[PATCH 00/19] Untracked cache to speed up "git status"

@@ -466,7 +466,8 @@ void add_exclude(const char *string, const char *base,
 	x->el = el;
 }
 
-static void *read_skip_worktree_file_from_index(const char *path, size_t *size)
+static void *read_skip_worktree_file_from_index(const char *path, size_t *size,
+						struct sha1_stat *ss)
 {
 	int pos, len;
 	unsigned long sz;

@@ -485,6 +486,10 @@ static void *read_skip_worktree_file_from_index(const char *path, size_t *size)
 		return NULL;
 	}
 	*size = xsize_t(sz);
+	if (ss) {
+		memset(&ss->stat, 0, sizeof(ss->stat));
+		hashcpy(ss->sha1, active_cache[pos]->sha1);
+	}
 	return data;
 }
 

@@ -529,11 +534,18 @@ static void trim_trailing_spaces(char *buf)
 		*last_space = '\0';
 }
 
-int add_excludes_from_file_to_list(const char *fname,
-				   const char *base,
-				   int baselen,
-				   struct exclude_list *el,
-				   int check_index)
+/*
+ * Given a file with name "fname", read it (either from disk, or from
+ * the index if "check_index" is non-zero), parse it and store the
+ * exclude rules in "el".
+ *
+ * If "ss" is not NULL, compute SHA-1 of the exclude file and fill
+ * stat data from disk (only valid if add_excludes returns zero). If
+ * ss_valid is non-zero, "ss" must contain good value as input.
+ */
+static int add_excludes(const char *fname, const char *base, int baselen,
+			struct exclude_list *el, int check_index,
+			struct sha1_stat *ss, int ss_valid)
 {
 	struct stat st;
 	int fd, i, lineno = 1;

@@ -547,7 +559,7 @@ int add_excludes_from_file_to_list(const char *fname,
 		if (0 <= fd)
 			close(fd);
 		if (!check_index ||
-		    (buf = read_skip_worktree_file_from_index(fname, &size)) == NULL)
+		    (buf = read_skip_worktree_file_from_index(fname, &size, ss)) == NULL)
 			return -1;
 		if (size == 0) {
 			free(buf);

@@ -560,6 +572,10 @@ int add_excludes_from_file_to_list(const char *fname,
 	} else {
 		size = xsize_t(st.st_size);
 		if (size == 0) {
+			if (ss) {
+				fill_stat_data(&ss->stat, &st);
+				hashcpy(ss->sha1, EMPTY_BLOB_SHA1_BIN);
+			}
 			close(fd);
 			return 0;
 		}

@@ -571,6 +587,19 @@ int add_excludes_from_file_to_list(const char *fname,
 		}
 		buf[size++] = '\n';
 		close(fd);
+		if (ss) {
+			int pos;
+			if (ss_valid && !match_stat_data(&ss->stat, &st))
+				; /* no content change, ss->sha1 still good */
+			else if (check_index &&
+				 (pos = cache_name_pos(fname, strlen(fname))) >= 0 &&
+				 !ce_stage(active_cache[pos]) &&
+				 ce_uptodate(active_cache[pos]))
+				hashcpy(ss->sha1, active_cache[pos]->sha1);
+			else
+				hash_sha1_file(buf, size, "blob", ss->sha1);
+			fill_stat_data(&ss->stat, &st);
+		}
 	}
 
 	el->filebuf = buf;

@@ -589,6 +618,13 @@ int add_excludes_from_file_to_list(const char *fname,
 	return 0;
 }
 
+int add_excludes_from_file_to_list(const char *fname, const char *base,
+				   int baselen, struct exclude_list *el,
+				   int check_index)
+{
+	return add_excludes(fname, base, baselen, el, check_index, NULL, 0);
+}
+
 struct exclude_list *add_exclude_list(struct dir_struct *dir,
 				      int group_type, const char *src)
 {

@@ -73,6 +73,11 @@ struct exclude_list_group {
 	struct exclude_list *el;
 };
 
+struct sha1_stat {
+	struct stat_data stat;
+	unsigned char sha1[20];
+};
+
 struct dir_struct {
 	int nr, alloc;
 	int ignored_nr, ignored_alloc;

