odb: get rid of the_repository when handling submodule sources

The "--recursive" flag for git-grep(1) allows users to grep for a string
across submodule boundaries. To make this work we add each submodule's
object sources to our own object database so that the objects can be
accessed directly.

The infrastructure for this depends on a global string list of submodule
paths. The caller is expected to call `add_submodule_odb_by_path()` for
each source and the object database will then eventually register all
submodule sources via `do_oid_object_info_extended()` in case it isn't
able to look up a specific object.

This reliance on global state is of course suboptimal with regards to
our libification efforts.

Refactor the logic so that the list of submodule sources is instead
tracked in the object database itself. This allows us to lose the
condition of `r == the_repository` before registering submodule sources
as we only ever add submodule sources to `the_repository` anyway. As
such, behaviour before and after this refactoring should always be the
same.

Rename the functions accordingly.

Signed-off-by: Patrick Steinhardt <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pks-t

builtin/grep.c

@@ -505,7 +505,8 @@ static int grep_submodule(struct grep_opt *opt,
 	 * lazily registered as alternates when needed (and except in an
 	 * unexpected code interaction, it won't be needed).
 	 */
-	add_submodule_odb_by_path(subrepo->objects->sources->path);
+	odb_add_submodule_source_by_path(the_repository->objects,
+					 subrepo->objects->sources->path);
 	obj_read_unlock();
 
 	memcpy(&subopt, opt, sizeof(subopt));

odb.c

@@ -24,6 +24,7 @@
 #include "strbuf.h"
 #include "strvec.h"
 #include "submodule.h"
+#include "trace2.h"
 #include "write-or-die.h"
 
 KHASH_INIT(odb_path_map, const char * /* key: odb_path */,
@@ -469,6 +470,12 @@ struct odb_source *odb_find_source(struct object_database *odb, const char *obj_
 	return source;
 }
 
+void odb_add_submodule_source_by_path(struct object_database *odb,
+				      const char *path)
+{
+	string_list_insert(&odb->submodule_source_paths, path);
+}
+
 static void fill_alternate_refs_command(struct child_process *cmd,
 					const char *repo_path)
 {
@@ -623,6 +630,23 @@ void disable_obj_read_lock(void)
 
 int fetch_if_missing = 1;
 
+static int register_all_submodule_alternates(struct object_database *odb)
+{
+	int ret = odb->submodule_source_paths.nr;
+
+	for (size_t i = 0; i < odb->submodule_source_paths.nr; i++)
+		odb_add_to_alternates_memory(odb,
+					     odb->submodule_source_paths.items[i].string);
+	if (ret) {
+		string_list_clear(&odb->submodule_source_paths, 0);
+		trace2_data_intmax("submodule", odb->repo,
+				   "register_all_submodule_alternates/registered", ret);
+		if (git_env_bool("GIT_TEST_FATAL_REGISTER_SUBMODULE_ODB", 0))
+			BUG("register_all_submodule_alternates() called");
+	}
+	return ret;
+}
+
 static int do_oid_object_info_extended(struct repository *r,
 				       const struct object_id *oid,
 				       struct object_info *oi, unsigned flags)
@@ -676,13 +700,12 @@ static int do_oid_object_info_extended(struct repository *r,
 		}
 
 		/*
-		 * If r is the_repository, this might be an attempt at
-		 * accessing a submodule object as if it were in the_repository
-		 * (having called add_submodule_odb() on that submodule's ODB).
-		 * If any such ODBs exist, register them and try again.
+		 * This might be an attempt at accessing a submodule object as
+		 * if it were in main object store (having called
+		 * `odb_add_submodule_source_by_path()` on that submodule's
+		 * ODB). If any such ODBs exist, register them and try again.
 		 */
-		if (r == the_repository &&
-		    register_all_submodule_odb_as_alternates())
+		if (register_all_submodule_alternates(r->objects))
 			/* We added some alternates; retry */
 			continue;
 
@@ -968,6 +991,7 @@ struct object_database *odb_new(struct repository *repo)
 	INIT_LIST_HEAD(&o->packed_git_mru);
 	hashmap_init(&o->pack_map, pack_map_entry_cmp, NULL, 0);
 	pthread_mutex_init(&o->replace_mutex, NULL);
+	string_list_init_dup(&o->submodule_source_paths);
 	return o;
 }
 
