 +678,44 @@ xrep_reap_fsblocks(
 	return 0;
 }
 
+/*
+ * Dispose of every block of an old metadata btree that used to be rooted in a
+ * metadata directory file.
+ */
+int
+xrep_reap_metadir_fsblocks(
+	struct xfs_scrub		*sc,
+	struct xfsb_bitmap		*bitmap)
+{
+	/*
+	 * Reap old metadir btree blocks with XFS_AG_RESV_NONE because the old
+	 * blocks are no longer mapped by the inode, and inode metadata space
+	 * reservations can only account freed space to the i_nblocks.
+	 */
+	struct xfs_owner_info		oinfo;
+	struct xreap_state		rs = {
+		.sc			= sc,
+		.oinfo			= &oinfo,
+		.resv			= XFS_AG_RESV_NONE,
+	};
+	int				error;
+
+	ASSERT(xfs_has_rmapbt(sc->mp));
+	ASSERT(sc->ip != NULL);
+	ASSERT(xfs_is_metadir_inode(sc->ip));
+
+	xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, XFS_DATA_FORK);
+
+	error = xfsb_bitmap_walk(bitmap, xreap_fsmeta_extent, &rs);
+	if (error)
+		return error;
+
+	if (xreap_dirty(&rs))
+		return xrep_defer_finish(sc);
+
+	return 0;
+}
+
 /*
  * Metadata files are not supposed to share blocks with anything else.
  * If blocks are shared, we remove the reverse mapping (thus reducing the

fs/xfs/scrub/reap.h

@@ -14,6 +14,8 @@ int xrep_reap_agblocks(struct xfs_scrub *sc, struct xagb_bitmap *bitmap,
 int xrep_reap_fsblocks(struct xfs_scrub *sc, struct xfsb_bitmap *bitmap,
 		const struct xfs_owner_info *oinfo);
 int xrep_reap_ifork(struct xfs_scrub *sc, struct xfs_inode *ip, int whichfork);
+int xrep_reap_metadir_fsblocks(struct xfs_scrub *sc,
+		struct xfsb_bitmap *bitmap);
 
 /* Buffer cache scan context. */
 struct xrep_bufscan {

fs/xfs/scrub/repair.c

@@ -37,6 +37,11 @@
 #include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_dir2.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtalloc.h"
+#include "xfs_metafile.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -62,6 +67,7 @@ xrep_attempt(
 	trace_xrep_attempt(XFS_I(file_inode(sc->file)), sc->sm, error);
 
 	xchk_ag_btcur_free(&sc->sa);
+	xchk_rtgroup_btcur_free(&sc->sr);
 
 	/* Repair whatever's broken. */
 	ASSERT(sc->ops->repair);
@@ -378,6 +384,41 @@ xrep_calc_ag_resblks(
 	return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz));
 }
 
+#ifdef CONFIG_XFS_RT
+/*
+ * Figure out how many blocks to reserve for a rtgroup repair.  We calculate
+ * the worst case estimate for the number of blocks we'd need to rebuild one of
+ * any type of per-rtgroup btree.
+ */
+xfs_extlen_t
+xrep_calc_rtgroup_resblks(
+	struct xfs_scrub		*sc)
+{
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_scrub_metadata	*sm = sc->sm;
+	uint64_t			usedlen;
+	xfs_extlen_t			rmapbt_sz = 0;
+
+	if (!(sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
+		return 0;
+	if (!xfs_has_rtgroups(mp)) {
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	usedlen = xfs_rtbxlen_to_blen(mp, xfs_rtgroup_extents(mp, sm->sm_agno));
+	ASSERT(usedlen <= XFS_MAX_RGBLOCKS);
+
+	if (xfs_has_rmapbt(mp))
+		rmapbt_sz = xfs_rtrmapbt_calc_size(mp, usedlen);
+
+	trace_xrep_calc_rtgroup_resblks_btsize(mp, sm->sm_agno, usedlen,
+			rmapbt_sz);
+
+	return rmapbt_sz;
+}
+#endif /* CONFIG_XFS_RT */
+
 /*
  * Reconstructing per-AG Btrees
  *
@@ -954,6 +995,22 @@ xrep_ag_init(
 }
 
 #ifdef CONFIG_XFS_RT
+/* Initialize all the btree cursors for a RT repair. */
+void
+xrep_rtgroup_btcur_init(
+	struct xfs_scrub	*sc,
+	struct xchk_rt		*sr)
+{
+	struct xfs_mount	*mp = sc->mp;
+
+	ASSERT(sr->rtg != NULL);
+
+	if (sc->sm->sm_type != XFS_SCRUB_TYPE_RTRMAPBT &&
+	    (sr->rtlock_flags & XFS_RTGLOCK_RMAP) &&
+	    xfs_has_rtrmapbt(mp))
+		sr->rmap_cur = xfs_rtrmapbt_init_cursor(sc->tp, sr->rtg);
+}
+
 /*
  * 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.
@@ -972,6 +1029,33 @@ xrep_rtgroup_init(
 
 	/* Grab our own passive reference from the caller's ref. */
 	sr->rtg = xfs_rtgroup_hold(rtg);
+	xrep_rtgroup_btcur_init(sc, sr);
+	return 0;
+}
+
+/* Ensure that all rt blocks in the given range are not marked free. */
+int
+xrep_require_rtext_inuse(
+	struct xfs_scrub	*sc,
+	xfs_rgblock_t		rgbno,
+	xfs_filblks_t		len)
+{
+	struct xfs_mount	*mp = sc->mp;
+	xfs_rtxnum_t		startrtx;
+	xfs_rtxnum_t		endrtx;
+	bool			is_free = false;
+	int			error;
+
+	startrtx = xfs_rgbno_to_rtx(mp, rgbno);
+	endrtx = xfs_rgbno_to_rtx(mp, rgbno + len - 1);
+
+	error = xfs_rtalloc_extent_is_free(sc->sr.rtg, sc->tp, startrtx,
+			endrtx - startrtx + 1, &is_free);
+	if (error)
+		return error;
+	if (is_free)
+		return -EFSCORRUPTED;
+
 	return 0;
 }
 #endif /* CONFIG_XFS_RT */
@@ -1237,3 +1321,110 @@ xrep_buf_verify_struct(
 
 	return fa == NULL;
 }
+
+/* Check the sanity of a rmap record for a metadata btree inode. */
+int
+xrep_check_ino_btree_mapping(
+	struct xfs_scrub		*sc,
+	const struct xfs_rmap_irec	*rec)
+{
+	enum xbtree_recpacking		outcome;
+	int				error;
+
+	/*
+	 * Metadata btree inodes never have extended attributes, and all blocks
+	 * should have the bmbt block flag set.
+	 */
+	if ((rec->rm_flags & XFS_RMAP_ATTR_FORK) ||
+	    !(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
+		return -EFSCORRUPTED;
+
+	/* Make sure the block is within the AG. */
+	if (!xfs_verify_agbext(sc->sa.pag, rec->rm_startblock,
+				rec->rm_blockcount))
+		return -EFSCORRUPTED;
+
+	/* Make sure this isn't free space. */
+	error = xfs_alloc_has_records(sc->sa.bno_cur, rec->rm_startblock,
+			rec->rm_blockcount, &outcome);
+	if (error)
+		return error;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/*
+ * Reset the block count of the inode being repaired, and adjust the dquot
+ * block usage to match.  The inode must not have an xattr fork.
+ */
+void
+xrep_inode_set_nblocks(
+	struct xfs_scrub	*sc,
+	int64_t			new_blocks)
+{
+	int64_t			delta =
+		new_blocks - sc->ip->i_nblocks;
+
+	sc->ip->i_nblocks = new_blocks;
+
+	xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+	if (delta != 0)
+		xfs_trans_mod_dquot_byino(sc->tp, sc->ip, XFS_TRANS_DQ_BCOUNT,
+				delta);
+}
+
+/* Reset the block reservation for a metadata inode. */
+int
+xrep_reset_metafile_resv(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_inode	*ip = sc->ip;
+	int64_t			delta;
+	int			error;
+
+	delta = ip->i_nblocks + ip->i_delayed_blks - ip->i_meta_resv_asked;
+	if (delta == 0)
+		return 0;
+
+	/*
+	 * Too many blocks have been reserved, transfer some from the incore
+	 * reservation back to the filesystem.
+	 */
+	if (delta > 0) {
+		int64_t		give_back;
+
+		give_back = min_t(uint64_t, delta, ip->i_delayed_blks);
+		if (give_back > 0) {
+			xfs_mod_delalloc(ip, 0, -give_back);
+			xfs_add_fdblocks(ip->i_mount, give_back);
+			ip->i_delayed_blks -= give_back;
+		}
+
+		return 0;
+	}
+
+	/*
+	 * Not enough reservation; try to take some blocks from the filesystem
+	 * to the metadata inode.  @delta is negative here, so invert the sign.
+	 */
+	delta = -delta;
+	error = xfs_dec_fdblocks(sc->mp, delta, true);
+	while (error == -ENOSPC) {
+		delta--;
+		if (delta == 0) {
+			xfs_warn(sc->mp,
+"Insufficient free space to reset space reservation for inode 0x%llx after repair.",
+					ip->i_ino);
+			return 0;
+		}
+		error = xfs_dec_fdblocks(sc->mp, delta, true);
+	}
+	if (error)
+		return error;
+
+	xfs_mod_delalloc(ip, 0, delta);
+	ip->i_delayed_blks += delta;
+	return 0;
+}

fs/xfs/scrub/repair.h

@@ -97,6 +97,7 @@ int xrep_setup_parent(struct xfs_scrub *sc);
 int xrep_setup_nlinks(struct xfs_scrub *sc);
 int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *resblks);
 int xrep_setup_dirtree(struct xfs_scrub *sc);
+int xrep_setup_rtrmapbt(struct xfs_scrub *sc);
 
 /* Repair setup functions */
 int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -110,10 +111,18 @@ int xrep_ag_init(struct xfs_scrub *sc, struct xfs_perag *pag,
 #ifdef CONFIG_XFS_RT
 int xrep_rtgroup_init(struct xfs_scrub *sc, struct xfs_rtgroup *rtg,
 		struct xchk_rt *sr, unsigned int rtglock_flags);
+void xrep_rtgroup_btcur_init(struct xfs_scrub *sc, struct xchk_rt *sr);
+int xrep_require_rtext_inuse(struct xfs_scrub *sc, xfs_rgblock_t rgbno,
+		xfs_filblks_t len);
+xfs_extlen_t xrep_calc_rtgroup_resblks(struct xfs_scrub *sc);
 #else
 # define xrep_rtgroup_init(sc, rtg, sr, lockflags)	(-ENOSYS)
+# define xrep_calc_rtgroup_resblks(sc)			(0)
 #endif /* CONFIG_XFS_RT */
 
+int xrep_check_ino_btree_mapping(struct xfs_scrub *sc,
+		const struct xfs_rmap_irec *rec);
+
 /* Metadata revalidators */
 
 int xrep_revalidate_allocbt(struct xfs_scrub *sc);
@@ -147,10 +156,12 @@ int xrep_metapath(struct xfs_scrub *sc);
 int xrep_rtbitmap(struct xfs_scrub *sc);
 int xrep_rtsummary(struct xfs_scrub *sc);
 int xrep_rgsuperblock(struct xfs_scrub *sc);
+int xrep_rtrmapbt(struct xfs_scrub *sc);
 #else
 # define xrep_rtbitmap			xrep_notsupported
 # define xrep_rtsummary			xrep_notsupported
 # define xrep_rgsuperblock		xrep_notsupported
+# define xrep_rtrmapbt			xrep_notsupported
 #endif /* CONFIG_XFS_RT */
 
 #ifdef CONFIG_XFS_QUOTA
@@ -169,6 +180,8 @@ int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep,
 void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp);
 
 bool xrep_buf_verify_struct(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
+void xrep_inode_set_nblocks(struct xfs_scrub *sc, int64_t new_blocks);
+int xrep_reset_metafile_resv(struct xfs_scrub *sc);
 
 #else
 
@@ -192,6 +205,8 @@ xrep_calc_ag_resblks(
 	return 0;
 }
 
+#define xrep_calc_rtgroup_resblks	xrep_calc_ag_resblks
+
 static inline int
 xrep_reset_perag_resv(
 	struct xfs_scrub	*sc)
@@ -219,6 +234,7 @@ 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_rtrmapbt		xrep_setup_nothing
 
 #define xrep_setup_inode(sc, imap)	((void)0)
 
@@ -256,6 +272,7 @@ static inline int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *x)
 #define xrep_dirtree			xrep_notsupported
 #define xrep_metapath			xrep_notsupported
 #define xrep_rgsuperblock		xrep_notsupported
+#define xrep_rtrmapbt			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 

fs/xfs/scrub/rgsuper.c

@@ -13,6 +13,7 @@
 #include "xfs_log_format.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
+#include "xfs_rmap.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
@@ -34,6 +35,7 @@ xchk_rgsuperblock_xref(
 		return;
 
 	xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), 1);
+	xchk_xref_is_only_rt_owned_by(sc, 0, 1, &XFS_RMAP_OINFO_FS);
 }
 
 int
@@ -61,7 +63,9 @@ xchk_rgsuperblock(
 	if (!xchk_xref_process_error(sc, 0, 0, &error))
 		return error;
 
-	xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP_SHARED);
+	error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP_SHARED);
+	if (error)
+		return error;
 
 	/*
 	 * Since we already validated the rt superblock at mount time, we don't

fs/xfs/scrub/rmap_repair.c

@@ -31,6 +31,8 @@
 #include "xfs_refcount.h"
 #include "xfs_refcount_btree.h"
 #include "xfs_ag.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_rtgroup.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -499,6 +501,63 @@ xrep_rmap_scan_iext(
 	return xrep_rmap_stash_accumulated(rf);
 }
 
+static int
+xrep_rmap_scan_meta_btree(
+	struct xrep_rmap_ifork	*rf,
+	struct xfs_inode	*ip)
+{
+	struct xfs_scrub	*sc = rf->rr->sc;
+	struct xfs_rtgroup	*rtg = NULL;
+	struct xfs_btree_cur	*cur = NULL;
+	enum xfs_rtg_inodes	type;
+	int			error;
+
+	if (rf->whichfork != XFS_DATA_FORK)
+		return -EFSCORRUPTED;
+
+	switch (ip->i_metatype) {
+	case XFS_METAFILE_RTRMAP:
+		type = XFS_RTGI_RMAP;
+		break;
+	default:
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) {
+		if (ip == rtg->rtg_inodes[type])
+			goto found;
+	}
+
+	/*
+	 * We should never find an rt metadata btree inode that isn't
+	 * associated with an rtgroup yet has ondisk blocks allocated to it.
+	 */
+	if (ip->i_nblocks) {
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	return 0;
+
+found:
+	switch (ip->i_metatype) {
+	case XFS_METAFILE_RTRMAP:
+		cur = xfs_rtrmapbt_init_cursor(sc->tp, rtg);
+		break;
+	default:
+		ASSERT(0);
+		error = -EFSCORRUPTED;
+		goto out_rtg;
+	}
+
+	error = xrep_rmap_scan_iroot_btree(rf, cur);
+	xfs_btree_del_cursor(cur, error);
+out_rtg:
+	xfs_rtgroup_rele(rtg);
+	return error;
+}
+
 /* Find all the extents from a given AG in an inode fork. */
 STATIC int
 xrep_rmap_scan_ifork(
@@ -512,14 +571,14 @@ xrep_rmap_scan_ifork(
 		.whichfork	= whichfork,
 	};
 	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
+	bool			mappings_done;
 	int			error = 0;
 
 	if (!ifp)
 		return 0;
 
-	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
-		bool		mappings_done;
-
+	switch (ifp->if_format) {
+	case XFS_DINODE_FMT_BTREE:
 		/*
 		 * Scan the bmap btree for data device mappings.  This includes
 		 * the btree blocks themselves, even if this is a realtime
@@ -528,15 +587,18 @@ xrep_rmap_scan_ifork(
 		error = xrep_rmap_scan_bmbt(&rf, ip, &mappings_done);
 		if (error || mappings_done)
 			return error;
-	} else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) {
-		return 0;
+		fallthrough;
+	case XFS_DINODE_FMT_EXTENTS:
+		/* Scan incore extent cache if this isn't a realtime file. */
+		if (xfs_ifork_is_realtime(ip, whichfork))
+			return 0;
+
+		return xrep_rmap_scan_iext(&rf, ifp);
+	case XFS_DINODE_FMT_META_BTREE:
+		return xrep_rmap_scan_meta_btree(&rf, ip);
 	}
 
-	/* Scan incore extent cache if this isn't a realtime file. */
-	if (xfs_ifork_is_realtime(ip, whichfork))
-		return 0;
-
-	return xrep_rmap_scan_iext(&rf, ifp);
+	return 0;
 }
 
 /*
@@ -1552,7 +1614,7 @@ xrep_rmapbt_live_update(
 	if (!xrep_rmapbt_want_live_update(&rr->iscan, &p->oinfo))
 		goto out_unlock;
 
-	trace_xrep_rmap_live_update(rr->sc->sa.pag, action, p);
+	trace_xrep_rmap_live_update(pag_group(rr->sc->sa.pag), action, p);
 
 	error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp);
 	if (error)

fs/xfs/scrub/rtbitmap.c

@@ -9,17 +9,24 @@
 #include "xfs_format.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_btree.h"
 #include "xfs_log_format.h"
 #include "xfs_trans.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
 #include "xfs_bit.h"
+#include "xfs_rtgroup.h"
 #include "xfs_sb.h"
+#include "xfs_rmap.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_exchmaps.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
+#include "scrub/tempexch.h"
 #include "scrub/rtbitmap.h"
+#include "scrub/btree.h"
 
 /* Set us up with the realtime metadata locked. */
 int
@@ -30,10 +37,15 @@ xchk_setup_rtbitmap(
 	struct xchk_rtbitmap	*rtb;
 	int			error;
 
-	rtb = kzalloc(sizeof(struct xchk_rtbitmap), XCHK_GFP_FLAGS);
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
+	rtb = kzalloc(struct_size(rtb, words, xchk_rtbitmap_wordcnt(sc)),
+			XCHK_GFP_FLAGS);
 	if (!rtb)
 		return -ENOMEM;
 	sc->buf = rtb;
+	rtb->sc = sc;
 
 	error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr);
 	if (error)
@@ -49,8 +61,7 @@ xchk_setup_rtbitmap(
 	if (error)
 		return error;
 
-	error = xchk_install_live_inode(sc,
-			sc->sr.rtg->rtg_inodes[XFS_RTGI_BITMAP]);
+	error = xchk_install_live_inode(sc, rtg_bitmap(sc->sr.rtg));
 	if (error)
 		return error;
 
@@ -58,12 +69,15 @@ xchk_setup_rtbitmap(
 	if (error)
 		return error;
 
+	error = xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL);
+	if (error)
+		return error;
+
 	/*
 	 * 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_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks);
 		rtb->rextslog = xfs_compute_rextslog(rtb->rextents);
@@ -73,7 +87,30 @@ xchk_setup_rtbitmap(
 	return 0;
 }
 