@@ -32,7 +32,7 @@ enum path_treatment {
 };
 
 static enum path_treatment read_directory_recursive(struct dir_struct *dir,
-	const char *path, int len,
+	const char *path, int len, struct untracked_cache_dir *untracked,
 	int check_only, const struct path_simplify *simplify);
 static int get_dtype(struct dirent *de, const char *path, int len);
 

@@ -535,6 +535,53 @@ static void trim_trailing_spaces(char *buf)
 }
 
 /*
+ * Given a subdirectory name and "dir" of the current directory,
+ * search the subdir in "dir" and return it, or create a new one if it
+ * does not exist in "dir".
+ *
+ * If "name" has the trailing slash, it'll be excluded in the search.
+ */
+static struct untracked_cache_dir *lookup_untracked(struct untracked_cache *uc,
+						    struct untracked_cache_dir *dir,
+						    const char *name, int len)
+{
+	int first, last;
+	struct untracked_cache_dir *d;
+	if (!dir)
+		return NULL;
+	if (len && name[len - 1] == '/')
+		len--;
+	first = 0;
+	last = dir->dirs_nr;
+	while (last > first) {
+		int cmp, next = (last + first) >> 1;
+		d = dir->dirs[next];
+		cmp = strncmp(name, d->name, len);
+		if (!cmp && strlen(d->name) > len)
+			cmp = -1;
+		if (!cmp)
+			return d;
+		if (cmp < 0) {
+			last = next;
+			continue;
+		}
+		first = next+1;
+	}
+
+	uc->dir_created++;
+	d = xmalloc(sizeof(*d) + len);
+	memset(d, 0, sizeof(*d) + len);
+	memcpy(d->name, name, len);
+
+	ALLOC_GROW(dir->dirs, dir->dirs_nr + 1, dir->dirs_alloc);
+	memmove(dir->dirs + first + 1, dir->dirs + first,
+		(dir->dirs_nr - first) * sizeof(*dir->dirs));
+	dir->dirs_nr++;
+	dir->dirs[first] = d;
+	return d;
+}
+
+/*
  * Given a file with name "fname", read it (either from disk, or from
  * the index if "check_index" is non-zero), parse it and store the
  * exclude rules in "el".

@@ -642,14 +689,20 @@ struct exclude_list *add_exclude_list(struct dir_struct *dir,
 /*
  * Used to set up core.excludesfile and .git/info/exclude lists.
  */
-void add_excludes_from_file(struct dir_struct *dir, const char *fname)
+static void add_excludes_from_file_1(struct dir_struct *dir, const char *fname,
+				     struct sha1_stat *ss, int ss_valid)
 {
 	struct exclude_list *el;
 	el = add_exclude_list(dir, EXC_FILE, fname);
-	if (add_excludes_from_file_to_list(fname, "", 0, el, 0) < 0)
+	if (add_excludes(fname, "", 0, el, 0, ss, ss_valid) < 0)
 		die("cannot use %s as an exclude file", fname);
 }
 
+void add_excludes_from_file(struct dir_struct *dir, const char *fname)
+{
+	add_excludes_from_file_1(dir, fname, NULL, 0);
+}
+
 int match_basename(const char *basename, int basenamelen,
 		   const char *pattern, int prefix, int patternlen,
 		   int flags)

@@ -824,6 +877,7 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 	struct exclude_list_group *group;
 	struct exclude_list *el;
 	struct exclude_stack *stk = NULL;
+	struct untracked_cache_dir *untracked;
 	int current;
 
 	group = &dir->exclude_list_group[EXC_DIRS];

@@ -861,9 +915,15 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 	/* Read from the parent directories and push them down. */
 	current = stk ? stk->baselen : -1;
 	strbuf_setlen(&dir->basebuf, current < 0 ? 0 : current);
+	if (dir->untracked)
+		untracked = stk ? stk->ucd : dir->untracked->root;
+	else
+		untracked = NULL;
+
 	while (current < baselen) {
 		struct exclude_stack *stk = xcalloc(1, sizeof(*stk));
 		const char *cp;
+		struct sha1_stat ss;
 
 		if (current < 0) {
 			cp = base;

