1 files changed, 482 insertions, 101 deletions

diff --git a/builtin/grep.c b/builtin/grep.c
index 69ac2d8797..9304c33e75 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -18,17 +18,27 @@
 #include "quote.h"
 #include "dir.h"
 #include "pathspec.h"
+#include "submodule.h"
+#include "submodule-config.h"
 
 static char const * const grep_usage[] = {
-	N_("git grep [options] [-e] <pattern> [<rev>...] [[--] <path>...]"),
+	N_("git grep [<options>] [-e] <pattern> [<rev>...] [[--] <path>...]"),
 	NULL
 };
 
-static int use_threads = 1;
+static const char *super_prefix;
+static int recurse_submodules;
+static struct argv_array submodule_options = ARGV_ARRAY_INIT;
+static const char *parent_basename;
+
+static int grep_submodule_launch(struct grep_opt *opt,
+				 const struct grep_source *gs);
+
+#define GREP_NUM_THREADS_DEFAULT 8
+static int num_threads;
 
 #ifndef NO_PTHREADS
-#define THREADS 8
-static pthread_t threads[THREADS];
+static pthread_t *threads;
 
 /* We use one producer thread and THREADS consumer
  * threads. The producer adds struct work_items to 'todo' and the
@@ -63,13 +73,13 @@ static pthread_mutex_t grep_mutex;
 
 static inline void grep_lock(void)
 {
-	if (use_threads)
+	if (num_threads)
 		pthread_mutex_lock(&grep_mutex);
 }
 
 static inline void grep_unlock(void)
 {
-	if (use_threads)
+	if (num_threads)
 		pthread_mutex_unlock(&grep_mutex);
 }
 
@@ -174,7 +184,10 @@ static void *run(void *arg)
 			break;
 
 		opt->output_priv = w;
-		hit |= grep_source(opt, &w->source);
+		if (w->source.type == GREP_SOURCE_SUBMODULE)
+			hit |= grep_submodule_launch(opt, &w->source);
+		else
+			hit |= grep_source(opt, &w->source);
 		grep_source_clear_data(&w->source);
 		work_done(w);
 	}
@@ -206,7 +219,8 @@ static void start_threads(struct grep_opt *opt)
 		strbuf_init(&todo[i].out, 0);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+	threads = xcalloc(num_threads, sizeof(*threads));
+	for (i = 0; i < num_threads; i++) {
 		int err;
 		struct grep_opt *o = grep_opt_dup(opt);
 		o->output = strbuf_out;
@@ -238,12 +252,14 @@ static int wait_all(void)
 	pthread_cond_broadcast(&cond_add);
 	grep_unlock();
 
-	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+	for (i = 0; i < num_threads; i++) {
 		void *h;
 		pthread_join(threads[i], &h);
 		hit |= (int) (intptr_t) h;
 	}
 
+	free(threads);
+
 	pthread_mutex_destroy(&grep_mutex);
 	pthread_mutex_destroy(&grep_read_mutex);
 	pthread_mutex_destroy(&grep_attr_mutex);
@@ -267,6 +283,14 @@ static int grep_cmd_config(const char *var, const char *value, void *cb)
 	int st = grep_config(var, value, cb);
 	if (git_color_default_config(var, value, cb) < 0)
 		st = -1;
+
+	if (!strcmp(var, "grep.threads")) {
+		num_threads = git_config_int(var, value);
+		if (num_threads < 0)
+			die(_("invalid number of threads specified (%d) for %s"),
+			    num_threads, var);
+	}
+
 	return st;
 }
 
@@ -289,12 +313,16 @@ static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1,
 	if (opt->relative && opt->prefix_length) {
 		quote_path_relative(filename + tree_name_len, opt->prefix, &pathbuf);
 		strbuf_insert(&pathbuf, 0, filename, tree_name_len);
+	} else if (super_prefix) {
+		strbuf_add(&pathbuf, filename, tree_name_len);
+		strbuf_addstr(&pathbuf, super_prefix);
+		strbuf_addstr(&pathbuf, filename + tree_name_len);
 	} else {
 		strbuf_addstr(&pathbuf, filename);
 	}
 