@@ -1017,4 +1041,5 @@ void odb_clear(struct object_database *o)
 	o->packed_git = NULL;
 
 	hashmap_clear(&o->pack_map);
+	string_list_clear(&o->submodule_source_paths, 0);
 }

odb.h

@@ -6,6 +6,7 @@
 #include "list.h"
 #include "oidset.h"
 #include "oidmap.h"
+#include "string-list.h"
 #include "thread-utils.h"
 
 struct oidmap;
@@ -165,6 +166,12 @@ struct object_database {
 	 * packs.
 	 */
 	unsigned packed_git_initialized : 1;
+
+	/*
+	 * Submodule source paths that will be added as additional sources to
+	 * allow lookup of submodule objects via the main object database.
+	 */
+	struct string_list submodule_source_paths;
 };
 
 struct object_database *odb_new(struct repository *repo);
@@ -190,6 +197,14 @@ void odb_restore_primary_source(struct object_database *odb,
 				struct odb_source *restore_source,
 				const char *old_path);
 
+/*
+ * Call odb_add_submodule_source_by_path() to add the submodule at the given
+ * path to a list. The object stores of all submodules in that list will be
+ * added as additional sources in the object store when looking up objects.
+ */
+void odb_add_submodule_source_by_path(struct object_database *odb,
+				      const char *path);
+
 /*
  * Iterate through all alternates of the database and execute the provided
  * callback function for each of them. Stop iterating once the callback

submodule-config.c

@@ -810,7 +810,8 @@ static void config_from_gitmodules(config_fn_t fn, struct repository *repo, void
 			   repo_get_oid(repo, GITMODULES_HEAD, &oid) >= 0) {
 			config_source.blob = oidstr = xstrdup(oid_to_hex(&oid));
 			if (repo != the_repository)
-				add_submodule_odb_by_path(repo->objects->sources->path);
+				odb_add_submodule_source_by_path(the_repository->objects,
+								 repo->objects->sources->path);
 		} else {
 			goto out;
 		}

submodule.c

@@ -31,7 +31,6 @@
 #include "commit-reach.h"
 #include "read-cache-ll.h"
 #include "setup.h"
-#include "trace2.h"
 
 static int config_update_recurse_submodules = RECURSE_SUBMODULES_OFF;
 static int initialized_fetch_ref_tips;
@@ -176,31 +175,6 @@ void stage_updated_gitmodules(struct index_state *istate)
 		die(_("staging updated .gitmodules failed"));
 }
 
-static struct string_list added_submodule_odb_paths = STRING_LIST_INIT_DUP;
-
-void add_submodule_odb_by_path(const char *path)
-{
-	string_list_insert(&added_submodule_odb_paths, path);
-}
-
-int register_all_submodule_odb_as_alternates(void)
-{
-	int i;
-	int ret = added_submodule_odb_paths.nr;
-
-	for (i = 0; i < added_submodule_odb_paths.nr; i++)
-		odb_add_to_alternates_memory(the_repository->objects,
-					     added_submodule_odb_paths.items[i].string);
-	if (ret) {
-		string_list_clear(&added_submodule_odb_paths, 0);
-		trace2_data_intmax("submodule", the_repository,
-				   "register_all_submodule_odb_as_alternates/registered", ret);
-		if (git_env_bool("GIT_TEST_FATAL_REGISTER_SUBMODULE_ODB", 0))
-			BUG("register_all_submodule_odb_as_alternates() called");
-	}
-	return ret;
-}
-
 void set_diffopt_flags_from_submodule_config(struct diff_options *diffopt,
 					     const char *path)
 {

submodule.h

@@ -104,15 +104,6 @@ int submodule_uses_gitfile(const char *path);
 #define SUBMODULE_REMOVAL_IGNORE_IGNORED_UNTRACKED (1<<2)
 int bad_to_remove_submodule(const char *path, unsigned flags);
 
-/*
- * Call add_submodule_odb_by_path() to add the submodule at the given
- * path to a list. When register_all_submodule_odb_as_alternates() is
- * called, the object stores of all submodules in that list will be
- * added as alternates in the_repository.
- */
-void add_submodule_odb_by_path(const char *path);
-int register_all_submodule_odb_as_alternates(void);
-
 /*
  * Checks if there are submodule changes in a..b. If a is the null OID,
  * checks b and all its ancestors instead.