-/* Realtime bitmap. */
+/* Per-rtgroup bitmap contents. */
+
+/* Cross-reference rtbitmap entries with other metadata. */
+STATIC void
+xchk_rtbitmap_xref(
+	struct xchk_rtbitmap	*rtb,
+	xfs_rtblock_t		startblock,
+	xfs_rtblock_t		blockcount)
+{
+	struct xfs_scrub	*sc = rtb->sc;
+	xfs_rgblock_t		rgbno = xfs_rtb_to_rgbno(sc->mp, startblock);
+
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return;
+	if (!sc->sr.rmap_cur)
+		return;
+
+	xchk_xref_has_no_rt_owner(sc, rgbno, blockcount);
+
+	if (rtb->next_free_rgbno < rgbno)
+		xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno,
+				rgbno - rtb->next_free_rgbno);
+	rtb->next_free_rgbno = rgbno + blockcount;
+}
 
 /* Scrub a free extent record from the realtime bitmap. */
 STATIC int
@@ -83,7 +120,8 @@ xchk_rtbitmap_rec(
 	const struct xfs_rtalloc_rec *rec,
 	void			*priv)
 {
-	struct xfs_scrub	*sc = priv;
+	struct xchk_rtbitmap	*rtb = priv;
+	struct xfs_scrub	*sc = rtb->sc;
 	xfs_rtblock_t		startblock;
 	xfs_filblks_t		blockcount;
 
@@ -92,6 +130,12 @@ xchk_rtbitmap_rec(
 
 	if (!xfs_verify_rtbext(rtg_mount(rtg), startblock, blockcount))
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+
+	xchk_rtbitmap_xref(rtb, startblock, blockcount);
+
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return -ECANCELED;
+
 	return 0;
 }
 
@@ -139,15 +183,16 @@ xchk_rtbitmap_check_extents(
 	return error;
 }
 
-/* Scrub the realtime bitmap. */
+/* Scrub this group's realtime bitmap. */
 int
 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 xfs_inode	*rbmip = rtg_bitmap(rtg);
 	struct xchk_rtbitmap	*rtb = sc->buf;
+	xfs_rgblock_t		last_rgbno;
 	int			error;
 
 	/* Is sb_rextents correct? */
@@ -200,10 +245,20 @@ xchk_rtbitmap(
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 
-	error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, sc);
+	rtb->next_free_rgbno = 0;
+	error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, rtb);
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		return error;
 
+	/*
+	 * Check that the are rmappings for all rt extents between the end of
+	 * the last free extent we saw and the last possible extent in the rt
+	 * group.
+	 */
+	last_rgbno = rtg->rtg_extents * mp->m_sb.sb_rextsize - 1;
+	if (rtb->next_free_rgbno < last_rgbno)
+		xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno,
+				last_rgbno - rtb->next_free_rgbno);
 	return 0;
 }
 
@@ -215,7 +270,7 @@ xchk_xref_is_used_rt_space(
 	xfs_extlen_t		len)
 {
 	struct xfs_rtgroup	*rtg = sc->sr.rtg;
-	struct xfs_inode	*rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
+	struct xfs_inode	*rbmip = rtg_bitmap(rtg);
 	xfs_rtxnum_t		startext;
 	xfs_rtxnum_t		endext;
 	bool			is_free;

fs/xfs/scrub/rtbitmap.h

@@ -6,17 +6,72 @@
 #ifndef __XFS_SCRUB_RTBITMAP_H__
 #define __XFS_SCRUB_RTBITMAP_H__
 
+/*
+ * We use an xfile to construct new bitmap blocks for the portion of the
+ * rtbitmap file that we're replacing.  Whereas the ondisk bitmap must be
+ * accessed through the buffer cache, the xfile bitmap supports direct
+ * word-level accesses.  Therefore, we create a small abstraction for linear
+ * access.
+ */
+typedef unsigned long long xrep_wordoff_t;
+typedef unsigned int xrep_wordcnt_t;
+
+/* Mask to round an rtx down to the nearest bitmap word. */
+#define XREP_RTBMP_WORDMASK	((1ULL << XFS_NBWORDLOG) - 1)
+
+
 struct xchk_rtbitmap {
+	struct xfs_scrub	*sc;
+
 	uint64_t		rextents;
 	uint64_t		rbmblocks;
 	unsigned int		rextslog;
 	unsigned int		resblks;
+
+	/* The next free rt group block number that we expect to see. */
+	xfs_rgblock_t		next_free_rgbno;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+	/* stuff for staging a new bitmap */
+	struct xfs_rtalloc_args	args;
+	struct xrep_tempexch	tempexch;
+#endif
+
+	/* The next rtgroup block we expect to see during our rtrmapbt walk. */
+	xfs_rgblock_t		next_rgbno;
+
+	/* rtgroup lock flags */
+	unsigned int		rtglock_flags;
+
+	/* rtword position of xfile as we write buffers to disk. */
+	xrep_wordoff_t		prep_wordoff;
+
+	/* In-Memory rtbitmap for repair. */
+	union xfs_rtword_raw	words[];
 };
 
 #ifdef CONFIG_XFS_ONLINE_REPAIR
 int xrep_setup_rtbitmap(struct xfs_scrub *sc, struct xchk_rtbitmap *rtb);
+
+/*
+ * How big should the words[] buffer be?
+ *
+ * For repairs, we want a full fsblock worth of space so that we can memcpy a
+ * buffer full of 1s into the xfile bitmap.  The xfile bitmap doesn't have
+ * rtbitmap block headers, so we don't use blockwsize.  Scrub doesn't use the
+ * words buffer at all.
+ */
+static inline unsigned int
+xchk_rtbitmap_wordcnt(
+	struct xfs_scrub	*sc)
+{
+	if (xchk_could_repair(sc))
+		return sc->mp->m_sb.sb_blocksize >> XFS_WORDLOG;
+	return 0;
+}
 #else
 # define xrep_setup_rtbitmap(sc, rtb)	(0)
+# define xchk_rtbitmap_wordcnt(sc)	(0)
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
 #endif /* __XFS_SCRUB_RTBITMAP_H__ */

fs/xfs/scrub/rtbitmap_repair.c

@@ -12,32 +12,65 @@
 #include "xfs_btree.h"
 #include "xfs_log_format.h"
 #include "xfs_trans.h"
+#include "xfs_rtalloc.h"
 #include "xfs_inode.h"
 #include "xfs_bit.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_btree.h"
+#include "xfs_rmap.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_exchmaps.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
+#include "xfs_extent_busy.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/repair.h"
 #include "scrub/xfile.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempexch.h"
+#include "scrub/reap.h"
 #include "scrub/rtbitmap.h"
 
-/* Set up to repair the realtime bitmap file metadata. */
+/* rt bitmap content repairs */
+
+/* Set up to repair the realtime bitmap for this group. */
 int
 xrep_setup_rtbitmap(
 	struct xfs_scrub	*sc,
 	struct xchk_rtbitmap	*rtb)
 {
 	struct xfs_mount	*mp = sc->mp;
-	unsigned long long	blocks = 0;
+	char			*descr;
+	unsigned long long	blocks = mp->m_sb.sb_rbmblocks;
+	int			error;
+
+	error = xrep_tempfile_create(sc, S_IFREG);
+	if (error)
+		return error;
+
+	/* Create an xfile to hold our reconstructed bitmap. */
+	descr = xchk_xfile_rtgroup_descr(sc, "bitmap file");
+	error = xfile_create(descr, blocks * mp->m_sb.sb_blocksize, &sc->xfile);
+	kfree(descr);
+	if (error)
+		return error;
 
 	/*
-	 * Reserve enough blocks to write out a completely new bmbt for a
-	 * maximally fragmented bitmap file.  We do not hold the rtbitmap
-	 * ILOCK yet, so this is entirely speculative.
+	 * Reserve enough blocks to write out a completely new bitmap file,
+	 * plus twice as many blocks as we would need if we can only allocate
+	 * one block per data fork mapping.  This should cover the
+	 * preallocation of the temporary file and exchanging the extent
+	 * mappings.
+	 *
+	 * We cannot use xfs_exchmaps_estimate because we have not yet
+	 * constructed the replacement bitmap and therefore do not know how
+	 * many extents it will use.  By the time we do, we will have a dirty
+	 * transaction (which we cannot drop because we cannot drop the
+	 * rtbitmap ILOCK) and cannot ask for more reservation.
 	 */
-	blocks = xfs_bmbt_calc_size(mp, mp->m_sb.sb_rbmblocks);
+	blocks += xfs_bmbt_calc_size(mp, blocks) * 2;
 	if (blocks > UINT_MAX)
 		return -EOPNOTSUPP;
 
@@ -45,6 +78,304 @@ xrep_setup_rtbitmap(
 	return 0;
 }
 
+static inline xrep_wordoff_t
+rtx_to_wordoff(
+	struct xfs_mount	*mp,
+	xfs_rtxnum_t		rtx)
+{
+	return rtx >> XFS_NBWORDLOG;
+}
+
+static inline xrep_wordcnt_t
+rtxlen_to_wordcnt(
+	xfs_rtxlen_t	rtxlen)
+{
+	return rtxlen >> XFS_NBWORDLOG;
+}
+
+/* Helper functions to record rtwords in an xfile. */
+
+static inline int
+xfbmp_load(
+	struct xchk_rtbitmap	*rtb,
+	xrep_wordoff_t		wordoff,
+	xfs_rtword_t		*word)
+{
+	union xfs_rtword_raw	urk;
+	int			error;
+
+	ASSERT(xfs_has_rtgroups(rtb->sc->mp));
+
+	error = xfile_load(rtb->sc->xfile, &urk,
+			sizeof(union xfs_rtword_raw),
+			wordoff << XFS_WORDLOG);
+	if (error)
+		return error;
+
+	*word = be32_to_cpu(urk.rtg);
+	return 0;
+}
+
+static inline int
+xfbmp_store(
+	struct xchk_rtbitmap	*rtb,
+	xrep_wordoff_t		wordoff,
+	const xfs_rtword_t	word)
+{
+	union xfs_rtword_raw	urk;
+
+	ASSERT(xfs_has_rtgroups(rtb->sc->mp));
+
+	urk.rtg = cpu_to_be32(word);
+	return xfile_store(rtb->sc->xfile, &urk,
+			sizeof(union xfs_rtword_raw),
+			wordoff << XFS_WORDLOG);
+}
+
+static inline int
+xfbmp_copyin(
+	struct xchk_rtbitmap	*rtb,
+	xrep_wordoff_t		wordoff,
+	const union xfs_rtword_raw	*word,
+	xrep_wordcnt_t		nr_words)
+{
+	return xfile_store(rtb->sc->xfile, word, nr_words << XFS_WORDLOG,
+			wordoff << XFS_WORDLOG);
+}
+
+static inline int
+xfbmp_copyout(
+	struct xchk_rtbitmap	*rtb,
+	xrep_wordoff_t		wordoff,
+	union xfs_rtword_raw	*word,
+	xrep_wordcnt_t		nr_words)
+{
+	return xfile_load(rtb->sc->xfile, word, nr_words << XFS_WORDLOG,
+			wordoff << XFS_WORDLOG);
+}
+
+/* Perform a logical OR operation on an rtword in the incore bitmap. */
+static int
+xrep_rtbitmap_or(
+	struct xchk_rtbitmap	*rtb,
+	xrep_wordoff_t		wordoff,
+	xfs_rtword_t		mask)
+{
+	xfs_rtword_t		word;
+	int			error;
+
+	error = xfbmp_load(rtb, wordoff, &word);
+	if (error)
+		return error;
+
+	trace_xrep_rtbitmap_or(rtb->sc->mp, wordoff, mask, word);
+
+	return xfbmp_store(rtb, wordoff, word | mask);
+}
+
+/*
+ * Mark as free every rt extent between the next rt block we expected to see
+ * in the rtrmap records and the given rt block.
+ */
+STATIC int
+xrep_rtbitmap_mark_free(
+	struct xchk_rtbitmap	*rtb,
+	xfs_rgblock_t		rgbno)
+{
+	struct xfs_mount	*mp = rtb->sc->mp;
+	struct xfs_rtgroup	*rtg = rtb->sc->sr.rtg;
+	xfs_rtxnum_t		startrtx;
+	xfs_rtxnum_t		nextrtx;
+	xrep_wordoff_t		wordoff, nextwordoff;
+	unsigned int		bit;
+	unsigned int		bufwsize;
+	xfs_extlen_t		mod;
+	xfs_rtword_t		mask;
+	int			error;
+
+	if (!xfs_verify_rgbext(rtg, rtb->next_rgbno, rgbno - rtb->next_rgbno))
+		return -EFSCORRUPTED;
+
+	/*
+	 * Convert rt blocks to rt extents  The block range we find must be
+	 * aligned to an rtextent boundary on both ends.
+	 */
+	startrtx = xfs_rgbno_to_rtx(mp, rtb->next_rgbno);
+	mod = xfs_rgbno_to_rtxoff(mp, rtb->next_rgbno);
+	if (mod)
+		return -EFSCORRUPTED;
+
+	nextrtx = xfs_rgbno_to_rtx(mp, rgbno - 1) + 1;
+	mod = xfs_rgbno_to_rtxoff(mp, rgbno - 1);
+	if (mod != mp->m_sb.sb_rextsize - 1)
+		return -EFSCORRUPTED;
+
+	trace_xrep_rtbitmap_record_free(mp, startrtx, nextrtx - 1);
+
+	/* Set bits as needed to round startrtx up to the nearest word. */
+	bit = startrtx & XREP_RTBMP_WORDMASK;
+	if (bit) {
+		xfs_rtblock_t	len = nextrtx - startrtx;
+		unsigned int	lastbit;
+
+		lastbit = min(bit + len, XFS_NBWORD);
+		mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit;
+
+		error = xrep_rtbitmap_or(rtb, rtx_to_wordoff(mp, startrtx),
+				mask);
+		if (error || lastbit - bit == len)
+			return error;
+		startrtx += XFS_NBWORD - bit;
+	}
+
+	/* Set bits as needed to round nextrtx down to the nearest word. */
+	bit = nextrtx & XREP_RTBMP_WORDMASK;
+	if (bit) {
+		mask = ((xfs_rtword_t)1 << bit) - 1;
+
+		error = xrep_rtbitmap_or(rtb, rtx_to_wordoff(mp, nextrtx),
+				mask);
+		if (error || startrtx + bit == nextrtx)
+			return error;
+		nextrtx -= bit;
+	}
+
+	trace_xrep_rtbitmap_record_free_bulk(mp, startrtx, nextrtx - 1);
+
+	/* Set all the words in between, up to a whole fs block at once. */
+	wordoff = rtx_to_wordoff(mp, startrtx);
+	nextwordoff = rtx_to_wordoff(mp, nextrtx);
+	bufwsize = mp->m_sb.sb_blocksize >> XFS_WORDLOG;
+
+	while (wordoff < nextwordoff) {
+		xrep_wordoff_t	rem;
+		xrep_wordcnt_t	wordcnt;
+
+		wordcnt = min_t(xrep_wordcnt_t, nextwordoff - wordoff,
+				bufwsize);
+
+		/*
+		 * Try to keep us aligned to the rtwords buffer to reduce the
+		 * number of xfile writes.
+		 */
+		rem = wordoff & (bufwsize - 1);
+		if (rem)
+			wordcnt = min_t(xrep_wordcnt_t, wordcnt,
+					bufwsize - rem);
+
+		error = xfbmp_copyin(rtb, wordoff, rtb->words, wordcnt);
+		if (error)
+			return error;
+
+		wordoff += wordcnt;
+	}
+
+	return 0;
+}
+
+/* Set free space in the rtbitmap based on rtrmapbt records. */
+STATIC int
+xrep_rtbitmap_walk_rtrmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xchk_rtbitmap		*rtb = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(rtb->sc, &error))
+		return error;
+
+	if (rtb->next_rgbno < rec->rm_startblock) {
+		error = xrep_rtbitmap_mark_free(rtb, rec->rm_startblock);
+		if (error)
+			return error;
+	}
+
+	rtb->next_rgbno = max(rtb->next_rgbno,
+			      rec->rm_startblock + rec->rm_blockcount);
+	return 0;
+}
+
+/*
+ * Walk the rtrmapbt to find all the gaps between records, and mark the gaps
+ * in the realtime bitmap that we're computing.
+ */
+STATIC int
+xrep_rtbitmap_find_freespace(
+	struct xchk_rtbitmap	*rtb)
+{
+	struct xfs_scrub	*sc = rtb->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_rtgroup	*rtg = sc->sr.rtg;
+	uint64_t		blockcount;
+	int			error;
+
+	/* Prepare a buffer of ones so that we can accelerate bulk setting. */
+	memset(rtb->words, 0xFF, mp->m_sb.sb_blocksize);
+
+	xrep_rtgroup_btcur_init(sc, &sc->sr);
+	error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_rtbitmap_walk_rtrmap,
+			rtb);
+	if (error)
+		goto out;
+
+	/*
+	 * Mark as free every possible rt extent from the last one we saw to
+	 * the end of the rt group.
+	 */
+	blockcount = rtg->rtg_extents * mp->m_sb.sb_rextsize;
+	if (rtb->next_rgbno < blockcount) {
+		error = xrep_rtbitmap_mark_free(rtb, blockcount);
+		if (error)
+			goto out;
+	}
+
+out:
+	xchk_rtgroup_btcur_free(&sc->sr);
+	return error;
+}
+
+static int
+xrep_rtbitmap_prep_buf(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp,
+	void			*data)
+{
+	struct xchk_rtbitmap	*rtb = data;
+	struct xfs_mount	*mp = sc->mp;
+	union xfs_rtword_raw	*ondisk;
+	int			error;
+
+	rtb->args.mp = sc->mp;
+	rtb->args.tp = sc->tp;
+	rtb->args.rbmbp = bp;
+	ondisk = xfs_rbmblock_wordptr(&rtb->args, 0);
+	rtb->args.rbmbp = NULL;
+
+	error = xfbmp_copyout(rtb, rtb->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_RTBITMAP_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_rtbitmap_buf_ops;
+	} else {
+		bp->b_ops = &xfs_rtbuf_ops;
+	}
+
+	rtb->prep_wordoff += mp->m_blockwsize;
+	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_RTBITMAP_BUF);
+	return 0;
+}
+
 /*
  * Make sure that the given range of the data fork of the realtime file is
  * mapped to written blocks.  The caller must ensure that the inode is joined
@@ -160,9 +491,18 @@ xrep_rtbitmap(
 {
 	struct xchk_rtbitmap	*rtb = sc->buf;
 	struct xfs_mount	*mp = sc->mp;
+	struct xfs_group	*xg = rtg_group(sc->sr.rtg);
 	unsigned long long	blocks = 0;
+	unsigned int		busy_gen;
 	int			error;
 
+	/* We require the realtime rmapbt to rebuild anything. */
+	if (!xfs_has_rtrmapbt(sc->mp))
+		return -EOPNOTSUPP;
+	/* We require atomic file exchange range to rebuild anything. */
+	if (!xfs_has_exchange_range(sc->mp))
+		return -EOPNOTSUPP;
+
 	/* Impossibly large rtbitmap means we can't touch the filesystem. */
 	if (rtb->rbmblocks > U32_MAX)
 		return 0;
@@ -195,6 +535,79 @@ xrep_rtbitmap(
 	if (error)
 		return error;
 