@@ -873,10 +933,15 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 			if (!cp)
 				die("oops in prep_exclude");
 			cp++;
+			untracked =
+				lookup_untracked(dir->untracked, untracked,
+						 base + current,
+						 cp - base - current);
 		}
 		stk->prev = dir->exclude_stack;
 		stk->baselen = cp - base;
 		stk->exclude_ix = group->nr;
+		stk->ucd = untracked;
 		el = add_exclude_list(dir, EXC_DIRS, NULL);
 		strbuf_add(&dir->basebuf, base + current, stk->baselen - current);
 		assert(stk->baselen == dir->basebuf.len);

@@ -899,6 +964,7 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 		}
 
 		/* Try to read per-directory file */
+		hashclr(ss.sha1);
 		if (dir->exclude_per_dir) {
 			/*
 			 * dir->basebuf gets reused by the traversal, but we

@@ -912,8 +978,11 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 			strbuf_addbuf(&sb, &dir->basebuf);
 			strbuf_addstr(&sb, dir->exclude_per_dir);
 			el->src = strbuf_detach(&sb, NULL);
-			add_excludes_from_file_to_list(el->src, el->src,
-						       stk->baselen, el, 1);
+			add_excludes(el->src, el->src, stk->baselen, el, 1,
+				     untracked ? &ss : NULL, 0);
+		}
+		if (untracked) {
+			hashcpy(untracked->exclude_sha1, ss.sha1);
 		}
 		dir->exclude_stack = stk;
 		current = stk->baselen;

@@ -1094,6 +1163,7 @@ static enum exist_status directory_exists_in_index(const char *dirname, int len)
  *  (c) otherwise, we recurse into it.
  */
 static enum path_treatment treat_directory(struct dir_struct *dir,
+	struct untracked_cache_dir *untracked,
 	const char *dirname, int len, int exclude,
 	const struct path_simplify *simplify)
 {

@@ -1121,7 +1191,9 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
 	if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
 		return exclude ? path_excluded : path_untracked;
 
-	return read_directory_recursive(dir, dirname, len, 1, simplify);
+	untracked = lookup_untracked(dir->untracked, untracked, dirname, len);
+	return read_directory_recursive(dir, dirname, len,
+					untracked, 1, simplify);
 }
 
 /*

@@ -1237,6 +1309,7 @@ static int get_dtype(struct dirent *de, const char *path, int len)
 }
 
 static enum path_treatment treat_one_path(struct dir_struct *dir,
+					  struct untracked_cache_dir *untracked,
 					  struct strbuf *path,
 					  const struct path_simplify *simplify,
 					  int dtype, struct dirent *de)

@@ -1289,7 +1362,7 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 		return path_none;
 	case DT_DIR:
 		strbuf_addch(path, '/');
-		return treat_directory(dir, path->buf, path->len, exclude,
+		return treat_directory(dir, untracked, path->buf, path->len, exclude,
 			simplify);
 	case DT_REG:
 	case DT_LNK:

@@ -1298,6 +1371,7 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 }
 
 static enum path_treatment treat_path(struct dir_struct *dir,
+				      struct untracked_cache_dir *untracked,
 				      struct dirent *de,
 				      struct strbuf *path,
 				      int baselen,

@@ -1313,7 +1387,16 @@ static enum path_treatment treat_path(struct dir_struct *dir,
 		return path_none;
 
 	dtype = DTYPE(de);
-	return treat_one_path(dir, path, simplify, dtype, de);
+	return treat_one_path(dir, untracked, path, simplify, dtype, de);
+}
+
+static void add_untracked(struct untracked_cache_dir *dir, const char *name)
+{
+	if (!dir)
+		return;
+	ALLOC_GROW(dir->untracked, dir->untracked_nr + 1,
+		   dir->untracked_alloc);
+	dir->untracked[dir->untracked_nr++] = xstrdup(name);
 }
 
 /*

@@ -1329,7 +1412,7 @@ static enum path_treatment treat_path(struct dir_struct *dir,
  */
 static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 				    const char *base, int baselen,
-				    int check_only,
+				    struct untracked_cache_dir *untracked, int check_only,
 				    const struct path_simplify *simplify)
 {
 	DIR *fdir;

@@ -1343,24 +1426,36 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 	if (!fdir)
 		goto out;
 
