xfs: support in-memory btrees

Adapt the generic btree cursor code to be able to create a btree whose
buffers come from a (presumably in-memory) buftarg with a header block
that's specific to in-memory btrees.  We'll connect this to other parts
of online scrub in the next patches.

Note that in-memory btrees always have a block size matching the system
memory page size for efficiency reasons.

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

13 files changed, 648 insertions, 24 deletions

diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 6d245ef73f271..79481cf12c7a4 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -102,6 +102,9 @@ config XFS_DRAIN_INTENTS
 config XFS_IN_MEMORY_FILE
 	bool
 
+config XFS_IN_MEMORY_BTREE
+	bool
+
 config XFS_ONLINE_SCRUB
 	bool "XFS online metadata check support"
 	default n
@@ -128,6 +131,7 @@ config XFS_ONLINE_REPAIR
 	bool "XFS online metadata repair support"
 	default n
 	depends on XFS_FS && XFS_ONLINE_SCRUB
+	select XFS_IN_MEMORY_BTREE
 	help
 	  If you say Y here you will be able to repair metadata on a
 	  mounted XFS filesystem.  This feature is intended to reduce
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 69d27ba99eb69..56926e94f2147 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -199,6 +199,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   symlink_repair.o \
 				   tempfile.o \
 				   xfblob.o \
+				   xfbtree.o \
 				   )
 
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 355e6cddeb376..748d0193d68ef 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -34,6 +34,9 @@
 #include "xfs_quota.h"
 #include "xfs_imeta.h"
 #include "xfs_rtrefcount_btree.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+#include "xfs_btree_mem.h"
 
 /*
  * Btree magic numbers.
@@ -218,6 +221,8 @@ xfs_btree_check_lptr(
 {
 	if (level <= 0)
 		return false;
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		return xfbtree_verify_xfileoff(cur, fsbno);
 	return xfs_verify_fsbno(cur->bc_mp, fsbno);
 }
 
@@ -230,6 +235,8 @@ xfs_btree_check_sptr(
 {
 	if (level <= 0)
 		return false;
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		return xfbtree_verify_xfileoff(cur, agbno);
 	return xfs_verify_agbno(cur->bc_mp, cur->bc_ag.pag->pag_agno, agbno);
 }
 
@@ -244,6 +251,9 @@ xfs_btree_check_ptr(
 	int				index,
 	int				level)
 {
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		return xfbtree_check_ptr(cur, ptr, index, level);
+
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		if (xfs_btree_check_lptr(cur, be64_to_cpu((&ptr->l)[index]),
 				level))
@@ -394,11 +404,32 @@ xfs_btree_del_cursor(
 	       xfs_is_shutdown(cur->bc_mp));
 	if (unlikely(cur->bc_flags & XFS_BTREE_STAGING))
 		kmem_free(cur->bc_ops);
-	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag)
+	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
+	    !(cur->bc_flags & XFS_BTREE_IN_MEMORY) && cur->bc_ag.pag)
 		xfs_perag_put(cur->bc_ag.pag);
 	kmem_cache_free(cur->bc_cache, cur);
 }
 