-	/* Fix inconsistent bitmap geometry */
-	return xrep_rtbitmap_geometry(sc, rtb);
+	/*
+	 * Fix inconsistent bitmap geometry.  This function returns with a
+	 * clean scrub transaction.
+	 */
+	error = xrep_rtbitmap_geometry(sc, rtb);
+	if (error)
+		return error;
+
+	/*
+	 * Make sure the busy extent list is clear because we can't put extents
+	 * on there twice.
+	 */
+	if (!xfs_extent_busy_list_empty(xg, &busy_gen)) {
+		error = xfs_extent_busy_flush(sc->tp, xg, busy_gen, 0);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Generate the new rtbitmap data.  We don't need the rtbmp information
+	 * once this call is finished.
+	 */
+	error = xrep_rtbitmap_find_freespace(rtb);
+	if (error)
+		return error;
+
+	/*
+	 * Try to take ILOCK_EXCL of the temporary file.  We had better be the
+	 * only ones holding onto this inode, but we can't block while holding
+	 * the rtbitmap file's ILOCK_EXCL.
+	 */
+	while (!xrep_tempfile_ilock_nowait(sc)) {
+		if (xchk_should_terminate(sc, &error))
+			return error;
+		delay(1);
+	}
+
+	/*
+	 * Make sure we have space allocated for the part of the bitmap
+	 * file that corresponds to this group.  We already joined sc->ip.
+	 */
+	xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+	error = xrep_tempfile_prealloc(sc, 0, rtb->rbmblocks);
+	if (error)
+		return error;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	/* Copy the bitmap file that we generated. */
+	error = xrep_tempfile_copyin(sc, 0, rtb->rbmblocks,
+			xrep_rtbitmap_prep_buf, rtb);
+	if (error)
+		return error;
+	error = xrep_tempfile_set_isize(sc,
+			XFS_FSB_TO_B(sc->mp, sc->mp->m_sb.sb_rbmblocks));
+	if (error)
+		return error;
+
+	/*
+	 * Now exchange the data fork contents.  We're done with the temporary
+	 * buffer, so we can reuse it for the tempfile exchmaps information.
+	 */
+	error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0,
+			rtb->rbmblocks, &rtb->tempexch);
+	if (error)
+		return error;
+
+	error = xrep_tempexch_contents(sc, &rtb->tempexch);
+	if (error)
+		return error;
+
+	/* Free the old rtbitmap blocks if they're not in use. */
+	return xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK);
 }

fs/xfs/scrub/rtrmap.c

@@ -0,0 +1,271 @@
+// 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_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_inode.h"
+#include "xfs_rtalloc.h"
+#include "xfs_rtgroup.h"
+#include "xfs_metafile.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/* Set us up with the realtime metadata locked. */
+int
+xchk_setup_rtrmapbt(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
+	if (xchk_could_repair(sc)) {
+		error = xrep_setup_rtrmapbt(sc);
+		if (error)
+			return error;
+	}
+
+	error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr);
+	if (error)
+		return error;
+
+	error = xchk_setup_rt(sc);
+	if (error)
+		return error;
+
+	error = xchk_install_live_inode(sc, rtg_rmap(sc->sr.rtg));
+	if (error)
+		return error;
+
+	return xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL);
+}
+
+/* Realtime reverse mapping. */
+
+struct xchk_rtrmap {
+	/*
+	 * The furthest-reaching of the rmapbt records that we've already
+	 * processed.  This enables us to detect overlapping records for space
+	 * allocations that cannot be shared.
+	 */
+	struct xfs_rmap_irec	overlap_rec;
+
+	/*
+	 * The previous rmapbt record, so that we can check for two records
+	 * that could be one.
+	 */
+	struct xfs_rmap_irec	prev_rec;
+};
+
+/* Flag failures for records that overlap but cannot. */
+STATIC void
+xchk_rtrmapbt_check_overlapping(
+	struct xchk_btree		*bs,
+	struct xchk_rtrmap		*cr,
+	const struct xfs_rmap_irec	*irec)
+{
+	xfs_rtblock_t			pnext, inext;
+
+	if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return;
+
+	/* No previous record? */
+	if (cr->overlap_rec.rm_blockcount == 0)
+		goto set_prev;
+
+	/* Do overlap_rec and irec overlap? */
+	pnext = cr->overlap_rec.rm_startblock + cr->overlap_rec.rm_blockcount;
+	if (pnext <= irec->rm_startblock)
+		goto set_prev;
+
+	xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+	/* Save whichever rmap record extends furthest. */
+	inext = irec->rm_startblock + irec->rm_blockcount;
+	if (pnext > inext)
+		return;
+
+set_prev:
+	memcpy(&cr->overlap_rec, irec, sizeof(struct xfs_rmap_irec));
+}
+
+/* Decide if two reverse-mapping records can be merged. */
+static inline bool
+xchk_rtrmap_mergeable(
+	struct xchk_rtrmap		*cr,
+	const struct xfs_rmap_irec	*r2)
+{
+	const struct xfs_rmap_irec	*r1 = &cr->prev_rec;
+
+	/* Ignore if prev_rec is not yet initialized. */
+	if (cr->prev_rec.rm_blockcount == 0)
+		return false;
+
+	if (r1->rm_owner != r2->rm_owner)
+		return false;
+	if (r1->rm_startblock + r1->rm_blockcount != r2->rm_startblock)
+		return false;
+	if ((unsigned long long)r1->rm_blockcount + r2->rm_blockcount >
+	    XFS_RMAP_LEN_MAX)
+		return false;
+	if (r1->rm_flags != r2->rm_flags)
+		return false;
+	return r1->rm_offset + r1->rm_blockcount == r2->rm_offset;
+}
+
+/* Flag failures for records that could be merged. */
+STATIC void
+xchk_rtrmapbt_check_mergeable(
+	struct xchk_btree		*bs,
+	struct xchk_rtrmap		*cr,
+	const struct xfs_rmap_irec	*irec)
+{
+	if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return;
+
+	if (xchk_rtrmap_mergeable(cr, irec))
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+	memcpy(&cr->prev_rec, irec, sizeof(struct xfs_rmap_irec));
+}
+
+/* Cross-reference with other metadata. */
+STATIC void
+xchk_rtrmapbt_xref(
+	struct xfs_scrub	*sc,
+	struct xfs_rmap_irec	*irec)
+{
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return;
+
+	xchk_xref_is_used_rt_space(sc,
+			xfs_rgbno_to_rtb(sc->sr.rtg, irec->rm_startblock),
+			irec->rm_blockcount);
+}
+
+/* Scrub a realtime rmapbt record. */
+STATIC int
+xchk_rtrmapbt_rec(
+	struct xchk_btree		*bs,
+	const union xfs_btree_rec	*rec)
+{
+	struct xchk_rtrmap		*cr = bs->private;
+	struct xfs_rmap_irec		irec;
+
+	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL ||
+	    xfs_rtrmap_check_irec(to_rtg(bs->cur->bc_group), &irec) != NULL) {
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+		return 0;
+	}
+
+	if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return 0;
+
+	xchk_rtrmapbt_check_mergeable(bs, cr, &irec);
+	xchk_rtrmapbt_check_overlapping(bs, cr, &irec);
+	xchk_rtrmapbt_xref(bs->sc, &irec);
+	return 0;
+}
+
+/* Scrub the realtime rmap btree. */
+int
+xchk_rtrmapbt(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_inode	*ip = rtg_rmap(sc->sr.rtg);
+	struct xfs_owner_info	oinfo;
+	struct xchk_rtrmap	cr = { };
+	int			error;
+
+	error = xchk_metadata_inode_forks(sc);
+	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+		return error;
+
+	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, XFS_DATA_FORK);
+	return xchk_btree(sc, sc->sr.rmap_cur, xchk_rtrmapbt_rec, &oinfo, &cr);
+}
+
+/* xref check that the extent has no realtime reverse mapping at all */
+void
+xchk_xref_has_no_rt_owner(
+	struct xfs_scrub	*sc,
+	xfs_rgblock_t		bno,
+	xfs_extlen_t		len)
+{
+	enum xbtree_recpacking	outcome;
+	int			error;
+
+	if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm))
+		return;
+
+	error = xfs_rmap_has_records(sc->sr.rmap_cur, bno, len, &outcome);
+	if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur))
+		return;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0);
+}
+
+/* xref check that the extent is completely mapped */
+void
+xchk_xref_has_rt_owner(
+	struct xfs_scrub	*sc,
+	xfs_rgblock_t		bno,
+	xfs_extlen_t		len)
+{
+	enum xbtree_recpacking	outcome;
+	int			error;
+
+	if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm))
+		return;
+
+	error = xfs_rmap_has_records(sc->sr.rmap_cur, bno, len, &outcome);
+	if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur))
+		return;
+	if (outcome != XBTREE_RECPACKING_FULL)
+		xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0);
+}
+
+/* xref check that the extent is only owned by a given owner */
+void
+xchk_xref_is_only_rt_owned_by(
+	struct xfs_scrub		*sc,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	const struct xfs_owner_info	*oinfo)
+{
+	struct xfs_rmap_matches		res;
+	int				error;
+
+	if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm))
+		return;
+
+	error = xfs_rmap_count_owners(sc->sr.rmap_cur, bno, len, oinfo, &res);
+	if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur))
+		return;
+	if (res.matches != 1)
+		xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0);
+	if (res.bad_non_owner_matches)
+		xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0);
+	if (res.non_owner_matches)
+		xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0);
+}

