1 files changed, 334 insertions, 102 deletions

diff --git a/submodule.c b/submodule.c
index 0ef2ff4321..0a2831d846 100644
--- a/submodule.c
+++ b/submodule.c
@@ -14,6 +14,7 @@
 #include "blob.h"
 #include "thread-utils.h"
 #include "quote.h"
+#include "worktree.h"
 
 static int config_fetch_recurse_submodules = RECURSE_SUBMODULES_ON_DEMAND;
 static int parallel_jobs = 1;
@@ -123,9 +124,7 @@ void stage_updated_gitmodules(void)
 static int add_submodule_odb(const char *path)
 {
 	struct strbuf objects_directory = STRBUF_INIT;
-	struct alternate_object_database *alt_odb;
 	int ret = 0;
-	size_t alloc;
 
 	ret = strbuf_git_path_submodule(&objects_directory, path, "objects/");
 	if (ret)
@@ -134,26 +133,7 @@ static int add_submodule_odb(const char *path)
 		ret = -1;
 		goto done;
 	}
-	/* avoid adding it twice */
-	prepare_alt_odb();
-	for (alt_odb = alt_odb_list; alt_odb; alt_odb = alt_odb->next)
-		if (alt_odb->name - alt_odb->base == objects_directory.len &&
-				!strncmp(alt_odb->base, objects_directory.buf,
-					objects_directory.len))
-			goto done;
-
-	alloc = st_add(objects_directory.len, 42); /* for "12/345..." sha1 */
-	alt_odb = xmalloc(st_add(sizeof(*alt_odb), alloc));
-	alt_odb->next = alt_odb_list;
-	xsnprintf(alt_odb->base, alloc, "%s", objects_directory.buf);
-	alt_odb->name = alt_odb->base + objects_directory.len;
-	alt_odb->name[2] = '/';
-	alt_odb->name[40] = '\0';
-	alt_odb->name[41] = '\0';
-	alt_odb_list = alt_odb;
-
-	/* add possible alternates from the submodule */
-	read_info_alternates(objects_directory.buf, 0);
+	add_to_alternates_memory(objects_directory.buf);
 done:
 	strbuf_release(&objects_directory);
 	return ret;
@@ -219,6 +199,56 @@ void gitmodules_config(void)
 	}
 }
 
+void gitmodules_config_sha1(const unsigned char *commit_sha1)
+{
+	struct strbuf rev = STRBUF_INIT;
+	unsigned char sha1[20];
+
+	if (gitmodule_sha1_from_commit(commit_sha1, sha1, &rev)) {
+		git_config_from_blob_sha1(submodule_config, rev.buf,
+					  sha1, NULL);
+	}
+	strbuf_release(&rev);
+}
+
+/*
+ * Determine if a submodule has been initialized at a given 'path'
+ */
+int is_submodule_initialized(const char *path)
+{
+	int ret = 0;
+	const struct submodule *module = NULL;
+
+	module = submodule_from_path(null_sha1, path);
+
+	if (module) {
+		char *key = xstrfmt("submodule.%s.url", module->name);
+		char *value = NULL;
+
+		ret = !git_config_get_string(key, &value);
+
+		free(value);
+		free(key);
+	}
+
+	return ret;
+}
+
+/*
+ * Determine if a submodule has been populated at a given 'path'
+ */
+int is_submodule_populated(const char *path)
+{
+	int ret = 0;
+	char *gitdir = xstrfmt("%s/.git", path);
+
+	if (resolve_gitdir(gitdir))
+		ret = 1;
+
+	free(gitdir);
+	return ret;
+}
+
 int parse_submodule_update_strategy(const char *value,
 		struct submodule_update_strategy *dst)
 {
@@ -392,11 +422,10 @@ static void show_submodule_header(FILE *f, const char *path,
 	}
 
