1 files changed, 128 insertions, 54 deletions
diff --git a/dir.c b/dir.c
index c617dc763b..23b4417268 100644
--- a/dir.c
+++ b/dir.c
@@ -53,10 +53,15 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 	int check_only, int stop_at_first_file, const struct pathspec *pathspec);
 static int resolve_dtype(int dtype, struct index_state *istate,
 			 const char *path, int len);
-
-void dir_init(struct dir_struct *dir)
+struct dirent *readdir_skip_dot_and_dotdot(DIR *dirp)
 {
-	memset(dir, 0, sizeof(*dir));
+	struct dirent *e;
+
+	while ((e = readdir(dirp)) != NULL) {
+		if (!is_dot_or_dotdot(e->d_name))
+			break;
+	}
+	return e;
 }
 
 int count_slashes(const char *s)
@@ -73,11 +78,21 @@ int fspathcmp(const char *a, const char *b)
 	return ignore_case ? strcasecmp(a, b) : strcmp(a, b);
 }
 
+int fspatheq(const char *a, const char *b)
+{
+	return !fspathcmp(a, b);
+}
+
 int fspathncmp(const char *a, const char *b, size_t count)
 {
 	return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
 }
 
+unsigned int fspathhash(const char *str)
+{
+	return ignore_case ? strihash(str) : strhash(str);
+}
+
 int git_fnmatch(const struct pathspec_item *item,
 		const char *pattern, const char *string,
 		int prefix)
@@ -1365,7 +1380,7 @@ enum pattern_match_result path_matches_pattern_list(
 	struct path_pattern *pattern;
 	struct strbuf parent_pathname = STRBUF_INIT;
 	int result = NOT_MATCHED;
-	const char *slash_pos;
+	size_t slash_pos;
 
 	if (!pl->use_cone_patterns) {
 		pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
@@ -1386,21 +1401,35 @@ enum pattern_match_result path_matches_pattern_list(
 	strbuf_addch(&parent_pathname, '/');
 	strbuf_add(&parent_pathname, pathname, pathlen);
 
+	/*
+	 * Directory entries are matched if and only if a file
+	 * contained immediately within them is matched. For the
+	 * case of a directory entry, modify the path to create
+	 * a fake filename within this directory, allowing us to
+	 * use the file-base matching logic in an equivalent way.
+	 */
+	if (parent_pathname.len > 0 &&
+	    parent_pathname.buf[parent_pathname.len - 1] == '/') {
+		slash_pos = parent_pathname.len - 1;
+		strbuf_add(&parent_pathname, "-", 1);
+	} else {
+		const char *slash_ptr = strrchr(parent_pathname.buf, '/');
+		slash_pos = slash_ptr ? slash_ptr - parent_pathname.buf : 0;
+	}
+
 	if (hashmap_contains_path(&pl->recursive_hashmap,
 				  &parent_pathname)) {
 		result = MATCHED_RECURSIVE;
 		goto done;
 	}
 
-	slash_pos = strrchr(parent_pathname.buf, '/');
-
-	if (slash_pos == parent_pathname.buf) {
+	if (!slash_pos) {
 		/* include every file in root */
 		result = MATCHED;
 		goto done;
 	}
 
-	strbuf_setlen(&parent_pathname, slash_pos - parent_pathname.buf);
+	strbuf_setlen(&parent_pathname, slash_pos);
 
 	if (hashmap_contains_path(&pl->parent_hashmap, &parent_pathname)) {
 		result = MATCHED;
@@ -1749,13 +1778,13 @@ static enum exist_status directory_exists_in_index(struct index_state *istate,
  * Case 3: if we didn't have it in the index previously, we
  * have a few sub-cases:
  *
- *  (a) if "show_other_directories" is true, we show it as
- *      just a directory, unless "hide_empty_directories" is
+ *  (a) if DIR_SHOW_OTHER_DIRECTORIES flag is set, we show it as
+ *      just a directory, unless DIR_HIDE_EMPTY_DIRECTORIES is
  *      also true, in which case we need to check if it contains any
  *      untracked and / or ignored files.
- *  (b) if it looks like a git directory, and we don't have
- *      'no_gitlinks' set we treat it as a gitlink, and show it
- *      as a directory.
+ *  (b) if it looks like a git directory and we don't have the
+ *      DIR_NO_GITLINKS flag, then we treat it as a gitlink, and
+ *      show it as a directory.
  *  (c) otherwise, we recurse into it.
  */
 static enum path_treatment treat_directory(struct dir_struct *dir,
@@ -1843,7 +1872,7 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
 		return path_recurse;
 	}
 