+/* Return the buffer target for this btree's buffer. */
+static inline struct xfs_buftarg *
+xfs_btree_buftarg(
+	struct xfs_btree_cur	*cur)
+{
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		return xfbtree_target(cur->bc_mem.xfbtree);
+	return cur->bc_mp->m_ddev_targp;
+}
+
+/* Return the block size (in units of 512b sectors) for this btree. */
+static inline unsigned int
+xfs_btree_bbsize(
+	struct xfs_btree_cur	*cur)
+{
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		return xfbtree_bbsize();
+	return cur->bc_mp->m_bsize;
+}
+
 /*
  * Duplicate the btree cursor.
  * Allocate a new one, copy the record, re-get the buffers.
@@ -436,10 +467,11 @@ xfs_btree_dup_cursor(
 		new->bc_levels[i].ra = cur->bc_levels[i].ra;
 		bp = cur->bc_levels[i].bp;
 		if (bp) {
-			error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
-						   xfs_buf_daddr(bp), mp->m_bsize,
-						   0, &bp,
-						   cur->bc_ops->buf_ops);
+			error = xfs_trans_read_buf(mp, tp,
+					xfs_btree_buftarg(cur),
+					xfs_buf_daddr(bp),
+					xfs_btree_bbsize(cur), 0, &bp,
+					cur->bc_ops->buf_ops);
 			if (xfs_metadata_is_sick(error))
 				xfs_btree_mark_sick(new);
 			if (error) {
@@ -880,6 +912,9 @@ xfs_btree_readahead_lblock(
 	xfs_fsblock_t		left = be64_to_cpu(block->bb_u.l.bb_leftsib);
 	xfs_fsblock_t		right = be64_to_cpu(block->bb_u.l.bb_rightsib);
 
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		return 0;
+
 	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) {
 		xfs_btree_reada_bufl(cur->bc_mp, left, 1,
 				     cur->bc_ops->buf_ops);
@@ -905,6 +940,8 @@ xfs_btree_readahead_sblock(
 	xfs_agblock_t		left = be32_to_cpu(block->bb_u.s.bb_leftsib);
 	xfs_agblock_t		right = be32_to_cpu(block->bb_u.s.bb_rightsib);
 
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		return 0;
 
 	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) {
 		xfs_btree_reada_bufs(cur->bc_mp, cur->bc_ag.pag->pag_agno,
@@ -966,6 +1003,11 @@ xfs_btree_ptr_to_daddr(
 	if (error)
 		return error;
 
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY) {
+		*daddr = xfbtree_ptr_to_daddr(cur, ptr);
+		return 0;
+	}
+
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		fsbno = be64_to_cpu(ptr->l);
 		*daddr = XFS_FSB_TO_DADDR(cur->bc_mp, fsbno);
@@ -994,8 +1036,9 @@ xfs_btree_readahead_ptr(
 
 	if (xfs_btree_ptr_to_daddr(cur, ptr, &daddr))
 		return;
-	xfs_buf_readahead(cur->bc_mp->m_ddev_targp, daddr,
-			  cur->bc_mp->m_bsize * count, cur->bc_ops->buf_ops);
+	xfs_buf_readahead(xfs_btree_buftarg(cur), daddr,
+			xfs_btree_bbsize(cur) * count,
+			cur->bc_ops->buf_ops);
 }
 
 /*
@@ -1169,7 +1212,9 @@ xfs_btree_init_block_cur(
 	 * change in future, but is safe for current users of the generic btree
 	 * code.
 	 */
-	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		owner = cur->bc_mem.xfbtree->owner;
+	else if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
 		owner = cur->bc_ino.ip->i_ino;
 	else
 		owner = cur->bc_ag.pag->pag_agno;
@@ -1209,6 +1254,11 @@ xfs_btree_buf_to_ptr(
 	struct xfs_buf		*bp,
 	union xfs_btree_ptr	*ptr)
 {
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY) {
+		xfbtree_buf_to_ptr(cur, bp, ptr);
+		return;
+	}
+
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
 		ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp,
 					xfs_buf_daddr(bp)));
@@ -1255,15 +1305,14 @@ xfs_btree_get_buf_block(
 	struct xfs_btree_block		**block,
 	struct xfs_buf			**bpp)
 {
-	struct xfs_mount	*mp = cur->bc_mp;
-	xfs_daddr_t		d;
-	int			error;
+	xfs_daddr_t			d;
+	int				error;
 
 	error = xfs_btree_ptr_to_daddr(cur, ptr, &d);
 	if (error)
 		return error;
-	error = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d, mp->m_bsize,
-			0, bpp);
+	error = xfs_trans_get_buf(cur->bc_tp, xfs_btree_buftarg(cur), d,
+			xfs_btree_bbsize(cur), 0, bpp);
 	if (error)
 		return error;
 
