packfile.c: protect against disappearing indexes

In 17c35c8969 (packfile: skip loading index if in multi-pack-index,
2018-07-12) we stopped loading the .idx file for packs that are
contained within a multi-pack index.

This saves us the effort of loading an .idx and doing some lightweight
validity checks by way of 'packfile.c:load_idx()', but introduces a race
between processes that need to load the index (e.g., to generate a
reverse index) and processes that can delete the index.

For example, running the following in your shell:

    $ git init repo && cd repo
    $ git commit --allow-empty -m 'base'
    $ git repack -ad && git multi-pack-index write

followed by:

    $ rm -f .git/objects/pack/pack-*.idx
    $ git rev-parse HEAD | git cat-file --batch-check='%(objectsize:disk)'

will result in a segfault prior to this patch. What's happening here is
that we notice that the pack is in the multi-pack index, and so don't
check that it still has a .idx. When we then try and load that index to
generate a reverse index, we don't have it, so the call to
'find_pack_revindex()' in 'packfile.c:packed_object_info()' returns
NULL, and then dereferencing it causes a segfault.

Of course, we don't ever expect someone to remove the index file by
hand, or to be in a state where we never wrote it to begin with (yet
find that pack in the multi-pack-index). But, this can happen in a
timing race with 'git repack -ad', which removes all existing packs
after writing a new pack containing all of their objects.

Avoid this by reverting the hunk of 17c35c8969 which stops loading the
index when the pack is contained in a MIDX. This makes the latter half
of 17c35c8969 useless, since we'll always have a non-NULL
'p->index_data', in which case that if statement isn't guarding
anything.

These two together effectively revert 17c35c8969, and avoid the race
explained above.

Co-authored-by: Jeff King <peff@peff.net>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

packfile.c

@@ -514,19 +514,8 @@ static int open_packed_git_1(struct packed_git *p)
 	ssize_t read_result;
 	const unsigned hashsz = the_hash_algo->rawsz;
 
-	if (!p->index_data) {
-		struct multi_pack_index *m;
-		const char *pack_name = pack_basename(p);
-
-		for (m = the_repository->objects->multi_pack_index;
-		     m; m = m->next) {
-			if (midx_contains_pack(m, pack_name))
-				break;
-		}
-
-		if (!m && open_pack_index(p))
-			return error("packfile %s index unavailable", p->pack_name);
-	}
+	if (open_pack_index(p))
+		return error("packfile %s index unavailable", p->pack_name);
 
 	if (!pack_max_fds) {
 		unsigned int max_fds = get_max_fd_limit();
@@ -577,10 +566,6 @@ static int open_packed_git_1(struct packed_git *p)
 			" supported (try upgrading GIT to a newer version)",
 			p->pack_name, ntohl(hdr.hdr_version));
 
-	/* Skip index checking if in multi-pack-index */
-	if (!p->index_data)
-		return 0;
-
 	/* Verify the pack matches its index. */
 	if (p->num_objects != ntohl(hdr.hdr_entries))
 		return error("packfile %s claims to have %"PRIu32" objects"

t/t5319-multi-pack-index.sh

@@ -117,7 +117,7 @@ test_expect_success 'write midx with one v2 pack' '
 
 compare_results_with_midx "one v2 pack"
 
-test_expect_success 'corrupt idx not opened' '
+test_expect_success 'corrupt idx reports errors' '
 	idx=$(test-tool read-midx $objdir | grep "\.idx\$") &&
 	mv $objdir/pack/$idx backup-$idx &&
 	test_when_finished "mv backup-\$idx \$objdir/pack/\$idx" &&
@@ -128,7 +128,7 @@ test_expect_success 'corrupt idx not opened' '
 	test_copy_bytes 1064 <backup-$idx >$objdir/pack/$idx &&
 
 	git -c core.multiPackIndex=true rev-list --objects --all 2>err &&
-	test_must_be_empty err
+	grep "index unavailable" err
 '
 
 test_expect_success 'add more objects' '
@@ -547,4 +547,24 @@ test_expect_success 'repack --batch-size=0 repacks everything' '
 	)
 '
 
+test_expect_success 'load reverse index when missing .idx' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		git config core.multiPackIndex true &&
+
+		test_commit base &&
+		git repack -ad &&
+		git multi-pack-index write &&
+
+		git rev-parse HEAD >tip &&
+		idx=$(ls .git/objects/pack/pack-*.idx) &&
+
+		mv $idx $idx.bak &&
+		git cat-file --batch-check="%(objectsize:disk)" <tip
+	)
+'
+
 test_done