Merge branch 'gc/recursive-fetch-with-unused-submodules'

When "git fetch --recurse-submodules" grabbed submodule commits
that would be needed to recursively check out newly fetched commits
in the superproject, it only paid attention to submodules that are
in the current checkout of the superproject.  We now do so for all
submodules that have been run "git submodule init" on.

* gc/recursive-fetch-with-unused-submodules:
  submodule: fix latent check_has_commit() bug
  fetch: fetch unpopulated, changed submodules
  submodule: move logic into fetch_task_create()
  submodule: extract get_fetch_task()
  submodule: store new submodule commits oid_array in a struct
  submodule: inline submodule_commits() into caller
  submodule: make static functions read submodules from commits
  t5526: create superproject commits with test helper
  t5526: stop asserting on stderr literally
  t5526: introduce test helper to assert on fetches

6 files changed, 761 insertions, 312 deletions

diff --git a/Documentation/fetch-options.txt b/Documentation/fetch-options.txt
index f903683189..6cdd9d43c5 100644
--- a/Documentation/fetch-options.txt
+++ b/Documentation/fetch-options.txt
@@ -186,15 +186,23 @@ endif::git-pull[]
 ifndef::git-pull[]
 --recurse-submodules[=yes|on-demand|no]::
 	This option controls if and under what conditions new commits of
-	populated submodules should be fetched too. It can be used as a
-	boolean option to completely disable recursion when set to 'no' or to
-	unconditionally recurse into all populated submodules when set to
-	'yes', which is the default when this option is used without any
-	value. Use 'on-demand' to only recurse into a populated submodule
-	when the superproject retrieves a commit that updates the submodule's
-	reference to a commit that isn't already in the local submodule
-	clone. By default, 'on-demand' is used, unless
-	`fetch.recurseSubmodules` is set (see linkgit:git-config[1]).
+	submodules should be fetched too. When recursing through submodules,
+	`git fetch` always attempts to fetch "changed" submodules, that is, a
+	submodule that has commits that are referenced by a newly fetched
+	superproject commit but are missing in the local submodule clone. A
+	changed submodule can be fetched as long as it is present locally e.g.
+	in `$GIT_DIR/modules/` (see linkgit:gitsubmodules[7]); if the upstream
+	adds a new submodule, that submodule cannot be fetched until it is
+	cloned e.g. by `git submodule update`.
++
+When set to 'on-demand', only changed submodules are fetched. When set
+to 'yes', all populated submodules are fetched and submodules that are
+both unpopulated and changed are fetched. When set to 'no', submodules
+are never fetched.
++
+When unspecified, this uses the value of `fetch.recurseSubmodules` if it
+is set (see linkgit:git-config[1]), defaulting to 'on-demand' if unset.
+When this option is used without any value, it defaults to 'yes'.
 endif::git-pull[]
 
 -j::
diff --git a/Documentation/git-fetch.txt b/Documentation/git-fetch.txt
index 550c16ca61..e9d364669a 100644
--- a/Documentation/git-fetch.txt
+++ b/Documentation/git-fetch.txt
@@ -287,12 +287,10 @@ include::transfer-data-leaks.txt[]
 
 BUGS
 ----
-Using --recurse-submodules can only fetch new commits in already checked
-out submodules right now. When e.g. upstream added a new submodule in the
-just fetched commits of the superproject the submodule itself cannot be
-fetched, making it impossible to check out that submodule later without
-having to do a fetch again. This is expected to be fixed in a future Git
-version.
+Using --recurse-submodules can only fetch new commits in submodules that are
+present locally e.g. in `$GIT_DIR/modules/`. If the upstream adds a new
+submodule, that submodule cannot be fetched until it is cloned e.g. by `git
+submodule update`. This is expected to be fixed in a future Git version.
 
 SEE ALSO
 --------
diff --git a/builtin/fetch.c b/builtin/fetch.c
index 4d12c2fd4d..9b4018f62c 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -2258,13 +2258,13 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 			max_children = fetch_parallel_config;
 
 		add_options_to_argv(&options);
-		result = fetch_populated_submodules(the_repository,
-						    &options,
-						    submodule_prefix,
-						    recurse_submodules,
-						    recurse_submodules_default,
-						    verbosity < 0,
-						    max_children);
+		result = fetch_submodules(the_repository,
+					  &options,
+					  submodule_prefix,
+					  recurse_submodules,
+					  recurse_submodules_default,
+					  verbosity < 0,
+					  max_children);
 		strvec_clear(&options);
 	}
 
diff --git a/submodule.c b/submodule.c
index 5ace18a7d9..93c78a4dc3 100644
--- a/submodule.c
+++ b/submodule.c
@@ -167,26 +167,6 @@ void stage_updated_gitmodules(struct index_state *istate)
 
 static struct string_list added_submodule_odb_paths = STRING_LIST_INIT_NODUP;
 
-/* TODO: remove this function, use repo_submodule_init instead. */
-int add_submodule_odb(const char *path)
-{
-	struct strbuf objects_directory = STRBUF_INIT;
-	int ret = 0;
-
-	ret = strbuf_git_path_submodule(&objects_directory, path, "objects/");
-	if (ret)
-		goto done;
-	if (!is_directory(objects_directory.buf)) {
-		ret = -1;
-		goto done;
-	}
-	string_list_insert(&added_submodule_odb_paths,
-			   strbuf_detach(&objects_directory, NULL));
-done:
-	strbuf_release(&objects_directory);
-	return ret;
-}
-
 void add_submodule_odb_by_path(const char *path)
 {
 	string_list_insert(&added_submodule_odb_paths, xstrdup(path));
@@ -782,19 +762,6 @@ const struct submodule *submodule_from_ce(const struct cache_entry *ce)
 	return submodule_from_path(the_repository, null_oid(), ce->name);
 }
 
-static struct oid_array *submodule_commits(struct string_list *submodules,
-					   const char *name)
-{
-	struct string_list_item *item;
-
-	item = string_list_insert(submodules, name);
-	if (item->util)
-		return (struct oid_array *) item->util;
-
-	/* NEEDSWORK: should we have oid_array_init()? */
-	item->util = xcalloc(1, sizeof(struct oid_array));
-	return (struct oid_array *) item->util;
-}
 
 struct collect_changed_submodules_cb_data {
 	struct repository *repo;
@@ -819,6 +786,52 @@ static const char *default_name_or_path(const char *path_or_name)
 	return path_or_name;
 }
 
