1 files changed, 45 insertions, 26 deletions

diff --git a/builtin/grep.c b/builtin/grep.c
index 5de725f..51278b0 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -65,6 +65,9 @@ static int todo_done;
 /* Has all work items been added? */
 static int all_work_added;
 
+static struct repository **repos_to_free;
+static size_t repos_to_free_nr, repos_to_free_alloc;
+
 /* This lock protects all the variables above. */
 static pthread_mutex_t grep_mutex;
 
@@ -168,6 +171,19 @@ static void work_done(struct work_item *w)
 	grep_unlock();
 }
 
+static void free_repos(void)
+{
+	int i;
+
+	for (i = 0; i < repos_to_free_nr; i++) {
+		repo_clear(repos_to_free[i]);
+		free(repos_to_free[i]);
+	}
+	FREE_AND_NULL(repos_to_free);
+	repos_to_free_nr = 0;
+	repos_to_free_alloc = 0;
+}
+
 static void *run(void *arg)
 {
 	int hit = 0;
@@ -333,7 +349,7 @@ static int grep_oid(struct grep_opt *opt, const struct object_id *oid,
 	struct grep_source gs;
 
 	grep_source_name(opt, filename, tree_name_len, &pathbuf);
-	grep_source_init(&gs, GREP_SOURCE_OID, pathbuf.buf, path, oid);
+	grep_source_init_oid(&gs, pathbuf.buf, path, oid, opt->repo);
 	strbuf_release(&pathbuf);
 
 	if (num_threads > 1) {
@@ -359,7 +375,7 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 	struct grep_source gs;
 
 	grep_source_name(opt, filename, 0, &buf);
-	grep_source_init(&gs, GREP_SOURCE_FILE, buf.buf, filename, filename);
+	grep_source_init_file(&gs, buf.buf, filename);
 	strbuf_release(&buf);
 
 	if (num_threads > 1) {
@@ -415,19 +431,24 @@ static int grep_submodule(struct grep_opt *opt,
 			  const struct object_id *oid,
 			  const char *filename, const char *path, int cached)
 {
-	struct repository subrepo;
+	struct repository *subrepo;
 	struct repository *superproject = opt->repo;
 	const struct submodule *sub;
 	struct grep_opt subopt;
-	int hit;
+	int hit = 0;
 
-	sub = submodule_from_path(superproject, &null_oid, path);
+	sub = submodule_from_path(superproject, null_oid(), path);
 
 	if (!is_submodule_active(superproject, path))
 		return 0;
 
-	if (repo_submodule_init(&subrepo, superproject, sub))
+	subrepo = xmalloc(sizeof(*subrepo));
+	if (repo_submodule_init(subrepo, superproject, sub)) {
+		free(subrepo);
 		return 0;
+	}
+	ALLOC_GROW(repos_to_free, repos_to_free_nr + 1, repos_to_free_alloc);
+	repos_to_free[repos_to_free_nr++] = subrepo;
 
 	/*
 	 * NEEDSWORK: repo_read_gitmodules() might call
@@ -438,53 +459,49 @@ static int grep_submodule(struct grep_opt *opt,
 	 * subrepo's odbs to the in-memory alternates list.
 	 */
 	obj_read_lock();
-	repo_read_gitmodules(&subrepo, 0);
+	repo_read_gitmodules(subrepo, 0);
 
 	/*
-	 * NEEDSWORK: This adds the submodule's object directory to the list of
-	 * alternates for the single in-memory object store.  This has some bad
-	 * consequences for memory (processed objects will never be freed) and
-	 * performance (this increases the number of pack files git has to pay
-	 * attention to, to the sum of the number of pack files in all the
-	 * repositories processed so far).  This can be removed once the object
-	 * store is no longer global and instead is a member of the repository
-	 * object.
+	 * All code paths tested by test code no longer need submodule ODBs to
+	 * be added as alternates, but add it to the list just in case.
+	 * Submodule ODBs added through add_submodule_odb_by_path() will be
+	 * lazily registered as alternates when needed (and except in an
+	 * unexpected code interaction, it won't be needed).
 	 */
-	add_to_alternates_memory(subrepo.objects->odb->path);
+	add_submodule_odb_by_path(subrepo->objects->odb->path);
 	obj_read_unlock();
 
 	memcpy(&subopt, opt, sizeof(subopt));
-	subopt.repo = &subrepo;
+	subopt.repo = subrepo;
 
 	if (oid) {
-		struct object *object;
+		enum object_type object_type;
 		struct tree_desc tree;
 		void *data;
 		unsigned long size;
 		struct strbuf base = STRBUF_INIT;
 
 		obj_read_lock();
-		object = parse_object_or_die(oid, NULL);
+		object_type = oid_object_info(subrepo, oid, NULL);
 		obj_read_unlock();
-		data = read_object_with_reference(&subrepo,
-						  &object->oid, tree_type,
+		data = read_object_with_reference(subrepo,
+						  oid, tree_type,
 						  &size, NULL);
 		if (!data)
-			die(_("unable to read tree (%s)"), oid_to_hex(&object->oid));
+			die(_("unable to read tree (%s)"), oid_to_hex(oid));
 
 		strbuf_addstr(&base, filename);
 		strbuf_addch(&base, '/');
 
 		init_tree_desc(&tree, data, size);
 		hit = grep_tree(&subopt, pathspec, &tree, &base, base.len,
-				object->type == OBJ_COMMIT);
+				object_type == OBJ_COMMIT);
 		strbuf_release(&base);
 		free(data);
 	} else {
 		hit = grep_cache(&subopt, pathspec, cached);
 	}
 
-	repo_clear(&subrepo);
 	return hit;
 }
 
@@ -504,6 +521,8 @@ static int grep_cache(struct grep_opt *opt,
 	if (repo_read_index(repo) < 0)
 		die(_("index file corrupt"));
 
+	/* TODO: audit for interaction with sparse-index. */
+	ensure_full_index(repo->index);
 	for (nr = 0; nr < repo->index->cache_nr; nr++) {
 		const struct cache_entry *ce = repo->index->cache[nr];
 
@@ -702,10 +721,9 @@ static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec,
 static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec,
 			  int exc_std, int use_index)
 {
-	struct dir_struct dir;
+	struct dir_struct dir = DIR_INIT;
 	int i, hit = 0;
 
-	dir_init(&dir);
 	if (!use_index)
 		dir.flags |= DIR_NO_GITLINKS;
 	if (exc_std)
@@ -1181,5 +1199,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		run_pager(&opt, prefix);
 	clear_pathspec(&pathspec);
 	free_grep_patterns(&opt);
+	free_repos();
 	return !hit;
 }