Merge branch 'jt/partial-clone-submodule-1'

Prepare the internals for lazily fetching objects in submodules
from their promisor remotes.

* jt/partial-clone-submodule-1:
  promisor-remote: teach lazy-fetch in any repo
  run-command: refactor subprocess env preparation
  submodule: refrain from filtering GIT_CONFIG_COUNT
  promisor-remote: support per-repository config
  repository: move global r_f_p_c to repo struct

Makefile

@@ -729,6 +729,7 @@ TEST_BUILTINS_OBJS += test-oidmap.o
 TEST_BUILTINS_OBJS += test-online-cpus.o
 TEST_BUILTINS_OBJS += test-parse-options.o
 TEST_BUILTINS_OBJS += test-parse-pathspec-file.o
+TEST_BUILTINS_OBJS += test-partial-clone.o
 TEST_BUILTINS_OBJS += test-path-utils.o
 TEST_BUILTINS_OBJS += test-pcre2-config.o
 TEST_BUILTINS_OBJS += test-pkt-line.o

object-file.c

@@ -1584,15 +1584,12 @@ static int do_oid_object_info_extended(struct repository *r,
 		}
 
 		/* Check if it is a missing object */
-		if (fetch_if_missing && has_promisor_remote() &&
-		    !already_retried && r == the_repository &&
+		if (fetch_if_missing && repo_has_promisor_remote(r) &&
+		    !already_retried &&
 		    !(flags & OBJECT_INFO_SKIP_FETCH_OBJECT)) {
 			/*
 			 * TODO Investigate checking promisor_remote_get_direct()
 			 * TODO return value and stopping on error here.
-			 * TODO Pass a repository struct through
-			 * promisor_remote_get_direct(), such that arbitrary
-			 * repositories work.
 			 */
 			promisor_remote_get_direct(r, real, 1);
 			already_retried = 1;

promisor-remote.c

@@ -5,12 +5,10 @@
 #include "transport.h"
 #include "strvec.h"
 
-static char *repository_format_partial_clone;
-
-void set_repository_format_partial_clone(char *partial_clone)
-{
-	repository_format_partial_clone = xstrdup_or_null(partial_clone);
-}
+struct promisor_remote_config {
+	struct promisor_remote *promisors;
+	struct promisor_remote **promisors_tail;
+};
 
 static int fetch_objects(struct repository *repo,
 			 const char *remote_name,
@@ -23,6 +21,8 @@ static int fetch_objects(struct repository *repo,
 
 	child.git_cmd = 1;
 	child.in = -1;
+	if (repo != the_repository)
+		prepare_other_repo_env(&child.env_array, repo->gitdir);
 	strvec_pushl(&child.args, "-c", "fetch.negotiationAlgorithm=noop",
 		     "fetch", remote_name, "--no-tags",
 		     "--no-write-fetch-head", "--recurse-submodules=no",
@@ -45,10 +45,8 @@ static int fetch_objects(struct repository *repo,
 	return finish_command(&child) ? -1 : 0;
 }
 
-static struct promisor_remote *promisors;
-static struct promisor_remote **promisors_tail = &promisors;
-
-static struct promisor_remote *promisor_remote_new(const char *remote_name)
+static struct promisor_remote *promisor_remote_new(struct promisor_remote_config *config,
+						   const char *remote_name)
 {
 	struct promisor_remote *r;
 
@@ -60,18 +58,19 @@ static struct promisor_remote *promisor_remote_new(const char *remote_name)
 
 	FLEX_ALLOC_STR(r, name, remote_name);
 
-	*promisors_tail = r;
-	promisors_tail = &r->next;
+	*config->promisors_tail = r;
+	config->promisors_tail = &r->next;
 
 	return r;
 }
 
-static struct promisor_remote *promisor_remote_lookup(const char *remote_name,
+static struct promisor_remote *promisor_remote_lookup(struct promisor_remote_config *config,
+						      const char *remote_name,
 						      struct promisor_remote **previous)
 {
 	struct promisor_remote *r, *p;
 
-	for (p = NULL, r = promisors; r; p = r, r = r->next)
+	for (p = NULL, r = config->promisors; r; p = r, r = r->next)
 		if (!strcmp(r->name, remote_name)) {
 			if (previous)
 				*previous = p;
@@ -81,7 +80,8 @@ static struct promisor_remote *promisor_remote_lookup(const char *remote_name,
 	return NULL;
 }
 
