Merge branch 'sb/submodule-recursive-fetch-gets-the-tip'

"git fetch --recurse-submodules" may not fetch the necessary commit
that is bound to the superproject, which is getting corrected.

* sb/submodule-recursive-fetch-gets-the-tip:
  fetch: ensure submodule objects fetched
  submodule.c: fetch in submodules git directory instead of in worktree
  submodule: migrate get_next_submodule to use repository structs
  repository: repo_submodule_init to take a submodule struct
  submodule: store OIDs in changed_submodule_names
  submodule.c: tighten scope of changed_submodule_names struct
  submodule.c: sort changed_submodule_names before searching it
  submodule.c: fix indentation
  sha1-array: provide oid_array_filter

1 files changed, 239 insertions, 45 deletions

diff --git a/submodule.c b/submodule.c
index d393e94..7b5cea8 100644
--- a/submodule.c
+++ b/submodule.c
@@ -25,7 +25,6 @@
 #include "commit-reach.h"
 
 static int config_update_recurse_submodules = RECURSE_SUBMODULES_OFF;
-static struct string_list changed_submodule_names = STRING_LIST_INIT_DUP;
 static int initialized_fetch_ref_tips;
 static struct oid_array ref_tips_before_fetch;
 static struct oid_array ref_tips_after_fetch;
@@ -495,6 +494,12 @@ void prepare_submodule_repo_env(struct argv_array *out)
 			 DEFAULT_GIT_DIR_ENVIRONMENT);
 }
 
+static void prepare_submodule_repo_env_in_gitdir(struct argv_array *out)
+{
+	prepare_submodule_repo_env_no_git_dir(out);
+	argv_array_pushf(out, "%s=.", GIT_DIR_ENVIRONMENT);
+}
+
 /* Helper function to display the submodule header line prior to the full
  * summary output. If it can locate the submodule objects directory it will
  * attempt to lookup both the left and right commits and put them into the
@@ -1136,11 +1141,11 @@ void check_for_new_submodule_commits(struct object_id *oid)
 	oid_array_append(&ref_tips_after_fetch, oid);
 }
 
-static void calculate_changed_submodule_paths(struct repository *r)
+static void calculate_changed_submodule_paths(struct repository *r,
+		struct string_list *changed_submodule_names)
 {
 	struct argv_array argv = ARGV_ARRAY_INIT;
-	struct string_list changed_submodules = STRING_LIST_INIT_DUP;
-	const struct string_list_item *name;
+	struct string_list_item *name;
 
 	/* No need to check if there are no submodules configured */
 	if (!submodule_from_path(r, NULL, NULL))
@@ -1157,9 +1162,9 @@ static void calculate_changed_submodule_paths(struct repository *r)
 	 * Collect all submodules (whether checked out or not) for which new
 	 * commits have been recorded upstream in "changed_submodule_names".
 	 */
-	collect_changed_submodules(r, &changed_submodules, &argv);
+	collect_changed_submodules(r, changed_submodule_names, &argv);
 
-	for_each_string_list_item(name, &changed_submodules) {
+	for_each_string_list_item(name, changed_submodule_names) {
 		struct oid_array *commits = name->util;
 		const struct submodule *submodule;
 		const char *path = NULL;
@@ -1173,11 +1178,14 @@ static void calculate_changed_submodule_paths(struct repository *r)
 		if (!path)
 			continue;
 
-		if (!submodule_has_commits(r, path, commits))
-			string_list_append(&changed_submodule_names, name->string);
+		if (submodule_has_commits(r, path, commits)) {
+			oid_array_clear(commits);
+			*name->string = '\0';
+		}
 	}
 
-	free_submodules_oids(&changed_submodules);
+	string_list_remove_empty_items(changed_submodule_names, 1);
+
 	argv_array_clear(&argv);
 	oid_array_clear(&ref_tips_before_fetch);
 	oid_array_clear(&ref_tips_after_fetch);
@@ -1221,8 +1229,16 @@ struct submodule_parallel_fetch {
 	int default_option;
 	int quiet;
 	int result;
+
+	struct string_list changed_submodule_names;
+
+	/* Pending fetches by OIDs */
+	struct fetch_task **oid_fetch_tasks;
+	int oid_fetch_tasks_nr, oid_fetch_tasks_alloc;
 };
-#define SPF_INIT {0, ARGV_ARRAY_INIT, NULL, NULL, 0, 0, 0, 0}
+#define SPF_INIT {0, ARGV_ARRAY_INIT, NULL, NULL, 0, 0, 0, 0, \
+		  STRING_LIST_INIT_DUP, \
+		  NULL, 0, 0}
 
 static int get_fetch_recurse_config(const struct submodule *submodule,
 				    struct submodule_parallel_fetch *spf)
@@ -1249,40 +1265,126 @@ static int get_fetch_recurse_config(const struct submodule *submodule,
 	return spf->default_option;
 }
 