@@ -1294,9 +1343,9 @@ xfs_btree_read_buf_block(
 	error = xfs_btree_ptr_to_daddr(cur, ptr, &d);
 	if (error)
 		return error;
-	error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
-				   mp->m_bsize, flags, bpp,
-				   cur->bc_ops->buf_ops);
+	error = xfs_trans_read_buf(mp, cur->bc_tp, xfs_btree_buftarg(cur), d,
+			xfs_btree_bbsize(cur), flags, bpp,
+			cur->bc_ops->buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_btree_mark_sick(cur);
 	if (error)
@@ -1740,6 +1789,37 @@ error0:
 	return error;
 }
 
+/*
+ * Check the btree block owner now that we have the context to know who the
+ * real owner is.
+ */
+static inline xfs_failaddr_t
+xfs_btree_check_block_owner(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block)
+{
+	if (!xfs_has_crc(cur->bc_mp))
+		return NULL;
+
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		return xfbtree_check_block_owner(cur, block);
+
+	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS)) {
+		if (be32_to_cpu(block->bb_u.s.bb_owner) !=
+						cur->bc_ag.pag->pag_agno)
+			return __this_address;
+		return NULL;
+	}
+
+	if (cur->bc_ino.flags & XFS_BTCUR_BMBT_INVALID_OWNER)
+		return NULL;
+
+	if (be64_to_cpu(block->bb_u.l.bb_owner) != cur->bc_ino.ip->i_ino)
+		return __this_address;
+
+	return NULL;
+}
+
 int
 xfs_btree_lookup_get_block(
 	struct xfs_btree_cur		*cur,	/* btree cursor */
@@ -1778,11 +1858,7 @@ xfs_btree_lookup_get_block(
 		return error;
 
 	/* Check the inode owner since the verifiers don't. */
-	if (xfs_has_crc(cur->bc_mp) &&
-	    !(cur->bc_ino.flags & XFS_BTCUR_BMBT_INVALID_OWNER) &&
-	    (cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
-	    be64_to_cpu((*blkp)->bb_u.l.bb_owner) !=
-			cur->bc_ino.ip->i_ino)
+	if (xfs_btree_check_block_owner(cur, *blkp) != NULL)
 		goto out_bad;
 
 	/* Did we get the level we were looking for? */
@@ -4706,6 +4782,8 @@ xfs_btree_lblock_verify(
 	struct xfs_mount	*mp = bp->b_mount;
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
 
+	ASSERT(!xfs_buftarg_in_memory(bp->b_target));
+
 	/* numrecs verification */
 	if (be16_to_cpu(block->bb_numrecs) > max_recs)
 		return __this_address;
@@ -4761,6 +4839,8 @@ xfs_btree_sblock_verify(
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
 	xfs_agblock_t		agno;
 
+	ASSERT(!xfs_buftarg_in_memory(bp->b_target));
+
 	/* numrecs verification */
 	if (be16_to_cpu(block->bb_numrecs) > max_recs)
 		return __this_address;
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 9b4fde6c476e4..1ec2e7998c147 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -221,6 +221,14 @@ struct xfs_btree_cur_ino {
 	struct xbtree_refc		refc;
 };
 
+/* In-memory btree information */
+struct xfbtree;
+
+struct xfs_btree_cur_mem {
+	struct xfbtree			*xfbtree;
+	struct xfs_buf			*head_bp;
+};
+
 struct xfs_btree_level {
 	/* buffer pointer */
 	struct xfs_buf		*bp;
@@ -260,6 +268,7 @@ struct xfs_btree_cur
 	union {
 		struct xfs_btree_cur_ag	bc_ag;
 		struct xfs_btree_cur_ino bc_ino;
+		struct xfs_btree_cur_mem bc_mem;
 	};
 
 	/* Must be at the end of the struct! */
@@ -291,6 +300,13 @@ xfs_btree_cur_sizeof(unsigned int nlevels)
 #define XFS_BTREE_STAGING		(1<<5)
 #define XFS_BTREE_IROOT_RECORDS		(1<<6)	/* iroot can store records */
 