fs/xfs/scrub/rtrmap_repair.c

@@ -0,0 +1,903 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 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_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_buf_mem.h"
+#include "xfs_btree_mem.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_alloc.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_quota.h"
+#include "xfs_rtalloc.h"
+#include "xfs_ag.h"
+#include "xfs_rtgroup.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/fsb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/iscan.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Realtime Reverse Mapping Btree Repair
+ * =====================================
+ *
+ * This isn't quite as difficult as repairing the rmap btree on the data
+ * device, since we only store the data fork extents of realtime files on the
+ * realtime device.  We still have to freeze the filesystem and stop the
+ * background threads like we do for the rmap repair, but we only have to scan
+ * realtime inodes.
+ *
+ * Collecting entries for the new realtime rmap btree is easy -- all we have
+ * to do is generate rtrmap entries from the data fork mappings of all realtime
+ * files in the filesystem.  We then scan the rmap btrees of the data device
+ * looking for extents belonging to the old btree and note them in a bitmap.
+ *
+ * To rebuild the realtime rmap btree, we bulk-load the collected mappings into
+ * a new btree cursor and atomically swap that into the realtime inode.  Then
+ * we can free the blocks from the old btree.
+ *
+ * We use the 'xrep_rtrmap' prefix for all the rmap functions.
+ */
+
+/* Context for collecting rmaps */
+struct xrep_rtrmap {
+	/* new rtrmapbt information */
+	struct xrep_newbt	new_btree;
+
+	/* lock for the xfbtree and xfile */
+	struct mutex		lock;
+
+	/* rmap records generated from primary metadata */
+	struct xfbtree		rtrmap_btree;
+
+	struct xfs_scrub	*sc;
+
+	/* bitmap of old rtrmapbt blocks */
+	struct xfsb_bitmap	old_rtrmapbt_blocks;
+
+	/* Hooks into rtrmap update code. */
+	struct xfs_rmap_hook	rhook;
+
+	/* inode scan cursor */
+	struct xchk_iscan	iscan;
+
+	/* in-memory btree cursor for the ->get_blocks walk */
+	struct xfs_btree_cur	*mcur;
+
+	/* Number of records we're staging in the new btree. */
+	uint64_t		nr_records;
+};
+
+/* Set us up to repair rt reverse mapping btrees. */
+int
+xrep_setup_rtrmapbt(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_rtrmap	*rr;
+	char			*descr;
+	int			error;
+
+	xchk_fsgates_enable(sc, XCHK_FSGATES_RMAP);
+
+	descr = xchk_xfile_rtgroup_descr(sc, "reverse mapping records");
+	error = xrep_setup_xfbtree(sc, descr);
+	kfree(descr);
+	if (error)
+		return error;
+
+	rr = kzalloc(sizeof(struct xrep_rtrmap), XCHK_GFP_FLAGS);
+	if (!rr)
+		return -ENOMEM;
+
+	rr->sc = sc;
+	sc->buf = rr;
+	return 0;
+}
+
+/* Make sure there's nothing funny about this mapping. */
+STATIC int
+xrep_rtrmap_check_mapping(
+	struct xfs_scrub	*sc,
+	const struct xfs_rmap_irec *rec)
+{
+	if (xfs_rtrmap_check_irec(sc->sr.rtg, rec) != NULL)
+		return -EFSCORRUPTED;
+
+	/* Make sure this isn't free space. */
+	return xrep_require_rtext_inuse(sc, rec->rm_startblock,
+			rec->rm_blockcount);
+}
+
+/* Store a reverse-mapping record. */
+static inline int
+xrep_rtrmap_stash(
+	struct xrep_rtrmap	*rr,
+	xfs_rgblock_t		startblock,
+	xfs_extlen_t		blockcount,
+	uint64_t		owner,
+	uint64_t		offset,
+	unsigned int		flags)
+{
+	struct xfs_rmap_irec	rmap = {
+		.rm_startblock	= startblock,
+		.rm_blockcount	= blockcount,
+		.rm_owner	= owner,
+		.rm_offset	= offset,
+		.rm_flags	= flags,
+	};
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_btree_cur	*mcur;
+	int			error = 0;
+
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	if (xchk_iscan_aborted(&rr->iscan))
+		return -EFSCORRUPTED;
+
+	trace_xrep_rtrmap_found(sc->mp, &rmap);
+
+	/* Add entry to in-memory btree. */
+	mutex_lock(&rr->lock);
+	mcur = xfs_rtrmapbt_mem_cursor(sc->sr.rtg, sc->tp, &rr->rtrmap_btree);
+	error = xfs_rmap_map_raw(mcur, &rmap);
+	xfs_btree_del_cursor(mcur, error);
+	if (error)
+		goto out_cancel;
+
+	error = xfbtree_trans_commit(&rr->rtrmap_btree, sc->tp);
+	if (error)
+		goto out_abort;
+
+	mutex_unlock(&rr->lock);
+	return 0;
+
+out_cancel:
+	xfbtree_trans_cancel(&rr->rtrmap_btree, sc->tp);
+out_abort:
+	xchk_iscan_abort(&rr->iscan);
+	mutex_unlock(&rr->lock);
+	return error;
+}
+
+/* Finding all file and bmbt extents. */
+
+/* Context for accumulating rmaps for an inode fork. */
+struct xrep_rtrmap_ifork {
+	/*
+	 * Accumulate rmap data here to turn multiple adjacent bmaps into a
+	 * single rmap.
+	 */
+	struct xfs_rmap_irec	accum;
+
+	struct xrep_rtrmap	*rr;
+};
+
+/* Stash an rmap that we accumulated while walking an inode fork. */
+STATIC int
+xrep_rtrmap_stash_accumulated(
+	struct xrep_rtrmap_ifork	*rf)
+{
+	if (rf->accum.rm_blockcount == 0)
+		return 0;
+
+	return xrep_rtrmap_stash(rf->rr, rf->accum.rm_startblock,
+			rf->accum.rm_blockcount, rf->accum.rm_owner,
+			rf->accum.rm_offset, rf->accum.rm_flags);
+}
+
+/* Accumulate a bmbt record. */
+STATIC int
+xrep_rtrmap_visit_bmbt(
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*rec,
+	void			*priv)
+{
+	struct xrep_rtrmap_ifork *rf = priv;
+	struct xfs_rmap_irec	*accum = &rf->accum;
+	struct xfs_mount	*mp = rf->rr->sc->mp;
+	xfs_rgblock_t		rgbno;
+	unsigned int		rmap_flags = 0;
+	int			error;
+
+	if (xfs_rtb_to_rgno(mp, rec->br_startblock) !=
+	    rtg_rgno(rf->rr->sc->sr.rtg))
+		return 0;
+
+	if (rec->br_state == XFS_EXT_UNWRITTEN)
+		rmap_flags |= XFS_RMAP_UNWRITTEN;
+
+	/* If this bmap is adjacent to the previous one, just add it. */
+	rgbno = xfs_rtb_to_rgbno(mp, rec->br_startblock);
+	if (accum->rm_blockcount > 0 &&
+	    rec->br_startoff == accum->rm_offset + accum->rm_blockcount &&
+	    rgbno == accum->rm_startblock + accum->rm_blockcount &&
+	    rmap_flags == accum->rm_flags) {
+		accum->rm_blockcount += rec->br_blockcount;
+		return 0;
+	}
+
+	/* Otherwise stash the old rmap and start accumulating a new one. */
+	error = xrep_rtrmap_stash_accumulated(rf);
+	if (error)
+		return error;
+
+	accum->rm_startblock = rgbno;
+	accum->rm_blockcount = rec->br_blockcount;
+	accum->rm_offset = rec->br_startoff;
+	accum->rm_flags = rmap_flags;
+	return 0;
+}
+
+/*
+ * Iterate the block mapping btree to collect rmap records for anything in this
+ * fork that maps to the rt volume.  Sets @mappings_done to true if we've
+ * scanned the block mappings in this fork.
+ */
+STATIC int
+xrep_rtrmap_scan_bmbt(
+	struct xrep_rtrmap_ifork *rf,
+	struct xfs_inode	*ip,
+	bool			*mappings_done)
+{
+	struct xrep_rtrmap	*rr = rf->rr;
+	struct xfs_btree_cur	*cur;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+	int			error = 0;
+
+	*mappings_done = false;
+
+	/*
+	 * If the incore extent cache is already loaded, we'll just use the
+	 * incore extent scanner to record mappings.  Don't bother walking the
+	 * ondisk extent tree.
+	 */
+	if (!xfs_need_iread_extents(ifp))
+		return 0;
+
+	/* Accumulate all the mappings in the bmap btree. */
+	cur = xfs_bmbt_init_cursor(rr->sc->mp, rr->sc->tp, ip, XFS_DATA_FORK);
+	error = xfs_bmap_query_all(cur, xrep_rtrmap_visit_bmbt, rf);
+	xfs_btree_del_cursor(cur, error);
+	if (error)
+		return error;
+
+	/* Stash any remaining accumulated rmaps and exit. */
+	*mappings_done = true;
+	return xrep_rtrmap_stash_accumulated(rf);
+}
+
+/*
+ * Iterate the in-core extent cache to collect rmap records for anything in
+ * this fork that matches the AG.
+ */
+STATIC int
+xrep_rtrmap_scan_iext(
+	struct xrep_rtrmap_ifork *rf,
+	struct xfs_ifork	*ifp)
+{
+	struct xfs_bmbt_irec	rec;
+	struct xfs_iext_cursor	icur;
+	int			error;
+
+	for_each_xfs_iext(ifp, &icur, &rec) {
+		if (isnullstartblock(rec.br_startblock))
+			continue;
+		error = xrep_rtrmap_visit_bmbt(NULL, &rec, rf);
+		if (error)
+			return error;
+	}
+
+	return xrep_rtrmap_stash_accumulated(rf);
+}
+
+/* Find all the extents on the realtime device mapped by an inode fork. */
+STATIC int
+xrep_rtrmap_scan_dfork(
+	struct xrep_rtrmap	*rr,
+	struct xfs_inode	*ip)
+{
+	struct xrep_rtrmap_ifork rf = {
+		.accum		= { .rm_owner = ip->i_ino, },
+		.rr		= rr,
+	};
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+	int			error = 0;
+
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
+		bool		mappings_done;
+
+		/*
+		 * Scan the bmbt for mappings.  If the incore extent tree is
+		 * loaded, we want to scan the cached mappings since that's
+		 * faster when the extent counts are very high.
+		 */
+		error = xrep_rtrmap_scan_bmbt(&rf, ip, &mappings_done);
+		if (error || mappings_done)
+			return error;
+	} else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) {
+		/* realtime data forks should only be extents or btree */
+		return -EFSCORRUPTED;
+	}
+
+	/* Scan incore extent cache. */
+	return xrep_rtrmap_scan_iext(&rf, ifp);
+}
+
+/* Record reverse mappings for a file. */
+STATIC int
+xrep_rtrmap_scan_inode(
+	struct xrep_rtrmap	*rr,
+	struct xfs_inode	*ip)
+{
+	unsigned int		lock_mode;
+	int			error = 0;
+
+	/* Skip the rt rmap btree inode. */
+	if (rr->sc->ip == ip)
+		return 0;
+
+	lock_mode = xfs_ilock_data_map_shared(ip);
+
+	/* Check the data fork if it's on the realtime device. */
+	if (XFS_IS_REALTIME_INODE(ip)) {
+		error = xrep_rtrmap_scan_dfork(rr, ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	xchk_iscan_mark_visited(&rr->iscan, ip);
+out_unlock:
+	xfs_iunlock(ip, lock_mode);
+	return error;
+}
+
+/* Record extents that belong to the realtime rmap inode. */
+STATIC int
+xrep_rtrmap_walk_rmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_rtrmap		*rr = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(rr->sc, &error))
+		return error;
+
+	/* Skip extents which are not owned by this inode and fork. */
+	if (rec->rm_owner != rr->sc->ip->i_ino)
+		return 0;
+
+	error = xrep_check_ino_btree_mapping(rr->sc, rec);
+	if (error)
+		return error;
+
+	return xfsb_bitmap_set(&rr->old_rtrmapbt_blocks,
+			xfs_gbno_to_fsb(cur->bc_group, rec->rm_startblock),
+			rec->rm_blockcount);
+}
+
+/* Scan one AG for reverse mappings for the realtime rmap btree. */
+STATIC int
+xrep_rtrmap_scan_ag(
+	struct xrep_rtrmap	*rr,
+	struct xfs_perag	*pag)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	int			error;
+
+	error = xrep_ag_init(sc, pag, &sc->sa);
+	if (error)
+		return error;
+
+	error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_rtrmap_walk_rmap, rr);
+	xchk_ag_free(sc, &sc->sa);
+	return error;
+}
+
+/* Count and check all collected records. */
+STATIC int
+xrep_rtrmap_check_record(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_rtrmap		*rr = priv;
+	int				error;
+
+	error = xrep_rtrmap_check_mapping(rr->sc, rec);
+	if (error)
+		return error;
+
+	rr->nr_records++;
+	return 0;
+}
+
+/* Generate all the reverse-mappings for the realtime device. */
+STATIC int
+xrep_rtrmap_find_rmaps(
+	struct xrep_rtrmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_perag	*pag = NULL;
+	struct xfs_inode	*ip;
+	struct xfs_btree_cur	*mcur;
+	int			error;
+
+	/* Generate rmaps for the realtime superblock */
+	if (xfs_has_rtsb(sc->mp) && rtg_rgno(rr->sc->sr.rtg) == 0) {
+		error = xrep_rtrmap_stash(rr, 0, sc->mp->m_sb.sb_rextsize,
+				XFS_RMAP_OWN_FS, 0, 0);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Set up for a potentially lengthy filesystem scan by reducing our
+	 * transaction resource usage for the duration.  Specifically:
+	 *
+	 * Unlock the realtime metadata inodes and cancel the transaction to
+	 * release the log grant space while we scan the filesystem.
+	 *
+	 * Create a new empty transaction to eliminate the possibility of the
+	 * inode scan deadlocking on cyclical metadata.
+	 *
+	 * We pass the empty transaction to the file scanning function to avoid
+	 * repeatedly cycling empty transactions.  This can be done even though
+	 * we take the IOLOCK to quiesce the file because empty transactions
+	 * do not take sb_internal.
+	 */
+	xchk_trans_cancel(sc);
+	xchk_rtgroup_unlock(&sc->sr);
+	error = xchk_trans_alloc_empty(sc);
+	if (error)
+		return error;
+
+	while ((error = xchk_iscan_iter(&rr->iscan, &ip)) == 1) {
+		error = xrep_rtrmap_scan_inode(rr, ip);
+		xchk_irele(sc, ip);
+		if (error)
+			break;
+
+		if (xchk_should_terminate(sc, &error))
+			break;
+	}
+	xchk_iscan_iter_finish(&rr->iscan);
+	if (error)
+		return error;
+
+	/*
+	 * Switch out for a real transaction and lock the RT metadata in
+	 * preparation for building a new tree.
+	 */
+	xchk_trans_cancel(sc);
+	error = xchk_setup_rt(sc);
+	if (error)
+		return error;
+	error = xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL);
+	if (error)
+		return error;
+
+	/*
+	 * If a hook failed to update the in-memory btree, we lack the data to
+	 * continue the repair.
+	 */
+	if (xchk_iscan_aborted(&rr->iscan))
+		return -EFSCORRUPTED;
+
+	/* Scan for old rtrmap blocks. */
+	while ((pag = xfs_perag_next(sc->mp, pag))) {
+		error = xrep_rtrmap_scan_ag(rr, pag);
+		if (error) {
+			xfs_perag_rele(pag);
+			return error;
+		}
+	}
+
+	/*
+	 * Now that we have everything locked again, we need to count the
+	 * number of rmap records stashed in the btree.  This should reflect
+	 * all actively-owned rt files in the filesystem.  At the same time,
+	 * check all our records before we start building a new btree, which
+	 * requires the rtbitmap lock.
+	 */
+	mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, NULL, &rr->rtrmap_btree);
+	rr->nr_records = 0;
+	error = xfs_rmap_query_all(mcur, xrep_rtrmap_check_record, rr);
+	xfs_btree_del_cursor(mcur, error);
+
+	return error;
+}
+
+/* Building the new rtrmap btree. */
+
+/* Retrieve rtrmapbt data for bulk load. */
+STATIC int
+xrep_rtrmap_get_records(
+	struct xfs_btree_cur		*cur,
+	unsigned int			idx,
+	struct xfs_btree_block		*block,
+	unsigned int			nr_wanted,
+	void				*priv)
+{
+	struct xrep_rtrmap		*rr = priv;
+	union xfs_btree_rec		*block_rec;
+	unsigned int			loaded;
+	int				error;
+
+	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+		int			stat = 0;
+
+		error = xfs_btree_increment(rr->mcur, 0, &stat);
+		if (error)
+			return error;
+		if (!stat)
+			return -EFSCORRUPTED;
+
+		error = xfs_rmap_get_rec(rr->mcur, &cur->bc_rec.r, &stat);
+		if (error)
+			return error;
+		if (!stat)
+			return -EFSCORRUPTED;
+
+		block_rec = xfs_btree_rec_addr(cur, idx, block);
+		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	}
+
+	return loaded;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_rtrmap_claim_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct xrep_rtrmap	*rr = priv;
+
+	return xrep_newbt_claim_block(cur, &rr->new_btree, ptr);
+}
+
+/* Figure out how much space we need to create the incore btree root block. */
+STATIC size_t
+xrep_rtrmap_iroot_size(
+	struct xfs_btree_cur	*cur,
+	unsigned int		level,
+	unsigned int		nr_this_level,
+	void			*priv)
+{
+	return xfs_rtrmap_broot_space_calc(cur->bc_mp, level, nr_this_level);
+}
+
+/*
+ * Use the collected rmap information to stage a new rmap btree.  If this is
+ * successful we'll return with the new btree root information logged to the
+ * repair transaction but not yet committed.  This implements section (III)
+ * above.
+ */
+STATIC int
+xrep_rtrmap_build_new_tree(
+	struct xrep_rtrmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_rtgroup	*rtg = sc->sr.rtg;
+	struct xfs_btree_cur	*rmap_cur;
+	int			error;
+
+	/*
+	 * Prepare to construct the new btree by reserving disk space for the
+	 * new btree and setting up all the accounting information we'll need
+	 * to root the new btree while it's under construction and before we
+	 * attach it to the realtime rmapbt inode.
+	 */
+	error = xrep_newbt_init_metadir_inode(&rr->new_btree, sc);
+	if (error)
+		return error;
+
+	rr->new_btree.bload.get_records = xrep_rtrmap_get_records;
+	rr->new_btree.bload.claim_block = xrep_rtrmap_claim_block;
+	rr->new_btree.bload.iroot_size = xrep_rtrmap_iroot_size;
+
+	rmap_cur = xfs_rtrmapbt_init_cursor(NULL, rtg);
+	xfs_btree_stage_ifakeroot(rmap_cur, &rr->new_btree.ifake);
+
+	/* Compute how many blocks we'll need for the rmaps collected. */
+	error = xfs_btree_bload_compute_geometry(rmap_cur,
+			&rr->new_btree.bload, rr->nr_records);
+	if (error)
+		goto err_cur;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		goto err_cur;
+
+	/*
+	 * Guess how many blocks we're going to need to rebuild an entire
+	 * rtrmapbt from the number of extents we found, and pump up our
+	 * transaction to have sufficient block reservation.  We're allowed
+	 * to exceed quota to repair inconsistent metadata, though this is
+	 * unlikely.
+	 */
+	error = xfs_trans_reserve_more_inode(sc->tp, rtg_rmap(rtg),
+			rr->new_btree.bload.nr_blocks, 0, true);
+	if (error)
+		goto err_cur;
+
+	/* Reserve the space we'll need for the new btree. */
+	error = xrep_newbt_alloc_blocks(&rr->new_btree,
+			rr->new_btree.bload.nr_blocks);
+	if (error)
+		goto err_cur;
+
+	/*
+	 * Create a cursor to the in-memory btree so that we can bulk load the
+	 * new btree.
+	 */
+	rr->mcur = xfs_rtrmapbt_mem_cursor(sc->sr.rtg, NULL, &rr->rtrmap_btree);
+	error = xfs_btree_goto_left_edge(rr->mcur);
+	if (error)
+		goto err_mcur;
+
+	/* Add all observed rmap records. */
+	rr->new_btree.ifake.if_fork->if_format = XFS_DINODE_FMT_META_BTREE;
+	error = xfs_btree_bload(rmap_cur, &rr->new_btree.bload, rr);
+	if (error)
+		goto err_mcur;
+
+	/*
+	 * Install the new rtrmap btree in the inode.  After this point the old
+	 * btree is no longer accessible, the new tree is live, and we can
+	 * delete the cursor.
+	 */
+	xfs_rtrmapbt_commit_staged_btree(rmap_cur, sc->tp);
+	xrep_inode_set_nblocks(rr->sc, rr->new_btree.ifake.if_blocks);
+	xfs_btree_del_cursor(rmap_cur, 0);
+	xfs_btree_del_cursor(rr->mcur, 0);
+	rr->mcur = NULL;
+
+	/*
+	 * Now that we've written the new btree to disk, we don't need to keep
+	 * updating the in-memory btree.  Abort the scan to stop live updates.
+	 */
+	xchk_iscan_abort(&rr->iscan);
+
+	/* Dispose of any unused blocks and the accounting information. */
+	error = xrep_newbt_commit(&rr->new_btree);
+	if (error)
+		return error;
+
+	return xrep_roll_trans(sc);
+
+err_mcur:
+	xfs_btree_del_cursor(rr->mcur, error);
+err_cur:
+	xfs_btree_del_cursor(rmap_cur, error);
+	xrep_newbt_cancel(&rr->new_btree);
+	return error;
+}
+
+/* Reaping the old btree. */
+
+/* Reap the old rtrmapbt blocks. */
+STATIC int
+xrep_rtrmap_remove_old_tree(
+	struct xrep_rtrmap	*rr)
+{
+	int			error;
+
+	/*
+	 * Free all the extents that were allocated to the former rtrmapbt and
+	 * aren't cross-linked with something else.
+	 */
+	error = xrep_reap_metadir_fsblocks(rr->sc, &rr->old_rtrmapbt_blocks);
+	if (error)
+		return error;
+
+	/*
+	 * Ensure the proper reservation for the rtrmap inode so that we don't
+	 * fail to expand the new btree.
+	 */
+	return xrep_reset_metafile_resv(rr->sc);
+}
+
+static inline bool
+xrep_rtrmapbt_want_live_update(
+	struct xchk_iscan		*iscan,
+	const struct xfs_owner_info	*oi)
+{
+	if (xchk_iscan_aborted(iscan))
+		return false;
+
+	/*
+	 * We scanned the CoW staging extents before we started the iscan, so
+	 * we need all the updates.
+	 */
+	if (XFS_RMAP_NON_INODE_OWNER(oi->oi_owner))
+		return true;
+
+	/* Ignore updates to files that the scanner hasn't visited yet. */
+	return xchk_iscan_want_live_update(iscan, oi->oi_owner);
+}
+
+/*
+ * Apply a rtrmapbt update from the regular filesystem into our shadow btree.
+ * We're running from the thread that owns the rtrmap ILOCK and is generating
+ * the update, so we must be careful about which parts of the struct
+ * xrep_rtrmap that we change.
+ */
+static int
+xrep_rtrmapbt_live_update(
+	struct notifier_block		*nb,
+	unsigned long			action,
+	void				*data)
+{
+	struct xfs_rmap_update_params	*p = data;
+	struct xrep_rtrmap		*rr;
+	struct xfs_mount		*mp;
+	struct xfs_btree_cur		*mcur;
+	struct xfs_trans		*tp;
+	void				*txcookie;
+	int				error;
+
+	rr = container_of(nb, struct xrep_rtrmap, rhook.rmap_hook.nb);
+	mp = rr->sc->mp;
+
+	if (!xrep_rtrmapbt_want_live_update(&rr->iscan, &p->oinfo))
+		goto out_unlock;
+
+	trace_xrep_rmap_live_update(rtg_group(rr->sc->sr.rtg), action, p);
+
+	error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp);
+	if (error)
+		goto out_abort;
+
+	mutex_lock(&rr->lock);
+	mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, tp, &rr->rtrmap_btree);
+	error = __xfs_rmap_finish_intent(mcur, action, p->startblock,
+			p->blockcount, &p->oinfo, p->unwritten);
+	xfs_btree_del_cursor(mcur, error);
+	if (error)
+		goto out_cancel;
+
+	error = xfbtree_trans_commit(&rr->rtrmap_btree, tp);
+	if (error)
+		goto out_cancel;
+
+	xrep_trans_cancel_hook_dummy(&txcookie, tp);
+	mutex_unlock(&rr->lock);
+	return NOTIFY_DONE;
+
+out_cancel:
+	xfbtree_trans_cancel(&rr->rtrmap_btree, tp);
+	xrep_trans_cancel_hook_dummy(&txcookie, tp);
+out_abort:
+	xchk_iscan_abort(&rr->iscan);
+	mutex_unlock(&rr->lock);
+out_unlock:
+	return NOTIFY_DONE;
+}
+
+/* Set up the filesystem scan components. */
+STATIC int
+xrep_rtrmap_setup_scan(
+	struct xrep_rtrmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	int			error;
+
+	mutex_init(&rr->lock);
+	xfsb_bitmap_init(&rr->old_rtrmapbt_blocks);
+
+	/* Set up some storage */
+	error = xfs_rtrmapbt_mem_init(sc->mp, &rr->rtrmap_btree, sc->xmbtp,
+			rtg_rgno(sc->sr.rtg));
+	if (error)
+		goto out_bitmap;
+
+	/* Retry iget every tenth of a second for up to 30 seconds. */
+	xchk_iscan_start(sc, 30000, 100, &rr->iscan);
+
+	/*
+	 * Hook into live rtrmap operations so that we can update our in-memory
+	 * btree to reflect live changes on the filesystem.  Since we drop the
+	 * rtrmap ILOCK to scan all the inodes, we need this piece to avoid
+	 * installing a stale btree.
+	 */
+	ASSERT(sc->flags & XCHK_FSGATES_RMAP);
+	xfs_rmap_hook_setup(&rr->rhook, xrep_rtrmapbt_live_update);
+	error = xfs_rmap_hook_add(rtg_group(sc->sr.rtg), &rr->rhook);
+	if (error)
+		goto out_iscan;
+	return 0;
+
+out_iscan:
+	xchk_iscan_teardown(&rr->iscan);
+	xfbtree_destroy(&rr->rtrmap_btree);
+out_bitmap:
+	xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks);
+	mutex_destroy(&rr->lock);
+	return error;
+}
+
+/* Tear down scan components. */
+STATIC void
+xrep_rtrmap_teardown(
+	struct xrep_rtrmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+
+	xchk_iscan_abort(&rr->iscan);
+	xfs_rmap_hook_del(rtg_group(sc->sr.rtg), &rr->rhook);
+	xchk_iscan_teardown(&rr->iscan);
+	xfbtree_destroy(&rr->rtrmap_btree);
+	xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks);
+	mutex_destroy(&rr->lock);
+}
+
+/* Repair the realtime rmap btree. */
+int
+xrep_rtrmapbt(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_rtrmap	*rr = sc->buf;
+	int			error;
+
+	/* Make sure any problems with the fork are fixed. */
+	error = xrep_metadata_inode_forks(sc);
+	if (error)
+		return error;
+
+	error = xrep_rtrmap_setup_scan(rr);
+	if (error)
+		return error;
+
+	/* Collect rmaps for realtime files. */
+	error = xrep_rtrmap_find_rmaps(rr);
+	if (error)
+		goto out_records;
+
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	/* Rebuild the rtrmap information. */
+	error = xrep_rtrmap_build_new_tree(rr);
+	if (error)
+		goto out_records;
+
+	/* Kill the old tree. */
+	error = xrep_rtrmap_remove_old_tree(rr);
+	if (error)
+		goto out_records;
+
+out_records:
+	xrep_rtrmap_teardown(rr);
+	return error;
+}

fs/xfs/scrub/rtsummary.c

@@ -81,8 +81,7 @@ xchk_setup_rtsummary(
 	if (error)
 		return error;
 
-	error = xchk_install_live_inode(sc,
-			sc->sr.rtg->rtg_inodes[XFS_RTGI_SUMMARY]);
+	error = xchk_install_live_inode(sc, rtg_summary(sc->sr.rtg));
 	if (error)
 		return error;
 