+	if (untracked)
+		untracked->check_only = !!check_only;
+
 	while ((de = readdir(fdir)) != NULL) {
 		/* check how the file or directory should be treated */
-		state = treat_path(dir, de, &path, baselen, simplify);
+		state = treat_path(dir, untracked, de, &path, baselen, simplify);
+
 		if (state > dir_state)
 			dir_state = state;
 
 		/* recurse into subdir if instructed by treat_path */
 		if (state == path_recurse) {
-			subdir_state = read_directory_recursive(dir, path.buf,
-				path.len, check_only, simplify);
+			struct untracked_cache_dir *ud;
+			ud = lookup_untracked(dir->untracked, untracked,
+					      path.buf + baselen,
+					      path.len - baselen);
+			subdir_state =
+				read_directory_recursive(dir, path.buf, path.len,
+							 ud, check_only, simplify);
 			if (subdir_state > dir_state)
 				dir_state = subdir_state;
 		}
 
 		if (check_only) {
 			/* abort early if maximum state has been reached */
-			if (dir_state == path_untracked)
+			if (dir_state == path_untracked) {
+				if (untracked)
+					add_untracked(untracked, path.buf + baselen);
 				break;
+			}
 			/* skip the dir_add_* part */
 			continue;
 		}

@@ -1378,8 +1473,11 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 			break;
 
 		case path_untracked:
-			if (!(dir->flags & DIR_SHOW_IGNORED))
-				dir_add_name(dir, path.buf, path.len);
+			if (dir->flags & DIR_SHOW_IGNORED)
+				break;
+			dir_add_name(dir, path.buf, path.len);
+			if (untracked)
+				add_untracked(untracked, path.buf + baselen);
 			break;
 
 		default:

@@ -1456,7 +1554,7 @@ static int treat_leading_path(struct dir_struct *dir,
 			break;
 		if (simplify_away(sb.buf, sb.len, simplify))
 			break;
-		if (treat_one_path(dir, &sb, simplify,
+		if (treat_one_path(dir, NULL, &sb, simplify,
 				   DT_DIR, NULL) == path_none)
 			break; /* do not recurse into it */
 		if (len <= baselen) {

@@ -1496,7 +1594,9 @@ int read_directory(struct dir_struct *dir, const char *path, int len, const stru
 	 */
 	simplify = create_simplify(pathspec ? pathspec->_raw : NULL);
 	if (!len || treat_leading_path(dir, path, len, simplify))
-		read_directory_recursive(dir, path, len, 0, simplify);
+		read_directory_recursive(dir, path, len,
+					 dir->untracked ? dir->untracked->root : NULL,
+					 0, simplify);
 	free_simplify(simplify);
 	qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
 	qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name);

@@ -1666,10 +1766,18 @@ void setup_standard_excludes(struct dir_struct *dir)
 		home_config_paths(NULL, &xdg_path, "ignore");
 		excludes_file = xdg_path;
 	}
-	if (!access_or_warn(path, R_OK, 0))
-		add_excludes_from_file(dir, path);
-	if (excludes_file && !access_or_warn(excludes_file, R_OK, 0))
-		add_excludes_from_file(dir, excludes_file);
+	if (!access_or_warn(path, R_OK, 0)) {
+		struct sha1_stat *ss = NULL;
+		if (dir->untracked)
+			ss = &dir->ss_info_exclude;
+		add_excludes_from_file_1(dir, path, ss, 0);
+	}
+	if (excludes_file && !access_or_warn(excludes_file, R_OK, 0)) {
+		struct sha1_stat *ss = NULL;
+		if (dir->untracked)
+			ss = &dir->ss_excludes_file;
+		add_excludes_from_file_1(dir, excludes_file, ss, 0);
+	}
 }
 
 int remove_path(const char *name)

@@ -66,6 +66,7 @@ struct exclude_stack {
 	struct exclude_stack *prev; /* the struct exclude_stack for the parent directory */
 	int baselen;
 	int exclude_ix; /* index of exclude_list within EXC_DIRS exclude_list_group */
+	struct untracked_cache_dir *ucd;
 };
 
 struct exclude_list_group {

@@ -78,6 +79,60 @@ struct sha1_stat {
 	unsigned char sha1[20];
 };
 