 output_header:
-	strbuf_addf(&sb, "%s%sSubmodule %s %s..", line_prefix, meta, path,
-			find_unique_abbrev(one->hash, DEFAULT_ABBREV));
-	if (!fast_backward && !fast_forward)
-		strbuf_addch(&sb, '.');
-	strbuf_addf(&sb, "%s", find_unique_abbrev(two->hash, DEFAULT_ABBREV));
+	strbuf_addf(&sb, "%s%sSubmodule %s ", line_prefix, meta, path);
+	strbuf_add_unique_abbrev(&sb, one->hash, DEFAULT_ABBREV);
+	strbuf_addstr(&sb, (fast_backward || fast_forward) ? ".." : "...");
+	strbuf_add_unique_abbrev(&sb, two->hash, DEFAULT_ABBREV);
 	if (message)
 		strbuf_addf(&sb, " %s%s\n", message, reset);
 	else
@@ -522,27 +551,67 @@ static int has_remote(const char *refname, const struct object_id *oid,
 	return 1;
 }
 
-static int submodule_needs_pushing(const char *path, const unsigned char sha1[20])
+static int append_sha1_to_argv(const unsigned char sha1[20], void *data)
+{
+	struct argv_array *argv = data;
+	argv_array_push(argv, sha1_to_hex(sha1));
+	return 0;
+}
+
+static int check_has_commit(const unsigned char sha1[20], void *data)
+{
+	int *has_commit = data;
+
+	if (!lookup_commit_reference(sha1))
+		*has_commit = 0;
+
+	return 0;
+}
+
+static int submodule_has_commits(const char *path, struct sha1_array *commits)
 {
-	if (add_submodule_odb(path) || !lookup_commit_reference(sha1))
+	int has_commit = 1;
+
+	if (add_submodule_odb(path))
+		return 0;
+
+	sha1_array_for_each_unique(commits, check_has_commit, &has_commit);
+	return has_commit;
+}
+
+static int submodule_needs_pushing(const char *path, struct sha1_array *commits)
+{
+	if (!submodule_has_commits(path, commits))
+		/*
+		 * NOTE: We do consider it safe to return "no" here. The
+		 * correct answer would be "We do not know" instead of
+		 * "No push needed", but it is quite hard to change
+		 * the submodule pointer without having the submodule
+		 * around. If a user did however change the submodules
+		 * without having the submodule around, this indicates
+		 * an expert who knows what they are doing or a
+		 * maintainer integrating work from other people. In
+		 * both cases it should be safe to skip this check.
+		 */
 		return 0;
 
 	if (for_each_remote_ref_submodule(path, has_remote, NULL) > 0) {
 		struct child_process cp = CHILD_PROCESS_INIT;
-		const char *argv[] = {"rev-list", NULL, "--not", "--remotes", "-n", "1" , NULL};
 		struct strbuf buf = STRBUF_INIT;
 		int needs_pushing = 0;
 
-		argv[1] = sha1_to_hex(sha1);
-		cp.argv = argv;
+		argv_array_push(&cp.args, "rev-list");
+		sha1_array_for_each_unique(commits, append_sha1_to_argv, &cp.args);
+		argv_array_pushl(&cp.args, "--not", "--remotes", "-n", "1" , NULL);
+
 		prepare_submodule_repo_env(&cp.env_array);
 		cp.git_cmd = 1;
 		cp.no_stdin = 1;
 		cp.out = -1;
 		cp.dir = path;
 		if (start_command(&cp))
-			die("Could not run 'git rev-list %s --not --remotes -n 1' command in submodule %s",
-				sha1_to_hex(sha1), path);
+			die("Could not run 'git rev-list <commits> --not --remotes -n 1' command in submodule %s",
+					path);
 		if (strbuf_read(&buf, cp.out, 41))
 			needs_pushing = 1;
 		finish_command(&cp);
@@ -554,19 +623,34 @@ static int submodule_needs_pushing(const char *path, const unsigned char sha1[20
 	return 0;
 }
 