 #ifndef NO_PTHREADS
-	if (use_threads) {
+	if (num_threads) {
 		add_work(opt, GREP_SOURCE_SHA1, pathbuf.buf, path, sha1);
 		strbuf_release(&pathbuf);
 		return 0;
@@ -317,13 +345,16 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 {
 	struct strbuf buf = STRBUF_INIT;
 
-	if (opt->relative && opt->prefix_length)
+	if (opt->relative && opt->prefix_length) {
 		quote_path_relative(filename, opt->prefix, &buf);
-	else
+	} else {
+		if (super_prefix)
+			strbuf_addstr(&buf, super_prefix);
 		strbuf_addstr(&buf, filename);
+	}
 
 #ifndef NO_PTHREADS
-	if (use_threads) {
+	if (num_threads) {
 		add_work(opt, GREP_SOURCE_FILE, buf.buf, filename, filename);
 		strbuf_release(&buf);
 		return 0;
@@ -354,45 +385,323 @@ static void append_path(struct grep_opt *opt, const void *data, size_t len)
 static void run_pager(struct grep_opt *opt, const char *prefix)
 {
 	struct string_list *path_list = opt->output_priv;
-	const char **argv = xmalloc(sizeof(const char *) * (path_list->nr + 1));
+	struct child_process child = CHILD_PROCESS_INIT;
 	int i, status;
 
 	for (i = 0; i < path_list->nr; i++)
-		argv[i] = path_list->items[i].string;
-	argv[path_list->nr] = NULL;
+		argv_array_push(&child.args, path_list->items[i].string);
+	child.dir = prefix;
+	child.use_shell = 1;
 
-	if (prefix && chdir(prefix))
-		die(_("Failed to chdir: %s"), prefix);
-	status = run_command_v_opt(argv, RUN_USING_SHELL);
+	status = run_command(&child);
 	if (status)
 		exit(status);
-	free(argv);
 }
 