+/*
+ * Holds relevant information for a changed submodule. Used as the .util
+ * member of the changed submodule name string_list_item.
+ *
+ * (super_oid, path) allows the submodule config to be read from _some_
+ * .gitmodules file. We store this information the first time we find a
+ * superproject commit that points to the submodule, but this is
+ * arbitrary - we can choose any (super_oid, path) that matches the
+ * submodule's name.
+ *
+ * NEEDSWORK: Storing an arbitrary commit is undesirable because we can't
+ * guarantee that we're reading the commit that the user would expect. A better
+ * scheme would be to just fetch a submodule by its name. This requires two
+ * steps:
+ * - Create a function that behaves like repo_submodule_init(), but accepts a
+ *   submodule name instead of treeish_name and path. This should be easy
+ *   because repo_submodule_init() internally uses the submodule's name.
+ *
+ * - Replace most instances of 'struct submodule' (which is the .gitmodules
+ *   config) with just the submodule name. This is OK because we expect
+ *   submodule settings to be stored in .git/config (via "git submodule init"),
+ *   not .gitmodules. This also lets us delete get_non_gitmodules_submodule(),
+ *   which constructs a bogus 'struct submodule' for the sake of giving a
+ *   placeholder name to a gitlink.
+ */
+struct changed_submodule_data {
+	/*
+	 * The first superproject commit in the rev walk that points to
+	 * the submodule.
+	 */
+	const struct object_id *super_oid;
+	/*
+	 * Path to the submodule in the superproject commit referenced
+	 * by 'super_oid'.
+	 */
+	char *path;
+	/* The submodule commits that have changed in the rev walk. */
+	struct oid_array new_commits;
+};
+
+static void changed_submodule_data_clear(struct changed_submodule_data *cs_data)
+{
+	oid_array_clear(&cs_data->new_commits);
+	free(cs_data->path);
+}
+
 static void collect_changed_submodules_cb(struct diff_queue_struct *q,
 					  struct diff_options *options,
 					  void *data)
@@ -830,9 +843,10 @@ static void collect_changed_submodules_cb(struct diff_queue_struct *q,
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
-		struct oid_array *commits;
 		const struct submodule *submodule;
 		const char *name;
+		struct string_list_item *item;
+		struct changed_submodule_data *cs_data;
 
 		if (!S_ISGITLINK(p->two->mode))
 			continue;
@@ -859,8 +873,16 @@ static void collect_changed_submodules_cb(struct diff_queue_struct *q,
 		if (!name)
 			continue;
 
-		commits = submodule_commits(changed, name);
-		oid_array_append(commits, &p->two->oid);
+		item = string_list_insert(changed, name);
+		if (item->util)
+			cs_data = item->util;
+		else {
+			item->util = xcalloc(1, sizeof(struct changed_submodule_data));
+			cs_data = item->util;
+			cs_data->super_oid = commit_oid;
+			cs_data->path = xstrdup(p->two->path);
+		}
+		oid_array_append(&cs_data->new_commits, &p->two->oid);
 	}
 }
 
@@ -907,11 +929,12 @@ static void collect_changed_submodules(struct repository *r,
 	reset_revision_walk();
 }
 
-static void free_submodules_oids(struct string_list *submodules)
+static void free_submodules_data(struct string_list *submodules)
 {
 	struct string_list_item *item;
 	for_each_string_list_item(item, submodules)
-		oid_array_clear((struct oid_array *) item->util);
+		changed_submodule_data_clear(item->util);
+
 	string_list_clear(submodules, 1);
 }
 
@@ -932,6 +955,7 @@ struct has_commit_data {
 	struct repository *repo;
 	int result;
 	const char *path;
+	const struct object_id *super_oid;
 };
 
 static int check_has_commit(const struct object_id *oid, void *data)
@@ -940,9 +964,10 @@ static int check_has_commit(const struct object_id *oid, void *data)
 	struct repository subrepo;
 	enum object_type type;
 
-	if (repo_submodule_init(&subrepo, cb->repo, cb->path, null_oid())) {
+	if (repo_submodule_init(&subrepo, cb->repo, cb->path, cb->super_oid)) {
 		cb->result = 0;
-		goto cleanup;
+		/* subrepo failed to init, so don't clean it up. */
+		return 0;
 	}
 
 	type = oid_object_info(&subrepo, oid, NULL);
@@ -968,21 +993,15 @@ cleanup:
 
 static int submodule_has_commits(struct repository *r,
 				 const char *path,
+				 const struct object_id *super_oid,
 				 struct oid_array *commits)
 {
-	struct has_commit_data has_commit = { r, 1, path };
-
-	/*
-	 * Perform a cheap, but incorrect check for the existence of 'commits'.
-	 * This is done by adding the submodule's object store to the in-core
-	 * object store, and then querying for each commit's existence.  If we
-	 * do not have the commit object anywhere, there is no chance we have
-	 * it in the object store of the correct submodule and have it
-	 * reachable from a ref, so we can fail early without spawning rev-list
-	 * which is expensive.
-	 */
-	if (add_submodule_odb(path))
-		return 0;
+	struct has_commit_data has_commit = {
+		.repo = r,
+		.result = 1,
+		.path = path,
+		.super_oid = super_oid
+	};
 
 	oid_array_for_each_unique(commits, check_has_commit, &has_commit);
 
@@ -1017,7 +1036,7 @@ static int submodule_needs_pushing(struct repository *r,
 				   const char *path,
 				   struct oid_array *commits)
 {
-	if (!submodule_has_commits(r, path, commits))
+	if (!submodule_has_commits(r, path, null_oid(), commits))
 		/*
 		 * NOTE: We do consider it safe to return "no" here. The
 		 * correct answer would be "We do not know" instead of
@@ -1077,7 +1096,7 @@ int find_unpushed_submodules(struct repository *r,
 	collect_changed_submodules(r, &submodules, &argv);
 
 	for_each_string_list_item(name, &submodules) {
-		struct oid_array *commits = name->util;
+		struct changed_submodule_data *cs_data = name->util;
 		const struct submodule *submodule;
 		const char *path = NULL;
 
@@ -1090,11 +1109,11 @@ int find_unpushed_submodules(struct repository *r,
 		if (!path)
 			continue;
 
-		if (submodule_needs_pushing(r, path, commits))
+		if (submodule_needs_pushing(r, path, &cs_data->new_commits))
 			string_list_insert(needs_pushing, path);
 	}
 
-	free_submodules_oids(&submodules);
+	free_submodules_data(&submodules);
 	strvec_clear(&argv);
 
 	return needs_pushing->nr;
@@ -1240,14 +1259,36 @@ void check_for_new_submodule_commits(struct object_id *oid)
 	oid_array_append(&ref_tips_after_fetch, oid);
 }
 
+/*
+ * Returns 1 if there is at least one submodule gitdir in
+ * $GIT_DIR/modules and 0 otherwise. This follows
+ * submodule_name_to_gitdir(), which looks for submodules in
+ * $GIT_DIR/modules, not $GIT_COMMON_DIR.
+ *
+ * A submodule can be moved to $GIT_DIR/modules manually by running "git
+ * submodule absorbgitdirs", or it may be initialized there by "git
+ * submodule update".
+ */
+static int repo_has_absorbed_submodules(struct repository *r)
+{
+	int ret;
+	struct strbuf buf = STRBUF_INIT;
+
+	strbuf_repo_git_path(&buf, r, "modules/");
+	ret = file_exists(buf.buf) && !is_empty_dir(buf.buf);
+	strbuf_release(&buf);
+	return ret;
+}
+
 static void calculate_changed_submodule_paths(struct repository *r,
 		struct string_list *changed_submodule_names)
 {
 	struct strvec argv = STRVEC_INIT;
 	struct string_list_item *name;
 
-	/* No need to check if there are no submodules configured */
-	if (!submodule_from_path(r, NULL, NULL))
+	/* No need to check if no submodules would be fetched */
+	if (!submodule_from_path(r, NULL, NULL) &&
+	    !repo_has_absorbed_submodules(r))
 		return;
 
 	strvec_push(&argv, "--"); /* argv[0] program name */
@@ -1264,7 +1305,7 @@ static void calculate_changed_submodule_paths(struct repository *r,
 	collect_changed_submodules(r, changed_submodule_names, &argv);
 
 	for_each_string_list_item(name, changed_submodule_names) {
-		struct oid_array *commits = name->util;
+		struct changed_submodule_data *cs_data = name->util;
 		const struct submodule *submodule;
 		const char *path = NULL;
 