+static struct sha1_array *submodule_commits(struct string_list *submodules,
+					    const char *path)
+{
+	struct string_list_item *item;
+
+	item = string_list_insert(submodules, path);
+	if (item->util)
+		return (struct sha1_array *) item->util;
+
+	/* NEEDSWORK: should we have sha1_array_init()? */
+	item->util = xcalloc(1, sizeof(struct sha1_array));
+	return (struct sha1_array *) item->util;
+}
+
 static void collect_submodules_from_diff(struct diff_queue_struct *q,
 					 struct diff_options *options,
 					 void *data)
 {
 	int i;
-	struct string_list *needs_pushing = data;
+	struct string_list *submodules = data;
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
+		struct sha1_array *commits;
 		if (!S_ISGITLINK(p->two->mode))
 			continue;
-		if (submodule_needs_pushing(p->two->path, p->two->oid.hash))
-			string_list_insert(needs_pushing, p->two->path);
+		commits = submodule_commits(submodules, p->two->path);
+		sha1_array_append(commits, p->two->oid.hash);
 	}
 }
 
@@ -582,46 +666,63 @@ static void find_unpushed_submodule_commits(struct commit *commit,
 	diff_tree_combined_merge(commit, 1, &rev);
 }
 
-int find_unpushed_submodules(unsigned char new_sha1[20],
+static void free_submodules_sha1s(struct string_list *submodules)
+{
+	struct string_list_item *item;
+	for_each_string_list_item(item, submodules)
+		sha1_array_clear((struct sha1_array *) item->util);
+	string_list_clear(submodules, 1);
+}
+
+int find_unpushed_submodules(struct sha1_array *commits,
 		const char *remotes_name, struct string_list *needs_pushing)
 {
 	struct rev_info rev;
 	struct commit *commit;
-	const char *argv[] = {NULL, NULL, "--not", "NULL", NULL};
-	int argc = ARRAY_SIZE(argv) - 1;
-	char *sha1_copy;
-
-	struct strbuf remotes_arg = STRBUF_INIT;
+	struct string_list submodules = STRING_LIST_INIT_DUP;
+	struct string_list_item *submodule;
+	struct argv_array argv = ARGV_ARRAY_INIT;
 
-	strbuf_addf(&remotes_arg, "--remotes=%s", remotes_name);
 	init_revisions(&rev, NULL);
-	sha1_copy = xstrdup(sha1_to_hex(new_sha1));
-	argv[1] = sha1_copy;
-	argv[3] = remotes_arg.buf;
-	setup_revisions(argc, argv, &rev, NULL);
+
+	/* argv.argv[0] will be ignored by setup_revisions */
+	argv_array_push(&argv, "find_unpushed_submodules");
+	sha1_array_for_each_unique(commits, append_sha1_to_argv, &argv);
+	argv_array_push(&argv, "--not");
+	argv_array_pushf(&argv, "--remotes=%s", remotes_name);
+
+	setup_revisions(argv.argc, argv.argv, &rev, NULL);
 	if (prepare_revision_walk(&rev))
 		die("revision walk setup failed");
 
 	while ((commit = get_revision(&rev)) != NULL)
-		find_unpushed_submodule_commits(commit, needs_pushing);
+		find_unpushed_submodule_commits(commit, &submodules);
 
 	reset_revision_walk();
-	free(sha1_copy);
-	strbuf_release(&remotes_arg);
+	argv_array_clear(&argv);
+
+	for_each_string_list_item(submodule, &submodules) {
+		struct sha1_array *commits = (struct sha1_array *) submodule->util;
+
+		if (submodule_needs_pushing(submodule->string, commits))
+			string_list_insert(needs_pushing, submodule->string);
+	}
+	free_submodules_sha1s(&submodules);
 
 	return needs_pushing->nr;
 }
 
-static int push_submodule(const char *path)
+static int push_submodule(const char *path, int dry_run)
 {
 	if (add_submodule_odb(path))
 		return 1;
 
 	if (for_each_remote_ref_submodule(path, has_remote, NULL) > 0) {
 		struct child_process cp = CHILD_PROCESS_INIT;
-		const char *argv[] = {"push", NULL};
+		argv_array_push(&cp.args, "push");
+		if (dry_run)
+			argv_array_push(&cp.args, "--dry-run");
 