-static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec, int cached)
+static void compile_submodule_options(const struct grep_opt *opt,
+				      const struct pathspec *pathspec,
+				      int cached, int untracked,
+				      int opt_exclude, int use_index,
+				      int pattern_type_arg)
+{
+	struct grep_pat *pattern;
+	int i;
+
+	if (recurse_submodules)
+		argv_array_push(&submodule_options, "--recurse-submodules");
+
+	if (cached)
+		argv_array_push(&submodule_options, "--cached");
+	if (!use_index)
+		argv_array_push(&submodule_options, "--no-index");
+	if (untracked)
+		argv_array_push(&submodule_options, "--untracked");
+	if (opt_exclude > 0)
+		argv_array_push(&submodule_options, "--exclude-standard");
+
+	if (opt->invert)
+		argv_array_push(&submodule_options, "-v");
+	if (opt->ignore_case)
+		argv_array_push(&submodule_options, "-i");
+	if (opt->word_regexp)
+		argv_array_push(&submodule_options, "-w");
+	switch (opt->binary) {
+	case GREP_BINARY_NOMATCH:
+		argv_array_push(&submodule_options, "-I");
+		break;
+	case GREP_BINARY_TEXT:
+		argv_array_push(&submodule_options, "-a");
+		break;
+	default:
+		break;
+	}
+	if (opt->allow_textconv)
+		argv_array_push(&submodule_options, "--textconv");
+	if (opt->max_depth != -1)
+		argv_array_pushf(&submodule_options, "--max-depth=%d",
+				 opt->max_depth);
+	if (opt->linenum)
+		argv_array_push(&submodule_options, "-n");
+	if (!opt->pathname)
+		argv_array_push(&submodule_options, "-h");
+	if (!opt->relative)
+		argv_array_push(&submodule_options, "--full-name");
+	if (opt->name_only)
+		argv_array_push(&submodule_options, "-l");
+	if (opt->unmatch_name_only)
+		argv_array_push(&submodule_options, "-L");
+	if (opt->null_following_name)
+		argv_array_push(&submodule_options, "-z");
+	if (opt->count)
+		argv_array_push(&submodule_options, "-c");
+	if (opt->file_break)
+		argv_array_push(&submodule_options, "--break");
+	if (opt->heading)
+		argv_array_push(&submodule_options, "--heading");
+	if (opt->pre_context)
+		argv_array_pushf(&submodule_options, "--before-context=%d",
+				 opt->pre_context);
+	if (opt->post_context)
+		argv_array_pushf(&submodule_options, "--after-context=%d",
+				 opt->post_context);
+	if (opt->funcname)
+		argv_array_push(&submodule_options, "-p");
+	if (opt->funcbody)
+		argv_array_push(&submodule_options, "-W");
+	if (opt->all_match)
+		argv_array_push(&submodule_options, "--all-match");
+	if (opt->debug)
+		argv_array_push(&submodule_options, "--debug");
+	if (opt->status_only)
+		argv_array_push(&submodule_options, "-q");
+
+	switch (pattern_type_arg) {
+	case GREP_PATTERN_TYPE_BRE:
+		argv_array_push(&submodule_options, "-G");
+		break;
+	case GREP_PATTERN_TYPE_ERE:
+		argv_array_push(&submodule_options, "-E");
+		break;
+	case GREP_PATTERN_TYPE_FIXED:
+		argv_array_push(&submodule_options, "-F");
+		break;
+	case GREP_PATTERN_TYPE_PCRE:
+		argv_array_push(&submodule_options, "-P");
+		break;
+	case GREP_PATTERN_TYPE_UNSPECIFIED:
+		break;
+	}
+
+	for (pattern = opt->pattern_list; pattern != NULL;
+	     pattern = pattern->next) {
+		switch (pattern->token) {
+		case GREP_PATTERN:
+			argv_array_pushf(&submodule_options, "-e%s",
+					 pattern->pattern);
+			break;
+		case GREP_AND:
+		case GREP_OPEN_PAREN:
+		case GREP_CLOSE_PAREN:
+		case GREP_NOT:
+		case GREP_OR:
+			argv_array_push(&submodule_options, pattern->pattern);
+			break;
+		/* BODY and HEAD are not used by git-grep */
+		case GREP_PATTERN_BODY:
+		case GREP_PATTERN_HEAD:
+			break;
+		}
+	}
+
+	/*
+	 * Limit number of threads for child process to use.
+	 * This is to prevent potential fork-bomb behavior of git-grep as each
+	 * submodule process has its own thread pool.
+	 */
+	argv_array_pushf(&submodule_options, "--threads=%d",
+			 (num_threads + 1) / 2);
+
+	/* Add Pathspecs */
+	argv_array_push(&submodule_options, "--");
+	for (i = 0; i < pathspec->nr; i++)
+		argv_array_push(&submodule_options,
+				pathspec->items[i].original);
+}
+
+/*
+ * Launch child process to grep contents of a submodule
+ */
+static int grep_submodule_launch(struct grep_opt *opt,
+				 const struct grep_source *gs)
+{
+	struct child_process cp = CHILD_PROCESS_INIT;
+	int status, i;
+	const char *end_of_base;
+	const char *name;
+	struct work_item *w = opt->output_priv;
+
+	end_of_base = strchr(gs->name, ':');
+	if (gs->identifier && end_of_base)
+		name = end_of_base + 1;
+	else
+		name = gs->name;
+
+	prepare_submodule_repo_env(&cp.env_array);
+	argv_array_push(&cp.env_array, GIT_DIR_ENVIRONMENT);
+
+	/* Add super prefix */
+	argv_array_pushf(&cp.args, "--super-prefix=%s%s/",
+			 super_prefix ? super_prefix : "",
+			 name);
+	argv_array_push(&cp.args, "grep");
+
+	/*
+	 * Add basename of parent project
+	 * When performing grep on a tree object the filename is prefixed
+	 * with the object's name: 'tree-name:filename'.  In order to
+	 * provide uniformity of output we want to pass the name of the
+	 * parent project's object name to the submodule so the submodule can
+	 * prefix its output with the parent's name and not its own SHA1.
+	 */
+	if (gs->identifier && end_of_base)
+		argv_array_pushf(&cp.args, "--parent-basename=%.*s",
+				 (int) (end_of_base - gs->name),
+				 gs->name);
+
+	/* Add options */
+	for (i = 0; i < submodule_options.argc; i++) {
+		/*
+		 * If there is a tree identifier for the submodule, add the
+		 * rev after adding the submodule options but before the
+		 * pathspecs.  To do this we listen for the '--' and insert the
+		 * sha1 before pushing the '--' onto the child process argv
+		 * array.
+		 */
+		if (gs->identifier &&
+		    !strcmp("--", submodule_options.argv[i])) {
+			argv_array_push(&cp.args, sha1_to_hex(gs->identifier));
+		}
+
+		argv_array_push(&cp.args, submodule_options.argv[i]);
+	}
+
+	cp.git_cmd = 1;
+	cp.dir = gs->path;
+
+	/*
+	 * Capture output to output buffer and check the return code from the
+	 * child process.  A '0' indicates a hit, a '1' indicates no hit and
+	 * anything else is an error.
+	 */
+	status = capture_command(&cp, &w->out, 0);
+	if (status && (status != 1)) {
+		/* flush the buffer */
+		write_or_die(1, w->out.buf, w->out.len);
+		die("process for submodule '%s' failed with exit code: %d",
+		    gs->name, status);
+	}
+
+	/* invert the return code to make a hit equal to 1 */
+	return !status;
+}
+
+/*
+ * Prep grep structures for a submodule grep
+ * sha1: the sha1 of the submodule or NULL if using the working tree
+ * filename: name of the submodule including tree name of parent
+ * path: location of the submodule
+ */
+static int grep_submodule(struct grep_opt *opt, const unsigned char *sha1,
+			  const char *filename, const char *path)
+{
+	if (!is_submodule_initialized(path))
+		return 0;
+	if (!is_submodule_populated(path)) {
+		/*
+		 * If searching history, check for the presense of the
+		 * submodule's gitdir before skipping the submodule.
+		 */
+		if (sha1) {
+			const struct submodule *sub =
+					submodule_from_path(null_sha1, path);
+			if (sub)
+				path = git_path("modules/%s", sub->name);
+
+			if (!(is_directory(path) && is_git_directory(path)))
+				return 0;
+		} else {
+			return 0;
+		}
+	}
+
+#ifndef NO_PTHREADS
+	if (num_threads) {
+		add_work(opt, GREP_SOURCE_SUBMODULE, filename, path, sha1);
+		return 0;
+	} else
+#endif
+	{
+		struct work_item w;
+		int hit;
+
+		grep_source_init(&w.source, GREP_SOURCE_SUBMODULE,
+				 filename, path, sha1);
+		strbuf_init(&w.out, 0);
+		opt->output_priv = &w;
+		hit = grep_submodule_launch(opt, &w.source);
+
+		write_or_die(1, w.out.buf, w.out.len);
+
+		grep_source_clear(&w.source);
+		strbuf_release(&w.out);
+		return hit;
+	}
+}
+
+static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec,
+		      int cached)
 {
 	int hit = 0;
 	int nr;
+	struct strbuf name = STRBUF_INIT;
+	int name_base_len = 0;
+	if (super_prefix) {
+		name_base_len = strlen(super_prefix);
+		strbuf_addstr(&name, super_prefix);
+	}
+
 	read_cache();
 
