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>

3 files changed, 223 insertions, 23 deletions

diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 76fc46b8db88..7c05f8bb5f0d 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -28,6 +28,9 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
 #include "xfs_health.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+#include "xfs_btree_mem.h"
 
 /*
  * Btree magic numbers.
@@ -82,6 +85,9 @@ xfs_btree_check_lblock_siblings(
 	if (level >= 0) {
 		if (!xfs_btree_check_lptr(cur, sibling, level + 1))
 			return __this_address;
+	} else if (cur && (cur->bc_flags & XFS_BTREE_IN_MEMORY)) {
+		if (!xfbtree_verify_xfileoff(cur, sibling))
+			return __this_address;
 	} else {
 		if (!xfs_verify_fsbno(mp, sibling))
 			return __this_address;
@@ -109,6 +115,9 @@ xfs_btree_check_sblock_siblings(
 	if (level >= 0) {
 		if (!xfs_btree_check_sptr(cur, sibling, level + 1))
 			return __this_address;
+	} else if (cur && (cur->bc_flags & XFS_BTREE_IN_MEMORY)) {
+		if (!xfbtree_verify_xfileoff(cur, sibling))
+			return __this_address;
 	} else {
 		if (!xfs_verify_agbno(pag, sibling))
 			return __this_address;
@@ -151,7 +160,9 @@ __xfs_btree_check_lblock(
 	    cur->bc_ops->get_maxrecs(cur, level))
 		return __this_address;
 
-	if (bp)
+	if ((cur->bc_flags & XFS_BTREE_IN_MEMORY) && bp)
+		fsb = xfbtree_buf_to_xfoff(cur, bp);
+	else if (bp)
 		fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
 
 	fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
@@ -218,8 +229,12 @@ __xfs_btree_check_sblock(
 	    cur->bc_ops->get_maxrecs(cur, level))
 		return __this_address;
 
-	if (bp)
+	if ((cur->bc_flags & XFS_BTREE_IN_MEMORY) && bp) {
+		pag = NULL;
+		agbno = xfbtree_buf_to_xfoff(cur, bp);
+	} else if (bp) {
 		agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
+	}
 
 	fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno,
 			block->bb_u.s.bb_leftsib);
@@ -276,6 +291,8 @@ 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);
 }
 
@@ -288,6 +305,8 @@ 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_ag.pag, agbno);
 }
 
@@ -302,6 +321,9 @@ 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))
@@ -458,11 +480,36 @@ xfs_btree_del_cursor(
 	       xfs_is_shutdown(cur->bc_mp) || error != 0);
 	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);
+	if (cur->bc_flags & XFS_BTREE_IN_MEMORY) {
+		if (cur->bc_mem.pag)
+			xfs_perag_put(cur->bc_mem.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.
@@ -500,10 +547,11 @@ 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) {
@@ -944,6 +992,9 @@ 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);
@@ -969,6 +1020,8 @@ 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,
@@ -1030,6 +1083,11 @@ 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);
@@ -1058,8 +1116,9 @@ 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);
 }
 
 /*
@@ -1233,7 +1292,9 @@ 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 = xfbtree_owner(cur);
+	else if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
 		owner = cur->bc_ino.ip->i_ino;
 	else
 		owner = cur->bc_ag.pag->pag_agno;
@@ -1273,6 +1334,11 @@ 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)));
@@ -1317,15 +1383,14 @@ 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;
 
@@ -1356,9 +1421,9 @@ 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)
@@ -1798,6 +1863,37 @@ 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 */
@@ -1836,11 +1932,7 @@ 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? */
@@ -4585,6 +4677,8 @@ xfs_btree_lblock_verify(
 	xfs_fsblock_t		fsb;
 	xfs_failaddr_t		fa;
 
+	ASSERT(!xfs_buftarg_in_memory(bp->b_target));
+
 	/* numrecs verification */
 	if (be16_to_cpu(block->bb_numrecs) > max_recs)
 		return __this_address;
@@ -4640,6 +4734,8 @@ xfs_btree_sblock_verify(
 	xfs_agblock_t		agbno;
 	xfs_failaddr_t		fa;
 
+	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 66c004481de7..292d02ac9304 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -248,6 +248,15 @@ struct xfs_btree_cur_ino {
 #define	XFS_BTCUR_BMBT_INVALID_OWNER	(1 << 1)
 };
 
+/* In-memory btree information */
+struct xfbtree;
+
+struct xfs_btree_cur_mem {
+	struct xfbtree			*xfbtree;
+	struct xfs_buf			*head_bp;
+	struct xfs_perag		*pag;
+};
+
 struct xfs_btree_level {
 	/* buffer pointer */
 	struct xfs_buf		*bp;
@@ -287,6 +296,7 @@ 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! */
@@ -317,6 +327,13 @@ xfs_btree_cur_sizeof(unsigned int nlevels)
  */
 #define XFS_BTREE_STAGING		(1<<5)
 
+/* 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 000000000000..6ca9ea64a9a4
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_btree_mem.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022 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);
+unsigned long long xfbtree_owner(struct xfs_btree_cur *cur);
+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);
+unsigned long long xfbtree_buf_to_xfoff(struct xfs_btree_cur *cur,
+		struct xfs_buf *bp);
+#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
+#define xfbtree_owner(cur)			(0ULL)
+#define xfbtree_buf_to_xfoff(cur, bp)		(-1)
+
+#endif /* CONFIG_XFS_IN_MEMORY_BTREE */
+
+#endif /* __XFS_BTREE_MEM_H__ */