-	/* This is the "show_other_directories" case */
+	assert(dir->flags & DIR_SHOW_OTHER_DIRECTORIES);
 
 	/*
 	 * If we have a pathspec which could match something _below_ this
@@ -1854,27 +1883,42 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
 	if (matches_how == MATCHED_RECURSIVELY_LEADING_PATHSPEC)
 		return path_recurse;
 
+	/* Special cases for where this directory is excluded/ignored */
+	if (excluded) {
+		/*
+		 * If DIR_SHOW_OTHER_DIRECTORIES is set and we're not
+		 * hiding empty directories, there is no need to
+		 * recurse into an ignored directory.
+		 */
+		if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
+			return path_excluded;
+
+		/*
+		 * Even if we are hiding empty directories, we can still avoid
+		 * recursing into ignored directories for DIR_SHOW_IGNORED_TOO
+		 * if DIR_SHOW_IGNORED_TOO_MODE_MATCHING is also set.
+		 */
+		if ((dir->flags & DIR_SHOW_IGNORED_TOO) &&
+		    (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING))
+			return path_excluded;
+	}
+
 	/*
-	 * Other than the path_recurse case immediately above, we only need
-	 * to recurse into untracked/ignored directories if either of the
-	 * following bits is set:
-	 *   - DIR_SHOW_IGNORED_TOO (because then we need to determine if
-	 *                           there are ignored entries below)
+	 * Other than the path_recurse case above, we only need to
+	 * recurse into untracked directories if any of the following
+	 * bits is set:
+	 *   - DIR_SHOW_IGNORED (because then we need to determine if
+	 *                       there are ignored entries below)
+	 *   - DIR_SHOW_IGNORED_TOO (same as above)
 	 *   - DIR_HIDE_EMPTY_DIRECTORIES (because we have to determine if
 	 *                                 the directory is empty)
 	 */
-	if (!(dir->flags & (DIR_SHOW_IGNORED_TOO | DIR_HIDE_EMPTY_DIRECTORIES)))
-		return excluded ? path_excluded : path_untracked;
-
-	/*
-	 * ...and even if DIR_SHOW_IGNORED_TOO is set, we can still avoid
-	 * recursing into ignored directories if the path is excluded and
-	 * DIR_SHOW_IGNORED_TOO_MODE_MATCHING is also set.
-	 */
-	if (excluded &&
-	    (dir->flags & DIR_SHOW_IGNORED_TOO) &&
-	    (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING))
-		return path_excluded;
+	if (!excluded &&
+	    !(dir->flags & (DIR_SHOW_IGNORED |
+			    DIR_SHOW_IGNORED_TOO |
+			    DIR_HIDE_EMPTY_DIRECTORIES))) {
+		return path_untracked;
+	}
 
 	/*
 	 * Even if we don't want to know all the paths under an untracked or
@@ -2326,7 +2370,7 @@ static int read_cached_dir(struct cached_dir *cdir)
 	struct dirent *de;
 
 	if (cdir->fdir) {
-		de = readdir(cdir->fdir);
+		de = readdir_skip_dot_and_dotdot(cdir->fdir);
 		if (!de) {
 			cdir->d_name = NULL;
 			cdir->d_type = DT_UNKNOWN;
@@ -2440,6 +2484,7 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 
 	if (open_cached_dir(&cdir, dir, untracked, istate, &path, check_only))
 		goto out;
+	dir->visited_directories++;
 
 	if (untracked)
 		untracked->check_only = !!check_only;
@@ -2448,6 +2493,7 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 		/* check how the file or directory should be treated */
 		state = treat_path(dir, untracked, &cdir, istate, &path,
 				   baselen, pathspec);
+		dir->visited_paths++;
 
 		if (state > dir_state)
 			dir_state = state;
@@ -2760,15 +2806,53 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d
 	return root;
 }
 