+/*
+ *  Untracked cache
+ *
+ *  The following inputs are sufficient to determine what files in a
+ *  directory are excluded:
+ *
+ *   - The list of files and directories of the direction in question
+ *   - The $GIT_DIR/index
+ *   - dir_struct flags
+ *   - The content of $GIT_DIR/info/exclude
+ *   - The content of core.excludesfile
+ *   - The content (or the lack) of .gitignore of all parent directories
+ *     from $GIT_WORK_TREE
+ *   - The check_only flag in read_directory_recursive (for
+ *     DIR_HIDE_EMPTY_DIRECTORIES)
+ *
+ *  The first input can be checked using directory mtime. In many
+ *  filesystems, directory mtime (stat_data field) is updated when its
+ *  files or direct subdirs are added or removed.
+ *
+ *  The second one can be hooked from cache_tree_invalidate_path().
+ *  Whenever a file (or a submodule) is added or removed from a
+ *  directory, we invalidate that directory.
+ *
+ *  The remaining inputs are easy, their SHA-1 could be used to verify
+ *  their contents (exclude_sha1[], info_exclude_sha1[] and
+ *  excludes_file_sha1[])
+ */
+struct untracked_cache_dir {
+	struct untracked_cache_dir **dirs;
+	char **untracked;
+	/* null SHA-1 means this directory does not have .gitignore */
+	unsigned char exclude_sha1[20];
+	struct stat_data stat_data;
+	unsigned int check_only : 1;
+	unsigned int untracked_nr : 29;
+	unsigned int untracked_alloc, dirs_nr, dirs_alloc;
+	char name[1];
+};
+
+struct untracked_cache {
+	struct sha1_stat ss_info_exclude;
+	struct sha1_stat ss_excludes_file;
+	const char *exclude_per_dir;
+	/*
+	 * dir_struct#flags must match dir_flags or the untracked
+	 * cache is ignored.
+	 */
+	unsigned dir_flags;
+	struct untracked_cache_dir *root;
+	/* Statistics */
+	int dir_created;
+};
+
 struct dir_struct {
 	int nr, alloc;
 	int ignored_nr, ignored_alloc;

@@ -125,6 +180,11 @@ struct dir_struct {
 	struct exclude_stack *exclude_stack;
 	struct exclude *exclude;
 	struct strbuf basebuf;
+
+	/* Enable untracked file cache if set */
+	struct untracked_cache *untracked;
+	struct sha1_stat ss_info_exclude;
+	struct sha1_stat ss_excludes_file;
 };
 
 /*

@@ -581,6 +581,22 @@ static struct untracked_cache_dir *lookup_untracked(struct untracked_cache *uc,
 	return d;
 }
 
+static void do_invalidate_gitignore(struct untracked_cache_dir *dir)
+{
+	int i;
+	dir->valid = 0;
+	dir->untracked_nr = 0;
+	for (i = 0; i < dir->dirs_nr; i++)
+		do_invalidate_gitignore(dir->dirs[i]);
+}
+
+static void invalidate_gitignore(struct untracked_cache *uc,
+				 struct untracked_cache_dir *dir)
+{
+	uc->gitignore_invalidated++;
+	do_invalidate_gitignore(dir);
+}
+
 /*
  * Given a file with name "fname", read it (either from disk, or from
  * the index if "check_index" is non-zero), parse it and store the

@@ -693,6 +709,13 @@ static void add_excludes_from_file_1(struct dir_struct *dir, const char *fname,
 				     struct sha1_stat *ss, int ss_valid)
 {
 	struct exclude_list *el;
+	/*
+	 * catch setup_standard_excludes() that's called before
+	 * dir->untracked is assigned. That function behaves
+	 * differently when dir->untracked is non-NULL.
+	 */
+	if (!dir->untracked)
+		dir->unmanaged_exclude_files++;
 	el = add_exclude_list(dir, EXC_FILE, fname);
 	if (add_excludes(fname, "", 0, el, 0, ss, ss_valid) < 0)
 		die("cannot use %s as an exclude file", fname);

@@ -700,6 +723,7 @@ static void add_excludes_from_file_1(struct dir_struct *dir, const char *fname,
 
 void add_excludes_from_file(struct dir_struct *dir, const char *fname)
 {
+	dir->unmanaged_exclude_files++; /* see validate_untracked_cache() */
 	add_excludes_from_file_1(dir, fname, NULL, 0);
 }
 