@@ -1277,8 +1318,8 @@ static void calculate_changed_submodule_paths(struct repository *r,
 		if (!path)
 			continue;
 
-		if (submodule_has_commits(r, path, commits)) {
-			oid_array_clear(commits);
+		if (submodule_has_commits(r, path, null_oid(), &cs_data->new_commits)) {
+			changed_submodule_data_clear(cs_data);
 			*name->string = '\0';
 		}
 	}
@@ -1315,12 +1356,21 @@ int submodule_touches_in_range(struct repository *r,
 
 	strvec_clear(&args);
 
-	free_submodules_oids(&subs);
+	free_submodules_data(&subs);
 	return ret;
 }
 
 struct submodule_parallel_fetch {
-	int count;
+	/*
+	 * The index of the last index entry processed by
+	 * get_fetch_task_from_index().
+	 */
+	int index_count;
+	/*
+	 * The index of the last string_list entry processed by
+	 * get_fetch_task_from_changed().
+	 */
+	int changed_count;
 	struct strvec args;
 	struct repository *r;
 	const char *prefix;
@@ -1329,7 +1379,16 @@ struct submodule_parallel_fetch {
 	int quiet;
 	int result;
 
+	/*
+	 * Names of submodules that have new commits. Generated by
+	 * walking the newly fetched superproject commits.
+	 */
 	struct string_list changed_submodule_names;
+	/*
+	 * Names of submodules that have already been processed. Lets us
+	 * avoid fetching the same submodule more than once.
+	 */
+	struct string_list seen_submodule_names;
 
 	/* Pending fetches by OIDs */
 	struct fetch_task **oid_fetch_tasks;
@@ -1340,6 +1399,7 @@ struct submodule_parallel_fetch {
 #define SPF_INIT { \
 	.args = STRVEC_INIT, \
 	.changed_submodule_names = STRING_LIST_INIT_DUP, \
+	.seen_submodule_names = STRING_LIST_INIT_DUP, \
 	.submodules_with_errors = STRBUF_INIT, \
 }
 
@@ -1376,6 +1436,8 @@ struct fetch_task {
 	struct repository *repo;
 	const struct submodule *sub;
 	unsigned free_sub : 1; /* Do we need to free the submodule? */
+	const char *default_argv; /* The default fetch mode. */
+	struct strvec git_args; /* Args for the child git process. */
 
 	struct oid_array *commits; /* Ensure these commits are fetched */
 };
@@ -1401,31 +1463,6 @@ static const struct submodule *get_non_gitmodules_submodule(const char *path)
 	return (const struct submodule *) ret;
 }
 
-static struct fetch_task *fetch_task_create(struct repository *r,
-					    const char *path)
-{
-	struct fetch_task *task = xmalloc(sizeof(*task));
-	memset(task, 0, sizeof(*task));
-
-	task->sub = submodule_from_path(r, null_oid(), path);
-	if (!task->sub) {
-		/*
-		 * No entry in .gitmodules? Technically not a submodule,
-		 * but historically we supported repositories that happen to be
-		 * in-place where a gitlink is. Keep supporting them.
-		 */
-		task->sub = get_non_gitmodules_submodule(path);
-		if (!task->sub) {
-			free(task);
-			return NULL;
-		}
-
-		task->free_sub = 1;
-	}
-
-	return task;
-}
-
 static void fetch_task_release(struct fetch_task *p)
 {
 	if (p->free_sub)
@@ -1436,14 +1473,17 @@ static void fetch_task_release(struct fetch_task *p)
 	if (p->repo)
 		repo_clear(p->repo);
 	FREE_AND_NULL(p->repo);
+
+	strvec_clear(&p->git_args);
 }
 
 static struct repository *get_submodule_repo_for(struct repository *r,
-						 const char *path)
+						 const char *path,
+						 const struct object_id *treeish_name)
 {
 	struct repository *ret = xmalloc(sizeof(*ret));
 
-	if (repo_submodule_init(ret, r, path, null_oid())) {
+	if (repo_submodule_init(ret, r, path, treeish_name)) {
 		free(ret);
 		return NULL;
 	}
@@ -1451,67 +1491,83 @@ static struct repository *get_submodule_repo_for(struct repository *r,
 	return ret;
 }
 
-static int get_next_submodule(struct child_process *cp,
-			      struct strbuf *err, void *data, void **task_cb)
+static struct fetch_task *fetch_task_create(struct submodule_parallel_fetch *spf,
+					    const char *path,
+					    const struct object_id *treeish_name)
 {
-	struct submodule_parallel_fetch *spf = data;
+	struct fetch_task *task = xmalloc(sizeof(*task));
+	memset(task, 0, sizeof(*task));
+
+	task->sub = submodule_from_path(spf->r, treeish_name, path);
 
-	for (; spf->count < spf->r->index->cache_nr; spf->count++) {
-		const struct cache_entry *ce = spf->r->index->cache[spf->count];
-		const char *default_argv;
+	if (!task->sub) {
+		/*
+		 * No entry in .gitmodules? Technically not a submodule,
+		 * but historically we supported repositories that happen to be
+		 * in-place where a gitlink is. Keep supporting them.
+		 */
+		task->sub = get_non_gitmodules_submodule(path);
+		if (!task->sub)
+			goto cleanup;
+
+		task->free_sub = 1;
+	}
+
+	if (string_list_lookup(&spf->seen_submodule_names, task->sub->name))
+		goto cleanup;
+
+	switch (get_fetch_recurse_config(task->sub, spf))
+	{
+	default:
+	case RECURSE_SUBMODULES_DEFAULT:
+	case RECURSE_SUBMODULES_ON_DEMAND:
+		if (!task->sub ||
+			!string_list_lookup(
+				&spf->changed_submodule_names,
+				task->sub->name))
+			goto cleanup;
+		task->default_argv = "on-demand";
+		break;
+	case RECURSE_SUBMODULES_ON:
+		task->default_argv = "yes";
+		break;
+	case RECURSE_SUBMODULES_OFF:
+		goto cleanup;
+	}
+
+	task->repo = get_submodule_repo_for(spf->r, path, treeish_name);
+
+	return task;
+
+ cleanup:
+	fetch_task_release(task);
+	free(task);
+	return NULL;
+}
+
+static struct fetch_task *
+get_fetch_task_from_index(struct submodule_parallel_fetch *spf,
+			  struct strbuf *err)
+{
+	for (; spf->index_count < spf->r->index->cache_nr; spf->index_count++) {
+		const struct cache_entry *ce =
+			spf->r->index->cache[spf->index_count];
 		struct fetch_task *task;
 
 		if (!S_ISGITLINK(ce->ce_mode))
 			continue;
 
-		task = fetch_task_create(spf->r, ce->name);
+		task = fetch_task_create(spf, ce->name, null_oid());
 		if (!task)
 			continue;
 
-		switch (get_fetch_recurse_config(task->sub, spf))
-		{
-		default:
-		case RECURSE_SUBMODULES_DEFAULT:
-		case RECURSE_SUBMODULES_ON_DEMAND:
-			if (!task->sub ||
-			    !string_list_lookup(
-					&spf->changed_submodule_names,
-					task->sub->name))
-				continue;
-			default_argv = "on-demand";
-			break;
-		case RECURSE_SUBMODULES_ON:
-			default_argv = "yes";
-			break;
-		case RECURSE_SUBMODULES_OFF:
-			continue;
-		}
-
-		task->repo = get_submodule_repo_for(spf->r, task->sub->path);
 		if (task->repo) {
-			struct strbuf submodule_prefix = STRBUF_INIT;
-			child_process_init(cp);
-			cp->dir = task->repo->gitdir;
-			prepare_submodule_repo_env_in_gitdir(&cp->env_array);
-			cp->git_cmd = 1;
 			if (!spf->quiet)
 				strbuf_addf(err, _("Fetching submodule %s%s\n"),
 					    spf->prefix, ce->name);
-			strvec_init(&cp->args);
-			strvec_pushv(&cp->args, spf->args.v);
-			strvec_push(&cp->args, default_argv);
-			strvec_push(&cp->args, "--submodule-prefix");
 
