midx: bounds-check large offset chunk

When we see a large offset bit in the regular midx offset table, we
use the entry as an index into a separate large offset table (just like
a pack idx does). But we don't bounds-check the access to that large
offset table (nor even record its size when we parse the chunk!).

The equivalent code for a regular pack idx is in check_pack_index_ptr().
But things are a bit simpler here because of the chunked format: we can
just check our array index directly.

As a bonus, we can get rid of the st_mult() here. If our array
bounds-check is successful, then we know that the result will fit in a
size_t (and the bounds check uses a division to avoid overflow
entirely).

Signed-off-by: Jeff King <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: peff

midx.c

@@ -180,7 +180,8 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
 	if (read_chunk(cf, MIDX_CHUNKID_OBJECTOFFSETS, midx_read_object_offsets, m))
 		die(_("multi-pack-index required object offsets chunk missing or corrupted"));
 
-	pair_chunk_unsafe(cf, MIDX_CHUNKID_LARGEOFFSETS, &m->chunk_large_offsets);
+	pair_chunk(cf, MIDX_CHUNKID_LARGEOFFSETS, &m->chunk_large_offsets,
+		   &m->chunk_large_offsets_len);
 
 	if (git_env_bool("GIT_TEST_MIDX_READ_RIDX", 1))
 		pair_chunk_unsafe(cf, MIDX_CHUNKID_REVINDEX, &m->chunk_revindex);
@@ -303,8 +304,9 @@ off_t nth_midxed_offset(struct multi_pack_index *m, uint32_t pos)
 			die(_("multi-pack-index stores a 64-bit offset, but off_t is too small"));
 
 		offset32 ^= MIDX_LARGE_OFFSET_NEEDED;
-		return get_be64(m->chunk_large_offsets +
-				st_mult(sizeof(uint64_t), offset32));
+		if (offset32 >= m->chunk_large_offsets_len / sizeof(uint64_t))
+			die(_("multi-pack-index large offset out of bounds"));
+		return get_be64(m->chunk_large_offsets + sizeof(uint64_t) * offset32);
 	}
 
 	return offset32;

midx.h

@@ -37,6 +37,7 @@ struct multi_pack_index {
 	const unsigned char *chunk_oid_lookup;
 	const unsigned char *chunk_object_offsets;
 	const unsigned char *chunk_large_offsets;
+	size_t chunk_large_offsets_len;
 	const unsigned char *chunk_revindex;
 
 	const char **pack_names;

t/t5319-multi-pack-index.sh

@@ -1118,4 +1118,24 @@ test_expect_success 'reader notices too-small object offset chunk' '
 	test_cmp expect err
 '
 
+test_expect_success 'reader bounds-checks large offset table' '
+	# re-use the objects64 dir here to cheaply get access to a midx
+	# with large offsets.
+	git init repo &&
+	test_when_finished "rm -rf repo" &&
+	(
+		cd repo &&
+		(cd ../objects64 && pwd) >.git/objects/info/alternates &&
+		git multi-pack-index --object-dir=../objects64 write &&
+		midx=../objects64/pack/multi-pack-index &&
+		corrupt_chunk_file $midx LOFF clear &&
+		test_must_fail git cat-file \
+			--batch-check --batch-all-objects 2>err &&
+		cat >expect <<-\EOF &&
+		fatal: multi-pack-index large offset out of bounds
+		EOF
+		test_cmp expect err
+	)
+'
+
 test_done