-static void promisor_remote_move_to_tail(struct promisor_remote *r,
+static void promisor_remote_move_to_tail(struct promisor_remote_config *config,
+					 struct promisor_remote *r,
 					 struct promisor_remote *previous)
 {
 	if (r->next == NULL)
@@ -90,14 +90,15 @@ static void promisor_remote_move_to_tail(struct promisor_remote *r,
 	if (previous)
 		previous->next = r->next;
 	else
-		promisors = r->next ? r->next : r;
+		config->promisors = r->next ? r->next : r;
 	r->next = NULL;
-	*promisors_tail = r;
-	promisors_tail = &r->next;
+	*config->promisors_tail = r;
+	config->promisors_tail = &r->next;
 }
 
 static int promisor_remote_config(const char *var, const char *value, void *data)
 {
+	struct promisor_remote_config *config = data;
 	const char *name;
 	size_t namelen;
 	const char *subkey;
@@ -113,8 +114,8 @@ static int promisor_remote_config(const char *var, const char *value, void *data
 
 		remote_name = xmemdupz(name, namelen);
 
-		if (!promisor_remote_lookup(remote_name, NULL))
-			promisor_remote_new(remote_name);
+		if (!promisor_remote_lookup(config, remote_name, NULL))
+			promisor_remote_new(config, remote_name);
 
 		free(remote_name);
 		return 0;
@@ -123,9 +124,9 @@ static int promisor_remote_config(const char *var, const char *value, void *data
 		struct promisor_remote *r;
 		char *remote_name = xmemdupz(name, namelen);
 
-		r = promisor_remote_lookup(remote_name, NULL);
+		r = promisor_remote_lookup(config, remote_name, NULL);
 		if (!r)
-			r = promisor_remote_new(remote_name);
+			r = promisor_remote_new(config, remote_name);
 
 		free(remote_name);
 
@@ -138,59 +139,63 @@ static int promisor_remote_config(const char *var, const char *value, void *data
 	return 0;
 }
 
-static int initialized;
-
-static void promisor_remote_init(void)
+static void promisor_remote_init(struct repository *r)
 {
-	if (initialized)
+	struct promisor_remote_config *config;
+
+	if (r->promisor_remote_config)
 		return;
-	initialized = 1;
+	config = r->promisor_remote_config =
+		xcalloc(sizeof(*r->promisor_remote_config), 1);
+	config->promisors_tail = &config->promisors;
 
-	git_config(promisor_remote_config, NULL);
+	repo_config(r, promisor_remote_config, config);
 
-	if (repository_format_partial_clone) {
+	if (r->repository_format_partial_clone) {
 		struct promisor_remote *o, *previous;
 
-		o = promisor_remote_lookup(repository_format_partial_clone,
+		o = promisor_remote_lookup(config,
+					   r->repository_format_partial_clone,
 					   &previous);
 		if (o)
-			promisor_remote_move_to_tail(o, previous);
+			promisor_remote_move_to_tail(config, o, previous);
 		else
-			promisor_remote_new(repository_format_partial_clone);
+			promisor_remote_new(config, r->repository_format_partial_clone);
 	}
 }
 
-static void promisor_remote_clear(void)
+void promisor_remote_clear(struct promisor_remote_config *config)
 {
-	while (promisors) {
-		struct promisor_remote *r = promisors;
-		promisors = promisors->next;
+	while (config->promisors) {
+		struct promisor_remote *r = config->promisors;
+		config->promisors = config->promisors->next;
 		free(r);
 	}
 
-	promisors_tail = &promisors;
+	config->promisors_tail = &config->promisors;
 }
 
-void promisor_remote_reinit(void)
+void repo_promisor_remote_reinit(struct repository *r)
 {
-	initialized = 0;
-	promisor_remote_clear();
-	promisor_remote_init();
+	promisor_remote_clear(r->promisor_remote_config);
+	FREE_AND_NULL(r->promisor_remote_config);
+	promisor_remote_init(r);
 }
 
-struct promisor_remote *promisor_remote_find(const char *remote_name)
+struct promisor_remote *repo_promisor_remote_find(struct repository *r,
+						  const char *remote_name)
 {
-	promisor_remote_init();
+	promisor_remote_init(r);
 
 	if (!remote_name)
-		return promisors;
+		return r->promisor_remote_config->promisors;
 