-			strbuf_addf(&submodule_prefix, "%s%s/",
-						       spf->prefix,
-						       task->sub->path);
-			strvec_push(&cp->args, submodule_prefix.buf);
-
-			spf->count++;
-			*task_cb = task;
-
-			strbuf_release(&submodule_prefix);
-			return 1;
+			spf->index_count++;
+			return task;
 		} else {
 			struct strbuf empty_submodule_path = STRBUF_INIT;
 
@@ -1535,6 +1591,111 @@ static int get_next_submodule(struct child_process *cp,
 			strbuf_release(&empty_submodule_path);
 		}
 	}
+	return NULL;
+}
+
+static struct fetch_task *
+get_fetch_task_from_changed(struct submodule_parallel_fetch *spf,
+			    struct strbuf *err)
+{
+	for (; spf->changed_count < spf->changed_submodule_names.nr;
+	     spf->changed_count++) {
+		struct string_list_item item =
+			spf->changed_submodule_names.items[spf->changed_count];
+		struct changed_submodule_data *cs_data = item.util;
+		struct fetch_task *task;
+
+		if (!is_tree_submodule_active(spf->r, cs_data->super_oid,cs_data->path))
+			continue;
+
+		task = fetch_task_create(spf, cs_data->path,
+					 cs_data->super_oid);
+		if (!task)
+			continue;
+
+		if (!task->repo) {
+			strbuf_addf(err, _("Could not access submodule '%s' at commit %s\n"),
+				    cs_data->path,
+				    find_unique_abbrev(cs_data->super_oid, DEFAULT_ABBREV));
+
+			fetch_task_release(task);
+			free(task);
+			continue;
+		}
+
+		if (!spf->quiet)
+			strbuf_addf(err,
+				    _("Fetching submodule %s%s at commit %s\n"),
+				    spf->prefix, task->sub->path,
+				    find_unique_abbrev(cs_data->super_oid,
+						       DEFAULT_ABBREV));
+
+		spf->changed_count++;
+		/*
+		 * NEEDSWORK: Submodules set/unset a value for
+		 * core.worktree when they are populated/unpopulated by
+		 * "git checkout" (and similar commands, see
+		 * submodule_move_head() and
+		 * connect_work_tree_and_git_dir()), but if the
+		 * submodule is unpopulated in another way (e.g. "git
+		 * rm", "rm -r"), core.worktree will still be set even
+		 * though the directory doesn't exist, and the child
+		 * process will crash while trying to chdir into the
+		 * nonexistent directory.
+		 *
+		 * In this case, we know that the submodule has no
+		 * working tree, so we can work around this by
+		 * setting "--work-tree=." (--bare does not work because
+		 * worktree settings take precedence over bare-ness).
+		 * However, this is not necessarily true in other cases,
+		 * so a generalized solution is still necessary.
+		 *
+		 * Possible solutions:
+		 * - teach "git [add|rm]" to unset core.worktree and
+		 *   discourage users from removing submodules without
+		 *   using a Git command.
+		 * - teach submodule child processes to ignore stale
+		 *   core.worktree values.
+		 */
+		strvec_push(&task->git_args, "--work-tree=.");
+		return task;
+	}
+	return NULL;
+}
+
+static int get_next_submodule(struct child_process *cp, struct strbuf *err,
+			      void *data, void **task_cb)
+{
+	struct submodule_parallel_fetch *spf = data;
+	struct fetch_task *task =
+		get_fetch_task_from_index(spf, err);
+	if (!task)
+		task = get_fetch_task_from_changed(spf, err);
+
+	if (task) {
+		struct strbuf submodule_prefix = STRBUF_INIT;
+
+		child_process_init(cp);
+		cp->dir = task->repo->gitdir;
+		prepare_submodule_repo_env_in_gitdir(&cp->env_array);
+		cp->git_cmd = 1;
+		strvec_init(&cp->args);
+		if (task->git_args.nr)
+			strvec_pushv(&cp->args, task->git_args.v);
+		strvec_pushv(&cp->args, spf->args.v);
+		strvec_push(&cp->args, task->default_argv);
+		strvec_push(&cp->args, "--submodule-prefix");
+
+		strbuf_addf(&submodule_prefix, "%s%s/",
+						spf->prefix,
+						task->sub->path);
+		strvec_push(&cp->args, submodule_prefix.buf);
+		*task_cb = task;
+
+		strbuf_release(&submodule_prefix);
+		string_list_insert(&spf->seen_submodule_names, task->sub->name);
+		return 1;
+	}
 
 	if (spf->oid_fetch_tasks_nr) {
 		struct fetch_task *task =
@@ -1597,7 +1758,7 @@ static int fetch_finish(int retvalue, struct strbuf *err,
 	struct fetch_task *task = task_cb;
 
 	struct string_list_item *it;
-	struct oid_array *commits;
+	struct changed_submodule_data *cs_data;
 
 	if (!task || !task->sub)
 		BUG("callback cookie bogus");
@@ -1625,14 +1786,14 @@ static int fetch_finish(int retvalue, struct strbuf *err,
 		/* Could be an unchanged submodule, not contained in the list */
 		goto out;
 
-	commits = it->util;
-	oid_array_filter(commits,
+	cs_data = it->util;
+	oid_array_filter(&cs_data->new_commits,
 			 commit_missing_in_sub,
 			 task->repo);
 
 	/* Are there commits we want, but do not exist? */
-	if (commits->nr) {
-		task->commits = commits;
+	if (cs_data->new_commits.nr) {
+		task->commits = &cs_data->new_commits;
 		ALLOC_GROW(spf->oid_fetch_tasks,
 			   spf->oid_fetch_tasks_nr + 1,
 			   spf->oid_fetch_tasks_alloc);
@@ -1647,11 +1808,11 @@ out:
 	return 0;
 }
 
-int fetch_populated_submodules(struct repository *r,
-			       const struct strvec *options,
-			       const char *prefix, int command_line_option,
-			       int default_option,
-			       int quiet, int max_parallel_jobs)
+int fetch_submodules(struct repository *r,
+		     const struct strvec *options,
+		     const char *prefix, int command_line_option,
+		     int default_option,
+		     int quiet, int max_parallel_jobs)
 {
 	int i;
 	struct submodule_parallel_fetch spf = SPF_INIT;
@@ -1690,7 +1851,7 @@ int fetch_populated_submodules(struct repository *r,
 
 	strvec_clear(&spf.args);
 out:
-	free_submodules_oids(&spf.changed_submodule_names);
+	free_submodules_data(&spf.changed_submodule_names);
 	return spf.result;
 }
 
diff --git a/submodule.h b/submodule.h
index 784ceffc0e..40c1445237 100644
--- a/submodule.h
+++ b/submodule.h
@@ -88,12 +88,12 @@ int should_update_submodules(void);
  */
 const struct submodule *submodule_from_ce(const struct cache_entry *ce);
 void check_for_new_submodule_commits(struct object_id *oid);
-int fetch_populated_submodules(struct repository *r,
-			       const struct strvec *options,
-			       const char *prefix,
-			       int command_line_option,
-			       int default_option,
-			       int quiet, int max_parallel_jobs);
+int fetch_submodules(struct repository *r,
+		     const struct strvec *options,
+		     const char *prefix,
+		     int command_line_option,
+		     int default_option,
+		     int quiet, int max_parallel_jobs);
 unsigned is_submodule_modified(const char *path, int ignore_untracked);
 int submodule_uses_gitfile(const char *path);
 