 	for (nr = 0; nr < active_nr; nr++) {
 		const struct cache_entry *ce = active_cache[nr];
-		if (!S_ISREG(ce->ce_mode))
-			continue;
-		if (!ce_path_match(ce, pathspec, NULL))
+		strbuf_setlen(&name, name_base_len);
+		strbuf_addstr(&name, ce->name);
+
+		if (S_ISREG(ce->ce_mode) &&
+		    match_pathspec(pathspec, name.buf, name.len, 0, NULL,
+				   S_ISDIR(ce->ce_mode) ||
+				   S_ISGITLINK(ce->ce_mode))) {
+			/*
+			 * If CE_VALID is on, we assume worktree file and its
+			 * cache entry are identical, even if worktree file has
+			 * been modified, so use cache version instead
+			 */
+			if (cached || (ce->ce_flags & CE_VALID) ||
+			    ce_skip_worktree(ce)) {
+				if (ce_stage(ce) || ce_intent_to_add(ce))
+					continue;
+				hit |= grep_sha1(opt, ce->oid.hash, ce->name,
+						 0, ce->name);
+			} else {
+				hit |= grep_file(opt, ce->name);
+			}
+		} else if (recurse_submodules && S_ISGITLINK(ce->ce_mode) &&
+			   submodule_path_match(pathspec, name.buf, NULL)) {
+			hit |= grep_submodule(opt, NULL, ce->name, ce->name);
+		} else {
 			continue;
-		/*
-		 * If CE_VALID is on, we assume worktree file and its cache entry
-		 * are identical, even if worktree file has been modified, so use
-		 * cache version instead
-		 */
-		if (cached || (ce->ce_flags & CE_VALID) || ce_skip_worktree(ce)) {
-			if (ce_stage(ce))
-				continue;
-			hit |= grep_sha1(opt, ce->sha1, ce->name, 0, ce->name);
 		}
-		else
-			hit |= grep_file(opt, ce->name);
+
 		if (ce_stage(ce)) {
 			do {
 				nr++;
@@ -403,6 +712,8 @@ static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec, int
 		if (hit && opt->status_only)
 			break;
 	}
+
+	strbuf_release(&name);
 	return hit;
 }
 
