Merge branch 'mt/threaded-grep-in-object-store'

Traditionally, we avoided threaded grep while searching in objects
(as opposed to files in the working tree) as accesses to the object
layer is not thread-safe.  This limitation is getting lifted.

* mt/threaded-grep-in-object-store:
  grep: use no. of cores as the default no. of threads
  grep: move driver pre-load out of critical section
  grep: re-enable threads in non-worktree case
  grep: protect packed_git [re-]initialization
  grep: allow submodule functions to run in parallel
  submodule-config: add skip_if_read option to repo_read_gitmodules()
  grep: replace grep_read_mutex by internal obj read lock
  object-store: allow threaded access to object reading
  replace-object: make replace operations thread-safe
  grep: fix racy calls in grep_objects()
  grep: fix race conditions at grep_submodule()
  grep: fix race conditions on userdiff calls

1 files changed, 46 insertions, 47 deletions

diff --git a/builtin/grep.c b/builtin/grep.c
index ae2d5bbafc..99e2685090 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -24,6 +24,7 @@
 #include "submodule.h"
 #include "submodule-config.h"
 #include "object-store.h"
+#include "packfile.h"
 
 static char const * const grep_usage[] = {
 	N_("git grep [<options>] [-e] <pattern> [<rev>...] [[--] <path>...]"),
@@ -32,7 +33,6 @@ static char const * const grep_usage[] = {
 
 static int recurse_submodules;
 
-#define GREP_NUM_THREADS_DEFAULT 8
 static int num_threads;
 
 static pthread_t *threads;
@@ -91,8 +91,11 @@ static pthread_cond_t cond_result;
 
 static int skip_first_line;
 
-static void add_work(struct grep_opt *opt, const struct grep_source *gs)
+static void add_work(struct grep_opt *opt, struct grep_source *gs)
 {
+	if (opt->binary != GREP_BINARY_TEXT)
+		grep_source_load_driver(gs, opt->repo->index);
+
 	grep_lock();
 
 	while ((todo_end+1) % ARRAY_SIZE(todo) == todo_done) {
@@ -100,9 +103,6 @@ static void add_work(struct grep_opt *opt, const struct grep_source *gs)
 	}
 
 	todo[todo_end].source = *gs;
-	if (opt->binary != GREP_BINARY_TEXT)
-		grep_source_load_driver(&todo[todo_end].source,
-					opt->repo->index);
 	todo[todo_end].done = 0;
 	strbuf_reset(&todo[todo_end].out);
 	todo_end = (todo_end + 1) % ARRAY_SIZE(todo);
@@ -200,12 +200,12 @@ static void start_threads(struct grep_opt *opt)
 	int i;
 
 	pthread_mutex_init(&grep_mutex, NULL);
-	pthread_mutex_init(&grep_read_mutex, NULL);
 	pthread_mutex_init(&grep_attr_mutex, NULL);
 	pthread_cond_init(&cond_add, NULL);
 	pthread_cond_init(&cond_write, NULL);
 	pthread_cond_init(&cond_result, NULL);
 	grep_use_locks = 1;
+	enable_obj_read_lock();
 
 	for (i = 0; i < ARRAY_SIZE(todo); i++) {
 		strbuf_init(&todo[i].out, 0);
@@ -257,12 +257,12 @@ static int wait_all(void)
 	free(threads);
 
 	pthread_mutex_destroy(&grep_mutex);
-	pthread_mutex_destroy(&grep_read_mutex);
 	pthread_mutex_destroy(&grep_attr_mutex);
 	pthread_cond_destroy(&cond_add);
 	pthread_cond_destroy(&cond_write);
 	pthread_cond_destroy(&cond_result);
 	grep_use_locks = 0;
+	disable_obj_read_lock();
 
 	return hit;
 }
@@ -295,16 +295,6 @@ static int grep_cmd_config(const char *var, const char *value, void *cb)
 	return st;
 }
 
-static void *lock_and_read_oid_file(const struct object_id *oid, enum object_type *type, unsigned long *size)
-{
-	void *data;
-
-	grep_read_lock();
-	data = read_object_file(oid, type, size);
-	grep_read_unlock();
-	return data;
-}
-
 static int grep_oid(struct grep_opt *opt, const struct object_id *oid,
 		     const char *filename, int tree_name_len,
 		     const char *path)
@@ -407,30 +397,28 @@ static int grep_submodule(struct grep_opt *opt,
 {
 	struct repository subrepo;
 	struct repository *superproject = opt->repo;
-	const struct submodule *sub = submodule_from_path(superproject,
-							  &null_oid, path);
+	const struct submodule *sub;
 	struct grep_opt subopt;
 	int hit;
 
-	/*
-	 * NEEDSWORK: submodules functions need to be protected because they
-	 * access the object store via config_from_gitmodules(): the latter
-	 * uses get_oid() which, for now, relies on the global the_repository
-	 * object.
-	 */
-	grep_read_lock();
+	sub = submodule_from_path(superproject, &null_oid, path);
 
