Merge tag 'repair-bitmap-rework-6.4_2023-04-11' of...

Merge tag 'repair-bitmap-rework-6.4_2023-04-11' of git://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into guilt/xfs-for-next

xfs: rework online fsck incore bitmap [v24.5]

In this series, we make some changes to the incore bitmap code: First,
we shorten the prefix to 'xbitmap'.  Then, we rework some utility
functions for later use by online repair and clarify how the walk
functions are supposed to be used.

Finally, we use all these new pieces to convert the incore bitmap to use
an interval tree instead of linked lists.  This lifts the limitation
that callers had to be careful not to set a range that was already set;
and gets us ready for the btree rebuilder functions needing to be able
to set bits in a bitmap and generate maximal contiguous extents for the
set ranges.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Dave Chinner <david@fromorbit.com>

fs/xfs/scrub/agheader_repair.c

@@ -487,10 +487,11 @@ xrep_agfl_walk_rmap(
 /* Strike out the blocks that are cross-linked according to the rmapbt. */
 STATIC int
 xrep_agfl_check_extent(
-	struct xrep_agfl	*ra,
 	uint64_t		start,
-	uint64_t		len)
+	uint64_t		len,
+	void			*priv)
 {
+	struct xrep_agfl	*ra = priv;
 	xfs_agblock_t		agbno = XFS_FSB_TO_AGBNO(ra->sc->mp, start);
 	xfs_agblock_t		last_agbno = agbno + len - 1;
 	int			error;
@@ -538,7 +539,6 @@ xrep_agfl_collect_blocks(
 	struct xrep_agfl	ra;
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_btree_cur	*cur;
-	struct xbitmap_range	*br, *n;
 	int			error;
 
 	ra.sc = sc;
@@ -579,11 +579,7 @@ xrep_agfl_collect_blocks(
 
 	/* Strike out the blocks that are cross-linked. */
 	ra.rmap_cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.pag);
-	for_each_xbitmap_extent(br, n, agfl_extents) {
-		error = xrep_agfl_check_extent(&ra, br->start, br->len);
-		if (error)
-			break;
-	}
+	error = xbitmap_walk(agfl_extents, xrep_agfl_check_extent, &ra);
 	xfs_btree_del_cursor(ra.rmap_cur, error);
 	if (error)
 		goto out_bmp;
@@ -629,21 +625,58 @@ xrep_agfl_update_agf(
 			XFS_AGF_FLFIRST | XFS_AGF_FLLAST | XFS_AGF_FLCOUNT);
 }
 
+struct xrep_agfl_fill {
+	struct xbitmap		used_extents;
+	struct xfs_scrub	*sc;
+	__be32			*agfl_bno;
+	xfs_agblock_t		flcount;
+	unsigned int		fl_off;
+};
+
+/* Fill the AGFL with whatever blocks are in this extent. */
+static int
+xrep_agfl_fill(
+	uint64_t		start,
+	uint64_t		len,
+	void			*priv)
+{
+	struct xrep_agfl_fill	*af = priv;
+	struct xfs_scrub	*sc = af->sc;
+	xfs_fsblock_t		fsbno = start;
+	int			error;
+
+	while (fsbno < start + len && af->fl_off < af->flcount)
+		af->agfl_bno[af->fl_off++] =
+				cpu_to_be32(XFS_FSB_TO_AGBNO(sc->mp, fsbno++));
+
+	trace_xrep_agfl_insert(sc->mp, sc->sa.pag->pag_agno,
+			XFS_FSB_TO_AGBNO(sc->mp, start), len);
+
+	error = xbitmap_set(&af->used_extents, start, fsbno - 1);
+	if (error)
+		return error;
+
+	if (af->fl_off == af->flcount)
+		return -ECANCELED;
+
+	return 0;
+}
+
 /* Write out a totally new AGFL. */
-STATIC void
+STATIC int
 xrep_agfl_init_header(
 	struct xfs_scrub	*sc,
 	struct xfs_buf		*agfl_bp,
 	struct xbitmap		*agfl_extents,
 	xfs_agblock_t		flcount)
 {
+	struct xrep_agfl_fill	af = {
+		.sc		= sc,
+		.flcount	= flcount,
+	};
 	struct xfs_mount	*mp = sc->mp;
-	__be32			*agfl_bno;
-	struct xbitmap_range	*br;
-	struct xbitmap_range	*n;
 	struct xfs_agfl		*agfl;
-	xfs_agblock_t		agbno;
-	unsigned int		fl_off;
+	int			error;
 