+/*
+ * Fetch in progress (if callback data) or
+ * pending (if in oid_fetch_tasks in struct submodule_parallel_fetch)
+ */
+struct fetch_task {
+	struct repository *repo;
+	const struct submodule *sub;
+	unsigned free_sub : 1; /* Do we need to free the submodule? */
+
+	struct oid_array *commits; /* Ensure these commits are fetched */
+};
+
+/**
+ * When a submodule is not defined in .gitmodules, we cannot access it
+ * via the regular submodule-config. Create a fake submodule, which we can
+ * work on.
+ */
+static const struct submodule *get_non_gitmodules_submodule(const char *path)
+{
+	struct submodule *ret = NULL;
+	const char *name = default_name_or_path(path);
+
+	if (!name)
+		return NULL;
+
+	ret = xmalloc(sizeof(*ret));
+	memset(ret, 0, sizeof(*ret));
+	ret->path = name;
+	ret->name = name;
+
+	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)
+		free((void*)p->sub);
+	p->free_sub = 0;
+	p->sub = NULL;
+
+	if (p->repo)
+		repo_clear(p->repo);
+	FREE_AND_NULL(p->repo);
+}
+
+static struct repository *get_submodule_repo_for(struct repository *r,
+						 const struct submodule *sub)
+{
+	struct repository *ret = xmalloc(sizeof(*ret));
+
+	if (repo_submodule_init(ret, r, 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.
+		 */
+		struct strbuf gitdir = STRBUF_INIT;
+		strbuf_repo_worktree_path(&gitdir, r, "%s/.git", sub->path);
+		if (repo_init(ret, gitdir.buf, NULL)) {
+			strbuf_release(&gitdir);
+			free(ret);
+			return NULL;
+		}
+		strbuf_release(&gitdir);
+	}
+
+	return ret;
+}
+
 static int get_next_submodule(struct child_process *cp,
 			      struct strbuf *err, void *data, void **task_cb)
 {
-	int ret = 0;
 	struct submodule_parallel_fetch *spf = data;
 
 	for (; spf->count < spf->r->index->cache_nr; spf->count++) {
-		struct strbuf submodule_path = STRBUF_INIT;
-		struct strbuf submodule_git_dir = STRBUF_INIT;
-		struct strbuf submodule_prefix = STRBUF_INIT;
 		const struct cache_entry *ce = spf->r->index->cache[spf->count];
-		const char *git_dir, *default_argv;
-		const struct submodule *submodule;
-		struct submodule default_submodule = SUBMODULE_INIT;
+		const char *default_argv;
+		struct fetch_task *task;
 
 		if (!S_ISGITLINK(ce->ce_mode))
 			continue;
 
-		submodule = submodule_from_path(spf->r, &null_oid, ce->name);
-		if (!submodule) {
-			const char *name = default_name_or_path(ce->name);
-			if (name) {
-				default_submodule.path = default_submodule.name = name;
-				submodule = &default_submodule;
-			}
-		}
+		task = fetch_task_create(spf->r, ce->name);
+		if (!task)
+			continue;
 
-		switch (get_fetch_recurse_config(submodule, spf))
+		switch (get_fetch_recurse_config(task->sub, spf))
 		{
 		default:
 		case RECURSE_SUBMODULES_DEFAULT:
 		case RECURSE_SUBMODULES_ON_DEMAND:
-			if (!submodule || !unsorted_string_list_lookup(&changed_submodule_names,
-							 submodule->name))
+			if (!task->sub ||
+			    !string_list_lookup(
+					&spf->changed_submodule_names,
+					task->sub->name))
 				continue;
 			default_argv = "on-demand";
 			break;
@@ -1293,16 +1395,12 @@ static int get_next_submodule(struct child_process *cp,
 			continue;
 		}
 