@@ -103,12 +103,11 @@ int submodule_uses_gitfile(const char *path);
 int bad_to_remove_submodule(const char *path, unsigned flags);
 
 /*
- * Call add_submodule_odb() 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.
+ * 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.
  */
-int add_submodule_odb(const char *path);
 void add_submodule_odb_by_path(const char *path);
 int register_all_submodule_odb_as_alternates(void);
 
diff --git a/t/t5526-fetch-submodules.sh b/t/t5526-fetch-submodules.sh
index 840c89cc8b..43dada8544 100755
--- a/t/t5526-fetch-submodules.sh
+++ b/t/t5526-fetch-submodules.sh
@@ -10,33 +10,122 @@ export GIT_TEST_FATAL_REGISTER_SUBMODULE_ODB
 
 pwd=$(pwd)
 
-add_upstream_commit() {
+write_expected_sub () {
+	NEW_HEAD=$1 &&
+	SUPER_HEAD=$2 &&
+	cat >"$pwd/expect.err.sub" <<-EOF
+	Fetching submodule submodule${SUPER_HEAD:+ at commit $SUPER_HEAD}
+	From $pwd/submodule
+	   OLD_HEAD..$NEW_HEAD  sub        -> origin/sub
+	EOF
+}
+
+write_expected_sub2 () {
+	NEW_HEAD=$1 &&
+	SUPER_HEAD=$2 &&
+	cat >"$pwd/expect.err.sub2" <<-EOF
+	Fetching submodule submodule2${SUPER_HEAD:+ at commit $SUPER_HEAD}
+	From $pwd/submodule2
+	   OLD_HEAD..$NEW_HEAD  sub2       -> origin/sub2
+	EOF
+}
+
+write_expected_deep () {
+	NEW_HEAD=$1 &&
+	SUB_HEAD=$2 &&
+	cat >"$pwd/expect.err.deep" <<-EOF
+	Fetching submodule submodule/subdir/deepsubmodule${SUB_HEAD:+ at commit $SUB_HEAD}
+	From $pwd/deepsubmodule
+	   OLD_HEAD..$NEW_HEAD  deep       -> origin/deep
+	EOF
+}
+
+write_expected_super () {
+	NEW_HEAD=$1 &&
+	cat >"$pwd/expect.err.super" <<-EOF
+	From $pwd/.
+	   OLD_HEAD..$NEW_HEAD  super      -> origin/super
+	EOF
+}
+
+# For each submodule in the test setup, this creates a commit and writes
+# a file that contains the expected err if that new commit were fetched.
+# These output files get concatenated in the right order by
+# verify_fetch_result().
+add_submodule_commits () {
 	(
 		cd submodule &&
-		head1=$(git rev-parse --short HEAD) &&
 		echo new >> subfile &&
 		test_tick &&
 		git add subfile &&
 		git commit -m new subfile &&
-		head2=$(git rev-parse --short HEAD) &&
-		echo "Fetching submodule submodule" > ../expect.err &&
-		echo "From $pwd/submodule" >> ../expect.err &&
-		echo "   $head1..$head2  sub        -> origin/sub" >> ../expect.err
+		new_head=$(git rev-parse --short HEAD) &&
+		write_expected_sub $new_head
 	) &&
 	(
 		cd deepsubmodule &&
-		head1=$(git rev-parse --short HEAD) &&
 		echo new >> deepsubfile &&
 		test_tick &&
 		git add deepsubfile &&
 		git commit -m new deepsubfile &&
-		head2=$(git rev-parse --short HEAD) &&
-		echo "Fetching submodule submodule/subdir/deepsubmodule" >> ../expect.err
-		echo "From $pwd/deepsubmodule" >> ../expect.err &&
-		echo "   $head1..$head2  deep       -> origin/deep" >> ../expect.err
+		new_head=$(git rev-parse --short HEAD) &&
+		write_expected_deep $new_head
 	)
 }
 
+# For each superproject in the test setup, update its submodule, add the
+# submodule and create a new commit with the submodule change.
+#
+# This requires add_submodule_commits() to be called first, otherwise
+# the submodules will not have changed and cannot be "git add"-ed.
+add_superproject_commits () {
+	(
+		cd submodule &&
+		(
+			cd subdir/deepsubmodule &&
+			git fetch &&
+			git checkout -q FETCH_HEAD
+		) &&
+		git add subdir/deepsubmodule &&
+		git commit -m "new deep submodule"
+	) &&
+	git add submodule &&
+	git commit -m "new submodule" &&
+	super_head=$(git rev-parse --short HEAD) &&
+	sub_head=$(git -C submodule rev-parse --short HEAD) &&
+	write_expected_super $super_head &&
+	write_expected_sub $sub_head
+}
+
+# Verifies that the expected repositories were fetched. This is done by
+# concatenating the files expect.err.[super|sub|deep] in the correct
+# order and comparing it to the actual stderr.
+#
+# If a repo should not be fetched in the test, its corresponding
+# expect.err file should be rm-ed.
+verify_fetch_result () {
+	ACTUAL_ERR=$1 &&
+	rm -f expect.err.combined &&
+	if test -f expect.err.super
+	then
+		cat expect.err.super >>expect.err.combined
+	fi &&
+	if test -f expect.err.sub
+	then
+		cat expect.err.sub >>expect.err.combined
+	fi &&
+	if test -f expect.err.deep
+	then
+		cat expect.err.deep >>expect.err.combined
+	fi &&
+	if test -f expect.err.sub2
+	then
+		cat expect.err.sub2 >>expect.err.combined
+	fi &&
+	sed -e 's/[0-9a-f][0-9a-f]*\.\./OLD_HEAD\.\./' "$ACTUAL_ERR" >actual.err.cmp &&
+	test_cmp expect.err.combined actual.err.cmp
+}
+
 test_expect_success setup '
 	mkdir deepsubmodule &&
 	(
@@ -68,38 +157,38 @@ test_expect_success setup '
 '
 
 test_expect_success "fetch --recurse-submodules recurses into submodules" '
-	add_upstream_commit &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		git fetch --recurse-submodules >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "submodule.recurse option triggers recursive fetch" '
-	add_upstream_commit &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		git -c submodule.recurse fetch >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "fetch --recurse-submodules -j2 has the same output behaviour" '
-	add_upstream_commit &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		GIT_TRACE="$TRASH_DIRECTORY/trace.out" git fetch --recurse-submodules -j2 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err &&
+	verify_fetch_result actual.err &&
 	grep "2 tasks" trace.out
 '
 
 test_expect_success "fetch alone only fetches superproject" '
-	add_upstream_commit &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		git fetch >../actual.out 2>../actual.err
@@ -124,11 +213,11 @@ test_expect_success "using fetchRecurseSubmodules=true in .gitmodules recurses i
 		git fetch >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "--no-recurse-submodules overrides .gitmodules config" '
-	add_upstream_commit &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		git fetch --no-recurse-submodules >../actual.out 2>../actual.err
@@ -155,7 +244,7 @@ test_expect_success "--recurse-submodules overrides fetchRecurseSubmodules setti
 		git config --unset submodule.submodule.fetchRecurseSubmodules
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "--quiet propagates to submodules" '
@@ -177,13 +266,13 @@ test_expect_success "--quiet propagates to parallel submodules" '
 '
 