@@ -414,12 +725,22 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 	enum interesting match = entry_not_interesting;
 	struct name_entry entry;
 	int old_baselen = base->len;
+	struct strbuf name = STRBUF_INIT;
+	int name_base_len = 0;
+	if (super_prefix) {
+		strbuf_addstr(&name, super_prefix);
+		name_base_len = name.len;
+	}
 
 	while (tree_entry(tree, &entry)) {
 		int te_len = tree_entry_len(&entry);
 
 		if (match != all_entries_interesting) {
-			match = tree_entry_interesting(&entry, base, tn_len, pathspec);
+			strbuf_addstr(&name, base->buf + tn_len);
+			match = tree_entry_interesting(&entry, &name,
+						       0, pathspec);
+			strbuf_setlen(&name, name_base_len);
+
 			if (match == all_entries_not_interesting)
 				break;
 			if (match == entry_not_interesting)
@@ -429,39 +750,44 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 		strbuf_add(base, entry.path, te_len);
 
 		if (S_ISREG(entry.mode)) {
-			hit |= grep_sha1(opt, entry.sha1, base->buf, tn_len,
+			hit |= grep_sha1(opt, entry.oid->hash, base->buf, tn_len,
 					 check_attr ? base->buf + tn_len : NULL);
-		}
-		else if (S_ISDIR(entry.mode)) {
+		} else if (S_ISDIR(entry.mode)) {
 			enum object_type type;
 			struct tree_desc sub;
 			void *data;
 			unsigned long size;
 
-			data = lock_and_read_sha1_file(entry.sha1, &type, &size);
+			data = lock_and_read_sha1_file(entry.oid->hash, &type, &size);
 			if (!data)
 				die(_("unable to read tree (%s)"),
-				    sha1_to_hex(entry.sha1));
+				    oid_to_hex(entry.oid));
 
 			strbuf_addch(base, '/');
 			init_tree_desc(&sub, data, size);
 			hit |= grep_tree(opt, pathspec, &sub, base, tn_len,
 					 check_attr);
 			free(data);
+		} else if (recurse_submodules && S_ISGITLINK(entry.mode)) {
+			hit |= grep_submodule(opt, entry.oid->hash, base->buf,
+					      base->buf + tn_len);
 		}
+
 		strbuf_setlen(base, old_baselen);
 
 		if (hit && opt->status_only)
 			break;
 	}
+
+	strbuf_release(&name);
 	return hit;
 }
 
 static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec,
-		       struct object *obj, const char *name, struct object_context *oc)
+		       struct object *obj, const char *name, const char *path)
 {
 	if (obj->type == OBJ_BLOB)
-		return grep_sha1(opt, obj->sha1, name, 0, oc ? oc->path : NULL);
+		return grep_sha1(opt, obj->oid.hash, name, 0, path);
 	if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) {
 		struct tree_desc tree;
 		void *data;
@@ -470,12 +796,16 @@ static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec,
 		int hit, len;
 