+/* btree stored in memory; not compatible with ROOT_IN_INODE */
+#ifdef CONFIG_XFS_IN_MEMORY_BTREE
+# define XFS_BTREE_IN_MEMORY		(1<<7)
+#else
+# define XFS_BTREE_IN_MEMORY		(0)
+#endif
+
 #define	XFS_BTREE_NOERROR	0
 #define	XFS_BTREE_ERROR		1
 
diff --git a/fs/xfs/libxfs/xfs_btree_mem.h b/fs/xfs/libxfs/xfs_btree_mem.h
new file mode 100644
index 0000000000000..de947efd8f206
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_btree_mem.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2021 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_BTREE_MEM_H__
+#define __XFS_BTREE_MEM_H__
+
+struct xfbtree;
+
+#ifdef CONFIG_XFS_IN_MEMORY_BTREE
+unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp);
+
+struct xfs_buftarg *xfbtree_target(struct xfbtree *xfbtree);
+int xfbtree_check_ptr(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr, int index, int level);
+xfs_daddr_t xfbtree_ptr_to_daddr(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr);
+void xfbtree_buf_to_ptr(struct xfs_btree_cur *cur, struct xfs_buf *bp,
+		union xfs_btree_ptr *ptr);
+
+unsigned int xfbtree_bbsize(void);
+
+void xfbtree_set_root(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr, int inc);
+void xfbtree_init_ptr_from_cur(struct xfs_btree_cur *cur,
+		union xfs_btree_ptr *ptr);
+struct xfs_btree_cur *xfbtree_dup_cursor(struct xfs_btree_cur *cur);
+bool xfbtree_verify_xfileoff(struct xfs_btree_cur *cur,
+		unsigned long long xfoff);
+xfs_failaddr_t xfbtree_check_block_owner(struct xfs_btree_cur *cur,
+		struct xfs_btree_block *block);
+xfs_failaddr_t xfbtree_lblock_verify(struct xfs_buf *bp, unsigned int max_recs);
+xfs_failaddr_t xfbtree_sblock_verify(struct xfs_buf *bp, unsigned int max_recs);
+#else
+static inline unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp)
+{
+	return 0;
+}
+
+static inline struct xfs_buftarg *
+xfbtree_target(struct xfbtree *xfbtree)
+{
+	return NULL;
+}
+
+static inline int
+xfbtree_check_ptr(struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr,
+		  int index, int level)
+{
+	return 0;
+}
+
+static inline xfs_daddr_t
+xfbtree_ptr_to_daddr(struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr)
+{
+	return 0;
+}
+
+static inline void
+xfbtree_buf_to_ptr(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	union xfs_btree_ptr	*ptr)
+{
+	memset(ptr, 0xFF, sizeof(*ptr));
+}
+
+static inline unsigned int xfbtree_bbsize(void)
+{
+	return 0;
+}
+
+#define xfbtree_set_root			NULL
+#define xfbtree_init_ptr_from_cur		NULL
+#define xfbtree_dup_cursor			NULL
+#define xfbtree_verify_xfileoff(cur, xfoff)	(false)
+#define xfbtree_check_block_owner(cur, block)	NULL
+#endif /* CONFIG_XFS_IN_MEMORY_BTREE */
+
+#endif /* __XFS_BTREE_MEM_H__ */
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
new file mode 100644
index 0000000000000..be24c90db2e11
--- /dev/null
+++ b/fs/xfs/scrub/xfbtree.c
@@ -0,0 +1,331 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2021 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_trans.h"
+#include "xfs_btree.h"
+#include "xfs_error.h"
+#include "xfs_btree_mem.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+
+/* btree ops functions for in-memory btrees. */
+
+static xfs_failaddr_t
+xfs_btree_mem_head_verify(
+	struct xfs_buf			*bp)
+{
+	struct xfs_btree_mem_head	*mhead = bp->b_addr;
+	struct xfs_mount		*mp = bp->b_mount;
+
+	if (!xfs_verify_magic(bp, mhead->mh_magic))
+		return __this_address;
+	if (be32_to_cpu(mhead->mh_nlevels) == 0)
+		return __this_address;
+	if (!uuid_equal(&mhead->mh_uuid, &mp->m_sb.sb_meta_uuid))
+		return __this_address;
+
+	return NULL;
+}
+
+static void
+xfs_btree_mem_head_read_verify(
+	struct xfs_buf		*bp)
+{
+	xfs_failaddr_t		fa = xfs_btree_mem_head_verify(bp);
+
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+static void
+xfs_btree_mem_head_write_verify(
+	struct xfs_buf		*bp)
+{
+	xfs_failaddr_t		fa = xfs_btree_mem_head_verify(bp);
