multi-pack-index: verify object offsets

The 'git multi-pack-index verify' command must verify the object
offsets stored in the multi-pack-index are correct. There are two
ways the offset chunk can be incorrect: the pack-int-id and the
object offset.

Replace the BUG() statement with a die() statement, now that we
may hit a bad pack-int-id during a 'verify' command on a corrupt
multi-pack-index, and it is covered by a test.

Signed-off-by: Derrick Stolee <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: derrickstolee

midx.c

@@ -197,7 +197,8 @@ int prepare_midx_pack(struct multi_pack_index *m, uint32_t pack_int_id)
 	struct strbuf pack_name = STRBUF_INIT;
 
 	if (pack_int_id >= m->num_packs)
-		BUG("bad pack-int-id");
+		die(_("bad pack-int-id: %u (%u total packs"),
+		    pack_int_id, m->num_packs);
 
 	if (m->packs[pack_int_id])
 		return 0;
@@ -970,5 +971,31 @@ int verify_midx_file(const char *object_dir)
 				    i, oid_to_hex(&oid1), oid_to_hex(&oid2), i + 1);
 	}
 
+	for (i = 0; i < m->num_objects; i++) {
+		struct object_id oid;
+		struct pack_entry e;
+		off_t m_offset, p_offset;
+
+		nth_midxed_object_oid(&oid, m, i);
+		if (!fill_midx_entry(&oid, &e, m)) {
+			midx_report(_("failed to load pack entry for oid[%d] = %s"),
+				    i, oid_to_hex(&oid));
+			continue;
+		}
+
+		if (open_pack_index(e.p)) {
+			midx_report(_("failed to load pack-index for packfile %s"),
+				    e.p->pack_name);
+			break;
+		}
+
+		m_offset = e.offset;
+		p_offset = find_pack_entry_one(oid.hash, e.p);
+
+		if (m_offset != p_offset)
+			midx_report(_("incorrect object offset for oid[%d] = %s: %"PRIx64" != %"PRIx64),
+				    i, oid_to_hex(&oid), m_offset, p_offset);
+	}
+
 	return verify_midx_error;
 }

t/t5319-multi-pack-index.sh

@@ -176,6 +176,7 @@ test_expect_success 'verify bad signature' '
 '
 
 HASH_LEN=20
+NUM_OBJECTS=74
 MIDX_BYTE_VERSION=4
 MIDX_BYTE_OID_VERSION=5
 MIDX_BYTE_CHUNK_COUNT=6
@@ -192,6 +193,10 @@ MIDX_OID_FANOUT_WIDTH=4
 MIDX_BYTE_OID_FANOUT_ORDER=$((MIDX_OFFSET_OID_FANOUT + 250 * $MIDX_OID_FANOUT_WIDTH + 1))
 MIDX_OFFSET_OID_LOOKUP=$(($MIDX_OFFSET_OID_FANOUT + 256 * $MIDX_OID_FANOUT_WIDTH))
 MIDX_BYTE_OID_LOOKUP=$(($MIDX_OFFSET_OID_LOOKUP + 16 * $HASH_LEN))
+MIDX_OFFSET_OBJECT_OFFSETS=$(($MIDX_OFFSET_OID_LOOKUP + $NUM_OBJECTS * $HASH_LEN))
+MIDX_OFFSET_WIDTH=8
+MIDX_BYTE_PACK_INT_ID=$(($MIDX_OFFSET_OBJECT_OFFSETS + 16 * $MIDX_OFFSET_WIDTH + 2))
+MIDX_BYTE_OFFSET=$(($MIDX_OFFSET_OBJECT_OFFSETS + 16 * $MIDX_OFFSET_WIDTH + 6))
 
 test_expect_success 'verify bad version' '
 	corrupt_midx_and_verify $MIDX_BYTE_VERSION "\00" $objdir \
@@ -243,6 +248,16 @@ test_expect_success 'verify oid lookup out of order' '
 		"oid lookup out of order"
 '
 
+test_expect_success 'verify incorrect pack-int-id' '
+	corrupt_midx_and_verify $MIDX_BYTE_PACK_INT_ID "\07" $objdir \
+		"bad pack-int-id"
+'
+
+test_expect_success 'verify incorrect offset' '
+	corrupt_midx_and_verify $MIDX_BYTE_OFFSET "\07" $objdir \
+		"incorrect object offset"
+'
+
 test_expect_success 'repack removes multi-pack-index' '
 	test_path_is_file $objdir/pack/multi-pack-index &&
 	git repack -adf &&
@@ -310,4 +325,16 @@ test_expect_success 'verify multi-pack-index with 64-bit offsets' '
 	git multi-pack-index verify --object-dir=objects64
 '
 
+NUM_OBJECTS=63
+MIDX_OFFSET_OID_FANOUT=$((MIDX_OFFSET_PACKNAMES + 54))
+MIDX_OFFSET_OID_LOOKUP=$((MIDX_OFFSET_OID_FANOUT + 256 * $MIDX_OID_FANOUT_WIDTH))
+MIDX_OFFSET_OBJECT_OFFSETS=$(($MIDX_OFFSET_OID_LOOKUP + $NUM_OBJECTS * $HASH_LEN))
+MIDX_OFFSET_LARGE_OFFSETS=$(($MIDX_OFFSET_OBJECT_OFFSETS + $NUM_OBJECTS * $MIDX_OFFSET_WIDTH))
+MIDX_BYTE_LARGE_OFFSET=$(($MIDX_OFFSET_LARGE_OFFSETS + 3))
+
+test_expect_success 'verify incorrect 64-bit offset' '
+	corrupt_midx_and_verify $MIDX_BYTE_LARGE_OFFSET "\07" objects64 \
+		"incorrect object offset"
+'
+
 test_done