 		grep_read_lock();
-		data = read_object_with_reference(obj->sha1, tree_type,
+		data = read_object_with_reference(obj->oid.hash, tree_type,
 						  &size, NULL);
 		grep_read_unlock();
 
 		if (!data)
-			die(_("unable to read tree (%s)"), sha1_to_hex(obj->sha1));
+			die(_("unable to read tree (%s)"), oid_to_hex(&obj->oid));
+
+		/* Use parent's name as base when recursing submodules */
+		if (recurse_submodules && parent_basename)
+			name = parent_basename;
 
 		len = name ? strlen(name) : 0;
 		strbuf_init(&base, PATH_MAX + len + 1);
@@ -503,7 +833,13 @@ static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec,
 	for (i = 0; i < nr; i++) {
 		struct object *real_obj;
 		real_obj = deref_tag(list->objects[i].item, NULL, 0);
-		if (grep_object(opt, pathspec, real_obj, list->objects[i].name, list->objects[i].context)) {
+
+		/* load the gitmodules file for this rev */
+		if (recurse_submodules) {
+			submodule_free();
+			gitmodules_config_sha1(real_obj->oid.hash);
+		}
+		if (grep_object(opt, pathspec, real_obj, list->objects[i].name, list->objects[i].path)) {
 			hit = 1;
 			if (opt->status_only)
 				break;
@@ -513,12 +849,14 @@ static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec,
 }
 
 static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec,
-			  int exc_std)
+			  int exc_std, int use_index)
 {
 	struct dir_struct dir;
 	int i, hit = 0;
 
 	memset(&dir, 0, sizeof(dir));
+	if (!use_index)
+		dir.flags |= DIR_NO_GITLINKS;
 	if (exc_std)
 		setup_standard_excludes(&dir);
 
@@ -564,7 +902,7 @@ static int file_callback(const struct option *opt, const char *arg, int unset)
 	patterns = from_stdin ? stdin : fopen(arg, "r");
 	if (!patterns)
 		die_errno(_("cannot open '%s'"), arg);
-	while (strbuf_getline(&sb, patterns, '\n') == 0) {
+	while (strbuf_getline(&sb, patterns) == 0) {
 		/* ignore empty line like grep does */
 		if (sb.len == 0)
 			continue;
@@ -614,11 +952,6 @@ static int pattern_callback(const struct option *opt, const char *arg,
 	return 0;
 }
 
-static int help_callback(const struct option *opt, const char *arg, int unset)
-{
-	return -1;
-}
-
 int cmd_grep(int argc, const char **argv, const char *prefix)
 {
 	int hit = 0;
@@ -634,6 +967,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	int dummy;
 	int use_index = 1;
 	int pattern_type_arg = GREP_PATTERN_TYPE_UNSPECIFIED;
+	int allow_revs;
 
 	struct option options[] = {
 		OPT_BOOL(0, "cached", &cached,
@@ -643,7 +977,12 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		OPT_BOOL(0, "untracked", &untracked,
 			N_("search in both tracked and untracked files")),
 		OPT_SET_INT(0, "exclude-standard", &opt_exclude,
-			    N_("search also in ignored files"), 1),
+			    N_("ignore files specified via '.gitignore'"), 1),
+		OPT_BOOL(0, "recurse-submodules", &recurse_submodules,
+			 N_("recursivley search in each submodule")),
+		OPT_STRING(0, "parent-basename", &parent_basename,
+			   N_("basename"),
+			   N_("prepend parent project's basename to output")),
 		OPT_GROUP(""),
 		OPT_BOOL('v', "invert-match", &opt.invert,
 			N_("show non-matching lines")),
@@ -704,6 +1043,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 			N_("show <n> context lines before matches")),
 		OPT_INTEGER('A', "after-context", &opt.post_context,
 			N_("show <n> context lines after matches")),
+		OPT_INTEGER(0, "threads", &num_threads,
+			N_("use <n> worker threads")),
 		OPT_NUMBER_CALLBACK(&opt, N_("shortcut for -C NUM"),
 			context_callback),
 		OPT_BOOL('p', "show-function", &opt.funcname,
@@ -740,21 +1081,13 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 			PARSE_OPT_OPTARG, NULL, (intptr_t)default_pager },
 		OPT_BOOL(0, "ext-grep", &external_grep_allowed__ignored,
 			 N_("allow calling of grep(1) (ignored by this build)")),
-		{ OPTION_CALLBACK, 0, "help-all", &options, NULL, N_("show usage"),
-		  PARSE_OPT_HIDDEN | PARSE_OPT_NOARG, help_callback },
 		OPT_END()
 	};
 