+
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+static const struct xfs_buf_ops xfs_btree_mem_head_buf_ops = {
+	.name			= "xfs_btree_mem_head",
+	.magic			= { cpu_to_be32(XFS_BTREE_MEM_HEAD_MAGIC),
+				    cpu_to_be32(XFS_BTREE_MEM_HEAD_MAGIC) },
+	.verify_read		= xfs_btree_mem_head_read_verify,
+	.verify_write		= xfs_btree_mem_head_write_verify,
+	.verify_struct		= xfs_btree_mem_head_verify,
+};
+
+/* Initialize the header block for an in-memory btree. */
+static inline void
+xfs_btree_mem_head_init(
+	struct xfs_buf			*head_bp,
+	unsigned long long		owner,
+	xfileoff_t			leaf_xfoff)
+{
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+	struct xfs_mount		*mp = head_bp->b_mount;
+
+	mhead->mh_magic = cpu_to_be32(XFS_BTREE_MEM_HEAD_MAGIC);
+	mhead->mh_nlevels = cpu_to_be32(1);
+	mhead->mh_owner = cpu_to_be64(owner);
+	mhead->mh_root = cpu_to_be64(leaf_xfoff);
+	uuid_copy(&mhead->mh_uuid, &mp->m_sb.sb_meta_uuid);
+
+	head_bp->b_ops = &xfs_btree_mem_head_buf_ops;
+}
+
+/* Return tree height from the in-memory btree head. */
+unsigned int
+xfs_btree_mem_head_nlevels(
+	struct xfs_buf			*head_bp)
+{
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+
+	return be32_to_cpu(mhead->mh_nlevels);
+}
+
+/* Extract the buftarg target for this xfile btree. */
+struct xfs_buftarg *
+xfbtree_target(struct xfbtree *xfbtree)
+{
+	return xfbtree->target;
+}
+
+/* Is this daddr (sector offset) contained within the buffer target? */
+static inline bool
+xfbtree_verify_buftarg_xfileoff(
+	struct xfs_buftarg	*btp,
+	xfileoff_t		xfoff)
+{
+	xfs_daddr_t		xfoff_daddr = xfo_to_bb(xfoff);
+
+	return xfs_buftarg_verify_daddr(btp, xfoff_daddr);
+}
+
+/* Is this btree xfile offset contained within the xfile? */
+bool
+xfbtree_verify_xfileoff(
+	struct xfs_btree_cur	*cur,
+	unsigned long long	xfoff)
+{
+	struct xfs_buftarg	*btp = xfbtree_target(cur->bc_mem.xfbtree);
+
+	return xfbtree_verify_buftarg_xfileoff(btp, xfoff);
+}
+
+/* Check if a btree pointer is reasonable. */
+int
+xfbtree_check_ptr(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr,
+	int				index,
+	int				level)
+{
+	xfileoff_t			bt_xfoff;
+	xfs_failaddr_t			fa = NULL;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_MEMORY);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		bt_xfoff = be64_to_cpu(ptr->l);
+	else
+		bt_xfoff = be32_to_cpu(ptr->s);
+
+	if (!xfbtree_verify_xfileoff(cur, bt_xfoff))
+		fa = __this_address;
+
+	if (fa) {
+		xfs_err(cur->bc_mp,
+"In-memory: Corrupt btree %d flags 0x%x pointer at level %d index %d fa %pS.",
+				cur->bc_btnum, cur->bc_flags, level, index,
+				fa);
+		return -EFSCORRUPTED;
+	}
+	return 0;
+}
+
+/* Convert a btree pointer to a daddr */
+xfs_daddr_t
+xfbtree_ptr_to_daddr(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr)
+{
+	xfileoff_t			bt_xfoff;
+
+	BUILD_BUG_ON(xfbtree_bbsize() != xfo_to_bb(1));
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		bt_xfoff = be64_to_cpu(ptr->l);
+	else
+		bt_xfoff = be32_to_cpu(ptr->s);
+	return xfo_to_bb(bt_xfoff);
+}
+
+/* Set the pointer to point to this buffer. */
+void
+xfbtree_buf_to_ptr(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	union xfs_btree_ptr	*ptr)
+{
+	xfileoff_t		xfoff = xfs_bb_to_xfo(xfs_buf_daddr(bp));
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		ptr->l = cpu_to_be64(xfoff);
+	else
+		ptr->s = cpu_to_be32(xfoff);
+}
+
+/* Return the in-memory btree block size, in units of 512 bytes. */
+unsigned int xfbtree_bbsize(void)
+{
+	return xfo_to_bb(1);
+}
+
+/* Set the root of an in-memory btree. */
+void
+xfbtree_set_root(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr,
+	int				inc)
+{
+	struct xfs_buf			*head_bp = cur->bc_mem.head_bp;
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_MEMORY);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		mhead->mh_root = ptr->l;
+	} else {