 test_expect_success "--dry-run propagates to submodules" '
-	add_upstream_commit &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		git fetch --recurse-submodules --dry-run >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "Without --dry-run propagates to submodules" '
@@ -192,22 +281,22 @@ test_expect_success "Without --dry-run propagates to submodules" '
 		git fetch --recurse-submodules >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "recurseSubmodules=true propagates into submodules" '
-	add_upstream_commit &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		git config fetch.recurseSubmodules true &&
 		git fetch >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "--recurse-submodules overrides config in submodule" '
-	add_upstream_commit &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		(
@@ -217,11 +306,11 @@ test_expect_success "--recurse-submodules overrides config in submodule" '
 		git fetch --recurse-submodules >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "--no-recurse-submodules overrides config setting" '
-	add_upstream_commit &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		git config fetch.recurseSubmodules true &&
@@ -246,36 +335,34 @@ test_expect_success "Recursion doesn't happen when no new commits are fetched in
 '
 
 test_expect_success "Recursion stops when no new submodule commits are fetched" '
-	head1=$(git rev-parse --short HEAD) &&
 	git add submodule &&
 	git commit -m "new submodule" &&
-	head2=$(git rev-parse --short HEAD) &&
-	echo "From $pwd/." > expect.err.sub &&
-	echo "   $head1..$head2  super      -> origin/super" >>expect.err.sub &&
-	head -3 expect.err >> expect.err.sub &&
+	new_head=$(git rev-parse --short HEAD) &&
+	write_expected_super $new_head &&
+	rm expect.err.deep &&
 	(
 		cd downstream &&
 		git fetch >../actual.out 2>../actual.err
 	) &&
-	test_cmp expect.err.sub actual.err &&
+	verify_fetch_result actual.err &&
 	test_must_be_empty actual.out
 '
 
 test_expect_success "Recursion doesn't happen when new superproject commits don't change any submodules" '
-	add_upstream_commit &&
-	head1=$(git rev-parse --short HEAD) &&
+	add_submodule_commits &&
 	echo a > file &&
 	git add file &&
 	git commit -m "new file" &&
-	head2=$(git rev-parse --short HEAD) &&
-	echo "From $pwd/." > expect.err.file &&
-	echo "   $head1..$head2  super      -> origin/super" >> expect.err.file &&
+	new_head=$(git rev-parse --short HEAD) &&
+	write_expected_super $new_head &&
+	rm expect.err.sub &&
+	rm expect.err.deep &&
 	(
 		cd downstream &&
 		git fetch >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err.file actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "Recursion picks up config in submodule" '
@@ -287,14 +374,11 @@ test_expect_success "Recursion picks up config in submodule" '
 			git config fetch.recurseSubmodules true
 		)
 	) &&
-	add_upstream_commit &&
-	head1=$(git rev-parse --short HEAD) &&
+	add_submodule_commits &&
 	git add submodule &&
 	git commit -m "new submodule" &&
-	head2=$(git rev-parse --short HEAD) &&
-	echo "From $pwd/." > expect.err.sub &&
-	echo "   $head1..$head2  super      -> origin/super" >> expect.err.sub &&
-	cat expect.err >> expect.err.sub &&
+	new_head=$(git rev-parse --short HEAD) &&
+	write_expected_super $new_head &&
 	(
 		cd downstream &&
 		git fetch >../actual.out 2>../actual.err &&
@@ -303,60 +387,23 @@ test_expect_success "Recursion picks up config in submodule" '
 			git config --unset fetch.recurseSubmodules
 		)
 	) &&
-	test_cmp expect.err.sub actual.err &&
+	verify_fetch_result actual.err &&
 	test_must_be_empty actual.out
 '
 
 test_expect_success "Recursion picks up all submodules when necessary" '
-	add_upstream_commit &&
-	(
-		cd submodule &&
-		(
-			cd subdir/deepsubmodule &&
-			git fetch &&
-			git checkout -q FETCH_HEAD
-		) &&
-		head1=$(git rev-parse --short HEAD^) &&
-		git add subdir/deepsubmodule &&
-		git commit -m "new deepsubmodule" &&
-		head2=$(git rev-parse --short HEAD) &&
-		echo "Fetching submodule submodule" > ../expect.err.sub &&
-		echo "From $pwd/submodule" >> ../expect.err.sub &&
-		echo "   $head1..$head2  sub        -> origin/sub" >> ../expect.err.sub
-	) &&
-	head1=$(git rev-parse --short HEAD) &&
-	git add submodule &&
-	git commit -m "new submodule" &&
-	head2=$(git rev-parse --short HEAD) &&
-	echo "From $pwd/." > expect.err.2 &&
-	echo "   $head1..$head2  super      -> origin/super" >> expect.err.2 &&
-	cat expect.err.sub >> expect.err.2 &&
-	tail -3 expect.err >> expect.err.2 &&
+	add_submodule_commits &&
+	add_superproject_commits &&
 	(
 		cd downstream &&
 		git fetch >../actual.out 2>../actual.err
 	) &&
-	test_cmp expect.err.2 actual.err &&
+	verify_fetch_result actual.err &&
 	test_must_be_empty actual.out
 '
 
 test_expect_success "'--recurse-submodules=on-demand' doesn't recurse when no new commits are fetched in the superproject (and ignores config)" '
-	add_upstream_commit &&
-	(
-		cd submodule &&
-		(
-			cd subdir/deepsubmodule &&
-			git fetch &&
-			git checkout -q FETCH_HEAD
-		) &&
-		head1=$(git rev-parse --short HEAD^) &&
-		git add subdir/deepsubmodule &&
-		git commit -m "new deepsubmodule" &&
-		head2=$(git rev-parse --short HEAD) &&
-		echo Fetching submodule submodule > ../expect.err.sub &&
-		echo "From $pwd/submodule" >> ../expect.err.sub &&
-		echo "   $head1..$head2  sub        -> origin/sub" >> ../expect.err.sub
-	) &&
+	add_submodule_commits &&
 	(
 		cd downstream &&
 		git config fetch.recurseSubmodules true &&
@@ -368,15 +415,8 @@ test_expect_success "'--recurse-submodules=on-demand' doesn't recurse when no ne
 '
 