-	/*
-	 * 'git grep -h', unlike 'git grep -h <pattern>', is a request
-	 * to show usage information and exit.
-	 */
-	if (argc == 2 && !strcmp(argv[1], "-h"))
-		usage_with_options(grep_usage, options);
-
 	init_grep_defaults();
 	git_config(grep_cmd_config, NULL);
 	grep_init(&opt, prefix);
+	super_prefix = get_super_prefix();
 
 	/*
 	 * If there is no -- then the paths must exist in the working
@@ -768,13 +1101,18 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	 */
 	argc = parse_options(argc, argv, prefix, options, grep_usage,
 			     PARSE_OPT_KEEP_DASHDASH |
-			     PARSE_OPT_STOP_AT_NON_OPTION |
-			     PARSE_OPT_NO_INTERNAL_HELP);
+			     PARSE_OPT_STOP_AT_NON_OPTION);
 	grep_commit_pattern_type(pattern_type_arg, &opt);
 
-	if (use_index && !startup_info->have_repository)
-		/* die the same way as if we did it at the beginning */
-		setup_git_directory();
+	if (use_index && !startup_info->have_repository) {
+		int fallback = 0;
+		git_config_get_bool("grep.fallbacktonoindex", &fallback);
+		if (fallback)
+			use_index = 0;
+		else
+			/* die the same way as if we did it at the beginning */
+			setup_git_directory();
+	}
 
 	/*
 	 * skip a -- separator; we know it cannot be
@@ -803,7 +1141,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		opt.output_priv = &path_list;
 		opt.output = append_path;
 		string_list_append(&path_list, show_in_pager);
-		use_threads = 0;
 	}
 
 	if (!opt.pattern_list)
@@ -813,35 +1150,82 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 
 	compile_grep_patterns(&opt);
 
-	/* Check revs and then paths */
+	/*
+	 * We have to find "--" in a separate pass, because its presence
+	 * influences how we will parse arguments that come before it.
+	 */
+	for (i = 0; i < argc; i++) {
+		if (!strcmp(argv[i], "--")) {
+			seen_dashdash = 1;
+			break;
+		}
+	}
+
+	/*
+	 * Resolve any rev arguments. If we have a dashdash, then everything up
+	 * to it must resolve as a rev. If not, then we stop at the first
+	 * non-rev and assume everything else is a path.
+	 */
+	allow_revs = use_index && !untracked;
 	for (i = 0; i < argc; i++) {
 		const char *arg = argv[i];
 		unsigned char sha1[20];
 		struct object_context oc;
-		/* Is it a rev? */
-		if (!get_sha1_with_context(arg, 0, sha1, &oc)) {
-			struct object *object = parse_object_or_die(sha1, arg);
-			if (!seen_dashdash)
-				verify_non_filename(prefix, arg);
-			add_object_array_with_context(object, arg, &list, xmemdupz(&oc, sizeof(struct object_context)));
-			continue;
-		}
+		struct object *object;
+
 		if (!strcmp(arg, "--")) {
 			i++;
-			seen_dashdash = 1;
+			break;
 		}
-		break;
+
+		if (!allow_revs) {
+			if (seen_dashdash)
+				die(_("--no-index or --untracked cannot be used with revs"));
+			break;
+		}
+
+		if (get_sha1_with_context(arg, 0, sha1, &oc)) {
+			if (seen_dashdash)
+				die(_("unable to resolve revision: %s"), arg);
+			break;
+		}
+
+		object = parse_object_or_die(sha1, arg);
+		if (!seen_dashdash)
+			verify_non_filename(prefix, arg);
+		add_object_array_with_path(object, arg, &list, oc.mode, oc.path);
+	}
+
+	/*
+	 * Anything left over is presumed to be a path. But in the non-dashdash
+	 * "do what I mean" case, we verify and complain when that isn't true.
+	 */
+	if (!seen_dashdash) {
+		int j;
+		for (j = i; j < argc; j++)
+			verify_filename(prefix, argv[j], j == i && allow_revs);
 	}
 