@@ -1567,9 +1591,87 @@ static int treat_leading_path(struct dir_struct *dir,
 	return rc;
 }
 
+static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *dir,
+						      int base_len,
+						      const struct pathspec *pathspec)
+{
+	struct untracked_cache_dir *root;
+
+	if (!dir->untracked)
+		return NULL;
+
+	/*
+	 * We only support $GIT_DIR/info/exclude and core.excludesfile
+	 * as the global ignore rule files. Any other additions
+	 * (e.g. from command line) invalidate the cache. This
+	 * condition also catches running setup_standard_excludes()
+	 * before setting dir->untracked!
+	 */
+	if (dir->unmanaged_exclude_files)
+		return NULL;
+
+	/*
+	 * Optimize for the main use case only: whole-tree git
+	 * status. More work involved in treat_leading_path() if we
+	 * use cache on just a subset of the worktree. pathspec
+	 * support could make the matter even worse.
+	 */
+	if (base_len || (pathspec && pathspec->nr))
+		return NULL;
+
+	/* Different set of flags may produce different results */
+	if (dir->flags != dir->untracked->dir_flags ||
+	    /*
+	     * See treat_directory(), case index_nonexistent. Without
+	     * this flag, we may need to also cache .git file content
+	     * for the resolve_gitlink_ref() call, which we don't.
+	     */
+	    !(dir->flags & DIR_SHOW_OTHER_DIRECTORIES) ||
+	    /* We don't support collecting ignore files */
+	    (dir->flags & (DIR_SHOW_IGNORED | DIR_SHOW_IGNORED_TOO |
+			   DIR_COLLECT_IGNORED)))
+		return NULL;
+
+	/*
+	 * If we use .gitignore in the cache and now you change it to
+	 * .gitexclude, everything will go wrong.
+	 */
+	if (dir->exclude_per_dir != dir->untracked->exclude_per_dir &&
+	    strcmp(dir->exclude_per_dir, dir->untracked->exclude_per_dir))
+		return NULL;
+
+	/*
+	 * EXC_CMDL is not considered in the cache. If people set it,
+	 * skip the cache.
+	 */
+	if (dir->exclude_list_group[EXC_CMDL].nr)
+		return NULL;
+
+	if (!dir->untracked->root) {
+		const int len = sizeof(*dir->untracked->root);
+		dir->untracked->root = xmalloc(len);
+		memset(dir->untracked->root, 0, len);
+	}
+
+	/* Validate $GIT_DIR/info/exclude and core.excludesfile */
+	root = dir->untracked->root;
+	if (hashcmp(dir->ss_info_exclude.sha1,
+		    dir->untracked->ss_info_exclude.sha1)) {
+		invalidate_gitignore(dir->untracked, root);
+		dir->untracked->ss_info_exclude = dir->ss_info_exclude;
+	}
+	if (hashcmp(dir->ss_excludes_file.sha1,
+		    dir->untracked->ss_excludes_file.sha1)) {
+		invalidate_gitignore(dir->untracked, root);
+		dir->untracked->ss_excludes_file = dir->ss_excludes_file;
+	}
+	return root;
+}
+
 int read_directory(struct dir_struct *dir, const char *path, int len, const struct pathspec *pathspec)
 {
 	struct path_simplify *simplify;
+	struct untracked_cache_dir *untracked;
 
 	/*
 	 * Check out create_simplify()

@@ -1593,10 +1695,15 @@ int read_directory(struct dir_struct *dir, const char *path, int len, const stru
 	 * create_simplify().
 	 */
 	simplify = create_simplify(pathspec ? pathspec->_raw : NULL);
+	untracked = validate_untracked_cache(dir, len, pathspec);
+	if (!untracked)
+		/*
+		 * make sure untracked cache code path is disabled,
+		 * e.g. prep_exclude()
+		 */
+		dir->untracked = NULL;
 	if (!len || treat_leading_path(dir, path, len, simplify))
-		read_directory_recursive(dir, path, len,
-					 dir->untracked ? dir->untracked->root : NULL,
-					 0, simplify);
+		read_directory_recursive(dir, path, len, untracked, 0, simplify);
 	free_simplify(simplify);
 	qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
 	qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name);