+		uint32_t		root = be32_to_cpu(ptr->s);
+
+		mhead->mh_root = cpu_to_be64(root);
+	}
+	be32_add_cpu(&mhead->mh_nlevels, inc);
+	xfs_trans_log_buf(cur->bc_tp, head_bp, 0, sizeof(*mhead) - 1);
+}
+
+/* Initialize a pointer from the in-memory btree header. */
+void
+xfbtree_init_ptr_from_cur(
+	struct xfs_btree_cur		*cur,
+	union xfs_btree_ptr		*ptr)
+{
+	struct xfs_buf			*head_bp = cur->bc_mem.head_bp;
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_MEMORY);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		ptr->l = mhead->mh_root;
+	} else {
+		uint64_t		root = be64_to_cpu(mhead->mh_root);
+
+		ptr->s = cpu_to_be32(root);
+	}
+}
+
+/* Duplicate an in-memory btree cursor. */
+struct xfs_btree_cur *
+xfbtree_dup_cursor(
+	struct xfs_btree_cur		*cur)
+{
+	struct xfs_btree_cur		*ncur;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_MEMORY);
+
+	ncur = xfs_btree_alloc_cursor(cur->bc_mp, cur->bc_tp, cur->bc_btnum,
+			cur->bc_maxlevels, cur->bc_cache);
+	ncur->bc_flags = cur->bc_flags;
+	ncur->bc_nlevels = cur->bc_nlevels;
+	ncur->bc_statoff = cur->bc_statoff;
+	ncur->bc_ops = cur->bc_ops;
+	memcpy(&ncur->bc_mem, &cur->bc_mem, sizeof(cur->bc_mem));
+
+	return ncur;
+}
+
+/* Check the owner of an in-memory btree block. */
+xfs_failaddr_t
+xfbtree_check_block_owner(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		if (be64_to_cpu(block->bb_u.l.bb_owner) != xfbt->owner)
+			return __this_address;
+
+		return NULL;
+	}
+
+	if (be32_to_cpu(block->bb_u.s.bb_owner) != xfbt->owner)
+		return __this_address;
+
+	return NULL;
+}
+
+/* Verify a long-format btree block. */
+xfs_failaddr_t
+xfbtree_lblock_verify(
+	struct xfs_buf		*bp,
+	unsigned int		max_recs)
+{
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_buftarg	*btp = bp->b_target;
+
+	/* numrecs verification */
+	if (be16_to_cpu(block->bb_numrecs) > max_recs)
+		return __this_address;
+
+	/* sibling pointer verification */
+	if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be64_to_cpu(block->bb_u.l.bb_leftsib)))
+		return __this_address;
+
+	if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be64_to_cpu(block->bb_u.l.bb_rightsib)))
+		return __this_address;
+
+	return NULL;
+}
+
+/* Verify a short-format btree block. */
+xfs_failaddr_t
+xfbtree_sblock_verify(
+	struct xfs_buf		*bp,
+	unsigned int		max_recs)
+{
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_buftarg	*btp = bp->b_target;
+
+	/* numrecs verification */
+	if (be16_to_cpu(block->bb_numrecs) > max_recs)
+		return __this_address;
+
+	/* sibling pointer verification */
+	if (block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be32_to_cpu(block->bb_u.s.bb_leftsib)))
+		return __this_address;
+
+	if (block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be32_to_cpu(block->bb_u.s.bb_rightsib)))
+		return __this_address;
+
+	return NULL;
+}
diff --git a/fs/xfs/scrub/xfbtree.h b/fs/xfs/scrub/xfbtree.h
new file mode 100644
index 0000000000000..f807f12519ef9
--- /dev/null
+++ b/fs/xfs/scrub/xfbtree.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2021 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef XFS_SCRUB_XFBTREE_H__
+#define XFS_SCRUB_XFBTREE_H__
+
+/* Root block for an in-memory btree. */
+struct xfs_btree_mem_head {
+	__be32				mh_magic;
+	__be32				mh_nlevels;
+	__be64				mh_owner;
+	__be64				mh_root;
+	uuid_t				mh_uuid;
+};
+
+#define XFS_BTREE_MEM_HEAD_MAGIC	0x4341544D	/* "CATM" */
+
+/* xfile-backed in-memory btrees */
+
+struct xfbtree {
+	/* buffer cache target for this in-memory btree */
+	struct xfs_buftarg		*target;
+
+	/* Owner of this btree. */
+	unsigned long long		owner;
+};
+
+#endif /* XFS_SCRUB_XFBTREE_H__ */
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index b9380a1d434f1..9983e683972ed 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -57,6 +57,47 @@ struct xfile_stat {
 int xfile_stat(struct xfile *xf, struct xfile_stat *statbuf);
 