-	if (!is_submodule_active(superproject, path)) {
-		grep_read_unlock();
+	if (!is_submodule_active(superproject, path))
 		return 0;
-	}
 
-	if (repo_submodule_init(&subrepo, superproject, sub)) {
-		grep_read_unlock();
+	if (repo_submodule_init(&subrepo, superproject, sub))
 		return 0;
-	}
 
-	repo_read_gitmodules(&subrepo);
+	/*
+	 * NEEDSWORK: repo_read_gitmodules() might call
+	 * add_to_alternates_memory() via config_from_gitmodules(). This
+	 * operation causes a race condition with concurrent object readings
+	 * performed by the worker threads. That's why we need obj_read_lock()
+	 * here. It should be removed once it's no longer necessary to add the
+	 * subrepo's odbs to the in-memory alternates list.
+	 */
+	obj_read_lock();
+	repo_read_gitmodules(&subrepo, 0);
 
 	/*
 	 * NEEDSWORK: This adds the submodule's object directory to the list of
@@ -443,7 +431,7 @@ static int grep_submodule(struct grep_opt *opt,
 	 * object.
 	 */
 	add_to_alternates_memory(subrepo.objects->odb->path);
-	grep_read_unlock();
+	obj_read_unlock();
 
 	memcpy(&subopt, opt, sizeof(subopt));
 	subopt.repo = &subrepo;
@@ -455,14 +443,12 @@ static int grep_submodule(struct grep_opt *opt,
 		unsigned long size;
 		struct strbuf base = STRBUF_INIT;
 
+		obj_read_lock();
 		object = parse_object_or_die(oid, oid_to_hex(oid));
-
-		grep_read_lock();
+		obj_read_unlock();
 		data = read_object_with_reference(&subrepo,
 						  &object->oid, tree_type,
 						  &size, NULL);
-		grep_read_unlock();
-
 		if (!data)
 			die(_("unable to read tree (%s)"), oid_to_hex(&object->oid));
 
@@ -587,7 +573,7 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 			void *data;
 			unsigned long size;
 
-			data = lock_and_read_oid_file(&entry.oid, &type, &size);
+			data = read_object_file(&entry.oid, &type, &size);
 			if (!data)
 				die(_("unable to read tree (%s)"),
 				    oid_to_hex(&entry.oid));
@@ -625,12 +611,9 @@ static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec,
 		struct strbuf base;
 		int hit, len;
 
-		grep_read_lock();
 		data = read_object_with_reference(opt->repo,
 						  &obj->oid, tree_type,
 						  &size, NULL);
-		grep_read_unlock();
-
 		if (!data)
 			die(_("unable to read tree (%s)"), oid_to_hex(&obj->oid));
 
@@ -659,13 +642,18 @@ static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec,
 
 	for (i = 0; i < nr; i++) {
 		struct object *real_obj;
+
+		obj_read_lock();
 		real_obj = deref_tag(opt->repo, list->objects[i].item,
 				     NULL, 0);
+		obj_read_unlock();
 
 		/* load the gitmodules file for this rev */
 		if (recurse_submodules) {
 			submodule_free(opt->repo);
+			obj_read_lock();
 			gitmodules_config_oid(&real_obj->oid);
+			obj_read_unlock();
 		}
 		if (grep_object(opt, pathspec, real_obj, list->objects[i].name,
 				list->objects[i].path)) {
@@ -1065,7 +1053,10 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	pathspec.recursive = 1;
 	pathspec.recurse_submodules = !!recurse_submodules;
 
-	if (list.nr || cached || show_in_pager) {
+	if (recurse_submodules && untracked)
+		die(_("--untracked not supported with --recurse-submodules"));
+
+	if (show_in_pager) {
 		if (num_threads > 1)
 			warning(_("invalid option combination, ignoring --threads"));
 		num_threads = 1;
@@ -1075,7 +1066,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	} else if (num_threads < 0)
 		die(_("invalid number of threads specified (%d)"), num_threads);
 	else if (num_threads == 0)
-		num_threads = HAVE_THREADS ? GREP_NUM_THREADS_DEFAULT : 1;
+		num_threads = HAVE_THREADS ? online_cpus() : 1;
 
 	if (num_threads > 1) {
 		if (!HAVE_THREADS)
@@ -1084,6 +1075,17 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		    && (opt.pre_context || opt.post_context ||
 			opt.file_break || opt.funcbody))
 			skip_first_line = 1;
+
+		/*
+		 * Pre-read gitmodules (if not read already) and force eager
+		 * initialization of packed_git to prevent racy lazy
+		 * reading/initialization once worker threads are started.
+		 */
+		if (recurse_submodules)
+			repo_read_gitmodules(the_repository, 1);
+		if (startup_info->have_repository)
+			(void)get_packed_git(the_repository);
+
 		start_threads(&opt);
 	} else {
 		/*
@@ -1118,9 +1120,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	if (recurse_submodules && untracked)
-		die(_("--untracked not supported with --recurse-submodules"));
-
 	if (!show_in_pager && !opt.status_only)
 		setup_pager();