+	parse_pathspec(&pathspec, 0,
+		       PATHSPEC_PREFER_CWD |
+		       (opt.max_depth != -1 ? PATHSPEC_MAXDEPTH_VALID : 0),
+		       prefix, argv + i);
+	pathspec.max_depth = opt.max_depth;
+	pathspec.recursive = 1;
+
 #ifndef NO_PTHREADS
-	if (list.nr || cached || online_cpus() == 1)
-		use_threads = 0;
+	if (list.nr || cached || show_in_pager)
+		num_threads = 0;
+	else if (num_threads == 0)
+		num_threads = GREP_NUM_THREADS_DEFAULT;
+	else if (num_threads < 0)
+		die(_("invalid number of threads specified (%d)"), num_threads);
 #else
-	use_threads = 0;
+	num_threads = 0;
 #endif
 
 #ifndef NO_PTHREADS
-	if (use_threads) {
+	if (num_threads) {
 		if (!(opt.name_only || opt.unmatch_name_only || opt.count)
 		    && (opt.pre_context || opt.post_context ||
 			opt.file_break || opt.funcbody))
@@ -850,20 +1234,13 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	}
 #endif
 
-	/* The rest are paths */
-	if (!seen_dashdash) {
-		int j;
-		for (j = i; j < argc; j++)
-			verify_filename(prefix, argv[j], j == i);
+	if (recurse_submodules) {
+		gitmodules_config();
+		compile_submodule_options(&opt, &pathspec, cached, untracked,
+					  opt_exclude, use_index,
+					  pattern_type_arg);
 	}
 
-	parse_pathspec(&pathspec, 0,
-		       PATHSPEC_PREFER_CWD |
-		       (opt.max_depth != -1 ? PATHSPEC_MAXDEPTH_VALID : 0),
-		       prefix, argv + i);
-	pathspec.max_depth = opt.max_depth;
-	pathspec.recursive = 1;
-
 	if (show_in_pager && (cached || list.nr))
 		die(_("--open-files-in-pager only works on the worktree"));
 
@@ -874,6 +1251,9 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		if (len > 4 && is_dir_sep(pager[len - 5]))
 			pager += len - 4;
 
+		if (opt.ignore_case && !strcmp("less", pager))
+			string_list_append(&path_list, "-I");
+
 		if (!strcmp("less", pager) || !strcmp("vi", pager)) {
 			struct strbuf buf = STRBUF_INIT;
 			strbuf_addf(&buf, "+/%s%s",
@@ -884,7 +1264,10 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	if (!show_in_pager)
+	if (recurse_submodules && (!use_index || untracked))
+		die(_("option not supported with --recurse-submodules."));
+
+	if (!show_in_pager && !opt.status_only)
 		setup_pager();
 
 	if (!use_index && (untracked || cached))
@@ -892,9 +1275,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 
 	if (!use_index || untracked) {
 		int use_exclude = (opt_exclude < 0) ? use_index : !!opt_exclude;
-		if (list.nr)
-			die(_("--no-index or --untracked cannot be used with revs."));
-		hit = grep_directory(&opt, &pathspec, use_exclude);
+		hit = grep_directory(&opt, &pathspec, use_exclude, use_index);
 	} else if (0 <= opt_exclude) {
 		die(_("--[no-]exclude-standard cannot be used for tracked contents."));
 	} else if (!list.nr) {
@@ -908,7 +1289,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		hit = grep_objects(&opt, &pathspec, &list);
 	}
 
-	if (use_threads)
+	if (num_threads)
 		hit |= wait_all();
 	if (hit && show_in_pager)
 		run_pager(&opt, prefix);