 	ASSERT(flcount <= xfs_agfl_size(mp));
 
@@ -662,36 +695,18 @@ xrep_agfl_init_header(
 	 * blocks than fit in the AGFL, they will be freed in a subsequent
 	 * step.
 	 */
-	fl_off = 0;
-	agfl_bno = xfs_buf_to_agfl_bno(agfl_bp);
-	for_each_xbitmap_extent(br, n, agfl_extents) {
-		agbno = XFS_FSB_TO_AGBNO(mp, br->start);
-
-		trace_xrep_agfl_insert(mp, sc->sa.pag->pag_agno, agbno,
-				br->len);
-
-		while (br->len > 0 && fl_off < flcount) {
-			agfl_bno[fl_off] = cpu_to_be32(agbno);
-			fl_off++;
-			agbno++;
-
-			/*
-			 * We've now used br->start by putting it in the AGFL,
-			 * so bump br so that we don't reap the block later.
-			 */
-			br->start++;
-			br->len--;
-		}
-
-		if (br->len)
-			break;
-		list_del(&br->list);
-		kfree(br);
-	}
+	xbitmap_init(&af.used_extents);
+	af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp),
+	xbitmap_walk(agfl_extents, xrep_agfl_fill, &af);
+	error = xbitmap_disunion(agfl_extents, &af.used_extents);
+	if (error)
+		return error;
 
 	/* Write new AGFL to disk. */
 	xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF);
 	xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1);
+	xbitmap_destroy(&af.used_extents);
+	return 0;
 }
 
 /* Repair the AGFL. */
@@ -744,7 +759,9 @@ xrep_agfl(
 	 * buffers until we know that part works.
 	 */
 	xrep_agfl_update_agf(sc, agf_bp, flcount);
-	xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount);
+	error = xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount);
+	if (error)
+		goto err;
 
 	/*
 	 * Ok, the AGFL should be ready to go now.  Roll the transaction to

fs/xfs/scrub/bitmap.h

@@ -6,26 +6,14 @@
 #ifndef __XFS_SCRUB_BITMAP_H__
 #define __XFS_SCRUB_BITMAP_H__
 
-struct xbitmap_range {
-	struct list_head	list;
-	uint64_t		start;
-	uint64_t		len;
-};
-
 struct xbitmap {
-	struct list_head	list;
+	struct rb_root_cached	xb_root;
 };
 
 void xbitmap_init(struct xbitmap *bitmap);
 void xbitmap_destroy(struct xbitmap *bitmap);
 
-#define for_each_xbitmap_extent(bex, n, bitmap) \
-	list_for_each_entry_safe((bex), (n), &(bitmap)->list, list)
-
-#define for_each_xbitmap_block(b, bex, n, bitmap) \
-	list_for_each_entry_safe((bex), (n), &(bitmap)->list, list) \
-		for ((b) = (bex)->start; (b) < (bex)->start + (bex)->len; (b)++)
-
+int xbitmap_clear(struct xbitmap *bitmap, uint64_t start, uint64_t len);
 int xbitmap_set(struct xbitmap *bitmap, uint64_t start, uint64_t len);
 int xbitmap_disunion(struct xbitmap *bitmap, struct xbitmap *sub);
 int xbitmap_set_btcur_path(struct xbitmap *bitmap,
@@ -34,4 +22,21 @@ int xbitmap_set_btblocks(struct xbitmap *bitmap,
 		struct xfs_btree_cur *cur);
 uint64_t xbitmap_hweight(struct xbitmap *bitmap);
 