 int xfile_dump(struct xfile *xf);
+
+static inline loff_t xfile_size(struct xfile *xf)
+{
+	return i_size_read(file_inode(xf->file));
+}
+
+/* file block (aka system page size) to basic block conversions. */
+typedef unsigned long long	xfileoff_t;
+#define XFB_BLOCKSIZE		(PAGE_SIZE)
+#define XFB_BSHIFT		(PAGE_SHIFT)
+#define XFB_SHIFT		(XFB_BSHIFT - BBSHIFT)
+
+static inline loff_t xfo_to_b(xfileoff_t xfoff)
+{
+	return xfoff << XFB_BSHIFT;
+}
+
+static inline xfileoff_t b_to_xfo(loff_t pos)
+{
+	return (pos + (XFB_BLOCKSIZE - 1)) >> XFB_BSHIFT;
+}
+
+static inline xfileoff_t b_to_xfot(loff_t pos)
+{
+	return pos >> XFB_BSHIFT;
+}
+
+static inline xfs_daddr_t xfo_to_bb(xfileoff_t xfoff)
+{
+	return xfoff << XFB_SHIFT;
+}
+
+static inline xfileoff_t xfs_bb_to_xfo(xfs_daddr_t bb)
+{
+	return (bb + (xfo_to_bb(1) - 1)) >> XFB_SHIFT;
+}
+
+static inline xfileoff_t xfs_bb_to_xfot(xfs_daddr_t bb)
+{
+	return bb >> XFB_SHIFT;
+}
 #else
 static inline int
 xfile_obj_load(struct xfile *xf, void *buf, size_t count, loff_t offset)
@@ -69,6 +110,11 @@ xfile_obj_store(struct xfile *xf, void *buf, size_t count, loff_t offset)
 {
 	return -EIO;
 }
+
+static inline loff_t xfile_size(struct xfile *xf)
+{
+	return 0;
+}
 #endif /* CONFIG_XFS_IN_MEMORY_FILE */
 