@@ -90,6 +89,10 @@ xchk_setup_rtsummary(
 	if (error)
 		return error;
 
+	error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP);
+	if (error)
+		return error;
+
 	/*
 	 * 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
@@ -100,7 +103,6 @@ xchk_setup_rtsummary(
 	 * 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) {
 		rts->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks);
 		rts->rbmblocks = xfs_rtbitmap_blockcount(mp);
@@ -191,8 +193,7 @@ xchk_rtsum_record_free(
 	rtlen = xfs_rtxlen_to_extlen(mp, rec->ar_extcount);
 
 	if (!xfs_verify_rtbext(mp, rtbno, rtlen)) {
-		xchk_ino_xref_set_corrupt(sc,
-				rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_ino);
+		xchk_ino_xref_set_corrupt(sc, rtg_bitmap(rtg)->i_ino);
 		return -EFSCORRUPTED;
 	}
 
@@ -218,7 +219,7 @@ xchk_rtsum_compute(
 
 	/* If the bitmap size doesn't match the computed size, bail. */
 	if (XFS_FSB_TO_B(mp, xfs_rtbitmap_blockcount(mp)) !=
-	    rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_disk_size)
+	    rtg_bitmap(rtg)->i_disk_size)
 		return -EFSCORRUPTED;
 
 	return xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtsum_record_free, sc);
@@ -310,8 +311,8 @@ xchk_rtsummary(
 {
 	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 xfs_inode	*rbmip = rtg_bitmap(rtg);
+	struct xfs_inode	*rsumip = rtg_summary(rtg);
 	struct xchk_rtsummary	*rts = sc->buf;
 	int			error;
 

fs/xfs/scrub/rtsummary_repair.c

@@ -165,7 +165,8 @@ xrep_rtsummary(
 	 * Now exchange the contents.  Nothing in repair uses the temporary
 	 * buffer, so we can reuse it for the tempfile exchrange information.
 	 */
-	error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, &rts->tempexch);
+	error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0,
+			rts->rsumblocks, &rts->tempexch);
 	if (error)
 		return error;
 

fs/xfs/scrub/scrub.c

@@ -164,7 +164,7 @@ xchk_fsgates_disable(
 	trace_xchk_fsgates_disable(sc, sc->flags & XCHK_FSGATES_ALL);
 
 	if (sc->flags & XCHK_FSGATES_DRAIN)
-		xfs_drain_wait_disable();
+		xfs_defer_drain_wait_disable();
 
 	if (sc->flags & XCHK_FSGATES_QUOTA)
 		xfs_dqtrx_hook_disable();
@@ -218,6 +218,8 @@ xchk_teardown(
 	int			error)
 {
 	xchk_ag_free(sc, &sc->sa);
+	xchk_rtgroup_btcur_free(&sc->sr);
+
 	if (sc->tp) {
 		if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
 			error = xfs_trans_commit(sc->tp);
@@ -458,6 +460,13 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.has	= xfs_has_rtsb,
 		.repair = xrep_rgsuperblock,
 	},
+	[XFS_SCRUB_TYPE_RTRMAPBT] = {	/* realtime group rmapbt */
+		.type	= ST_RTGROUP,
+		.setup	= xchk_setup_rtrmapbt,
+		.scrub	= xchk_rtrmapbt,
+		.has	= xfs_has_rtrmapbt,
+		.repair	= xrep_rtrmapbt,
+	},
 };
 
 static int

fs/xfs/scrub/scrub.h

@@ -126,6 +126,9 @@ struct xchk_rt {
 
 	/* XFS_RTGLOCK_* lock state if locked */
 	unsigned int		rtlock_flags;
+
+	/* rtgroup btrees */
+	struct xfs_btree_cur	*rmap_cur;
 };
 
 struct xfs_scrub {
@@ -280,10 +283,12 @@ int xchk_metapath(struct xfs_scrub *sc);
 int xchk_rtbitmap(struct xfs_scrub *sc);
 int xchk_rtsummary(struct xfs_scrub *sc);
 int xchk_rgsuperblock(struct xfs_scrub *sc);
+int xchk_rtrmapbt(struct xfs_scrub *sc);
 #else
 # define xchk_rtbitmap		xchk_nothing
 # define xchk_rtsummary		xchk_nothing
 # define xchk_rgsuperblock	xchk_nothing
+# define xchk_rtrmapbt		xchk_nothing
 #endif
 #ifdef CONFIG_XFS_QUOTA
 int xchk_quota(struct xfs_scrub *sc);
@@ -317,8 +322,17 @@ void xchk_xref_is_not_cow_staging(struct xfs_scrub *sc, xfs_agblock_t bno,
 #ifdef CONFIG_XFS_RT
 void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno,
 		xfs_extlen_t len);
+void xchk_xref_has_no_rt_owner(struct xfs_scrub *sc, xfs_rgblock_t rgbno,
+		xfs_extlen_t len);
+void xchk_xref_has_rt_owner(struct xfs_scrub *sc, xfs_rgblock_t rgbno,
+		xfs_extlen_t len);
+void xchk_xref_is_only_rt_owned_by(struct xfs_scrub *sc, xfs_rgblock_t rgbno,
+		xfs_extlen_t len, const struct xfs_owner_info *oinfo);
 #else
 # define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
+# define xchk_xref_has_no_rt_owner(sc, rtbno, len) do { } while (0)
+# define xchk_xref_has_rt_owner(sc, rtbno, len) do { } while (0)
+# define xchk_xref_is_only_rt_owned_by(sc, bno, len, oinfo) do { } while (0)
 #endif
 
 #endif	/* __XFS_SCRUB_SCRUB_H__ */

fs/xfs/scrub/stats.c

@@ -82,6 +82,7 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_DIRTREE]	= "dirtree",
 	[XFS_SCRUB_TYPE_METAPATH]	= "metapath",
 	[XFS_SCRUB_TYPE_RGSUPER]	= "rgsuper",
+	[XFS_SCRUB_TYPE_RTRMAPBT]	= "rtrmapbt",
 };
 
 /* Format the scrub stats into a text buffer, similar to pcp style. */

fs/xfs/scrub/tempexch.h

@@ -12,7 +12,7 @@ struct xrep_tempexch {
 };
 
 int xrep_tempexch_trans_reserve(struct xfs_scrub *sc, int whichfork,
-		struct xrep_tempexch *ti);
+		xfs_fileoff_t off, xfs_filblks_t len, struct xrep_tempexch *ti);
 int xrep_tempexch_trans_alloc(struct xfs_scrub *sc, int whichfork,
 		struct xrep_tempexch *ti);
 

fs/xfs/scrub/tempfile.c

@@ -606,6 +606,8 @@ STATIC int
 xrep_tempexch_prep_request(
 	struct xfs_scrub	*sc,
 	int			whichfork,
+	xfs_fileoff_t		off,
+	xfs_filblks_t		len,
 	struct xrep_tempexch	*tx)
 {
 	struct xfs_exchmaps_req	*req = &tx->req;
@@ -629,18 +631,19 @@ xrep_tempexch_prep_request(
 	/* Exchange all mappings in both forks. */
 	req->ip1 = sc->tempip;
 	req->ip2 = sc->ip;
-	req->startoff1 = 0;
-	req->startoff2 = 0;
+	req->startoff1 = off;
+	req->startoff2 = off;
 	switch (whichfork) {
 	case XFS_ATTR_FORK:
 		req->flags |= XFS_EXCHMAPS_ATTR_FORK;
 		break;
 	case XFS_DATA_FORK:
-		/* Always exchange sizes when exchanging data fork mappings. */
-		req->flags |= XFS_EXCHMAPS_SET_SIZES;
+		/* Exchange sizes when exchanging all data fork mappings. */
+		if (off == 0 && len == XFS_MAX_FILEOFF)
+			req->flags |= XFS_EXCHMAPS_SET_SIZES;
 		break;
 	}
-	req->blockcount = XFS_MAX_FILEOFF;
+	req->blockcount = len;
 
 	return 0;
 }
@@ -796,6 +799,8 @@ int
 xrep_tempexch_trans_reserve(
 	struct xfs_scrub	*sc,
 	int			whichfork,
+	xfs_fileoff_t		off,
+	xfs_filblks_t		len,
 	struct xrep_tempexch	*tx)
 {
 	int			error;
@@ -804,7 +809,7 @@ xrep_tempexch_trans_reserve(
 	xfs_assert_ilocked(sc->ip, XFS_ILOCK_EXCL);
 	xfs_assert_ilocked(sc->tempip, XFS_ILOCK_EXCL);
 
-	error = xrep_tempexch_prep_request(sc, whichfork, tx);
+	error = xrep_tempexch_prep_request(sc, whichfork, off, len, tx);
 	if (error)
 		return error;
 
@@ -842,7 +847,8 @@ xrep_tempexch_trans_alloc(
 	ASSERT(sc->tp == NULL);
 	ASSERT(xfs_has_exchange_range(sc->mp));
 
-	error = xrep_tempexch_prep_request(sc, whichfork, tx);
+	error = xrep_tempexch_prep_request(sc, whichfork, 0, XFS_MAX_FILEOFF,
+			tx);
 	if (error)
 		return error;
 

fs/xfs/scrub/trace.c

@@ -21,6 +21,7 @@
 #include "xfs_rmap.h"
 #include "xfs_parent.h"
 #include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
 #include "scrub/scrub.h"
 #include "scrub/xfile.h"
 #include "scrub/xfarray.h"

fs/xfs/scrub/trace.h

@@ -17,6 +17,7 @@
 #include "xfs_bit.h"
 #include "xfs_quota_defs.h"
 
+struct xfs_rtgroup;
 struct xfs_scrub;
 struct xfile;
 struct xfarray;
@@ -40,6 +41,9 @@ struct xchk_dirtree_outcomes;
 TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED);
 TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW);
 
+TRACE_DEFINE_ENUM(XG_TYPE_AG);
+TRACE_DEFINE_ENUM(XG_TYPE_RTG);
+
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PROBE);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_SB);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_AGF);
@@ -72,6 +76,7 @@ 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);
+TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTRMAPBT);
 
 #define XFS_SCRUB_TYPE_STRINGS \
 	{ XFS_SCRUB_TYPE_PROBE,		"probe" }, \
@@ -105,7 +110,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RGSUPER);
 	{ XFS_SCRUB_TYPE_DIRTREE,	"dirtree" }, \
 	{ XFS_SCRUB_TYPE_BARRIER,	"barrier" }, \
 	{ XFS_SCRUB_TYPE_METAPATH,	"metapath" }, \
-	{ XFS_SCRUB_TYPE_RGSUPER,	"rgsuper" }
+	{ XFS_SCRUB_TYPE_RGSUPER,	"rgsuper" }, \
+	{ XFS_SCRUB_TYPE_RTRMAPBT,	"rtrmapbt" }
 
 #define XFS_SCRUB_FLAG_STRINGS \
 	{ XFS_SCRUB_IFLAG_REPAIR,		"repair" }, \
@@ -2282,6 +2288,32 @@ TRACE_EVENT(xrep_calc_ag_resblks_btsize,
 		  __entry->rmapbt_sz,
 		  __entry->refcbt_sz)
 )
+
+#ifdef CONFIG_XFS_RT
+TRACE_EVENT(xrep_calc_rtgroup_resblks_btsize,
+	TP_PROTO(struct xfs_mount *mp, xfs_rgnumber_t rgno,
+		 xfs_rgblock_t usedlen, xfs_rgblock_t rmapbt_sz),
+	TP_ARGS(mp, rgno, usedlen, rmapbt_sz),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rgblock_t, usedlen)
+		__field(xfs_rgblock_t, rmapbt_sz)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rgno = rgno;
+		__entry->usedlen = usedlen;
+		__entry->rmapbt_sz = rmapbt_sz;
+	),
+	TP_printk("dev %d:%d rgno 0x%x usedlen %u rmapbt %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->usedlen,
+		  __entry->rmapbt_sz)
+);
+#endif /* CONFIG_XFS_RT */
+
 TRACE_EVENT(xrep_reset_counters,
 	TP_PROTO(struct xfs_mount *mp, struct xchk_fscounters *fsc),
 	TP_ARGS(mp, fsc),
@@ -2680,11 +2712,12 @@ 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(const struct xfs_perag *pag, unsigned int op,
+	TP_PROTO(const struct xfs_group *xg, unsigned int op,
 		 const struct xfs_rmap_update_params *p),
-	TP_ARGS(pag, op, p),
+	TP_ARGS(xg, op, p),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
+		__field(enum xfs_group_type, type)
 		__field(xfs_agnumber_t, agno)
 		__field(unsigned int, op)
 		__field(xfs_agblock_t, agbno)
@@ -2694,8 +2727,9 @@ TRACE_EVENT(xrep_rmap_live_update,
 		__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->agno = xg->xg_gno;
 		__entry->op = op;
 		__entry->agbno = p->startblock;
 		__entry->len = p->blockcount;
@@ -2704,10 +2738,12 @@ TRACE_EVENT(xrep_rmap_live_update,
 		if (p->unwritten)
 			__entry->flags |= XFS_RMAP_UNWRITTEN;
 	),
-	TP_printk("dev %d:%d agno 0x%x op %d agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
+	TP_printk("dev %d:%d %sno 0x%x op %d %sbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
 		  __entry->op,
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agbno,
 		  __entry->len,
 		  __entry->owner,
@@ -3605,6 +3641,186 @@ DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_try_unlink);
 DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_unlink);
 DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_link);
 
+#ifdef CONFIG_XFS_RT
+DECLARE_EVENT_CLASS(xrep_rtbitmap_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_rtxnum_t start, xfs_rtxnum_t end),
+	TP_ARGS(mp, start, end),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, rtdev)
+		__field(xfs_rtxnum_t, start)
+		__field(xfs_rtxnum_t, end)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rtdev = mp->m_rtdev_targp->bt_dev;
+		__entry->start = start;
+		__entry->end = end;
+	),
+	TP_printk("dev %d:%d rtdev %d:%d startrtx 0x%llx endrtx 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->rtdev), MINOR(__entry->rtdev),
+		  __entry->start,
+		  __entry->end)
+);
+#define DEFINE_REPAIR_RGBITMAP_EVENT(name) \
+DEFINE_EVENT(xrep_rtbitmap_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_rtxnum_t start, \
+		 xfs_rtxnum_t end), \
+	TP_ARGS(mp, start, end))
+DEFINE_REPAIR_RGBITMAP_EVENT(xrep_rtbitmap_record_free);
+DEFINE_REPAIR_RGBITMAP_EVENT(xrep_rtbitmap_record_free_bulk);
+
+TRACE_EVENT(xrep_rtbitmap_or,
+	TP_PROTO(struct xfs_mount *mp, unsigned long long wordoff,
+		 xfs_rtword_t mask, xfs_rtword_t word),
+	TP_ARGS(mp, wordoff, mask, word),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, rtdev)
+		__field(unsigned long long, wordoff)
+		__field(unsigned int, mask)
+		__field(unsigned int, word)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rtdev = mp->m_rtdev_targp->bt_dev;
+		__entry->wordoff = wordoff;
+		__entry->mask = mask;
+		__entry->word = word;
+	),
+	TP_printk("dev %d:%d rtdev %d:%d wordoff 0x%llx mask 0x%x word 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->rtdev), MINOR(__entry->rtdev),
+		  __entry->wordoff,
+		  __entry->mask,
+		  __entry->word)
+);
+
+TRACE_EVENT(xrep_rtbitmap_load,
+	TP_PROTO(struct xfs_rtgroup *rtg, xfs_fileoff_t rbmoff,
+		 xfs_rtxnum_t rtx, xfs_rtxnum_t len),
+	TP_ARGS(rtg, rbmoff, rtx, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, rtdev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_fileoff_t, rbmoff)
+		__field(xfs_rtxnum_t, rtx)
+		__field(xfs_rtxnum_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = rtg_mount(rtg)->m_super->s_dev;
+		__entry->rtdev = rtg_mount(rtg)->m_rtdev_targp->bt_dev;
+		__entry->rgno = rtg_rgno(rtg);
+		__entry->rbmoff = rbmoff;
+		__entry->rtx = rtx;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d rtdev %d:%d rgno 0x%x rbmoff 0x%llx rtx 0x%llx rtxcount 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->rtdev), MINOR(__entry->rtdev),
+		  __entry->rgno,
+		  __entry->rbmoff,
+		  __entry->rtx,
+		  __entry->len)
+);
+
+TRACE_EVENT(xrep_rtbitmap_load_words,
+	TP_PROTO(struct xfs_mount *mp, xfs_fileoff_t rbmoff,
+		 unsigned long long wordoff, unsigned int wordcnt),
+	TP_ARGS(mp, rbmoff, wordoff, wordcnt),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, rtdev)
+		__field(xfs_fileoff_t, rbmoff)
+		__field(unsigned long long, wordoff)
+		__field(unsigned int, wordcnt)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rtdev = mp->m_rtdev_targp->bt_dev;
+		__entry->rbmoff = rbmoff;
+		__entry->wordoff = wordoff;
+		__entry->wordcnt = wordcnt;
+	),
+	TP_printk("dev %d:%d rtdev %d:%d rbmoff 0x%llx wordoff 0x%llx wordcnt 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->rtdev), MINOR(__entry->rtdev),
+		  __entry->rbmoff,
+		  __entry->wordoff,
+		  __entry->wordcnt)
+);
+
+TRACE_EVENT(xrep_rtbitmap_load_word,
+	TP_PROTO(struct xfs_mount *mp, unsigned long long wordoff,
+		 unsigned int bit, xfs_rtword_t ondisk_word,
+		 xfs_rtword_t xfile_word, xfs_rtword_t word_mask),
+	TP_ARGS(mp, wordoff, bit, ondisk_word, xfile_word, word_mask),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, rtdev)
+		__field(unsigned long long, wordoff)
+		__field(unsigned int, bit)
+		__field(xfs_rtword_t, ondisk_word)
+		__field(xfs_rtword_t, xfile_word)
+		__field(xfs_rtword_t, word_mask)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rtdev = mp->m_rtdev_targp->bt_dev;
+		__entry->wordoff = wordoff;
+		__entry->bit = bit;
+		__entry->ondisk_word = ondisk_word;
+		__entry->xfile_word = xfile_word;
+		__entry->word_mask = word_mask;
+	),
+	TP_printk("dev %d:%d rtdev %d:%d wordoff 0x%llx bit %u ondisk 0x%x(0x%x) inmem 0x%x(0x%x) result 0x%x mask 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->rtdev), MINOR(__entry->rtdev),
+		  __entry->wordoff,
+		  __entry->bit,
+		  __entry->ondisk_word,
+		  __entry->ondisk_word & __entry->word_mask,
+		  __entry->xfile_word,
+		  __entry->xfile_word & ~__entry->word_mask,
+		  (__entry->xfile_word & ~__entry->word_mask) |
+		  (__entry->ondisk_word & __entry->word_mask),
+		  __entry->word_mask)
+);
+
+TRACE_EVENT(xrep_rtrmap_found,
+	TP_PROTO(struct xfs_mount *mp, const struct xfs_rmap_irec *rec),
+	TP_ARGS(mp, rec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, rtdev)
+		__field(xfs_rgblock_t, rgbno)
+		__field(xfs_extlen_t, len)
+		__field(uint64_t, owner)
+		__field(uint64_t, offset)
+		__field(unsigned int, flags)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rtdev = mp->m_rtdev_targp->bt_dev;
+		__entry->rgbno = 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 rtdev %d:%d rgbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->rtdev), MINOR(__entry->rtdev),
+		  __entry->rgbno,
+		  __entry->len,
+		  __entry->owner,
+		  __entry->offset,
+		  __entry->flags)
+);
+#endif /* CONFIG_XFS_RT */
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 #endif /* _TRACE_XFS_SCRUB_TRACE_H */

fs/xfs/xfs_buf.c

@@ -22,6 +22,7 @@
 #include "xfs_error.h"
 #include "xfs_ag.h"
 #include "xfs_buf_mem.h"
+#include "xfs_notify_failure.h"
 
 struct kmem_cache *xfs_buf_cache;
 

fs/xfs/xfs_buf_item_recover.c

@@ -262,6 +262,9 @@ xlog_recover_validate_buf_type(
 		case XFS_BMAP_MAGIC:
 			bp->b_ops = &xfs_bmbt_buf_ops;
 			break;
+		case XFS_RTRMAP_CRC_MAGIC:
+			bp->b_ops = &xfs_rtrmapbt_buf_ops;
+			break;
 		case XFS_RMAP_CRC_MAGIC:
 			bp->b_ops = &xfs_rmapbt_buf_ops;
 			break;
@@ -855,6 +858,7 @@ xlog_recover_get_buf_lsn(
 		uuid = &btb->bb_u.s.bb_uuid;
 		break;
 	}
+	case XFS_RTRMAP_CRC_MAGIC:
 	case XFS_BMAP_CRC_MAGIC:
 	case XFS_BMAP_MAGIC: {
 		struct xfs_btree_block *btb = blk;

fs/xfs/xfs_drain.c

@@ -13,28 +13,28 @@
 #include "xfs_trace.h"
 