-	return promisor_remote_lookup(remote_name, NULL);
+	return promisor_remote_lookup(r->promisor_remote_config, remote_name, NULL);
 }
 
-int has_promisor_remote(void)
+int repo_has_promisor_remote(struct repository *r)
 {
-	return !!promisor_remote_find(NULL);
+	return !!repo_promisor_remote_find(r, NULL);
 }
 
 static int remove_fetched_oids(struct repository *repo,
@@ -238,9 +243,9 @@ int promisor_remote_get_direct(struct repository *repo,
 	if (oid_nr == 0)
 		return 0;
 
-	promisor_remote_init();
+	promisor_remote_init(repo);
 
-	for (r = promisors; r; r = r->next) {
+	for (r = repo->promisor_remote_config->promisors; r; r = r->next) {
 		if (fetch_objects(repo, r->name, remaining_oids, remaining_nr) < 0) {
 			if (remaining_nr == 1)
 				continue;

promisor-remote.h

@@ -17,9 +17,25 @@ struct promisor_remote {
 	const char name[FLEX_ARRAY];
 };
 
-void promisor_remote_reinit(void);
-struct promisor_remote *promisor_remote_find(const char *remote_name);
-int has_promisor_remote(void);
+void repo_promisor_remote_reinit(struct repository *r);
+static inline void promisor_remote_reinit(void)
+{
+	repo_promisor_remote_reinit(the_repository);
+}
+
+void promisor_remote_clear(struct promisor_remote_config *config);
+
+struct promisor_remote *repo_promisor_remote_find(struct repository *r, const char *remote_name);
+static inline struct promisor_remote *promisor_remote_find(const char *remote_name)
+{
+	return repo_promisor_remote_find(the_repository, remote_name);
+}
+
+int repo_has_promisor_remote(struct repository *r);
+static inline int has_promisor_remote(void)
+{
+	return repo_has_promisor_remote(the_repository);
+}
 
 /*
  * Fetches all requested objects from all promisor remotes, trying them one at
@@ -32,10 +48,4 @@ int promisor_remote_get_direct(struct repository *repo,
 			       const struct object_id *oids,
 			       int oid_nr);
 
-/*
- * This should be used only once from setup.c to set the value we got
- * from the extensions.partialclone config option.
- */
-void set_repository_format_partial_clone(char *partial_clone);
-
 #endif /* PROMISOR_REMOTE_H */

repository.c

@@ -11,6 +11,7 @@
 #include "lockfile.h"
 #include "submodule-config.h"
 #include "sparse-index.h"
+#include "promisor-remote.h"
 
 /* The main repository */
 static struct repository the_repo;
@@ -172,6 +173,10 @@ int repo_init(struct repository *repo,
 
 	repo_set_hash_algo(repo, format.hash_algo);
 
+	/* take ownership of format.partial_clone */
+	repo->repository_format_partial_clone = format.partial_clone;
+	format.partial_clone = NULL;
+
 	if (worktree)
 		repo_set_worktree(repo, worktree);
 
@@ -258,6 +263,11 @@ void repo_clear(struct repository *repo)
 		if (repo->index != &the_index)
 			FREE_AND_NULL(repo->index);
 	}
+
+	if (repo->promisor_remote_config) {
+		promisor_remote_clear(repo->promisor_remote_config);
+		FREE_AND_NULL(repo->promisor_remote_config);
+	}
 }
 
 int repo_read_index(struct repository *repo)

repository.h

@@ -10,6 +10,7 @@ struct lock_file;
 struct pathspec;
 struct raw_object_store;
 struct submodule_cache;
+struct promisor_remote_config;
 
 enum untracked_cache_setting {
 	UNTRACKED_CACHE_UNSET = -1,
@@ -139,6 +140,10 @@ struct repository {
 	/* True if commit-graph has been disabled within this process. */
 	int commit_graph_disabled;
 
+	/* Configurations related to promisor remotes. */
+	char *repository_format_partial_clone;
+	struct promisor_remote_config *promisor_remote_config;
+
 	/* Configurations */
 