-		cp.argv = argv;
 		prepare_submodule_repo_env(&cp.env_array);
 		cp.git_cmd = 1;
 		cp.no_stdin = 1;
@@ -634,18 +735,20 @@ static int push_submodule(const char *path)
 	return 1;
 }
 
-int push_unpushed_submodules(unsigned char new_sha1[20], const char *remotes_name)
+int push_unpushed_submodules(struct sha1_array *commits,
+			     const char *remotes_name,
+			     int dry_run)
 {
 	int i, ret = 1;
 	struct string_list needs_pushing = STRING_LIST_INIT_DUP;
 
-	if (!find_unpushed_submodules(new_sha1, remotes_name, &needs_pushing))
+	if (!find_unpushed_submodules(commits, remotes_name, &needs_pushing))
 		return 1;
 
 	for (i = 0; i < needs_pushing.nr; i++) {
 		const char *path = needs_pushing.items[i].string;
 		fprintf(stderr, "Pushing submodule '%s'\n", path);
-		if (!push_submodule(path)) {
+		if (!push_submodule(path, dry_run)) {
 			fprintf(stderr, "Unable to push submodule '%s'\n", path);
 			ret = 0;
 		}
@@ -728,9 +831,10 @@ void check_for_new_submodule_commits(unsigned char new_sha1[20])
 	sha1_array_append(&ref_tips_after_fetch, new_sha1);
 }
 
-static void add_sha1_to_argv(const unsigned char sha1[20], void *data)
+static int add_sha1_to_argv(const unsigned char sha1[20], void *data)
 {
 	argv_array_push(data, sha1_to_hex(sha1));
+	return 0;
 }
 
 static void calculate_changed_submodule_paths(void)
@@ -1039,45 +1143,64 @@ int submodule_uses_gitfile(const char *path)
 	return 1;
 }
 
-int ok_to_remove_submodule(const char *path)
+/*
+ * Check if it is a bad idea to remove a submodule, i.e. if we'd lose data
+ * when doing so.
+ *
+ * Return 1 if we'd lose data, return 0 if the removal is fine,
+ * and negative values for errors.
+ */
+int bad_to_remove_submodule(const char *path, unsigned flags)
 {
 	ssize_t len;
 	struct child_process cp = CHILD_PROCESS_INIT;
-	const char *argv[] = {
-		"status",
-		"--porcelain",
-		"-u",
-		"--ignore-submodules=none",
-		NULL,
-	};
 	struct strbuf buf = STRBUF_INIT;
-	int ok_to_remove = 1;
+	int ret = 0;
 
 	if (!file_exists(path) || is_empty_dir(path))
-		return 1;
+		return 0;
 
 	if (!submodule_uses_gitfile(path))
-		return 0;
+		return 1;
+
+	argv_array_pushl(&cp.args, "status", "--porcelain",
+				   "--ignore-submodules=none", NULL);
+
+	if (flags & SUBMODULE_REMOVAL_IGNORE_UNTRACKED)
+		argv_array_push(&cp.args, "-uno");
+	else
+		argv_array_push(&cp.args, "-uall");
+
+	if (!(flags & SUBMODULE_REMOVAL_IGNORE_IGNORED_UNTRACKED))
+		argv_array_push(&cp.args, "--ignored");
 