+/*
+ * Return codes for the bitmap iterator functions are 0 to continue iterating,
+ * and non-zero to stop iterating.  Any non-zero value will be passed up to the
+ * iteration caller.  The special value -ECANCELED can be used to stop
+ * iteration, because neither bitmap iterator ever generates that error code on
+ * its own.  Callers must not modify the bitmap while walking it.
+ */
+typedef int (*xbitmap_walk_fn)(uint64_t start, uint64_t len, void *priv);
+int xbitmap_walk(struct xbitmap *bitmap, xbitmap_walk_fn fn,
+		void *priv);
+
+typedef int (*xbitmap_walk_bits_fn)(uint64_t bit, void *priv);
+int xbitmap_walk_bits(struct xbitmap *bitmap, xbitmap_walk_bits_fn fn,
+		void *priv);
+
+bool xbitmap_empty(struct xbitmap *bitmap);
+
 #endif	/* __XFS_SCRUB_BITMAP_H__ */

fs/xfs/scrub/repair.c

@@ -445,6 +445,30 @@ xrep_init_btblock(
  * buffers associated with @bitmap.
  */
 
+static int
+xrep_invalidate_block(
+	uint64_t		fsbno,
+	void			*priv)
+{
+	struct xfs_scrub	*sc = priv;
+	struct xfs_buf		*bp;
+	int			error;
+
+	/* Skip AG headers and post-EOFS blocks */
+	if (!xfs_verify_fsbno(sc->mp, fsbno))
+		return 0;
+
+	error = xfs_buf_incore(sc->mp->m_ddev_targp,
+			XFS_FSB_TO_DADDR(sc->mp, fsbno),
+			XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK, &bp);
+	if (error)
+		return 0;
+
+	xfs_trans_bjoin(sc->tp, bp);
+	xfs_trans_binval(sc->tp, bp);
+	return 0;
+}
+
 /*
  * Invalidate buffers for per-AG btree blocks we're dumping.  This function
  * is not intended for use with file data repairs; we have bunmapi for that.
@@ -454,11 +478,6 @@ xrep_invalidate_blocks(
 	struct xfs_scrub	*sc,
 	struct xbitmap		*bitmap)
 {
-	struct xbitmap_range	*bmr;
-	struct xbitmap_range	*n;
-	struct xfs_buf		*bp;
-	xfs_fsblock_t		fsbno;
-
 	/*
 	 * For each block in each extent, see if there's an incore buffer for
 	 * exactly that block; if so, invalidate it.  The buffer cache only
@@ -467,23 +486,7 @@ xrep_invalidate_blocks(
 	 * because we never own those; and if we can't TRYLOCK the buffer we
 	 * assume it's owned by someone else.
 	 */
-	for_each_xbitmap_block(fsbno, bmr, n, bitmap) {
-		int		error;
-
-		/* Skip AG headers and post-EOFS blocks */
-		if (!xfs_verify_fsbno(sc->mp, fsbno))
-			continue;
-		error = xfs_buf_incore(sc->mp->m_ddev_targp,
-				XFS_FSB_TO_DADDR(sc->mp, fsbno),
-				XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK, &bp);
-		if (error)
-			continue;
-
-		xfs_trans_bjoin(sc->tp, bp);
-		xfs_trans_binval(sc->tp, bp);
-	}
-
-	return 0;
+	return xbitmap_walk_bits(bitmap, xrep_invalidate_block, sc);
 }
 
 /* Ensure the freelist is the correct size. */
@@ -504,6 +507,15 @@ xrep_fix_freelist(
 			can_shrink ? 0 : XFS_ALLOC_FLAG_NOSHRINK);
 }
 