 	/* Indicate if a repository has a different 'commondir' from 'gitdir' */

run-command.c

@@ -1891,3 +1891,15 @@ int run_auto_maintenance(int quiet)
 
 	return run_command(&maint);
 }
+
+void prepare_other_repo_env(struct strvec *env_array, const char *new_git_dir)
+{
+	const char * const *var;
+
+	for (var = local_repo_env; *var; var++) {
+		if (strcmp(*var, CONFIG_DATA_ENVIRONMENT) &&
+		    strcmp(*var, CONFIG_COUNT_ENVIRONMENT))
+			strvec_push(env_array, *var);
+	}
+	strvec_pushf(env_array, "%s=%s", GIT_DIR_ENVIRONMENT, new_git_dir);
+}

run-command.h

@@ -486,4 +486,14 @@ int run_processes_parallel_tr2(int n, get_next_task_fn, start_failure_fn,
 			       task_finished_fn, void *pp_cb,
 			       const char *tr2_category, const char *tr2_label);
 
+/**
+ * Convenience function which prepares env_array for a command to be run in a
+ * new repo. This adds all GIT_* environment variables to env_array with the
+ * exception of GIT_CONFIG_PARAMETERS and GIT_CONFIG_COUNT (which cause the
+ * corresponding environment variables to be unset in the subprocess) and adds
+ * an environment variable pointing to new_git_dir. See local_repo_env in
+ * cache.h for more information.
+ */
+void prepare_other_repo_env(struct strvec *env_array, const char *new_git_dir);
+
 #endif

setup.c

@@ -468,8 +468,6 @@ static enum extension_result handle_extension_v0(const char *var,
 			data->precious_objects = git_config_bool(var, value);
 			return EXTENSION_OK;
 		} else if (!strcmp(ext, "partialclone")) {
-			if (!value)
-				return config_error_nonbool(var);
 			data->partial_clone = xstrdup(value);
 			return EXTENSION_OK;
 		} else if (!strcmp(ext, "worktreeconfig")) {
@@ -566,7 +564,6 @@ static int check_repository_format_gently(const char *gitdir, struct repository_
 	}
 
 	repository_format_precious_objects = candidate->precious_objects;
-	set_repository_format_partial_clone(candidate->partial_clone);
 	repository_format_worktree_config = candidate->worktree_config;
 	string_list_clear(&candidate->unknown_extensions, 0);
 	string_list_clear(&candidate->v1_only_extensions, 0);
@@ -1197,6 +1194,11 @@ int discover_git_directory(struct strbuf *commondir,
 		return -1;
 	}
 
+	/* take ownership of candidate.partial_clone */
+	the_repository->repository_format_partial_clone =
+		candidate.partial_clone;
+	candidate.partial_clone = NULL;
+
 	clear_repository_format(&candidate);
 	return 0;
 }
@@ -1304,8 +1306,13 @@ const char *setup_git_directory_gently(int *nongit_ok)
 				gitdir = DEFAULT_GIT_DIR_ENVIRONMENT;
 			setup_git_env(gitdir);
 		}
-		if (startup_info->have_repository)
+		if (startup_info->have_repository) {
 			repo_set_hash_algo(the_repository, repo_fmt.hash_algo);
+			/* take ownership of repo_fmt.partial_clone */
+			the_repository->repository_format_partial_clone =
+				repo_fmt.partial_clone;
+			repo_fmt.partial_clone = NULL;
+		}
 	}
 	/*
 	 * Since precompose_string_if_needed() needs to look at
@@ -1390,6 +1397,8 @@ void check_repository_format(struct repository_format *fmt)
 	check_repository_format_gently(get_git_dir(), fmt, NULL);
 	startup_info->have_repository = 1;
 	repo_set_hash_algo(the_repository, fmt->hash_algo);
+	the_repository->repository_format_partial_clone =
+		xstrdup_or_null(fmt->partial_clone);
 	clear_repository_format(&repo_fmt);
 }
 

submodule.c

@@ -484,27 +484,14 @@ static void print_submodule_diff_summary(struct repository *r, struct rev_info *
 	strbuf_release(&sb);
 }
 
-static void prepare_submodule_repo_env_no_git_dir(struct strvec *out)
-{
-	const char * const *var;
-
-	for (var = local_repo_env; *var; var++) {
-		if (strcmp(*var, CONFIG_DATA_ENVIRONMENT))
-			strvec_push(out, *var);
-	}
-}
-
 void prepare_submodule_repo_env(struct strvec *out)
 {
-	prepare_submodule_repo_env_no_git_dir(out);
-	strvec_pushf(out, "%s=%s", GIT_DIR_ENVIRONMENT,
-		     DEFAULT_GIT_DIR_ENVIRONMENT);
+	prepare_other_repo_env(out, DEFAULT_GIT_DIR_ENVIRONMENT);
 }
 
 static void prepare_submodule_repo_env_in_gitdir(struct strvec *out)
 {
-	prepare_submodule_repo_env_no_git_dir(out);
-	strvec_pushf(out, "%s=.", GIT_DIR_ENVIRONMENT);
+	prepare_other_repo_env(out, ".");
 }
 