 /*
- * Use a static key here to reduce the overhead of xfs_drain_rele.  If the
- * compiler supports jump labels, the static branch will be replaced by a nop
- * sled when there are no xfs_drain_wait callers.  Online fsck is currently
- * the only caller, so this is a reasonable tradeoff.
+ * Use a static key here to reduce the overhead of xfs_defer_drain_rele.  If
+ * the compiler supports jump labels, the static branch will be replaced by a
+ * nop sled when there are no xfs_defer_drain_wait callers.  Online fsck is
+ * currently the only caller, so this is a reasonable tradeoff.
  *
  * Note: Patching the kernel code requires taking the cpu hotplug lock.  Other
  * parts of the kernel allocate memory with that lock held, which means that
  * XFS callers cannot hold any locks that might be used by memory reclaim or
  * writeback when calling the static_branch_{inc,dec} functions.
  */
-static DEFINE_STATIC_KEY_FALSE(xfs_drain_waiter_gate);
+static DEFINE_STATIC_KEY_FALSE(xfs_defer_drain_waiter_gate);
 
 void
-xfs_drain_wait_disable(void)
+xfs_defer_drain_wait_disable(void)
 {
-	static_branch_dec(&xfs_drain_waiter_gate);
+	static_branch_dec(&xfs_defer_drain_waiter_gate);
 }
 
 void
-xfs_drain_wait_enable(void)
+xfs_defer_drain_wait_enable(void)
 {
-	static_branch_inc(&xfs_drain_waiter_gate);
+	static_branch_inc(&xfs_defer_drain_waiter_gate);
 }
 
 void
@@ -71,7 +71,7 @@ static inline bool has_waiters(struct wait_queue_head *wq_head)
 static inline void xfs_defer_drain_rele(struct xfs_defer_drain *dr)
 {
 	if (atomic_dec_and_test(&dr->dr_count) &&
-	    static_branch_unlikely(&xfs_drain_waiter_gate) &&
+	    static_branch_unlikely(&xfs_defer_drain_waiter_gate) &&
 	    has_waiters(&dr->dr_waiters))
 		wake_up(&dr->dr_waiters);
 }

fs/xfs/xfs_drain.h

@@ -26,8 +26,8 @@ struct xfs_defer_drain {
 void xfs_defer_drain_init(struct xfs_defer_drain *dr);
 void xfs_defer_drain_free(struct xfs_defer_drain *dr);
 
-void xfs_drain_wait_disable(void);
-void xfs_drain_wait_enable(void);
+void xfs_defer_drain_wait_disable(void);
+void xfs_defer_drain_wait_enable(void);
 
 /*
  * Deferred Work Intent Drains
@@ -61,6 +61,9 @@ void xfs_drain_wait_enable(void);
  * All functions that create work items must increment the intent counter as
  * soon as the item is added to the transaction and cannot drop the counter
  * until the item is finished or cancelled.
+ *
+ * The same principles apply to realtime groups because the rt metadata inode
+ * ILOCKs are not held across transaction rolls.
  */
 struct xfs_group *xfs_group_intent_get(struct xfs_mount *mp,
 		xfs_fsblock_t fsbno, enum xfs_group_type type);

fs/xfs/xfs_fsmap.c

@@ -26,6 +26,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_ag.h"
 #include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
 
 /* Convert an xfs_fsmap to an fsmap. */
 static void
@@ -832,6 +833,174 @@ xfs_getfsmap_rtdev_rtbitmap(
 
 	return error;
 }
+
+/* Transform a realtime rmapbt record into a fsmap */
+STATIC int
+xfs_getfsmap_rtdev_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_group_helper(info, cur->bc_tp, cur->bc_group,
+			rec->rm_startblock, rec->rm_blockcount, &frec);
+}
+
+/* Actually query the rtrmap btree. */
+STATIC int
+xfs_getfsmap_rtdev_rmapbt_query(
+	struct xfs_trans		*tp,
+	struct xfs_getfsmap_info	*info,
+	struct xfs_btree_cur		**curpp)
+{
+	struct xfs_rtgroup		*rtg = to_rtg(info->group);
+
+	/* Query the rtrmapbt */
+	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+	*curpp = xfs_rtrmapbt_init_cursor(tp, rtg);
+	return xfs_rmap_query_range(*curpp, &info->low, &info->high,
+			xfs_getfsmap_rtdev_rmapbt_helper, info);
+}
+
+/* Execute a getfsmap query against the realtime device rmapbt. */
+STATIC int
+xfs_getfsmap_rtdev_rmapbt(
+	struct xfs_trans		*tp,
+	const struct xfs_fsmap		*keys,
+	struct xfs_getfsmap_info	*info)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_rtgroup		*rtg = NULL;
+	struct xfs_btree_cur		*bt_cur = NULL;
+	xfs_rtblock_t			start_rtb;
+	xfs_rtblock_t			end_rtb;
+	xfs_rgnumber_t			start_rg, end_rg;
+	uint64_t			eofs;
+	int				error = 0;
+
+	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
+	if (keys[0].fmr_physical >= eofs)
+		return 0;
+	start_rtb = xfs_daddr_to_rtb(mp, keys[0].fmr_physical);
+	end_rtb = xfs_daddr_to_rtb(mp, min(eofs - 1, keys[1].fmr_physical));
+
+	info->missing_owner = XFS_FMR_OWN_FREE;
+
+	/*
+	 * Convert the fsmap low/high keys to rtgroup based keys.  Initialize
+	 * low to the fsmap low key and max out the high key to the end
+	 * of the rtgroup.
+	 */
+	info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
+	error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
+	if (error)
+		return error;
+	info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length);
+	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
+
+	/* Adjust the low key if we are continuing from where we left off. */
+	if (info->low.rm_blockcount == 0) {
+		/* No previous record from which to continue */
+	} else if (rmap_not_shareable(mp, &info->low)) {
+		/* Last record seen was an unshareable extent */
+		info->low.rm_owner = 0;
+		info->low.rm_offset = 0;
+
+		start_rtb += info->low.rm_blockcount;
+		if (xfs_rtb_to_daddr(mp, start_rtb) >= eofs)
+			return 0;
+	} else {
+		/* Last record seen was a shareable file data extent */
+		info->low.rm_offset += info->low.rm_blockcount;
+	}
+	info->low.rm_startblock = xfs_rtb_to_rgbno(mp, start_rtb);
+
+	info->high.rm_startblock = -1U;
+	info->high.rm_owner = ULLONG_MAX;
+	info->high.rm_offset = ULLONG_MAX;
+	info->high.rm_blockcount = 0;
+	info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS;
+
+	start_rg = xfs_rtb_to_rgno(mp, start_rtb);
+	end_rg = xfs_rtb_to_rgno(mp, end_rtb);
+
+	while ((rtg = xfs_rtgroup_next_range(mp, rtg, start_rg, end_rg))) {
+		/*
+		 * Set the rtgroup high key from the fsmap high key if this
+		 * is the last rtgroup that we're querying.
+		 */
+		info->group = rtg_group(rtg);
+		if (rtg_rgno(rtg) == end_rg) {
+			info->high.rm_startblock =
+				xfs_rtb_to_rgbno(mp, end_rtb);
+			info->high.rm_offset =
+				XFS_BB_TO_FSBT(mp, keys[1].fmr_offset);
+			error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]);
+			if (error)
+				break;
+			xfs_getfsmap_set_irec_flags(&info->high, &keys[1]);
+		}
+
+		if (bt_cur) {
+			xfs_rtgroup_unlock(to_rtg(bt_cur->bc_group),
+					XFS_RTGLOCK_RMAP);
+			xfs_btree_del_cursor(bt_cur, XFS_BTREE_NOERROR);
+			bt_cur = NULL;
+		}
+
+		trace_xfs_fsmap_low_group_key(mp, info->dev, rtg_rgno(rtg),
+				&info->low);
+		trace_xfs_fsmap_high_group_key(mp, info->dev, rtg_rgno(rtg),
+				&info->high);
+
+		error = xfs_getfsmap_rtdev_rmapbt_query(tp, info, &bt_cur);
+		if (error)
+			break;
+
+		/*
+		 * Set the rtgroup low key to the start of the rtgroup prior to
+		 * moving on to the next rtgroup.
+		 */
+		if (rtg_rgno(rtg) == start_rg)
+			memset(&info->low, 0, sizeof(info->low));
+
+		/*
+		 * If this is the last rtgroup, report any gap at the end of it
+		 * before we drop the reference to the perag when the loop
+		 * terminates.
+		 */
+		if (rtg_rgno(rtg) == end_rg) {
+			info->last = true;
+			error = xfs_getfsmap_rtdev_rmapbt_helper(bt_cur,
+					&info->high, info);
+			if (error)
+				break;
+		}
+		info->group = NULL;
+	}
+
+	if (bt_cur) {
+		xfs_rtgroup_unlock(to_rtg(bt_cur->bc_group),
+				XFS_RTGLOCK_RMAP);
+		xfs_btree_del_cursor(bt_cur, error < 0 ? XFS_BTREE_ERROR :
+							 XFS_BTREE_NOERROR);
+	}
+
+	/* loop termination case */
+	if (rtg) {
+		info->group = NULL;
+		xfs_rtgroup_rele(rtg);
+	}
+
+	return error;
+}
 #endif /* CONFIG_XFS_RT */
 
 /* Do we recognize the device? */
@@ -971,7 +1140,10 @@ xfs_getfsmap(
 	if (mp->m_rtdev_targp) {
 		handlers[2].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
 		handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev);
-		handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap;
+		if (use_rmap)
+			handlers[2].fn = xfs_getfsmap_rtdev_rmapbt;
+		else
+			handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap;
 	}
 #endif /* CONFIG_XFS_RT */
 

fs/xfs/xfs_fsops.c

@@ -22,6 +22,7 @@
 #include "xfs_ag_resv.h"
 #include "xfs_trace.h"
 #include "xfs_rtalloc.h"
+#include "xfs_rtrmap_btree.h"
 
 /*
  * Write new AG headers to disk. Non-transactional, but need to be
@@ -114,6 +115,12 @@ xfs_growfs_data_private(
 		xfs_buf_relse(bp);
 	}
 
+	/* Make sure the new fs size won't cause problems with the log. */
+	error = xfs_growfs_check_rtgeom(mp, nb, mp->m_sb.sb_rblocks,
+			mp->m_sb.sb_rextsize);
+	if (error)
+		return error;
+
 	nb_div = nb;
 	nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
 	if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS)
@@ -221,7 +228,11 @@ xfs_growfs_data_private(
 		error = xfs_fs_reserve_ag_blocks(mp);
 		if (error == -ENOSPC)
 			error = 0;
+
+		/* Compute new maxlevels for rt btrees. */
+		xfs_rtrmapbt_compute_maxlevels(mp);
 	}
+
 	return error;
 
 out_trans_cancel:

fs/xfs/xfs_health.c

@@ -447,6 +447,7 @@ 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 },
+	{ XFS_SICK_RG_RMAPBT,	XFS_RTGROUP_GEOM_SICK_RMAPBT },
 };
 
 /* Fill out rtgroup geometry health info. */

fs/xfs/xfs_inode.c

@@ -2382,7 +2382,16 @@ xfs_iflush(
 			__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
 		goto flush_out;
 	}
-	if (S_ISREG(VFS_I(ip)->i_mode)) {
+	if (ip->i_df.if_format == XFS_DINODE_FMT_META_BTREE) {
+		if (!S_ISREG(VFS_I(ip)->i_mode) ||
+		    !(ip->i_diflags2 & XFS_DIFLAG2_METADATA)) {
+			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+				"%s: Bad %s meta btree inode %Lu, ptr "PTR_FMT,
+				__func__, xfs_metafile_type_str(ip->i_metatype),
+				ip->i_ino, ip);
+			goto flush_out;
+		}
+	} else if (S_ISREG(VFS_I(ip)->i_mode)) {
 		if (XFS_TEST_ERROR(
 		    ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
 		    ip->i_df.if_format != XFS_DINODE_FMT_BTREE,
@@ -2422,6 +2431,14 @@ xfs_iflush(
 		goto flush_out;
 	}
 
+	if (xfs_inode_has_attr_fork(ip) &&
+	    ip->i_af.if_format == XFS_DINODE_FMT_META_BTREE) {
+		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+			"%s: meta btree in inode %Lu attr fork, ptr "PTR_FMT,
+			__func__, ip->i_ino, ip);
+		goto flush_out;
+	}
+
 	/*
 	 * Inode item log recovery for v2 inodes are dependent on the flushiter
 	 * count for correct sequencing.  We bump the flush iteration count so

fs/xfs/xfs_inode_item.c

@@ -242,6 +242,7 @@ xfs_inode_item_data_fork_size(
 		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
+	case XFS_DINODE_FMT_META_BTREE:
 		if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
 		    ip->i_df.if_broot_bytes > 0) {
 			*nbytes += ip->i_df.if_broot_bytes;
@@ -362,6 +363,7 @@ xfs_inode_item_format_data_fork(
 		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
+	case XFS_DINODE_FMT_META_BTREE:
 		iip->ili_fields &=
 			~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV);
 

fs/xfs/xfs_inode_item_recover.c

@@ -22,6 +22,7 @@
 #include "xfs_log_recover.h"
 #include "xfs_icache.h"
 #include "xfs_bmap_btree.h"
+#include "xfs_rtrmap_btree.h"
 
 STATIC void
 xlog_recover_inode_ra_pass2(
@@ -266,6 +267,38 @@ xlog_dinode_verify_extent_counts(
 	return 0;
 }
 
+static inline int
+xlog_recover_inode_dbroot(
+	struct xfs_mount	*mp,
+	void			*src,
+	unsigned int		len,
+	struct xfs_dinode	*dip)
+{
+	void			*dfork = XFS_DFORK_DPTR(dip);
+	unsigned int		dsize = XFS_DFORK_DSIZE(dip, mp);
+
+	switch (dip->di_format) {
+	case XFS_DINODE_FMT_BTREE:
+		xfs_bmbt_to_bmdr(mp, src, len, dfork, dsize);
+		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		switch (be16_to_cpu(dip->di_metatype)) {
+		case XFS_METAFILE_RTRMAP:
+			xfs_rtrmapbt_to_disk(mp, src, len, dfork, dsize);
+			return 0;
+		default:
+			ASSERT(0);
+			return -EFSCORRUPTED;
+		}
+		break;
+	default:
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	return 0;
+}
+
 STATIC int
 xlog_recover_inode_commit_pass2(
 	struct xlog			*log,
@@ -393,8 +426,9 @@ xlog_recover_inode_commit_pass2(
 
 
 	if (unlikely(S_ISREG(ldip->di_mode))) {
-		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
-		    (ldip->di_format != XFS_DINODE_FMT_BTREE)) {
+		if (ldip->di_format != XFS_DINODE_FMT_EXTENTS &&
+		    ldip->di_format != XFS_DINODE_FMT_BTREE &&
+		    ldip->di_format != XFS_DINODE_FMT_META_BTREE) {
 			XFS_CORRUPTION_ERROR(
 				"Bad log dinode data fork format for regular file",
 				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
@@ -475,9 +509,9 @@ xlog_recover_inode_commit_pass2(
 		break;
 
 	case XFS_ILOG_DBROOT:
-		xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src, len,
-				 (struct xfs_bmdr_block *)XFS_DFORK_DPTR(dip),
-				 XFS_DFORK_DSIZE(dip, mp));
+		error = xlog_recover_inode_dbroot(mp, src, len, dip);
+		if (error)
+			goto out_release;
 		break;
 
 	default:

fs/xfs/xfs_log_recover.c

@@ -1820,6 +1820,8 @@ static const struct xlog_recover_item_ops *xlog_recover_item_ops[] = {
 	&xlog_xmd_item_ops,
 	&xlog_rtefi_item_ops,
 	&xlog_rtefd_item_ops,
+	&xlog_rtrui_item_ops,
+	&xlog_rtrud_item_ops,
 };
 
 static const struct xlog_recover_item_ops *

fs/xfs/xfs_mount.c

@@ -37,6 +37,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_metafile.h"
 #include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
 #include "scrub/stats.h"
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
@@ -655,8 +656,7 @@ static inline void
 xfs_rtbtree_compute_maxlevels(
 	struct xfs_mount	*mp)
 {
-	/* This will be filled in later. */
-	mp->m_rtbtree_maxlevels = 0;
+	mp->m_rtbtree_maxlevels = mp->m_rtrmap_maxlevels;
 }
 