 test_expect_success "'--recurse-submodules=on-demand' recurses as deep as necessary (and ignores config)" '
-	head1=$(git rev-parse --short HEAD) &&
-	git add submodule &&
-	git commit -m "new submodule" &&
-	head2=$(git rev-parse --short HEAD) &&
-	tail -3 expect.err > expect.err.deepsub &&
-	echo "From $pwd/." > expect.err &&
-	echo "   $head1..$head2  super      -> origin/super" >>expect.err &&
-	cat expect.err.sub >> expect.err &&
-	cat expect.err.deepsub >> expect.err &&
+	add_submodule_commits &&
+	add_superproject_commits &&
 	(
 		cd downstream &&
 		git config fetch.recurseSubmodules false &&
@@ -392,24 +432,165 @@ test_expect_success "'--recurse-submodules=on-demand' recurses as deep as necess
 		)
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err
+	verify_fetch_result actual.err
+'
+
+# These tests verify that we can fetch submodules that aren't in the
+# index.
+#
+# First, test the simple case where the index is empty and we only fetch
+# submodules that are not in the index.
+test_expect_success 'setup downstream branch without submodules' '
+	(
+		cd downstream &&
+		git checkout --recurse-submodules -b no-submodules &&
+		git rm .gitmodules &&
+		git rm submodule &&
+		git commit -m "no submodules" &&
+		git checkout --recurse-submodules super
+	)
+'
+
+test_expect_success "'--recurse-submodules=on-demand' should fetch submodule commits if the submodule is changed but the index has no submodules" '
+	add_submodule_commits &&
+	add_superproject_commits &&
+	# Fetch the new superproject commit
+	(
+		cd downstream &&
+		git switch --recurse-submodules no-submodules &&
+		git fetch --recurse-submodules=on-demand >../actual.out 2>../actual.err
+	) &&
+	super_head=$(git rev-parse --short HEAD) &&
+	sub_head=$(git -C submodule rev-parse --short HEAD) &&
+	deep_head=$(git -C submodule/subdir/deepsubmodule rev-parse --short HEAD) &&
+
+	# assert that these are fetched from commits, not the index
+	write_expected_sub $sub_head $super_head &&
+	write_expected_deep $deep_head $sub_head &&
+
+	test_must_be_empty actual.out &&
+	verify_fetch_result actual.err
+'
+
+test_expect_success "'--recurse-submodules' should fetch submodule commits if the submodule is changed but the index has no submodules" '
+	add_submodule_commits &&
+	add_superproject_commits &&
+	# Fetch the new superproject commit
+	(
+		cd downstream &&
+		git switch --recurse-submodules no-submodules &&
+		git fetch --recurse-submodules >../actual.out 2>../actual.err
+	) &&
+	super_head=$(git rev-parse --short HEAD) &&
+	sub_head=$(git -C submodule rev-parse --short HEAD) &&
+	deep_head=$(git -C submodule/subdir/deepsubmodule rev-parse --short HEAD) &&
+
+	# assert that these are fetched from commits, not the index
+	write_expected_sub $sub_head $super_head &&
+	write_expected_deep $deep_head $sub_head &&
+
+	test_must_be_empty actual.out &&
+	verify_fetch_result actual.err
+'
+
+test_expect_success "'--recurse-submodules' should ignore changed, inactive submodules" '
+	add_submodule_commits &&
+	add_superproject_commits &&
+
+	# Fetch the new superproject commit
+	(
+		cd downstream &&
+		git switch --recurse-submodules no-submodules &&
+		git -c submodule.submodule.active=false fetch --recurse-submodules >../actual.out 2>../actual.err
+	) &&
+	test_must_be_empty actual.out &&
+	super_head=$(git rev-parse --short HEAD) &&
+	write_expected_super $super_head &&
+	# Neither should be fetched because the submodule is inactive
+	rm expect.err.sub &&
+	rm expect.err.deep &&
+	verify_fetch_result actual.err
+'
+
+# Now that we know we can fetch submodules that are not in the index,
+# test that we can fetch index and non-index submodules in the same
+# operation.
+test_expect_success 'setup downstream branch with other submodule' '
+	mkdir submodule2 &&
+	(
+		cd submodule2 &&
+		git init &&
+		echo sub2content >sub2file &&
+		git add sub2file &&
+		git commit -a -m new &&
+		git branch -M sub2
+	) &&
+	git checkout -b super-sub2-only &&
+	git submodule add "$pwd/submodule2" submodule2 &&
+	git commit -m "add sub2" &&
+	git checkout super &&
+	(
+		cd downstream &&
+		git fetch --recurse-submodules origin &&
+		git checkout super-sub2-only &&
+		# Explicitly run "git submodule update" because sub2 is new
+		# and has not been cloned.
+		git submodule update --init &&
+		git checkout --recurse-submodules super
+	)
+'
+
+test_expect_success "'--recurse-submodules' should fetch submodule commits in changed submodules and the index" '
+	test_when_finished "rm expect.err.sub2" &&
+	# Create new commit in origin/super
+	add_submodule_commits &&
+	add_superproject_commits &&
+
+	# Create new commit in origin/super-sub2-only
+	git checkout super-sub2-only &&
+	(
+		cd submodule2 &&
+		test_commit --no-tag foo
+	) &&
+	git add submodule2 &&
+	git commit -m "new submodule2" &&
+
+	git checkout super &&
+	(
+		cd downstream &&
+		git fetch --recurse-submodules >../actual.out 2>../actual.err
+	) &&
+	test_must_be_empty actual.out &&
+	sub2_head=$(git -C submodule2 rev-parse --short HEAD) &&
+	super_head=$(git rev-parse --short super) &&
+	super_sub2_only_head=$(git rev-parse --short super-sub2-only) &&
+	write_expected_sub2 $sub2_head $super_sub2_only_head &&
+
+	# write_expected_super cannot handle >1 branch. Since this is a
+	# one-off, construct expect.err.super manually.
+	cat >"$pwd/expect.err.super" <<-EOF &&
+	From $pwd/.
+	   OLD_HEAD..$super_head  super           -> origin/super
+	   OLD_HEAD..$super_sub2_only_head  super-sub2-only -> origin/super-sub2-only
+	EOF
+	verify_fetch_result actual.err
 '
 
 test_expect_success "'--recurse-submodules=on-demand' stops when no new submodule commits are found in the superproject (and ignores config)" '
-	add_upstream_commit &&
-	head1=$(git rev-parse --short HEAD) &&
+	add_submodule_commits &&
 	echo a >> file &&
 	git add file &&
 	git commit -m "new file" &&
-	head2=$(git rev-parse --short HEAD) &&
-	echo "From $pwd/." > expect.err.file &&
-	echo "   $head1..$head2  super      -> origin/super" >> expect.err.file &&
+	new_head=$(git rev-parse --short HEAD) &&
+	write_expected_super $new_head &&
+	rm expect.err.sub &&
+	rm expect.err.deep &&
 	(
 		cd downstream &&
 		git fetch --recurse-submodules=on-demand >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err.file actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "'fetch.recurseSubmodules=on-demand' overrides global config" '
@@ -417,15 +598,13 @@ test_expect_success "'fetch.recurseSubmodules=on-demand' overrides global config
 		cd downstream &&
 		git fetch --recurse-submodules
 	) &&
-	add_upstream_commit &&
+	add_submodule_commits &&
 	git config --global fetch.recurseSubmodules false &&
-	head1=$(git rev-parse --short HEAD) &&
 	git add submodule &&
 	git commit -m "new submodule" &&
-	head2=$(git rev-parse --short HEAD) &&
-	echo "From $pwd/." > expect.err.2 &&
-	echo "   $head1..$head2  super      -> origin/super" >>expect.err.2 &&
-	head -3 expect.err >> expect.err.2 &&
+	new_head=$(git rev-parse --short HEAD) &&
+	write_expected_super $new_head &&
+	rm expect.err.deep &&
 	(
 		cd downstream &&
 		git config fetch.recurseSubmodules on-demand &&
@@ -437,7 +616,7 @@ test_expect_success "'fetch.recurseSubmodules=on-demand' overrides global config
 		git config --unset fetch.recurseSubmodules
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err.2 actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "'submodule.<sub>.fetchRecurseSubmodules=on-demand' overrides fetch.recurseSubmodules" '
@@ -445,15 +624,13 @@ test_expect_success "'submodule.<sub>.fetchRecurseSubmodules=on-demand' override
 		cd downstream &&
 		git fetch --recurse-submodules
 	) &&
-	add_upstream_commit &&
+	add_submodule_commits &&
 	git config fetch.recurseSubmodules false &&
-	head1=$(git rev-parse --short HEAD) &&
 	git add submodule &&
 	git commit -m "new submodule" &&
-	head2=$(git rev-parse --short HEAD) &&
-	echo "From $pwd/." > expect.err.2 &&
-	echo "   $head1..$head2  super      -> origin/super" >>expect.err.2 &&
-	head -3 expect.err >> expect.err.2 &&
+	new_head=$(git rev-parse --short HEAD) &&
+	write_expected_super $new_head &&
+	rm expect.err.deep &&
 	(
 		cd downstream &&
 		git config submodule.submodule.fetchRecurseSubmodules on-demand &&
@@ -465,7 +642,7 @@ test_expect_success "'submodule.<sub>.fetchRecurseSubmodules=on-demand' override
 		git config --unset submodule.submodule.fetchRecurseSubmodules
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err.2 actual.err
+	verify_fetch_result actual.err
 '
 
