commit-graph: verify corrupt OID fanout and lookup

In the commit-graph file, the OID fanout chunk provides an index into
the OID lookup. The 'verify' subcommand should find incorrect values
in the fanout.

Similarly, the 'verify' subcommand should find out-of-order values in
the OID lookup.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 58 insertions, 0 deletions

diff --git a/commit-graph.c b/commit-graph.c
index 26328c3..b34f62f 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -843,6 +843,9 @@ static void graph_report(const char *fmt, ...)
 
 int verify_commit_graph(struct repository *r, struct commit_graph *g)
 {
+	uint32_t i, cur_fanout_pos = 0;
+	struct object_id prev_oid, cur_oid;
+
 	if (!g) {
 		graph_report("no commit-graph file loaded");
 		return 1;
@@ -857,5 +860,38 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g)
 	if (!g->chunk_commit_data)
 		graph_report("commit-graph is missing the Commit Data chunk");
 
+	if (verify_commit_graph_error)
+		return verify_commit_graph_error;
+
+	for (i = 0; i < g->num_commits; i++) {
+		hashcpy(cur_oid.hash, g->chunk_oid_lookup + g->hash_len * i);
+
+		if (i && oidcmp(&prev_oid, &cur_oid) >= 0)
+			graph_report("commit-graph has incorrect OID order: %s then %s",
+				     oid_to_hex(&prev_oid),
+				     oid_to_hex(&cur_oid));
+
+		oidcpy(&prev_oid, &cur_oid);
+
+		while (cur_oid.hash[0] > cur_fanout_pos) {
+			uint32_t fanout_value = get_be32(g->chunk_oid_fanout + cur_fanout_pos);
+
+			if (i != fanout_value)
+				graph_report("commit-graph has incorrect fanout value: fanout[%d] = %u != %u",
+					     cur_fanout_pos, fanout_value, i);
+			cur_fanout_pos++;
+		}
+	}
+
+	while (cur_fanout_pos < 256) {
+		uint32_t fanout_value = get_be32(g->chunk_oid_fanout + cur_fanout_pos);
+
+		if (g->num_commits != fanout_value)
+			graph_report("commit-graph has incorrect fanout value: fanout[%d] = %u != %u",
+				     cur_fanout_pos, fanout_value, i);
+
+		cur_fanout_pos++;
+	}
+
 	return verify_commit_graph_error;
 }
diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh
index dc16849..8ae2a49 100755
--- a/t/t5318-commit-graph.sh
+++ b/t/t5318-commit-graph.sh
@@ -247,6 +247,7 @@ test_expect_success 'git commit-graph verify' '
 	git commit-graph verify >output
 '
 
+HASH_LEN=20
 GRAPH_BYTE_VERSION=4
 GRAPH_BYTE_HASH=5
 GRAPH_BYTE_CHUNK_COUNT=6
@@ -258,6 +259,12 @@ GRAPH_BYTE_OID_LOOKUP_ID=$(($GRAPH_CHUNK_LOOKUP_OFFSET + \
 			    1 * $GRAPH_CHUNK_LOOKUP_WIDTH))
 GRAPH_BYTE_COMMIT_DATA_ID=$(($GRAPH_CHUNK_LOOKUP_OFFSET + \
 			     2 * $GRAPH_CHUNK_LOOKUP_WIDTH))
+GRAPH_FANOUT_OFFSET=$(($GRAPH_CHUNK_LOOKUP_OFFSET + \
+		       $GRAPH_CHUNK_LOOKUP_WIDTH * $GRAPH_CHUNK_LOOKUP_ROWS))
+GRAPH_BYTE_FANOUT1=$(($GRAPH_FANOUT_OFFSET + 4 * 4))
+GRAPH_BYTE_FANOUT2=$(($GRAPH_FANOUT_OFFSET + 4 * 255))
+GRAPH_OID_LOOKUP_OFFSET=$(($GRAPH_FANOUT_OFFSET + 4 * 256))
+GRAPH_BYTE_OID_LOOKUP_ORDER=$(($GRAPH_OID_LOOKUP_OFFSET + $HASH_LEN * 8))
 
 # usage: corrupt_graph_and_verify <position> <data> <string>
 # Manipulates the commit-graph file at the position
@@ -312,4 +319,19 @@ test_expect_success 'detect missing commit data chunk' '
 		"missing the Commit Data chunk"
 '
 
+test_expect_success 'detect incorrect fanout' '
+	corrupt_graph_and_verify $GRAPH_BYTE_FANOUT1 "\01" \
+		"fanout value"
+'
+
+test_expect_success 'detect incorrect fanout final value' '
+	corrupt_graph_and_verify $GRAPH_BYTE_FANOUT2 "\01" \
+		"fanout value"
+'
+
+test_expect_success 'detect incorrect OID order' '
+	corrupt_graph_and_verify $GRAPH_BYTE_OID_LOOKUP_ORDER "\01" \
+		"incorrect OID order"
+'
+
 test_done