 #endif /* __XFS_SCRUB_XFILE_H__ */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 7ffdbfc95196c..457da4ca74e89 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2486,3 +2486,13 @@ xfs_verify_magic16(
 		return false;
 	return dmagic == bp->b_ops->magic16[idx];
 }
+
+/* Return the number of sectors for a buffer target. */
+xfs_daddr_t
+xfs_buftarg_nr_sectors(
+	struct xfs_buftarg	*btp)
+{
+	if (btp->bt_flags & XFS_BUFTARG_IN_MEMORY)
+		return xfile_size(btp->bt_xfile) >> SECTOR_SHIFT;
+	return bdev_nr_sectors(btp->bt_bdev);
+}
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 9bd3d7b1bccc1..bb0f583afa5d8 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -432,6 +432,16 @@ xfs_buftarg_zeroout(
 			flags);
 }
 
+xfs_daddr_t xfs_buftarg_nr_sectors(struct xfs_buftarg *btp);
+
+static inline bool
+xfs_buftarg_verify_daddr(
+	struct xfs_buftarg	*btp,
+	xfs_daddr_t		daddr)
+{
+	return daddr < xfs_buftarg_nr_sectors(btp);
+}
+
 int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
 bool xfs_verify_magic(struct xfs_buf *bp, __be32 dmagic);
 bool xfs_verify_magic16(struct xfs_buf *bp, __be16 dmagic);
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index bab2a3d69f1d8..1fe12509b1adc 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -510,6 +510,9 @@ xfs_btree_mark_sick(
 {
 	unsigned int			mask;
 
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY)
+		return;
+
 	switch (cur->bc_btnum) {
 	case XFS_BTNUM_BMAP:
 		xfs_bmap_mark_sick(cur->bc_ino.ip, cur->bc_ino.whichfork);
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 472fe274e1d7d..92e1fc25262de 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -41,6 +41,9 @@
 #include "xfs_rmap.h"
 #include "xfs_refcount.h"
 #include "xfs_fsrefs.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+#include "xfs_btree_mem.h"
 
 static inline void
 xfs_btree_crack_agno_opdev(
@@ -48,7 +51,10 @@ xfs_btree_crack_agno_opdev(
 	xfs_agnumber_t		*agno,
 	dev_t			*opdev)
 {
-	if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY) {
+		*agno = 0;
+		*opdev = xfbtree_target(cur->bc_mem.xfbtree)->bt_dev;
+	} else if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
 		*agno = 0;
 		*opdev = cur->bc_mp->m_rtdev_targp->bt_dev;
 	} else {
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 4927cd36c9ab6..cb01355d97991 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2614,7 +2614,10 @@ TRACE_EVENT(xfs_btree_alloc_block,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+		if (cur->bc_flags & XFS_BTREE_IN_MEMORY) {
+			__entry->agno = 0;
+			__entry->ino = 0;
+		} else if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
 			__entry->agno = 0;
 			__entry->ino = cur->bc_ino.ip->i_ino;
 		} else {
@@ -2920,7 +2923,10 @@ DECLARE_EVENT_CLASS(xfs_btree_error_class,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+		if (cur->bc_flags & XFS_BTREE_IN_MEMORY) {
+			__entry->agno = 0;
+			__entry->ino = 0;
+		} else if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
 			__entry->agno = 0;
 			__entry->ino = cur->bc_ino.ip->i_ino;
 		} else {