+/* Information about reaping extents after a repair. */
+struct xrep_reap_state {
+	struct xfs_scrub		*sc;
+
+	/* Reverse mapping owner and metadata reservation type. */
+	const struct xfs_owner_info	*oinfo;
+	enum xfs_ag_resv_type		resv;
+};
+
 /*
  * Put a block back on the AGFL.
  */
@@ -548,17 +560,23 @@ xrep_put_freelist(
 /* Dispose of a single block. */
 STATIC int
 xrep_reap_block(
-	struct xfs_scrub		*sc,
-	xfs_fsblock_t			fsbno,
-	const struct xfs_owner_info	*oinfo,
-	enum xfs_ag_resv_type		resv)
+	uint64_t			fsbno,
+	void				*priv)
 {
+	struct xrep_reap_state		*rs = priv;
+	struct xfs_scrub		*sc = rs->sc;
 	struct xfs_btree_cur		*cur;
 	struct xfs_buf			*agf_bp = NULL;
 	xfs_agblock_t			agbno;
 	bool				has_other_rmap;
 	int				error;
 
+	ASSERT(sc->ip != NULL ||
+	       XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.pag->pag_agno);
+	trace_xrep_dispose_btree_extent(sc->mp,
+			XFS_FSB_TO_AGNO(sc->mp, fsbno),
+			XFS_FSB_TO_AGBNO(sc->mp, fsbno), 1);
+
 	agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno);
 	ASSERT(XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.pag->pag_agno);
 
@@ -577,7 +595,8 @@ xrep_reap_block(
 	cur = xfs_rmapbt_init_cursor(sc->mp, sc->tp, agf_bp, sc->sa.pag);
 
 	/* Can we find any other rmappings? */
-	error = xfs_rmap_has_other_keys(cur, agbno, 1, oinfo, &has_other_rmap);
+	error = xfs_rmap_has_other_keys(cur, agbno, 1, rs->oinfo,
+			&has_other_rmap);
 	xfs_btree_del_cursor(cur, error);
 	if (error)
 		goto out_free;
@@ -597,12 +616,12 @@ xrep_reap_block(
 	 */
 	if (has_other_rmap)
 		error = xfs_rmap_free(sc->tp, agf_bp, sc->sa.pag, agbno,
-					1, oinfo);
-	else if (resv == XFS_AG_RESV_AGFL)
+					1, rs->oinfo);
+	else if (rs->resv == XFS_AG_RESV_AGFL)
 		error = xrep_put_freelist(sc, agbno);
 	else
-		error = xfs_free_extent(sc->tp, sc->sa.pag, agbno, 1, oinfo,
-				resv);
+		error = xfs_free_extent(sc->tp, sc->sa.pag, agbno, 1, rs->oinfo,
+				rs->resv);
 	if (agf_bp != sc->sa.agf_bp)
 		xfs_trans_brelse(sc->tp, agf_bp);
 	if (error)
@@ -626,26 +645,15 @@ xrep_reap_extents(
 	const struct xfs_owner_info	*oinfo,
 	enum xfs_ag_resv_type		type)
 {
-	struct xbitmap_range		*bmr;
-	struct xbitmap_range		*n;
-	xfs_fsblock_t			fsbno;
-	int				error = 0;
+	struct xrep_reap_state		rs = {
+		.sc			= sc,
+		.oinfo			= oinfo,
+		.resv			= type,
+	};
 
 	ASSERT(xfs_has_rmapbt(sc->mp));
 
-	for_each_xbitmap_block(fsbno, bmr, n, bitmap) {
-		ASSERT(sc->ip != NULL ||
-		       XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.pag->pag_agno);
-		trace_xrep_dispose_btree_extent(sc->mp,
-				XFS_FSB_TO_AGNO(sc->mp, fsbno),
-				XFS_FSB_TO_AGBNO(sc->mp, fsbno), 1);
-
-		error = xrep_reap_block(sc, fsbno, oinfo, type);
-		if (error)
-			break;
-	}
-
-	return error;
+	return xbitmap_walk_bits(bitmap, xrep_reap_block, &rs);
 }
 
 /*