 /*
@@ -727,6 +727,7 @@ xfs_mountfs(
 	xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
 	xfs_mount_setup_inode_geom(mp);
 	xfs_rmapbt_compute_maxlevels(mp);
+	xfs_rtrmapbt_compute_maxlevels(mp);
 	xfs_refcountbt_compute_maxlevels(mp);
 
 	xfs_agbtree_compute_maxlevels(mp);

fs/xfs/xfs_mount.h

@@ -158,11 +158,14 @@ typedef struct xfs_mount {
 	uint			m_bmap_dmnr[2];	/* min bmap btree records */
 	uint			m_rmap_mxr[2];	/* max rmap btree records */
 	uint			m_rmap_mnr[2];	/* min rmap btree records */
+	uint			m_rtrmap_mxr[2]; /* max rtrmap btree records */
+	uint			m_rtrmap_mnr[2]; /* min rtrmap btree records */
 	uint			m_refc_mxr[2];	/* max refc btree records */
 	uint			m_refc_mnr[2];	/* min refc btree records */
 	uint			m_alloc_maxlevels; /* max alloc btree levels */
 	uint			m_bm_maxlevels[2]; /* max bmap btree levels */
 	uint			m_rmap_maxlevels; /* max rmap btree levels */
+	uint			m_rtrmap_maxlevels; /* max rtrmap btree level */
 	uint			m_refc_maxlevels; /* max refcount btree level */
 	unsigned int		m_agbtree_maxlevels; /* max level of all AG btrees */
 	unsigned int		m_rtbtree_maxlevels; /* max level of all rt btrees */
@@ -399,6 +402,12 @@ static inline bool xfs_has_rtsb(struct xfs_mount *mp)
 	return xfs_has_rtgroups(mp) && xfs_has_realtime(mp);
 }
 
+static inline bool xfs_has_rtrmapbt(struct xfs_mount *mp)
+{
+	return xfs_has_rtgroups(mp) && xfs_has_realtime(mp) &&
+	       xfs_has_rmapbt(mp);
+}
+
 /*
  * Some features are always on for v5 file systems, allow the compiler to
  * eliminiate dead code when building without v4 support.

fs/xfs/xfs_notify_failure.c

@@ -19,6 +19,9 @@
 #include "xfs_rtalloc.h"
 #include "xfs_trans.h"
 #include "xfs_ag.h"
+#include "xfs_notify_failure.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
 
 #include <linux/mm.h>
 #include <linux/dax.h>
@@ -154,23 +157,115 @@ xfs_dax_notify_failure_thaw(
 }
 
 static int
-xfs_dax_notify_ddev_failure(
+xfs_dax_translate_range(
+	struct xfs_buftarg	*btp,
+	u64			offset,
+	u64			len,
+	xfs_daddr_t		*daddr,
+	uint64_t		*bblen)
+{
+	u64			dev_start = btp->bt_dax_part_off;
+	u64			dev_len = bdev_nr_bytes(btp->bt_bdev);
+	u64			dev_end = dev_start + dev_len - 1;
+
+	/* Notify failure on the whole device. */
+	if (offset == 0 && len == U64_MAX) {
+		offset = dev_start;
+		len = dev_len;
+	}
+
+	/* Ignore the range out of filesystem area */
+	if (offset + len - 1 < dev_start)
+		return -ENXIO;
+	if (offset > dev_end)
+		return -ENXIO;
+
+	/* Calculate the real range when it touches the boundary */
+	if (offset > dev_start)
+		offset -= dev_start;
+	else {
+		len -= dev_start - offset;
+		offset = 0;
+	}
+	if (offset + len - 1 > dev_end)
+		len = dev_end - offset + 1;
+
+	*daddr = BTOBB(offset);
+	*bblen = BTOBB(len);
+	return 0;
+}
+
+static int
+xfs_dax_notify_logdev_failure(
 	struct xfs_mount	*mp,
-	xfs_daddr_t		daddr,
-	xfs_daddr_t		bblen,
+	u64			offset,
+	u64			len,
 	int			mf_flags)
+{
+	xfs_daddr_t		daddr;
+	uint64_t		bblen;
+	int			error;
+
+	/*
+	 * Return ENXIO instead of shutting down the filesystem if the failed
+	 * region is beyond the end of the log.
+	 */
+	error = xfs_dax_translate_range(mp->m_logdev_targp,
+			offset, len, &daddr, &bblen);
+	if (error)
+		return error;
+
+	/*
+	 * In the pre-remove case the failure notification is attempting to
+	 * trigger a force unmount.  The expectation is that the device is
+	 * still present, but its removal is in progress and can not be
+	 * cancelled, proceed with accessing the log device.
+	 */
+	if (mf_flags & MF_MEM_PRE_REMOVE)
+		return 0;
+
+	xfs_err(mp, "ondisk log corrupt, shutting down fs!");
+	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
+	return -EFSCORRUPTED;
+}
+
+static int
+xfs_dax_notify_dev_failure(
+	struct xfs_mount	*mp,
+	u64			offset,
+	u64			len,
+	int			mf_flags,
+	enum xfs_group_type	type)
 {
 	struct xfs_failure_info	notify = { .mf_flags = mf_flags };
 	struct xfs_trans	*tp = NULL;
 	struct xfs_btree_cur	*cur = NULL;
-	struct xfs_buf		*agf_bp = NULL;
 	int			error = 0;
 	bool			kernel_frozen = false;
-	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, daddr);
-	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, fsbno);
-	xfs_fsblock_t		end_fsbno = XFS_DADDR_TO_FSB(mp,
-							     daddr + bblen - 1);
-	xfs_agnumber_t		end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);
+	uint32_t		start_gno, end_gno;
+	xfs_fsblock_t		start_bno, end_bno;
+	xfs_daddr_t		daddr;
+	uint64_t		bblen;
+	struct xfs_group	*xg = NULL;
+
+	if (!xfs_has_rmapbt(mp)) {
+		xfs_debug(mp, "notify_failure() needs rmapbt enabled!");
+		return -EOPNOTSUPP;
+	}
+
+	error = xfs_dax_translate_range(type == XG_TYPE_RTG ?
+			mp->m_rtdev_targp : mp->m_ddev_targp,
+			offset, len, &daddr, &bblen);
+	if (error)
+		return error;
+
+	if (type == XG_TYPE_RTG) {
+		start_bno = xfs_daddr_to_rtb(mp, daddr);
+		end_bno = xfs_daddr_to_rtb(mp, daddr + bblen - 1);
+	} else {
+		start_bno = XFS_DADDR_TO_FSB(mp, daddr);
+		end_bno = XFS_DADDR_TO_FSB(mp, daddr + bblen - 1);
+	}
 
 	if (mf_flags & MF_MEM_PRE_REMOVE) {
 		xfs_info(mp, "Device is about to be removed!");
@@ -189,46 +284,58 @@ xfs_dax_notify_ddev_failure(
 	if (error)
 		goto out;
 
-	for (; agno <= end_agno; agno++) {
+	start_gno = xfs_fsb_to_gno(mp, start_bno, type);
+	end_gno = xfs_fsb_to_gno(mp, end_bno, type);
+	while ((xg = xfs_group_next_range(mp, xg, start_gno, end_gno, type))) {
+		struct xfs_buf		*agf_bp = NULL;
+		struct xfs_rtgroup	*rtg = NULL;
 		struct xfs_rmap_irec	ri_low = { };
 		struct xfs_rmap_irec	ri_high;
-		struct xfs_agf		*agf;
-		struct xfs_perag	*pag;
-		xfs_agblock_t		range_agend;
 
-		pag = xfs_perag_get(mp, agno);
-		error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
-		if (error) {
-			xfs_perag_put(pag);
-			break;
+		if (type == XG_TYPE_AG) {
+			struct xfs_perag	*pag = to_perag(xg);
+
+			error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
+			if (error) {
+				xfs_perag_put(pag);
+				break;
+			}
+
+			cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag);
+		} else {
+			rtg = to_rtg(xg);
+			xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+			cur = xfs_rtrmapbt_init_cursor(tp, rtg);
 		}
 
-		cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag);
-
 		/*
 		 * Set the rmap range from ri_low to ri_high, which represents
 		 * a [start, end] where we looking for the files or metadata.
 		 */
 		memset(&ri_high, 0xFF, sizeof(ri_high));
-		ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno);
-		if (agno == end_agno)
-			ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno);
+		if (xg->xg_gno == start_gno)
+			ri_low.rm_startblock =
+				xfs_fsb_to_gbno(mp, start_bno, type);
+		if (xg->xg_gno == end_gno)
+			ri_high.rm_startblock =
+				xfs_fsb_to_gbno(mp, end_bno, type);
 
-		agf = agf_bp->b_addr;
-		range_agend = min(be32_to_cpu(agf->agf_length) - 1,
-				ri_high.rm_startblock);
 		notify.startblock = ri_low.rm_startblock;
-		notify.blockcount = range_agend + 1 - ri_low.rm_startblock;
+		notify.blockcount = min(xg->xg_block_count,
+					ri_high.rm_startblock + 1) -
+					ri_low.rm_startblock;
 
 		error = xfs_rmap_query_range(cur, &ri_low, &ri_high,
 				xfs_dax_failure_fn, &notify);
 		xfs_btree_del_cursor(cur, error);
-		xfs_trans_brelse(tp, agf_bp);
-		xfs_perag_put(pag);
-		if (error)
+		if (agf_bp)
+			xfs_trans_brelse(tp, agf_bp);
+		if (rtg)
+			xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
+		if (error) {
+			xfs_group_put(xg);
 			break;
-
-		fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0);
+		}
 	}
 
 	xfs_trans_cancel(tp);
@@ -263,67 +370,20 @@ xfs_dax_notify_failure(
 	int			mf_flags)
 {
 	struct xfs_mount	*mp = dax_holder(dax_dev);
-	u64			ddev_start;
-	u64			ddev_end;
 
 	if (!(mp->m_super->s_flags & SB_BORN)) {
 		xfs_warn(mp, "filesystem is not ready for notify_failure()!");
 		return -EIO;
 	}
 
-	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) {
-		xfs_debug(mp,
-			 "notify_failure() not supported on realtime device!");
-		return -EOPNOTSUPP;
+	if (mp->m_logdev_targp != mp->m_ddev_targp &&
+	    mp->m_logdev_targp->bt_daxdev == dax_dev) {
+		return xfs_dax_notify_logdev_failure(mp, offset, len, mf_flags);
 	}
 
-	if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev &&
-	    mp->m_logdev_targp != mp->m_ddev_targp) {
-		/*
-		 * In the pre-remove case the failure notification is attempting
-		 * to trigger a force unmount.  The expectation is that the
-		 * device is still present, but its removal is in progress and
-		 * can not be cancelled, proceed with accessing the log device.
-		 */
-		if (mf_flags & MF_MEM_PRE_REMOVE)
-			return 0;
-		xfs_err(mp, "ondisk log corrupt, shutting down fs!");
-		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
-		return -EFSCORRUPTED;
-	}
-
-	if (!xfs_has_rmapbt(mp)) {
-		xfs_debug(mp, "notify_failure() needs rmapbt enabled!");
-		return -EOPNOTSUPP;
-	}
-
-	ddev_start = mp->m_ddev_targp->bt_dax_part_off;
-	ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
-
-	/* Notify failure on the whole device. */
-	if (offset == 0 && len == U64_MAX) {
-		offset = ddev_start;
-		len = bdev_nr_bytes(mp->m_ddev_targp->bt_bdev);
-	}
-
-	/* Ignore the range out of filesystem area */
-	if (offset + len - 1 < ddev_start)
-		return -ENXIO;
-	if (offset > ddev_end)
-		return -ENXIO;
-
-	/* Calculate the real range when it touches the boundary */
-	if (offset > ddev_start)
-		offset -= ddev_start;
-	else {
-		len -= ddev_start - offset;
-		offset = 0;
-	}
-	if (offset + len - 1 > ddev_end)
-		len = ddev_end - offset + 1;
-
-	return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
-			mf_flags);
+	return xfs_dax_notify_dev_failure(mp, offset, len, mf_flags,
+		(mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) ?
+				XG_TYPE_RTG : XG_TYPE_AG);
 }
 
 const struct dax_holder_operations xfs_dax_holder_operations = {

fs/xfs/xfs_notify_failure.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_NOTIFY_FAILURE_H__
+#define __XFS_NOTIFY_FAILURE_H__
+
+extern const struct dax_holder_operations xfs_dax_holder_operations;
+
+#endif /* __XFS_NOTIFY_FAILURE_H__ */

fs/xfs/xfs_qm.c

@@ -230,10 +230,10 @@ xfs_qm_unmount_rt(
 
 	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]);
+	if (rtg_bitmap(rtg))
+		xfs_qm_dqdetach(rtg_bitmap(rtg));
+	if (rtg_summary(rtg))
+		xfs_qm_dqdetach(rtg_summary(rtg));
 	xfs_rtgroup_rele(rtg);
 }
 

fs/xfs/xfs_rmap_item.c

@@ -23,6 +23,7 @@
 #include "xfs_ag.h"
 #include "xfs_btree.h"
 #include "xfs_trace.h"
+#include "xfs_rtgroup.h"
 
 struct kmem_cache	*xfs_rui_cache;
 struct kmem_cache	*xfs_rud_cache;
@@ -94,7 +95,9 @@ xfs_rui_item_format(
 	ASSERT(atomic_read(&ruip->rui_next_extent) ==
 			ruip->rui_format.rui_nextents);
 
-	ruip->rui_format.rui_type = XFS_LI_RUI;
+	ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT);
+
+	ruip->rui_format.rui_type = lip->li_type;
 	ruip->rui_format.rui_size = 1;
 
 	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUI_FORMAT, &ruip->rui_format,
@@ -137,12 +140,15 @@ xfs_rui_item_release(
 STATIC struct xfs_rui_log_item *
 xfs_rui_init(
 	struct xfs_mount		*mp,
+	unsigned short			item_type,
 	uint				nextents)
 
 {
 	struct xfs_rui_log_item		*ruip;
 
 	ASSERT(nextents > 0);
+	ASSERT(item_type == XFS_LI_RUI || item_type == XFS_LI_RUI_RT);
+
 	if (nextents > XFS_RUI_MAX_FAST_EXTENTS)
 		ruip = kzalloc(xfs_rui_log_item_sizeof(nextents),
 				GFP_KERNEL | __GFP_NOFAIL);
@@ -150,7 +156,7 @@ xfs_rui_init(
 		ruip = kmem_cache_zalloc(xfs_rui_cache,
 					 GFP_KERNEL | __GFP_NOFAIL);
 
-	xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops);
+	xfs_log_item_init(mp, &ruip->rui_item, item_type, &xfs_rui_item_ops);
 	ruip->rui_format.rui_nextents = nextents;
 	ruip->rui_format.rui_id = (uintptr_t)(void *)ruip;
 	atomic_set(&ruip->rui_next_extent, 0);
@@ -189,7 +195,9 @@ xfs_rud_item_format(
 	struct xfs_rud_log_item	*rudp = RUD_ITEM(lip);
 	struct xfs_log_iovec	*vecp = NULL;
 
-	rudp->rud_format.rud_type = XFS_LI_RUD;
+	ASSERT(lip->li_type == XFS_LI_RUD || lip->li_type == XFS_LI_RUD_RT);
+
+	rudp->rud_format.rud_type = lip->li_type;
 	rudp->rud_format.rud_size = 1;
 
 	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUD_FORMAT, &rudp->rud_format,
@@ -233,6 +241,14 @@ static inline struct xfs_rmap_intent *ri_entry(const struct list_head *e)
 	return list_entry(e, struct xfs_rmap_intent, ri_list);
 }
 
+static inline bool
+xfs_rui_item_isrt(const struct xfs_log_item *lip)
+{
+	ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT);
+
+	return lip->li_type == XFS_LI_RUI_RT;
+}
+
 /* Sort rmap intents by AG. */
 static int
 xfs_rmap_update_diff_items(
@@ -304,6 +320,28 @@ xfs_rmap_update_log_item(
 	}
 }
 
+static struct xfs_log_item *
+__xfs_rmap_update_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort,
+	unsigned short			item_type)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_rui_log_item		*ruip;
+	struct xfs_rmap_intent		*ri;
+
+	ASSERT(count > 0);
+
+	ruip = xfs_rui_init(mp, item_type, count);
+	if (sort)
+		list_sort(mp, items, xfs_rmap_update_diff_items);
+	list_for_each_entry(ri, items, ri_list)
+		xfs_rmap_update_log_item(tp, ruip, ri);
+	return &ruip->rui_item;
+}
+
 static struct xfs_log_item *
 xfs_rmap_update_create_intent(
 	struct xfs_trans		*tp,
@@ -311,17 +349,14 @@ xfs_rmap_update_create_intent(
 	unsigned int			count,
 	bool				sort)
 {
-	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_rui_log_item		*ruip = xfs_rui_init(mp, count);
-	struct xfs_rmap_intent		*ri;
+	return __xfs_rmap_update_create_intent(tp, items, count, sort,
+			XFS_LI_RUI);
+}
 
-	ASSERT(count > 0);
-
-	if (sort)
-		list_sort(mp, items, xfs_rmap_update_diff_items);
-	list_for_each_entry(ri, items, ri_list)
-		xfs_rmap_update_log_item(tp, ruip, ri);
-	return &ruip->rui_item;
+static inline unsigned short
+xfs_rud_type_from_rui(const struct xfs_rui_log_item *ruip)
+{
+	return xfs_rui_item_isrt(&ruip->rui_item) ? XFS_LI_RUD_RT : XFS_LI_RUD;
 }
 
 /* Get an RUD so we can process all the deferred rmap updates. */
@@ -335,8 +370,8 @@ xfs_rmap_update_create_done(
 	struct xfs_rud_log_item		*rudp;
 
 	rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL);
-	xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
-			  &xfs_rud_item_ops);
+	xfs_log_item_init(tp->t_mountp, &rudp->rud_item,
+			xfs_rud_type_from_rui(ruip), &xfs_rud_item_ops);
 	rudp->rud_ruip = ruip;
 	rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id;
 
@@ -351,11 +386,20 @@ xfs_rmap_defer_add(
 {
 	struct xfs_mount	*mp = tp->t_mountp;
 
-	trace_xfs_rmap_defer(mp, ri);
-
+	/*
+	 * Deferred rmap updates for the realtime and data sections must use
+	 * separate transactions to finish deferred work because updates to
+	 * realtime metadata files can lock AGFs to allocate btree blocks and
+	 * we don't want that mixing with the AGF locks taken to finish data
+	 * section updates.
+	 */
 	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);
+			ri->ri_realtime ? XG_TYPE_RTG : XG_TYPE_AG);
+
+	trace_xfs_rmap_defer(mp, ri);
+	xfs_defer_add(tp, &ri->ri_list, ri->ri_realtime ?
+			&xfs_rtrmap_update_defer_type :
+			&xfs_rmap_update_defer_type);
 }
 
 /* Cancel a deferred rmap update. */
@@ -415,6 +459,7 @@ xfs_rmap_update_abort_intent(
 static inline bool
 xfs_rui_validate_map(
 	struct xfs_mount		*mp,
+	bool				isrt,
 	struct xfs_map_extent		*map)
 {
 	if (!xfs_has_rmapbt(mp))
@@ -444,6 +489,9 @@ xfs_rui_validate_map(
 	if (!xfs_verify_fileext(mp, map->me_startoff, map->me_len))
 		return false;
 
+	if (isrt)
+		return xfs_verify_rtbext(mp, map->me_startblock, map->me_len);
+
 	return xfs_verify_fsbext(mp, map->me_startblock, map->me_len);
 }
 
