midx: check size of revindex chunk

When we load a revindex from disk, we check the size of the file
compared to the number of objects we expect it to have. But when we use
a RIDX chunk stored directly in the midx, we just access the memory
directly. This can lead to out-of-bounds memory access for a corrupted
or malicious multi-pack-index file.

We can catch this by recording the RIDX chunk size, and then checking it
against the expected size when we "load" the revindex. Note that this
check is much simpler than the one that load_revindex_from_disk() does,
because we just have the data array with no header (so we do not need
to account for the header size, and nor do we need to bother validating
the header values).

The test confirms both that we catch this case, and that we continue the
process (the revindex is required to use the midx bitmaps, but we
fallback to a non-bitmap traversal).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

midx.c

@@ -184,7 +184,8 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
 		   &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);
+		pair_chunk(cf, MIDX_CHUNKID_REVINDEX, &m->chunk_revindex,
+			   &m->chunk_revindex_len);
 
 	CALLOC_ARRAY(m->pack_names, m->num_packs);
 	CALLOC_ARRAY(m->packs, m->num_packs);

midx.h

@@ -39,6 +39,7 @@ struct multi_pack_index {
 	const unsigned char *chunk_large_offsets;
 	size_t chunk_large_offsets_len;
 	const unsigned char *chunk_revindex;
+	size_t chunk_revindex_len;
 
 	const char **pack_names;
 	struct packed_git **packs;

pack-revindex.c

@@ -343,6 +343,17 @@ int verify_pack_revindex(struct packed_git *p)
 	return res;
 }
 
+static int can_use_midx_ridx_chunk(struct multi_pack_index *m)
+{
+	if (!m->chunk_revindex)
+		return 0;
+	if (m->chunk_revindex_len != st_mult(sizeof(uint32_t), m->num_objects)) {
+		error(_("multi-pack-index reverse-index chunk is the wrong size"));
+		return 0;
+	}
+	return 1;
+}
+
 int load_midx_revindex(struct multi_pack_index *m)
 {
 	struct strbuf revindex_name = STRBUF_INIT;
@@ -351,7 +362,7 @@ int load_midx_revindex(struct multi_pack_index *m)
 	if (m->revindex_data)
 		return 0;
 
-	if (m->chunk_revindex) {
+	if (can_use_midx_ridx_chunk(m)) {
 		/*
 		 * If the MIDX `m` has a `RIDX` chunk, then use its contents for
 		 * the reverse index instead of trying to load a separate `.rev`

t/t5319-multi-pack-index.sh

@@ -1138,4 +1138,21 @@ test_expect_success 'reader bounds-checks large offset table' '
 	)
 '
 
+test_expect_success 'reader notices too-small revindex chunk' '
+	# We only get a revindex with bitmaps (and likewise only
+	# load it when they are asked for).
+	test_config repack.writeBitmaps true &&
+	corrupt_chunk RIDX clear 00000000 &&
+	git -c core.multipackIndex=false rev-list \
+		--all --use-bitmap-index >expect.out &&
+	git -c core.multipackIndex=true rev-list \
+		--all --use-bitmap-index >out 2>err &&
+	test_cmp expect.out out &&
+	cat >expect.err <<-\EOF &&
+	error: multi-pack-index reverse-index chunk is the wrong size
+	warning: multi-pack bitmap is missing required reverse index
+	EOF
+	test_cmp expect.err err
+'
+
 test_done