From 6b5b9b1e6fc28099c66b63d8bccb1f0049736343 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Fri, 30 Dec 2022 14:19:42 -0800
Subject: [PATCH] xfs: improve metadata array field handling when fuzzing

Currently, we use some gnarly regular expressions to try to constrain
the amount of time we spend fuzzing each element of a metadata array.
This is pretty inflexible (and buggy) since we limit some arrays
(e.g. dir hashes) to the first ten elements and other arrays (e.g.
extent mappings) that use compact index ranges to the first one.

Replace this whole weird mess with logic that can tease out the array
indices, unroll the compact indices if needed, and give the user more
flexible control over which array elements get used.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Zorro Lang <zlang@redhat.com>
Signed-off-by: Zorro Lang <zlang@kernel.org>
---
 common/fuzzy | 52 +++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 43 insertions(+), 9 deletions(-)

diff --git a/common/fuzzy b/common/fuzzy
index a98e2ade..74230aac 100644
--- a/common/fuzzy
+++ b/common/fuzzy
@@ -53,12 +53,46 @@ _scratch_scrub() {
 	esac
 }
 
-# Filter out any keys with an array index >= 10, collapse any array range
-# ("[1-195]") to the first item, and ignore padding fields.
-__filter_xfs_db_keys() {
-	sed -e '/\([a-z]*\)\[\([0-9][0-9]\+\)\].*/d' \
-	    -e 's/\([a-zA-Z0-9_]*\)\[\([0-9]*\)-[0-9]*\]/\1[\2]/g' \
-	    -e '/pad/d'
+# Expand indexed keys (i.e. arrays) into a long format so that we can filter
+# the array indices individually, and pass regular keys right through.
+#
+# For example, "u3.bmx[0-1] = [foo,bar]" is exploded into:
+# u3.bmx[0] = [foo,bar]
+# u3.bmx[1] = [foo,bar]
+#
+# Note that we restrict array indices to [0-9] to reduce fuzz runtime.  The
+# minimum and maximum array indices can be changed by setting the variables
+# SCRATCH_XFS_{MIN,MAX}_ARRAY_IDX.
+#
+# Also filter padding fields.
+__explode_xfs_db_fields() {
+	local min_idx="${SCRATCH_XFS_MIN_ARRAY_IDX}"
+	local max_idx="${SCRATCH_XFS_MAX_ARRAY_IDX}"
+
+	test -z "${min_idx}" && min_idx=0
+	test -z "${max_idx}" && max_idx=9
+	test "${max_idx}" = "none" && max_idx=99999
+
+	grep ' = ' | \
+	sed -e 's/^\([.a-zA-Z0-9_]*\)\[\([0-9]*\)-\([0-9]*\)\]\(.*\) = \(.*\)$/\1[%d]\4 \2 \3 = \5/g' \
+	    -e 's/^\([.a-zA-Z0-9_]*\)\[\([0-9]*\)\]\(.*\) = \(.*\)$/\1[%d]\3 \2 \2 = \4/g' | \
+	while read name col1 col2 rest; do
+		if [[ "${name}" == *pad* ]]; then
+			continue
+		fi
+
+		if [ "${col1}" = "=" ]; then
+			echo "${name} ${col1} ${col2} ${rest}"
+			continue
+		fi
+
+		test "${min_idx}" -gt "${col1}" && col1="${min_idx}"
+		test "${max_idx}" -lt "${col2}" && col2="${max_idx}"
+
+		seq "${col1}" "${col2}" | while read idx; do
+			printf "${name} %s\n" "${idx}" "${rest}"
+		done
+	done
 }
 
 # Filter out metadata fields that are completely controlled by userspace
@@ -96,14 +130,14 @@ __filter_xfs_db_print_fields() {
 	if [ -z "${filter}" ] || [ "${filter}" = "nofilter" ]; then
 		filter='^'
 	fi
-	grep ' = ' | while read key equals value; do
-		fuzzkey="$(echo "${key}" | __filter_xfs_db_keys)"
+	__explode_xfs_db_fields | while read key equals value; do
+		fuzzkey="$(echo "${key}")"
 		if [ -z "${fuzzkey}" ]; then
 			continue
 		elif [[ "${value}" == "["* ]]; then
 			echo "${value}" | sed -e 's/^.//g' -e 's/.$//g' -e 's/,/\n/g' | while read subfield; do
 				echo "${fuzzkey}.${subfield}"
-			done | __filter_xfs_db_keys
+			done
 		else
 			echo "${fuzzkey}"
 		fi
-- 
2.39.5