 /*

t/helper/test-partial-clone.c

@@ -0,0 +1,43 @@
+#include "cache.h"
+#include "test-tool.h"
+#include "repository.h"
+#include "object-store.h"
+
+/*
+ * Prints the size of the object corresponding to the given hash in a specific
+ * gitdir. This is similar to "git -C gitdir cat-file -s", except that this
+ * exercises the code that accesses the object of an arbitrary repository that
+ * is not the_repository. ("git -C gitdir" makes it so that the_repository is
+ * the one in gitdir.)
+ */
+static void object_info(const char *gitdir, const char *oid_hex)
+{
+	struct repository r;
+	struct object_id oid;
+	unsigned long size;
+	struct object_info oi = {.sizep = &size};
+	const char *p;
+
+	if (repo_init(&r, gitdir, NULL))
+		die("could not init repo");
+	if (parse_oid_hex(oid_hex, &oid, &p))
+		die("could not parse oid");
+	if (oid_object_info_extended(&r, &oid, &oi, 0))
+		die("could not obtain object info");
+	printf("%d\n", (int) size);
+}
+
+int cmd__partial_clone(int argc, const char **argv)
+{
+	setup_git_directory();
+
+	if (argc < 4)
+		die("too few arguments");
+
+	if (!strcmp(argv[1], "object-info"))
+		object_info(argv[2], argv[3]);
+	else
+		die("invalid argument '%s'", argv[1]);
+
+	return 0;
+}

t/helper/test-tool.c

@@ -46,6 +46,7 @@ static struct test_cmd cmds[] = {
 	{ "online-cpus", cmd__online_cpus },
 	{ "parse-options", cmd__parse_options },
 	{ "parse-pathspec-file", cmd__parse_pathspec_file },
+	{ "partial-clone", cmd__partial_clone },
 	{ "path-utils", cmd__path_utils },
 	{ "pcre2-config", cmd__pcre2_config },
 	{ "pkt-line", cmd__pkt_line },

t/helper/test-tool.h

@@ -35,6 +35,7 @@ int cmd__oidmap(int argc, const char **argv);
 int cmd__online_cpus(int argc, const char **argv);
 int cmd__parse_options(int argc, const char **argv);
 int cmd__parse_pathspec_file(int argc, const char** argv);
+int cmd__partial_clone(int argc, const char **argv);
 int cmd__path_utils(int argc, const char **argv);
 int cmd__pcre2_config(int argc, const char **argv);
 int cmd__pkt_line(int argc, const char **argv);

t/t0410-partial-clone.sh

@@ -604,6 +604,29 @@ test_expect_success 'do not fetch when checking existence of tree we construct o
 	git -C repo cherry-pick side1
 '
 
+test_expect_success 'lazy-fetch when accessing object not in the_repository' '
+	rm -rf full partial.git &&
+	test_create_repo full &&
+	test_commit -C full create-a-file file.txt &&
+
+	test_config -C full uploadpack.allowfilter 1 &&
+	test_config -C full uploadpack.allowanysha1inwant 1 &&
+	git clone --filter=blob:none --bare "file://$(pwd)/full" partial.git &&
+	FILE_HASH=$(git -C full rev-parse HEAD:file.txt) &&
+
+	# Sanity check that the file is missing
+	git -C partial.git rev-list --objects --missing=print HEAD >out &&
+	grep "[?]$FILE_HASH" out &&
+
+	git -C full cat-file -s "$FILE_HASH" >expect &&
+	test-tool partial-clone object-info partial.git "$FILE_HASH" >actual &&
+	test_cmp expect actual &&
+
+	# Sanity check that the file is now present
+	git -C partial.git rev-list --objects --missing=print HEAD >out &&
+	! grep "[?]$FILE_HASH" out
+'
+
 . "$TEST_DIRECTORY"/lib-httpd.sh
 start_httpd