-	cp.argv = argv;
 	prepare_submodule_repo_env(&cp.env_array);
 	cp.git_cmd = 1;
 	cp.no_stdin = 1;
 	cp.out = -1;
 	cp.dir = path;
-	if (start_command(&cp))
-		die("Could not run 'git status --porcelain -uall --ignore-submodules=none' in submodule %s", path);
+	if (start_command(&cp)) {
+		if (flags & SUBMODULE_REMOVAL_DIE_ON_ERROR)
+			die(_("could not start 'git status in submodule '%s'"),
+				path);
+		ret = -1;
+		goto out;
+	}
 
 	len = strbuf_read(&buf, cp.out, 1024);
 	if (len > 2)
-		ok_to_remove = 0;
+		ret = 1;
 	close(cp.out);
 
-	if (finish_command(&cp))
-		die("'git status --porcelain -uall --ignore-submodules=none' failed in submodule %s", path);
-
+	if (finish_command(&cp)) {
+		if (flags & SUBMODULE_REMOVAL_DIE_ON_ERROR)
+			die(_("could not run 'git status in submodule '%s'"),
+				path);
+		ret = -1;
+	}
+out:
 	strbuf_release(&buf);
-	return ok_to_remove;
+	return ret;
 }
 
 static int find_first_merges(struct object_array *result, const char *path,
@@ -1243,30 +1366,6 @@ int merge_submodule(unsigned char result[20], const char *path,
 	return 0;
 }
 