-		strbuf_repo_worktree_path(&submodule_path, spf->r, "%s", ce->name);
-		strbuf_addf(&submodule_git_dir, "%s/.git", submodule_path.buf);
-		strbuf_addf(&submodule_prefix, "%s%s/", spf->prefix, ce->name);
-		git_dir = read_gitfile(submodule_git_dir.buf);
-		if (!git_dir)
-			git_dir = submodule_git_dir.buf;
-		if (is_directory(git_dir)) {
+		task->repo = get_submodule_repo_for(spf->r, task->sub);
+		if (task->repo) {
+			struct strbuf submodule_prefix = STRBUF_INIT;
 			child_process_init(cp);
-			cp->dir = strbuf_detach(&submodule_path, NULL);
-			prepare_submodule_repo_env(&cp->env_array);
+			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",
@@ -1311,17 +1409,66 @@ static int get_next_submodule(struct child_process *cp,
 			argv_array_pushv(&cp->args, spf->args.argv);
 			argv_array_push(&cp->args, default_argv);
 			argv_array_push(&cp->args, "--submodule-prefix");
+
+			strbuf_addf(&submodule_prefix, "%s%s/",
+						       spf->prefix,
+						       task->sub->path);
 			argv_array_push(&cp->args, submodule_prefix.buf);
-			ret = 1;
-		}
-		strbuf_release(&submodule_path);
-		strbuf_release(&submodule_git_dir);
-		strbuf_release(&submodule_prefix);
-		if (ret) {
+
 			spf->count++;
+			*task_cb = task;
+
+			strbuf_release(&submodule_prefix);
 			return 1;
+		} else {
+
+			fetch_task_release(task);
+			free(task);
+
+			/*
+			 * An empty directory is normal,
+			 * the submodule is not initialized
+			 */
+			if (S_ISGITLINK(ce->ce_mode) &&
+			    !is_empty_dir(ce->name)) {
+				spf->result = 1;
+				strbuf_addf(err,
+					    _("Could not access submodule '%s'"),
+					    ce->name);
+			}
 		}
 	}
+
+	if (spf->oid_fetch_tasks_nr) {
+		struct fetch_task *task =
+			spf->oid_fetch_tasks[spf->oid_fetch_tasks_nr - 1];
+		struct strbuf submodule_prefix = STRBUF_INIT;
+		spf->oid_fetch_tasks_nr--;
+
+		strbuf_addf(&submodule_prefix, "%s%s/",
+			    spf->prefix, task->sub->path);
+
+		child_process_init(cp);
+		prepare_submodule_repo_env_in_gitdir(&cp->env_array);
+		cp->git_cmd = 1;
+		cp->dir = task->repo->gitdir;
+
+		argv_array_init(&cp->args);
+		argv_array_pushv(&cp->args, spf->args.argv);
+		argv_array_push(&cp->args, "on-demand");
+		argv_array_push(&cp->args, "--submodule-prefix");
+		argv_array_push(&cp->args, submodule_prefix.buf);
+
+		/* NEEDSWORK: have get_default_remote from submodule--helper */
+		argv_array_push(&cp->args, "origin");
+		oid_array_for_each_unique(task->commits,
+					  append_oid_to_argv, &cp->args);
+
+		*task_cb = task;
+		strbuf_release(&submodule_prefix);
+		return 1;
+	}
+
 	return 0;
 }
 
@@ -1329,20 +1476,66 @@ static int fetch_start_failure(struct strbuf *err,
 			       void *cb, void *task_cb)
 {
 	struct submodule_parallel_fetch *spf = cb;
+	struct fetch_task *task = task_cb;
 
 	spf->result = 1;
 
+	fetch_task_release(task);
 	return 0;
 }
 
+static int commit_missing_in_sub(const struct object_id *oid, void *data)
+{
+	struct repository *subrepo = data;
+
+	enum object_type type = oid_object_info(subrepo, oid, NULL);
+
+	return type != OBJ_COMMIT;
+}
+
 static int fetch_finish(int retvalue, struct strbuf *err,
 			void *cb, void *task_cb)
 {
 	struct submodule_parallel_fetch *spf = cb;
+	struct fetch_task *task = task_cb;
+
+	struct string_list_item *it;
+	struct oid_array *commits;
 
 	if (retvalue)
 		spf->result = 1;
 
+	if (!task || !task->sub)
+		BUG("callback cookie bogus");
+
+	/* Is this the second time we process this submodule? */
+	if (task->commits)
+		goto out;
+
+	it = string_list_lookup(&spf->changed_submodule_names, task->sub->name);
+	if (!it)
+		/* Could be an unchanged submodule, not contained in the list */
+		goto out;
+
+	commits = it->util;
+	oid_array_filter(commits,
+			 commit_missing_in_sub,
+			 task->repo);
+
+	/* Are there commits we want, but do not exist? */
+	if (commits->nr) {
+		task->commits = commits;
+		ALLOC_GROW(spf->oid_fetch_tasks,
+			   spf->oid_fetch_tasks_nr + 1,
+			   spf->oid_fetch_tasks_alloc);
+		spf->oid_fetch_tasks[spf->oid_fetch_tasks_nr] = task;
+		spf->oid_fetch_tasks_nr++;
+		return 0;
+	}
+
+out:
+	fetch_task_release(task);
+
 	return 0;
 }
 
@@ -1373,7 +1566,8 @@ int fetch_populated_submodules(struct repository *r,
 	argv_array_push(&spf.args, "--recurse-submodules-default");
 	/* default value, "--submodule-prefix" and its value are added later */
 
-	calculate_changed_submodule_paths(r);
+	calculate_changed_submodule_paths(r, &spf.changed_submodule_names);
+	string_list_sort(&spf.changed_submodule_names);
 	run_processes_parallel(max_parallel_jobs,
 			       get_next_submodule,
 			       fetch_start_failure,
@@ -1382,7 +1576,7 @@ int fetch_populated_submodules(struct repository *r,
 
 	argv_array_clear(&spf.args);
 out:
-	string_list_clear(&changed_submodule_names, 1);
+	free_submodules_oids(&spf.changed_submodule_names);
 	return spf.result;
 }