 test_expect_success "don't fetch submodule when newly recorded commits are already present" '
@@ -473,18 +650,19 @@ test_expect_success "don't fetch submodule when newly recorded commits are alrea
 		cd submodule &&
 		git checkout -q HEAD^^
 	) &&
-	head1=$(git rev-parse --short HEAD) &&
 	git add submodule &&
 	git commit -m "submodule rewound" &&
-	head2=$(git rev-parse --short HEAD) &&
-	echo "From $pwd/." > expect.err &&
-	echo "   $head1..$head2  super      -> origin/super" >> expect.err &&
+	new_head=$(git rev-parse --short HEAD) &&
+	write_expected_super $new_head &&
+	rm expect.err.sub &&
+	# This file does not exist, but rm -f for readability
+	rm -f expect.err.deep &&
 	(
 		cd downstream &&
 		git fetch >../actual.out 2>../actual.err
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err actual.err &&
+	verify_fetch_result actual.err &&
 	(
 		cd submodule &&
 		git checkout -q sub
@@ -496,15 +674,13 @@ test_expect_success "'fetch.recurseSubmodules=on-demand' works also without .git
 		cd downstream &&
 		git fetch --recurse-submodules
 	) &&
-	add_upstream_commit &&
-	head1=$(git rev-parse --short HEAD) &&
+	add_submodule_commits &&
 	git add submodule &&
 	git rm .gitmodules &&
 	git commit -m "new submodule without .gitmodules" &&
-	head2=$(git rev-parse --short HEAD) &&
-	echo "From $pwd/." >expect.err.2 &&
-	echo "   $head1..$head2  super      -> origin/super" >>expect.err.2 &&
-	head -3 expect.err >>expect.err.2 &&
+	new_head=$(git rev-parse --short HEAD) &&
+	write_expected_super $new_head &&
+	rm expect.err.deep &&
 	(
 		cd downstream &&
 		rm .gitmodules &&
@@ -520,7 +696,7 @@ test_expect_success "'fetch.recurseSubmodules=on-demand' works also without .git
 		git reset --hard
 	) &&
 	test_must_be_empty actual.out &&
-	test_cmp expect.err.2 actual.err &&
+	verify_fetch_result actual.err &&
 	git checkout HEAD^ -- .gitmodules &&
 	git add .gitmodules &&
 	git commit -m "new submodule restored .gitmodules"
@@ -842,4 +1018,111 @@ test_expect_success 'recursive fetch after deinit a submodule' '
 	test_cmp expect actual
 '
 
+test_expect_success 'setup repo with upstreams that share a submodule name' '
+	mkdir same-name-1 &&
+	(
+		cd same-name-1 &&
+		git init -b main &&
+		test_commit --no-tag a
+	) &&
+	git clone same-name-1 same-name-2 &&
+	# same-name-1 and same-name-2 both add a submodule with the
+	# name "submodule"
+	(
+		cd same-name-1 &&
+		mkdir submodule &&
+		git -C submodule init -b main &&
+		test_commit -C submodule --no-tag a1 &&
+		git submodule add "$pwd/same-name-1/submodule" &&
+		git add submodule &&
+		git commit -m "super-a1"
+	) &&
+	(
+		cd same-name-2 &&
+		mkdir submodule &&
+		git -C submodule init -b main &&
+		test_commit -C submodule --no-tag a2 &&
+		git submodule add "$pwd/same-name-2/submodule" &&
+		git add submodule &&
+		git commit -m "super-a2"
+	) &&
+	git clone same-name-1 -o same-name-1 same-name-downstream &&
+	(
+		cd same-name-downstream &&
+		git remote add same-name-2 ../same-name-2 &&
+		git fetch --all &&
+		# init downstream with same-name-1
+		git submodule update --init
+	)
+'
+
+test_expect_success 'fetch --recurse-submodules updates name-conflicted, populated submodule' '
+	test_when_finished "git -C same-name-downstream checkout main" &&
+	(
+		cd same-name-1 &&
+		test_commit -C submodule --no-tag b1 &&
+		git add submodule &&
+		git commit -m "super-b1"
+	) &&
+	(
+		cd same-name-2 &&
+		test_commit -C submodule --no-tag b2 &&
+		git add submodule &&
+		git commit -m "super-b2"
+	) &&
+	(
+		cd same-name-downstream &&
+		# even though the .gitmodules is correct, we cannot
+		# fetch from same-name-2
+		git checkout same-name-2/main &&
+		git fetch --recurse-submodules same-name-1 &&
+		test_must_fail git fetch --recurse-submodules same-name-2
+	) &&
+	super_head1=$(git -C same-name-1 rev-parse HEAD) &&
+	git -C same-name-downstream cat-file -e $super_head1 &&
+
+	super_head2=$(git -C same-name-2 rev-parse HEAD) &&
+	git -C same-name-downstream cat-file -e $super_head2 &&
+
+	sub_head1=$(git -C same-name-1/submodule rev-parse HEAD) &&
+	git -C same-name-downstream/submodule cat-file -e $sub_head1 &&
+
+	sub_head2=$(git -C same-name-2/submodule rev-parse HEAD) &&
+	test_must_fail git -C same-name-downstream/submodule cat-file -e $sub_head2
+'
+
+test_expect_success 'fetch --recurse-submodules updates name-conflicted, unpopulated submodule' '
+	(
+		cd same-name-1 &&
+		test_commit -C submodule --no-tag c1 &&
+		git add submodule &&
+		git commit -m "super-c1"
+	) &&
+	(
+		cd same-name-2 &&
+		test_commit -C submodule --no-tag c2 &&
+		git add submodule &&
+		git commit -m "super-c2"
+	) &&
+	(
+		cd same-name-downstream &&
+		git checkout main &&
+		git rm .gitmodules &&
+		git rm submodule &&
+		git commit -m "no submodules" &&
+		git fetch --recurse-submodules same-name-1
+	) &&
+	head1=$(git -C same-name-1/submodule rev-parse HEAD) &&
+	head2=$(git -C same-name-2/submodule rev-parse HEAD) &&
+	(
+		cd same-name-downstream/.git/modules/submodule &&
+		# The submodule has core.worktree pointing to the "git
+		# rm"-ed directory, overwrite the invalid value. See
+		# comment in get_fetch_task_from_changed() for more
+		# information.
+		git --work-tree=. cat-file -e $head1 &&
+		test_must_fail git --work-tree=. cat-file -e $head2
+	)
+'
+
 test_done