-/* Update gitfile and core.worktree setting to connect work tree and git dir */
-void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir)
-{
-	struct strbuf file_name = STRBUF_INIT;
-	struct strbuf rel_path = STRBUF_INIT;
-	const char *real_work_tree = xstrdup(real_path(work_tree));
-
-	/* Update gitfile */
-	strbuf_addf(&file_name, "%s/.git", work_tree);
-	write_file(file_name.buf, "gitdir: %s",
-		   relative_path(git_dir, real_work_tree, &rel_path));
-
-	/* Update core.worktree setting */
-	strbuf_reset(&file_name);
-	strbuf_addf(&file_name, "%s/config", git_dir);
-	git_config_set_in_file(file_name.buf, "core.worktree",
-			       relative_path(real_work_tree, git_dir,
-					     &rel_path));
-
-	strbuf_release(&file_name);
-	strbuf_release(&rel_path);
-	free((void *)real_work_tree);
-}
-
 int parallel_submodules(void)
 {
 	return parallel_jobs;
@@ -1280,5 +1379,138 @@ void prepare_submodule_repo_env(struct argv_array *out)
 		if (strcmp(*var, CONFIG_DATA_ENVIRONMENT))
 			argv_array_push(out, *var);
 	}
-	argv_array_push(out, "GIT_DIR=.git");
+	argv_array_pushf(out, "%s=%s", GIT_DIR_ENVIRONMENT,
+			 DEFAULT_GIT_DIR_ENVIRONMENT);
+}
+
+/*
+ * Embeds a single submodules git directory into the superprojects git dir,
+ * non recursively.
+ */
+static void relocate_single_git_dir_into_superproject(const char *prefix,
+						      const char *path)
+{
+	char *old_git_dir = NULL, *real_old_git_dir = NULL, *real_new_git_dir = NULL;
+	const char *new_git_dir;
+	const struct submodule *sub;
+
+	if (submodule_uses_worktrees(path))
+		die(_("relocate_gitdir for submodule '%s' with "
+		      "more than one worktree not supported"), path);
+
+	old_git_dir = xstrfmt("%s/.git", path);
+	if (read_gitfile(old_git_dir))
+		/* If it is an actual gitfile, it doesn't need migration. */
+		return;
+
+	real_old_git_dir = real_pathdup(old_git_dir, 1);
+
+	sub = submodule_from_path(null_sha1, path);
+	if (!sub)
+		die(_("could not lookup name for submodule '%s'"), path);
+
+	new_git_dir = git_path("modules/%s", sub->name);
+	if (safe_create_leading_directories_const(new_git_dir) < 0)
+		die(_("could not create directory '%s'"), new_git_dir);
+	real_new_git_dir = real_pathdup(new_git_dir, 1);
+
+	if (!prefix)
+		prefix = get_super_prefix();
+
+	fprintf(stderr, _("Migrating git directory of '%s%s' from\n'%s' to\n'%s'\n"),
+		prefix ? prefix : "", path,
+		real_old_git_dir, real_new_git_dir);
+
+	relocate_gitdir(path, real_old_git_dir, real_new_git_dir);
+
+	free(old_git_dir);
+	free(real_old_git_dir);
+	free(real_new_git_dir);
+}
+
+/*
+ * Migrate the git directory of the submodule given by path from
+ * having its git directory within the working tree to the git dir nested
+ * in its superprojects git dir under modules/.
+ */
+void absorb_git_dir_into_superproject(const char *prefix,
+				      const char *path,
+				      unsigned flags)
+{
+	int err_code;
+	const char *sub_git_dir;
+	struct strbuf gitdir = STRBUF_INIT;
+	strbuf_addf(&gitdir, "%s/.git", path);
+	sub_git_dir = resolve_gitdir_gently(gitdir.buf, &err_code);
+
+	/* Not populated? */
+	if (!sub_git_dir) {
+		char *real_new_git_dir;
+		const char *new_git_dir;
+		const struct submodule *sub;
+
+		if (err_code == READ_GITFILE_ERR_STAT_FAILED) {
+			/* unpopulated as expected */
+			strbuf_release(&gitdir);
+			return;
+		}
+
+		if (err_code != READ_GITFILE_ERR_NOT_A_REPO)
+			/* We don't know what broke here. */
+			read_gitfile_error_die(err_code, path, NULL);
+
+		/*
+		* Maybe populated, but no git directory was found?
+		* This can happen if the superproject is a submodule
+		* itself and was just absorbed. The absorption of the
+		* superproject did not rewrite the git file links yet,
+		* fix it now.
+		*/
+		sub = submodule_from_path(null_sha1, path);
+		if (!sub)
+			die(_("could not lookup name for submodule '%s'"), path);
+		new_git_dir = git_path("modules/%s", sub->name);
+		if (safe_create_leading_directories_const(new_git_dir) < 0)
+			die(_("could not create directory '%s'"), new_git_dir);
+		real_new_git_dir = real_pathdup(new_git_dir, 1);
+		connect_work_tree_and_git_dir(path, real_new_git_dir);
+
+		free(real_new_git_dir);
+	} else {
+		/* Is it already absorbed into the superprojects git dir? */
+		char *real_sub_git_dir = real_pathdup(sub_git_dir, 1);
+		char *real_common_git_dir = real_pathdup(get_git_common_dir(), 1);
+
+		if (!starts_with(real_sub_git_dir, real_common_git_dir))
+			relocate_single_git_dir_into_superproject(prefix, path);
+
+		free(real_sub_git_dir);
+		free(real_common_git_dir);
+	}
+	strbuf_release(&gitdir);
+
+	if (flags & ABSORB_GITDIR_RECURSE_SUBMODULES) {
+		struct child_process cp = CHILD_PROCESS_INIT;
+		struct strbuf sb = STRBUF_INIT;
+
+		if (flags & ~ABSORB_GITDIR_RECURSE_SUBMODULES)
+			die("BUG: we don't know how to pass the flags down?");
+
+		if (get_super_prefix())
+			strbuf_addstr(&sb, get_super_prefix());
+		strbuf_addstr(&sb, path);
+		strbuf_addch(&sb, '/');
+
+		cp.dir = path;
+		cp.git_cmd = 1;
+		cp.no_stdin = 1;
+		argv_array_pushl(&cp.args, "--super-prefix", sb.buf,
+					   "submodule--helper",
+					   "absorb-git-dirs", NULL);
+		prepare_submodule_repo_env(&cp.env_array);
+		if (run_command(&cp))
+			die(_("could not recurse into submodule '%s'"), path);
+
+		strbuf_release(&sb);
+	}
 }