@@ -114,6 +114,8 @@ struct untracked_cache_dir {
 	unsigned char exclude_sha1[20];
 	struct stat_data stat_data;
 	unsigned int check_only : 1;
+	/* all data in this struct are good */
+	unsigned int valid : 1;
 	unsigned int untracked_nr : 29;
 	unsigned int untracked_alloc, dirs_nr, dirs_alloc;
 	char name[1];

@@ -131,6 +133,7 @@ struct untracked_cache {
 	struct untracked_cache_dir *root;
 	/* Statistics */
 	int dir_created;
+	int gitignore_invalidated;
 };
 
 struct dir_struct {

@@ -185,6 +188,7 @@ struct dir_struct {
 	struct untracked_cache *untracked;
 	struct sha1_stat ss_info_exclude;
 	struct sha1_stat ss_excludes_file;
+	unsigned unmanaged_exclude_files;
 };
 
 /*

@@ -1005,7 +1005,22 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 			add_excludes(el->src, el->src, stk->baselen, el, 1,
 				     untracked ? &ss : NULL, 0);
 		}
-		if (untracked) {
+		/*
+		 * NEEDSWORK: when untracked cache is enabled, prep_exclude()
+		 * will first be called in valid_cached_dir() then maybe many
+		 * times more in last_exclude_matching(). When the cache is
+		 * used, last_exclude_matching() will not be called and
+		 * reading .gitignore content will be a waste.
+		 *
+		 * So when it's called by valid_cached_dir() and we can get
+		 * .gitignore SHA-1 from the index (i.e. .gitignore is not
+		 * modified on work tree), we could delay reading the
+		 * .gitignore content until we absolutely need it in
+		 * last_exclude_matching(). Be careful about ignore rule
+		 * order, though, if you do that.
+		 */
+		if (untracked && hashcmp(ss.sha1, untracked->exclude_sha1)) {
+			invalidate_gitignore(dir->untracked, untracked);
 			hashcpy(untracked->exclude_sha1, ss.sha1);
 		}
 		dir->exclude_stack = stk;

@@ -31,6 +31,15 @@ enum path_treatment {
 	path_untracked
 };
 
+/*
+ * Support data structure for our opendir/readdir/closedir wrappers
+ */
+struct cached_dir {
+	DIR *fdir;
+	struct untracked_cache_dir *untracked;
+	struct dirent *de;
+};
+
 static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 	const char *path, int len, struct untracked_cache_dir *untracked,
 	int check_only, const struct path_simplify *simplify);

@@ -1411,12 +1420,13 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 
 static enum path_treatment treat_path(struct dir_struct *dir,
 				      struct untracked_cache_dir *untracked,
-				      struct dirent *de,
+				      struct cached_dir *cdir,
 				      struct strbuf *path,
 				      int baselen,
 				      const struct path_simplify *simplify)
 {
 	int dtype;
+	struct dirent *de = cdir->de;
 
 	if (is_dot_or_dotdot(de->d_name) || !strcmp(de->d_name, ".git"))
 		return path_none;

@@ -1438,6 +1448,37 @@ static void add_untracked(struct untracked_cache_dir *dir, const char *name)
 	dir->untracked[dir->untracked_nr++] = xstrdup(name);
 }
 
+static int open_cached_dir(struct cached_dir *cdir,
+			   struct dir_struct *dir,
+			   struct untracked_cache_dir *untracked,
+			   struct strbuf *path,
+			   int check_only)
+{
+	memset(cdir, 0, sizeof(*cdir));
+	cdir->untracked = untracked;
+	cdir->fdir = opendir(path->len ? path->buf : ".");
+	if (!cdir->fdir)
+		return -1;
+	return 0;
+}
+
+int read_cached_dir(struct cached_dir *cdir)
+{
+	if (cdir->fdir) {
+		cdir->de = readdir(cdir->fdir);
+		if (!cdir->de)
+			return -1;
+		return 0;
+	}
+	return -1;
+}
+
+static void close_cached_dir(struct cached_dir *cdir)
+{
+	if (cdir->fdir)
+		closedir(cdir->fdir);
+}
+
 /*
  * Read a directory tree. We currently ignore anything but
  * directories, regular files and symlinks. That's because git