+static void emit_traversal_statistics(struct dir_struct *dir,
+				      struct repository *repo,
+				      const char *path,
+				      int path_len)
+{
+	if (!trace2_is_enabled())
+		return;
+
+	if (!path_len) {
+		trace2_data_string("read_directory", repo, "path", "");
+	} else {
+		struct strbuf tmp = STRBUF_INIT;
+		strbuf_add(&tmp, path, path_len);
+		trace2_data_string("read_directory", repo, "path", tmp.buf);
+		strbuf_release(&tmp);
+	}
+
+	trace2_data_intmax("read_directory", repo,
+			   "directories-visited", dir->visited_directories);
+	trace2_data_intmax("read_directory", repo,
+			   "paths-visited", dir->visited_paths);
+
+	if (!dir->untracked)
+		return;
+	trace2_data_intmax("read_directory", repo,
+			   "node-creation", dir->untracked->dir_created);
+	trace2_data_intmax("read_directory", repo,
+			   "gitignore-invalidation",
+			   dir->untracked->gitignore_invalidated);
+	trace2_data_intmax("read_directory", repo,
+			   "directory-invalidation",
+			   dir->untracked->dir_invalidated);
+	trace2_data_intmax("read_directory", repo,
+			   "opendir", dir->untracked->dir_opened);
+}
+
 int read_directory(struct dir_struct *dir, struct index_state *istate,
 		   const char *path, int len, const struct pathspec *pathspec)
 {
 	struct untracked_cache_dir *untracked;
 
-	trace_performance_enter();
+	trace2_region_enter("dir", "read_directory", istate->repo);
+	dir->visited_paths = 0;
+	dir->visited_directories = 0;
 
 	if (has_symlink_leading_path(path, len)) {
-		trace_performance_leave("read directory %.*s", len, path);
+		trace2_region_leave("dir", "read_directory", istate->repo);
 		return dir->nr;
 	}
 
@@ -2784,23 +2868,15 @@ int read_directory(struct dir_struct *dir, struct index_state *istate,
 	QSORT(dir->entries, dir->nr, cmp_dir_entry);
 	QSORT(dir->ignored, dir->ignored_nr, cmp_dir_entry);
 
-	trace_performance_leave("read directory %.*s", len, path);
+	emit_traversal_statistics(dir, istate->repo, path, len);
+
+	trace2_region_leave("dir", "read_directory", istate->repo);
 	if (dir->untracked) {
 		static int force_untracked_cache = -1;
-		static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS);
 
 		if (force_untracked_cache < 0)
 			force_untracked_cache =
 				git_env_bool("GIT_FORCE_UNTRACKED_CACHE", 0);
-		trace_printf_key(&trace_untracked_stats,
-				 "node creation: %u\n"
-				 "gitignore invalidation: %u\n"
-				 "directory invalidation: %u\n"
-				 "opendir: %u\n",
-				 dir->untracked->dir_created,
-				 dir->untracked->gitignore_invalidated,
-				 dir->untracked->dir_invalidated,
-				 dir->untracked->dir_opened);
 		if (force_untracked_cache &&
 			dir->untracked == istate->untracked &&
 		    (dir->untracked->dir_opened ||
@@ -2811,6 +2887,7 @@ int read_directory(struct dir_struct *dir, struct index_state *istate,
 			FREE_AND_NULL(dir->untracked);
 		}
 	}
+
 	return dir->nr;
 }
 
@@ -2892,11 +2969,9 @@ int is_empty_dir(const char *path)
 	if (!dir)
 		return 0;
 
-	while ((e = readdir(dir)) != NULL)
-		if (!is_dot_or_dotdot(e->d_name)) {
-			ret = 0;
-			break;
-		}
+	e = readdir_skip_dot_and_dotdot(dir);
+	if (e)
+		ret = 0;
 
 	closedir(dir);
 	return ret;
@@ -2936,10 +3011,8 @@ static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
 	strbuf_complete(path, '/');
 
 	len = path->len;
-	while ((e = readdir(dir)) != NULL) {
+	while ((e = readdir_skip_dot_and_dotdot(dir)) != NULL) {
 		struct stat st;
-		if (is_dot_or_dotdot(e->d_name))
-			continue;
 
 		strbuf_setlen(path, len);
 		strbuf_addstr(path, e->d_name);
@@ -3050,6 +3123,7 @@ void dir_clear(struct dir_struct *dir)
 	struct exclude_list_group *group;
 	struct pattern_list *pl;
 	struct exclude_stack *stk;
+	struct dir_struct new = DIR_INIT;
 
 	for (i = EXC_CMDL; i <= EXC_FILE; i++) {
 		group = &dir->exclude_list_group[i];
@@ -3077,7 +3151,7 @@ void dir_clear(struct dir_struct *dir)
 	}
 	strbuf_release(&dir->basebuf);
 
-	dir_init(dir);
+	memcpy(dir, &new, sizeof(*dir));
 }
 
 struct ondisk_untracked_cache {