@@ -451,6 +499,7 @@ static inline void
 xfs_rui_recover_work(
 	struct xfs_mount		*mp,
 	struct xfs_defer_pending	*dfp,
+	bool				isrt,
 	const struct xfs_map_extent	*map)
 {
 	struct xfs_rmap_intent		*ri;
@@ -495,7 +544,9 @@ 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_group = xfs_group_intent_get(mp, map->me_startblock, XG_TYPE_AG);
+	ri->ri_group = xfs_group_intent_get(mp, map->me_startblock,
+			isrt ? XG_TYPE_RTG : XG_TYPE_AG);
+	ri->ri_realtime = isrt;
 
 	xfs_defer_add_item(dfp, &ri->ri_list);
 }
@@ -514,6 +565,7 @@ xfs_rmap_recover_work(
 	struct xfs_rui_log_item		*ruip = RUI_ITEM(lip);
 	struct xfs_trans		*tp;
 	struct xfs_mount		*mp = lip->li_log->l_mp;
+	bool				isrt = xfs_rui_item_isrt(lip);
 	int				i;
 	int				error = 0;
 
@@ -523,7 +575,7 @@ xfs_rmap_recover_work(
 	 * just toss the RUI.
 	 */
 	for (i = 0; i < ruip->rui_format.rui_nextents; i++) {
-		if (!xfs_rui_validate_map(mp,
+		if (!xfs_rui_validate_map(mp, isrt,
 					&ruip->rui_format.rui_extents[i])) {
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 					&ruip->rui_format,
@@ -531,7 +583,8 @@ xfs_rmap_recover_work(
 			return -EFSCORRUPTED;
 		}
 
-		xfs_rui_recover_work(mp, dfp, &ruip->rui_format.rui_extents[i]);
+		xfs_rui_recover_work(mp, dfp, isrt,
+				&ruip->rui_format.rui_extents[i]);
 	}
 
 	resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
@@ -566,10 +619,13 @@ xfs_rmap_relog_intent(
 	struct xfs_map_extent		*map;
 	unsigned int			count;
 
+	ASSERT(intent->li_type == XFS_LI_RUI ||
+	       intent->li_type == XFS_LI_RUI_RT);
+
 	count = RUI_ITEM(intent)->rui_format.rui_nextents;
 	map = RUI_ITEM(intent)->rui_format.rui_extents;
 
-	ruip = xfs_rui_init(tp->t_mountp, count);
+	ruip = xfs_rui_init(tp->t_mountp, intent->li_type, count);
 	memcpy(ruip->rui_format.rui_extents, map, count * sizeof(*map));
 	atomic_set(&ruip->rui_next_extent, count);
 
@@ -589,6 +645,47 @@ const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
 	.relog_intent	= xfs_rmap_relog_intent,
 };
 
+#ifdef CONFIG_XFS_RT
+static struct xfs_log_item *
+xfs_rtrmap_update_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	return __xfs_rmap_update_create_intent(tp, items, count, sort,
+			XFS_LI_RUI_RT);
+}
+
+/* Clean up after calling xfs_rmap_finish_one. */
+STATIC void
+xfs_rtrmap_finish_one_cleanup(
+	struct xfs_trans	*tp,
+	struct xfs_btree_cur	*rcur,
+	int			error)
+{
+	if (rcur)
+		xfs_btree_del_cursor(rcur, error);
+}
+
+const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = {
+	.name		= "rtrmap",
+	.max_items	= XFS_RUI_MAX_FAST_EXTENTS,
+	.create_intent	= xfs_rtrmap_update_create_intent,
+	.abort_intent	= xfs_rmap_update_abort_intent,
+	.create_done	= xfs_rmap_update_create_done,
+	.finish_item	= xfs_rmap_update_finish_item,
+	.finish_cleanup = xfs_rtrmap_finish_one_cleanup,
+	.cancel_item	= xfs_rmap_update_cancel_item,
+	.recover_work	= xfs_rmap_recover_work,
+	.relog_intent	= xfs_rmap_relog_intent,
+};
+#else
+const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = {
+	.name		= "rtrmap",
+};
+#endif
+
 STATIC bool
 xfs_rui_item_match(
 	struct xfs_log_item	*lip,
@@ -654,7 +751,7 @@ xlog_recover_rui_commit_pass2(
 		return -EFSCORRUPTED;
 	}
 
-	ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
+	ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents);
 	xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
 	atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
 
@@ -668,6 +765,61 @@ const struct xlog_recover_item_ops xlog_rui_item_ops = {
 	.commit_pass2		= xlog_recover_rui_commit_pass2,
 };
 
+#ifdef CONFIG_XFS_RT
+STATIC int
+xlog_recover_rtrui_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_rui_log_item		*ruip;
+	struct xfs_rui_log_format	*rui_formatp;
+	size_t				len;
+
+	rui_formatp = item->ri_buf[0].i_addr;
+
+	if (item->ri_buf[0].i_len < xfs_rui_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;
+	}
+
+	len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
+	if (item->ri_buf[0].i_len != len) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
+	ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents);
+	xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
+	atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
+
+	xlog_recover_intent_item(log, &ruip->rui_item, lsn,
+			&xfs_rtrmap_update_defer_type);
+	return 0;
+}
+#else
+STATIC int
+xlog_recover_rtrui_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_rtrui_item_ops = {
+	.item_type		= XFS_LI_RUI_RT,
+	.commit_pass2		= xlog_recover_rtrui_commit_pass2,
+};
+
 /*
  * This routine is called when an RUD format structure is found in a committed
  * transaction in the log. Its purpose is to cancel the corresponding RUI if it
@@ -699,3 +851,33 @@ const struct xlog_recover_item_ops xlog_rud_item_ops = {
 	.item_type		= XFS_LI_RUD,
 	.commit_pass2		= xlog_recover_rud_commit_pass2,
 };
+
+#ifdef CONFIG_XFS_RT
+STATIC int
+xlog_recover_rtrud_commit_pass2(
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
+{
+	struct xfs_rud_log_format	*rud_formatp;
+
+	rud_formatp = item->ri_buf[0].i_addr;
+	if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				rud_formatp, item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
+	xlog_recover_release_intent(log, XFS_LI_RUI_RT,
+			rud_formatp->rud_rui_id);
+	return 0;
+}
+#else
+# define xlog_recover_rtrud_commit_pass2	xlog_recover_rtrui_commit_pass2
+#endif
+
+const struct xlog_recover_item_ops xlog_rtrud_item_ops = {
+	.item_type		= XFS_LI_RUD_RT,
+	.commit_pass2		= xlog_recover_rtrud_commit_pass2,
+};

fs/xfs/xfs_rtalloc.c

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

fs/xfs/xfs_rtalloc.h

@@ -46,6 +46,8 @@ xfs_growfs_rt(
 	xfs_growfs_rt_t		*in);	/* user supplied growfs struct */
 
 int xfs_rtalloc_reinit_frextents(struct xfs_mount *mp);
+int xfs_growfs_check_rtgeom(const struct xfs_mount *mp, xfs_rfsblock_t dblocks,
+		xfs_rfsblock_t rblocks, xfs_agblock_t rextsize);
 #else
 # define xfs_growfs_rt(mp,in)				(-ENOSYS)
 # define xfs_rtalloc_reinit_frextents(m)		(0)
@@ -65,6 +67,14 @@ xfs_rtmount_init(
 # define xfs_rtunmount_inodes(m)
 # define xfs_rt_resv_free(mp)				((void)0)
 # define xfs_rt_resv_init(mp)				(0)
+
+static inline int
+xfs_growfs_check_rtgeom(const struct xfs_mount *mp,
+		xfs_rfsblock_t dblocks, xfs_rfsblock_t rblocks,
+		xfs_extlen_t rextsize)
+{
+	return 0;
+}
 #endif	/* CONFIG_XFS_RT */
 
 #endif	/* __XFS_RTALLOC_H__ */

fs/xfs/xfs_stats.c

@@ -52,7 +52,9 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 		{ "rmapbt",		xfsstats_offset(xs_refcbt_2)	},
 		{ "refcntbt",		xfsstats_offset(xs_rmap_mem_2)	},
 		{ "rmapbt_mem",		xfsstats_offset(xs_rcbag_2)	},
-		{ "rcbagbt",		xfsstats_offset(xs_qm_dqreclaims)},
+		{ "rcbagbt",		xfsstats_offset(xs_rtrmap_2)	},
+		{ "rtrmapbt",		xfsstats_offset(xs_rtrmap_mem_2)},
+		{ "rtrmapbt_mem",	xfsstats_offset(xs_qm_dqreclaims)},
 		/* we print both series of quota information together */
 		{ "qm",			xfsstats_offset(xs_xstrat_bytes)},
 	};

fs/xfs/xfs_stats.h

@@ -127,6 +127,8 @@ struct __xfsstats {
 	uint32_t		xs_refcbt_2[__XBTS_MAX];
 	uint32_t		xs_rmap_mem_2[__XBTS_MAX];
 	uint32_t		xs_rcbag_2[__XBTS_MAX];
+	uint32_t		xs_rtrmap_2[__XBTS_MAX];
+	uint32_t		xs_rtrmap_mem_2[__XBTS_MAX];
 	uint32_t		xs_qm_dqreclaims;
 	uint32_t		xs_qm_dqreclaim_misses;
 	uint32_t		xs_qm_dquot_dups;

fs/xfs/xfs_super.c

@@ -1767,12 +1767,6 @@ xfs_fs_fill_super(
 		}
 	}
 
-	if (xfs_has_rmapbt(mp) && mp->m_sb.sb_rblocks) {
-		xfs_alert(mp,
-	"reverse mapping btree not compatible with realtime device!");
-		error = -EINVAL;
-		goto out_filestream_unmount;
-	}
 
 	if (xfs_has_exchange_range(mp))
 		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_EXCHRANGE);

fs/xfs/xfs_super.h

@@ -92,7 +92,6 @@ extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *,
 
 extern const struct export_operations xfs_export_operations;
 extern const struct quotactl_ops xfs_quotactl_operations;
-extern const struct dax_holder_operations xfs_dax_holder_operations;
 
 extern void xfs_reinit_percpu_counters(struct xfs_mount *mp);
 

fs/xfs/xfs_trace.h

@@ -14,11 +14,15 @@
  * ino: filesystem inode number
  *
  * agbno: per-AG block number in fs blocks
+ * rgbno: per-rtgroup block number in fs blocks
  * startblock: physical block number for file mappings.  This is either a
  *             segmented fsblock for data device mappings, or a rfsblock
  *             for realtime device mappings
  * fsbcount: number of blocks in an extent, in fs blocks
  *
+ * gbno: generic allocation group block number.  This is an agbno for
+ *       space in a per-AG or a rgbno for space in a realtime group.
+ *
  * daddr: physical block number in 512b blocks
  * bbcount: number of blocks in a physical extent, in 512b blocks
  *
@@ -2295,6 +2299,7 @@ TRACE_DEFINE_ENUM(XFS_DINODE_FMT_LOCAL);
 TRACE_DEFINE_ENUM(XFS_DINODE_FMT_EXTENTS);
 TRACE_DEFINE_ENUM(XFS_DINODE_FMT_BTREE);
 TRACE_DEFINE_ENUM(XFS_DINODE_FMT_UUID);
+TRACE_DEFINE_ENUM(XFS_DINODE_FMT_META_BTREE);
 
 DECLARE_EVENT_CLASS(xfs_swap_extent_class,
 	TP_PROTO(struct xfs_inode *ip, int which),
@@ -2918,13 +2923,14 @@ DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_finish_item);
 /* rmap tracepoints */
 DECLARE_EVENT_CLASS(xfs_rmap_class,
 	TP_PROTO(struct xfs_btree_cur *cur,
-		 xfs_agblock_t agbno, xfs_extlen_t len, bool unwritten,
+		 xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten,
 		 const struct xfs_owner_info *oinfo),
-	TP_ARGS(cur, agbno, len, unwritten, oinfo),
+	TP_ARGS(cur, gbno, len, unwritten, oinfo),
 	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_agblock_t, gbno)
 		__field(xfs_extlen_t, len)
 		__field(uint64_t, owner)
 		__field(uint64_t, offset)
@@ -2932,8 +2938,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
+		__entry->type = cur->bc_group->xg_type;
 		__entry->agno = cur->bc_group->xg_gno;
-		__entry->agbno = agbno;
+		__entry->gbno = gbno;
 		__entry->len = len;
 		__entry->owner = oinfo->oi_owner;
 		__entry->offset = oinfo->oi_offset;
@@ -2941,10 +2948,11 @@ DECLARE_EVENT_CLASS(xfs_rmap_class,
 		if (unwritten)
 			__entry->flags |= XFS_RMAP_UNWRITTEN;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%lx",
+	TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%lx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
-		  __entry->agbno,
+		  __entry->gbno,
 		  __entry->len,
 		  __entry->owner,
 		  __entry->offset,
@@ -2953,9 +2961,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_class,
 #define DEFINE_RMAP_EVENT(name) \
 DEFINE_EVENT(xfs_rmap_class, name, \
 	TP_PROTO(struct xfs_btree_cur *cur, \
-		 xfs_agblock_t agbno, xfs_extlen_t len, bool unwritten, \
+		 xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten, \
 		 const struct xfs_owner_info *oinfo), \
-	TP_ARGS(cur, agbno, len, unwritten, oinfo))
+	TP_ARGS(cur, gbno, len, unwritten, oinfo))
 
 /* btree cursor error/%ip tracepoint class */
 DECLARE_EVENT_CLASS(xfs_btree_error_class,
@@ -3018,47 +3026,36 @@ TRACE_EVENT(xfs_rmap_convert_state,
 	TP_ARGS(cur, state, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
+		__field(enum xfs_group_type, type)
 		__field(xfs_agnumber_t, agno)
-		__field(xfs_ino_t, ino)
 		__field(int, state)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		switch (cur->bc_ops->type) {
-		case XFS_BTREE_TYPE_INODE:
-			__entry->agno = 0;
-			__entry->ino = cur->bc_ino.ip->i_ino;
-			break;
-		case XFS_BTREE_TYPE_AG:
-			__entry->agno = cur->bc_group->xg_gno;
-			__entry->ino = 0;
-			break;
-		case XFS_BTREE_TYPE_MEM:
-			__entry->agno = 0;
-			__entry->ino = 0;
-			break;
-		}
+		__entry->type = cur->bc_group->xg_type;
+		__entry->agno = cur->bc_group->xg_gno;
 		__entry->state = state;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d agno 0x%x ino 0x%llx state %d caller %pS",
+	TP_printk("dev %d:%d %sno 0x%x state %d caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
-		  __entry->ino,
 		  __entry->state,
 		  (char *)__entry->caller_ip)
 );
 
 DECLARE_EVENT_CLASS(xfs_rmapbt_class,
 	TP_PROTO(struct xfs_btree_cur *cur,
-		 xfs_agblock_t agbno, xfs_extlen_t len,
+		 xfs_agblock_t gbno, xfs_extlen_t len,
 		 uint64_t owner, uint64_t offset, unsigned int flags),
-	TP_ARGS(cur, agbno, len, owner, offset, flags),
+	TP_ARGS(cur, gbno, len, owner, offset, flags),
 	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_agblock_t, gbno)
 		__field(xfs_extlen_t, len)
 		__field(uint64_t, owner)
 		__field(uint64_t, offset)
@@ -3066,17 +3063,19 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
+		__entry->type = cur->bc_group->xg_type;
 		__entry->agno = cur->bc_group->xg_gno;
-		__entry->agbno = agbno;
+		__entry->gbno = gbno;
 		__entry->len = len;
 		__entry->owner = owner;
 		__entry->offset = offset;
 		__entry->flags = flags;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
+	TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
-		  __entry->agbno,
+		  __entry->gbno,
 		  __entry->len,
 		  __entry->owner,
 		  __entry->offset,
@@ -3085,9 +3084,9 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class,
 #define DEFINE_RMAPBT_EVENT(name) \
 DEFINE_EVENT(xfs_rmapbt_class, name, \
 	TP_PROTO(struct xfs_btree_cur *cur, \
-		 xfs_agblock_t agbno, xfs_extlen_t len, \
+		 xfs_agblock_t gbno, xfs_extlen_t len, \
 		 uint64_t owner, uint64_t offset, unsigned int flags), \
-	TP_ARGS(cur, agbno, len, owner, offset, flags))
+	TP_ARGS(cur, gbno, len, owner, offset, flags))
 
 TRACE_DEFINE_ENUM(XFS_RMAP_MAP);
 TRACE_DEFINE_ENUM(XFS_RMAP_MAP_SHARED);
@@ -3104,8 +3103,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(unsigned long long, owner)
+		__field(enum xfs_group_type, type)
 		__field(xfs_agnumber_t, agno)
-		__field(xfs_agblock_t, agbno)
+		__field(xfs_agblock_t, gbno)
 		__field(int, whichfork)
 		__field(xfs_fileoff_t, l_loff)
 		__field(xfs_filblks_t, l_len)
@@ -3114,9 +3114,11 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class,
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock);
-		__entry->agbno = XFS_FSB_TO_AGBNO(mp,
-					ri->ri_bmap.br_startblock);
+		__entry->type = ri->ri_group->xg_type;
+		__entry->agno = ri->ri_group->xg_gno;
+		__entry->gbno = xfs_fsb_to_gbno(mp,
+						ri->ri_bmap.br_startblock,
+						ri->ri_group->xg_type);
 		__entry->owner = ri->ri_owner;
 		__entry->whichfork = ri->ri_whichfork;
 		__entry->l_loff = ri->ri_bmap.br_startoff;
@@ -3124,11 +3126,12 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class,
 		__entry->l_state = ri->ri_bmap.br_state;
 		__entry->op = ri->ri_type;
 	),
-	TP_printk("dev %d:%d op %s agno 0x%x agbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d",
+	TP_printk("dev %d:%d op %s %sno 0x%x gbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __print_symbolic(__entry->op, XFS_RMAP_INTENT_STRINGS),
+		  __print_symbolic(__entry->type, XG_TYPE_STRINGS),
 		  __entry->agno,
-		  __entry->agbno,
+		  __entry->gbno,
 		  __entry->owner,
 		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
 		  __entry->l_loff,
@@ -3993,7 +3996,7 @@ TRACE_EVENT(xfs_fsmap_mapping,
 		__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",
+	TP_printk("dev %d:%d keydev %d:%d agno 0x%x gbno 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,
@@ -5619,6 +5622,27 @@ DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free_space);
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_critical);
 DEFINE_INODE_ERROR_EVENT(xfs_metafile_resv_init_error);
 
+#ifdef CONFIG_XFS_RT
+TRACE_EVENT(xfs_growfs_check_rtgeom,
+	TP_PROTO(const struct xfs_mount *mp, unsigned int min_logfsbs),
+	TP_ARGS(mp, min_logfsbs),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned int, logblocks)
+		__field(unsigned int, min_logfsbs)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->logblocks = mp->m_sb.sb_logblocks;
+		__entry->min_logfsbs = min_logfsbs;
+	),
+	TP_printk("dev %d:%d logblocks %u min_logfsbs %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->logblocks,
+		  __entry->min_logfsbs)
+);
+#endif /* CONFIG_XFS_RT */
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH