Merge branch 'nd/untracked-cache'

Teach the index to optionally remember already seen untracked files
to speed up "git status" in a working tree with tons of cruft.

* nd/untracked-cache: (24 commits)
  git-status.txt: advertisement for untracked cache
  untracked cache: guard and disable on system changes
  mingw32: add uname()
  t7063: tests for untracked cache
  update-index: test the system before enabling untracked cache
  update-index: manually enable or disable untracked cache
  status: enable untracked cache
  untracked-cache: temporarily disable with $GIT_DISABLE_UNTRACKED_CACHE
  untracked cache: mark index dirty if untracked cache is updated
  untracked cache: print stats with $GIT_TRACE_UNTRACKED_STATS
  untracked cache: avoid racy timestamps
  read-cache.c: split racy stat test to a separate function
  untracked cache: invalidate at index addition or removal
  untracked cache: load from UNTR index extension
  untracked cache: save to an index extension
  ewah: add convenient wrapper ewah_serialize_strbuf()
  untracked cache: don't open non-existent .gitignore
  untracked cache: mark what dirs should be recursed/saved
  untracked cache: record/validate dir mtime and reuse cached output
  untracked cache: make a wrapper around {open,read,close}dir()
  ...

.gitignore

@@ -184,6 +184,7 @@
 /test-delta
 /test-dump-cache-tree
 /test-dump-split-index
+/test-dump-untracked-cache
 /test-scrap-cache-tree
 /test-genrandom
 /test-hashmap

Documentation/git-status.txt

@@ -66,7 +66,10 @@ When `-u` option is not used, untracked files and directories are
 shown (i.e. the same as specifying `normal`), to help you avoid
 forgetting to add newly created files.  Because it takes extra work
 to find untracked files in the filesystem, this mode may take some
-time in a large working tree.  You can use `no` to have `git status`
+time in a large working tree.
+Consider enabling untracked cache and split index if supported (see
+`git update-index --untracked-cache` and `git update-index
+--split-index`), Otherwise you can use `no` to have `git status`
 return more quickly without showing untracked files.
 +
 The default can be changed using the status.showUntrackedFiles

Documentation/git-update-index.txt

@@ -170,6 +170,20 @@ may not support it yet.
 	the shared index file. This mode is designed for very large
 	indexes that take a significant amount of time to read or write.
 
+--untracked-cache::
+--no-untracked-cache::
+	Enable or disable untracked cache extension. This could speed
+	up for commands that involve determining untracked files such
+	as `git status`. The underlying operating system and file
+	system must change `st_mtime` field of a directory if files
+	are added or deleted in that directory.
+
+--force-untracked-cache::
+	For safety, `--untracked-cache` performs tests on the working
+	directory to make sure untracked cache can be used. These
+	tests can take a few seconds. `--force-untracked-cache` can be
+	used to skip the tests.
+
 \--::
 	Do not interpret any more arguments as options.
 

Documentation/technical/index-format.txt

@@ -233,3 +233,65 @@ Git index format
   The remaining index entries after replaced ones will be added to the
   final index. These added entries are also sorted by entry name then
   stage.
+
+== Untracked cache
+
+  Untracked cache saves the untracked file list and necessary data to
+  verify the cache. The signature for this extension is { 'U', 'N',
+  'T', 'R' }.
+
+  The extension starts with
+
+  - A sequence of NUL-terminated strings, preceded by the size of the
+    sequence in variable width encoding. Each string describes the
+    environment where the cache can be used.
+
+  - Stat data of $GIT_DIR/info/exclude. See "Index entry" section from
+    ctime field until "file size".
+
+  - Stat data of core.excludesfile
+
+  - 32-bit dir_flags (see struct dir_struct)
+
+  - 160-bit SHA-1 of $GIT_DIR/info/exclude. Null SHA-1 means the file
+    does not exist.
+
+  - 160-bit SHA-1 of core.excludesfile. Null SHA-1 means the file does
+    not exist.
+
+  - NUL-terminated string of per-dir exclude file name. This usually
+    is ".gitignore".
+
+  - The number of following directory blocks, variable width
+    encoding. If this number is zero, the extension ends here with a
+    following NUL.
+
+  - A number of directory blocks in depth-first-search order, each
+    consists of
+
+    - The number of untracked entries, variable width encoding.
+
+    - The number of sub-directory blocks, variable width encoding.
+
+    - The directory name terminated by NUL.
+
+    - A number of untrached file/dir names terminated by NUL.
+
+The remaining data of each directory block is grouped by type:
+
+  - An ewah bitmap, the n-th bit marks whether the n-th directory has
+    valid untracked cache entries.
+
+  - An ewah bitmap, the n-th bit records "check-only" bit of
+    read_directory_recursive() for the n-th directory.
+
+  - An ewah bitmap, the n-th bit indicates whether SHA-1 and stat data
+    is valid for the n-th directory and exists in the next data.
+
+  - An array of stat data. The n-th data corresponds with the n-th
+    "one" bit in the previous ewah bitmap.
+
+  - An array of SHA-1. The n-th SHA-1 corresponds with the n-th "one" bit
+    in the previous ewah bitmap.
+
+  - One NUL.

Makefile

@@ -574,6 +574,7 @@ TEST_PROGRAMS_NEED_X += test-date
 TEST_PROGRAMS_NEED_X += test-delta
 TEST_PROGRAMS_NEED_X += test-dump-cache-tree
 TEST_PROGRAMS_NEED_X += test-dump-split-index
+TEST_PROGRAMS_NEED_X += test-dump-untracked-cache
 TEST_PROGRAMS_NEED_X += test-genrandom
 TEST_PROGRAMS_NEED_X += test-hashmap
 TEST_PROGRAMS_NEED_X += test-index-version

builtin/commit.c

@@ -1366,13 +1366,14 @@ int cmd_status(int argc, const char **argv, const char *prefix)
 	refresh_index(&the_index, REFRESH_QUIET|REFRESH_UNMERGED, &s.pathspec, NULL, NULL);
 
 	fd = hold_locked_index(&index_lock, 0);
-	if (0 <= fd)
-		update_index_if_able(&the_index, &index_lock);
 
 	s.is_initial = get_sha1(s.reference, sha1) ? 1 : 0;
 	s.ignore_submodule_arg = ignore_submodule_arg;
 	wt_status_collect(&s);
 
+	if (0 <= fd)
+		update_index_if_able(&the_index, &index_lock);
+
 	if (s.relative_paths)
 		s.prefix = prefix;
 

builtin/update-index.c

@@ -33,6 +33,7 @@ static int mark_valid_only;
 static int mark_skip_worktree_only;
 #define MARK_FLAG 1
 #define UNMARK_FLAG 2
+static struct strbuf mtime_dir = STRBUF_INIT;
 
 __attribute__((format (printf, 1, 2)))
 static void report(const char *fmt, ...)
@@ -48,6 +49,166 @@ static void report(const char *fmt, ...)
 	va_end(vp);
 }
 
+static void remove_test_directory(void)
+{
+	if (mtime_dir.len)
+		remove_dir_recursively(&mtime_dir, 0);
+}
+
+static const char *get_mtime_path(const char *path)
+{
+	static struct strbuf sb = STRBUF_INIT;
+	strbuf_reset(&sb);
+	strbuf_addf(&sb, "%s/%s", mtime_dir.buf, path);
+	return sb.buf;
+}
+
+static void xmkdir(const char *path)
+{
+	path = get_mtime_path(path);
+	if (mkdir(path, 0700))
+		die_errno(_("failed to create directory %s"), path);
+}
+
+static int xstat_mtime_dir(struct stat *st)
+{
+	if (stat(mtime_dir.buf, st))
+		die_errno(_("failed to stat %s"), mtime_dir.buf);
+	return 0;
+}
+
+static int create_file(const char *path)
+{
+	int fd;
+	path = get_mtime_path(path);
+	fd = open(path, O_CREAT | O_RDWR, 0644);
+	if (fd < 0)
+		die_errno(_("failed to create file %s"), path);
+	return fd;
+}
+
+static void xunlink(const char *path)
+{
+	path = get_mtime_path(path);
+	if (unlink(path))
+		die_errno(_("failed to delete file %s"), path);
+}
+
+static void xrmdir(const char *path)
+{
+	path = get_mtime_path(path);
+	if (rmdir(path))
+		die_errno(_("failed to delete directory %s"), path);
+}
+
+static void avoid_racy(void)
+{
+	/*
+	 * not use if we could usleep(10) if USE_NSEC is defined. The
+	 * field nsec could be there, but the OS could choose to
+	 * ignore it?
+	 */
+	sleep(1);
+}
+
+static int test_if_untracked_cache_is_supported(void)
+{
+	struct stat st;
+	struct stat_data base;
+	int fd, ret = 0;
+
+	strbuf_addstr(&mtime_dir, "mtime-test-XXXXXX");
+	if (!mkdtemp(mtime_dir.buf))
+		die_errno("Could not make temporary directory");
+
+	fprintf(stderr, _("Testing "));
+	atexit(remove_test_directory);
+	xstat_mtime_dir(&st);
+	fill_stat_data(&base, &st);
+	fputc('.', stderr);
+
+	avoid_racy();
+	fd = create_file("newfile");
+	xstat_mtime_dir(&st);
+	if (!match_stat_data(&base, &st)) {
+		close(fd);
+		fputc('\n', stderr);
+		fprintf_ln(stderr,_("directory stat info does not "
+				    "change after adding a new file"));
+		goto done;
+	}
+	fill_stat_data(&base, &st);
+	fputc('.', stderr);
+
+	avoid_racy();
+	xmkdir("new-dir");
+	xstat_mtime_dir(&st);
+	if (!match_stat_data(&base, &st)) {
+		close(fd);
+		fputc('\n', stderr);
+		fprintf_ln(stderr, _("directory stat info does not change "
+				     "after adding a new directory"));
+		goto done;
+	}
+	fill_stat_data(&base, &st);
+	fputc('.', stderr);
+
+	avoid_racy();
+	write_or_die(fd, "data", 4);
+	close(fd);
+	xstat_mtime_dir(&st);
+	if (match_stat_data(&base, &st)) {
+		fputc('\n', stderr);
+		fprintf_ln(stderr, _("directory stat info changes "
+				     "after updating a file"));
+		goto done;
+	}
+	fputc('.', stderr);
+
+	avoid_racy();
+	close(create_file("new-dir/new"));
+	xstat_mtime_dir(&st);
+	if (match_stat_data(&base, &st)) {
+		fputc('\n', stderr);
+		fprintf_ln(stderr, _("directory stat info changes after "
+				     "adding a file inside subdirectory"));
+		goto done;
+	}
+	fputc('.', stderr);
+
+	avoid_racy();
+	xunlink("newfile");
+	xstat_mtime_dir(&st);
+	if (!match_stat_data(&base, &st)) {
+		fputc('\n', stderr);
+		fprintf_ln(stderr, _("directory stat info does not "
+				     "change after deleting a file"));
+		goto done;
+	}
+	fill_stat_data(&base, &st);
+	fputc('.', stderr);
+
+	avoid_racy();
+	xunlink("new-dir/new");
+	xrmdir("new-dir");
+	xstat_mtime_dir(&st);
+	if (!match_stat_data(&base, &st)) {
+		fputc('\n', stderr);
+		fprintf_ln(stderr, _("directory stat info does not "
+				     "change after deleting a directory"));
+		goto done;
+	}
+
+	if (rmdir(mtime_dir.buf))
+		die_errno(_("failed to delete directory %s"), mtime_dir.buf);
+	fprintf_ln(stderr, _(" OK"));
+	ret = 1;
+
+done:
+	strbuf_release(&mtime_dir);
+	return ret;
+}
+
 static int mark_ce_flags(const char *path, int flag, int mark)
 {
 	int namelen = strlen(path);
@@ -741,6 +902,7 @@ static int reupdate_callback(struct parse_opt_ctx_t *ctx,
 int cmd_update_index(int argc, const char **argv, const char *prefix)
 {
 	int newfd, entries, has_errors = 0, line_termination = '\n';
+	int untracked_cache = -1;
 	int read_from_stdin = 0;
 	int prefix_length = prefix ? strlen(prefix) : 0;
 	int preferred_index_format = 0;
@@ -832,6 +994,10 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 			N_("write index in this format")),
 		OPT_BOOL(0, "split-index", &split_index,
 			N_("enable or disable split index")),
+		OPT_BOOL(0, "untracked-cache", &untracked_cache,
+			N_("enable/disable untracked cache")),
+		OPT_SET_INT(0, "force-untracked-cache", &untracked_cache,
+			    N_("enable untracked cache without testing the filesystem"), 2),
 		OPT_END()
 	};
 
@@ -938,6 +1104,28 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 		the_index.split_index = NULL;
 		the_index.cache_changed |= SOMETHING_CHANGED;
 	}
+	if (untracked_cache > 0) {
+		struct untracked_cache *uc;
+
+		if (untracked_cache < 2) {
+			setup_work_tree();
+			if (!test_if_untracked_cache_is_supported())
+				return 1;
+		}
+		if (!the_index.untracked) {
+			uc = xcalloc(1, sizeof(*uc));
+			strbuf_init(&uc->ident, 100);
+			uc->exclude_per_dir = ".gitignore";
+			/* should be the same flags used by git-status */
+			uc->dir_flags = DIR_SHOW_OTHER_DIRECTORIES | DIR_HIDE_EMPTY_DIRECTORIES;
+			the_index.untracked = uc;
+		}
+		add_untracked_ident(the_index.untracked);
+		the_index.cache_changed |= UNTRACKED_CHANGED;
+	} else if (!untracked_cache && the_index.untracked) {
+		the_index.untracked = NULL;
+		the_index.cache_changed |= UNTRACKED_CHANGED;
+	}
 
 	if (active_cache_changed) {
 		if (newfd < 0) {

cache.h

@@ -297,8 +297,11 @@ static inline unsigned int canon_mode(unsigned int mode)
 #define RESOLVE_UNDO_CHANGED	(1 << 4)
 #define CACHE_TREE_CHANGED	(1 << 5)
 #define SPLIT_INDEX_ORDERED	(1 << 6)
+#define UNTRACKED_CHANGED	(1 << 7)
 
 struct split_index;
+struct untracked_cache;
+
 struct index_state {
 	struct cache_entry **cache;
 	unsigned int version;
@@ -312,6 +315,7 @@ struct index_state {
 	struct hashmap name_hash;
 	struct hashmap dir_hash;
 	unsigned char sha1[20];
+	struct untracked_cache *untracked;
 };
 
 extern struct index_state the_index;
@@ -563,6 +567,8 @@ extern void fill_stat_data(struct stat_data *sd, struct stat *st);
  * INODE_CHANGED, and DATA_CHANGED.
  */
 extern int match_stat_data(const struct stat_data *sd, struct stat *st);
+extern int match_stat_data_racy(const struct index_state *istate,
+				const struct stat_data *sd, struct stat *st);
 
 extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st);
 

compat/mingw.c

@@ -2128,3 +2128,14 @@ void mingw_startup()
 	/* initialize Unicode console */
 	winansi_init();
 }
+
+int uname(struct utsname *buf)
+{
+	DWORD v = GetVersion();
+	memset(buf, 0, sizeof(*buf));
+	strcpy(buf->sysname, "Windows");
+	sprintf(buf->release, "%u.%u", v & 0xff, (v >> 8) & 0xff);
+	/* assuming NT variants only.. */
+	sprintf(buf->version, "%u", (v >> 16) & 0x7fff);
+	return 0;
+}

compat/mingw.h

@@ -76,6 +76,14 @@ struct itimerval {
 };
 #define ITIMER_REAL 0
 
+struct utsname {
+	char sysname[16];
+	char nodename[1];
+	char release[16];
+	char version[16];
+	char machine[1];
+};
+
 /*
  * sanitize preprocessor namespace polluted by Windows headers defining
  * macros which collide with git local versions
@@ -175,6 +183,7 @@ struct passwd *getpwuid(uid_t uid);
 int setitimer(int type, struct itimerval *in, struct itimerval *out);
 int sigaction(int sig, struct sigaction *in, struct sigaction *out);
 int link(const char *oldpath, const char *newpath);
+int uname(struct utsname *buf);
 
 /*
  * replacements of existing functions

dir.h

@@ -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 {
@@ -73,6 +74,73 @@ struct exclude_list_group {
 	struct exclude_list *el;
 };
 
+struct sha1_stat {
+	struct stat_data stat;
+	unsigned char sha1[20];
+	int valid;
+};
+
+/*
+ *  Untracked cache
+ *
+ *  The following inputs are sufficient to determine what files in a
+ *  directory are excluded:
+ *
+ *   - The list of files and directories of the directory 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;
+	struct stat_data stat_data;
+	unsigned int untracked_alloc, dirs_nr, dirs_alloc;
+	unsigned int untracked_nr;
+	unsigned int check_only : 1;
+	/* all data except 'dirs' in this struct are good */
+	unsigned int valid : 1;
+	unsigned int recurse : 1;
+	/* null SHA-1 means this directory does not have .gitignore */
+	unsigned char exclude_sha1[20];
+	char name[FLEX_ARRAY];
+};
+
+struct untracked_cache {
+	struct sha1_stat ss_info_exclude;
+	struct sha1_stat ss_excludes_file;
+	const char *exclude_per_dir;
+	struct strbuf ident;
+	/*
+	 * 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;
+	int gitignore_invalidated;
+	int dir_invalidated;
+	int dir_opened;
+};
+
 struct dir_struct {
 	int nr, alloc;
 	int ignored_nr, ignored_alloc;
@@ -120,6 +188,12 @@ 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;
+	unsigned unmanaged_exclude_files;
 };
 
 /*
@@ -226,4 +300,12 @@ static inline int dir_path_match(const struct dir_entry *ent,
 			      has_trailing_dir);
 }
 
+void untracked_cache_invalidate_path(struct index_state *, const char *);
+void untracked_cache_remove_from_index(struct index_state *, const char *);
+void untracked_cache_add_to_index(struct index_state *, const char *);
+
+void free_untracked_cache(struct untracked_cache *);
+struct untracked_cache *read_untracked_extension(const void *data, unsigned long sz);
+void write_untracked_extension(struct strbuf *out, struct untracked_cache *untracked);
+void add_untracked_ident(struct untracked_cache *);
 #endif

ewah/ewah_io.c

@@ -19,6 +19,7 @@
  */
 #include "git-compat-util.h"
 #include "ewok.h"
+#include "strbuf.h"
 
 int ewah_serialize_native(struct ewah_bitmap *self, int fd)
 {
@@ -110,6 +111,18 @@ int ewah_serialize(struct ewah_bitmap *self, int fd)
 	return ewah_serialize_to(self, write_helper, (void *)(intptr_t)fd);
 }
 
+static int write_strbuf(void *user_data, const void *data, size_t len)
+{
+	struct strbuf *sb = user_data;
+	strbuf_add(sb, data, len);
+	return len;
+}
+
+int ewah_serialize_strbuf(struct ewah_bitmap *self, struct strbuf *sb)
+{
+	return ewah_serialize_to(self, write_strbuf, sb);
+}
+
 int ewah_read_mmap(struct ewah_bitmap *self, const void *map, size_t len)
 {
 	const uint8_t *ptr = map;

ewah/ewok.h

@@ -30,6 +30,7 @@
 #	define ewah_calloc xcalloc
 #endif
 
+struct strbuf;
 typedef uint64_t eword_t;
 #define BITS_IN_WORD (sizeof(eword_t) * 8)
 
@@ -98,6 +99,7 @@ int ewah_serialize_to(struct ewah_bitmap *self,
 		      void *out);
 int ewah_serialize(struct ewah_bitmap *self, int fd);
 int ewah_serialize_native(struct ewah_bitmap *self, int fd);
+int ewah_serialize_strbuf(struct ewah_bitmap *self, struct strbuf *);
 
 int ewah_deserialize(struct ewah_bitmap *self, int fd);
 int ewah_read_mmap(struct ewah_bitmap *self, const void *map, size_t len);

git-compat-util.h

@@ -189,6 +189,7 @@
 #elif defined(_MSC_VER)
 #include "compat/msvc.h"
 #else
+#include <sys/utsname.h>
 #include <sys/wait.h>
 #include <sys/resource.h>
 #include <sys/socket.h>

read-cache.c

@@ -39,11 +39,12 @@ static struct cache_entry *refresh_cache_entry(struct cache_entry *ce,
 #define CACHE_EXT_TREE 0x54524545	/* "TREE" */
 #define CACHE_EXT_RESOLVE_UNDO 0x52455543 /* "REUC" */
 #define CACHE_EXT_LINK 0x6c696e6b	  /* "link" */
+#define CACHE_EXT_UNTRACKED 0x554E5452	  /* "UNTR" */
 
 /* changes that can be kept in $GIT_DIR/index (basically all extensions) */
 #define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
 		 CE_ENTRY_ADDED | CE_ENTRY_REMOVED | CE_ENTRY_CHANGED | \
-		 SPLIT_INDEX_ORDERED)
+		 SPLIT_INDEX_ORDERED | UNTRACKED_CHANGED)
 
 struct index_state the_index;
 static const char *alternate_index_output;
@@ -79,6 +80,7 @@ void rename_index_entry_at(struct index_state *istate, int nr, const char *new_n
 	memcpy(new->name, new_name, namelen + 1);
 
 	cache_tree_invalidate_path(istate, old->name);
+	untracked_cache_remove_from_index(istate, old->name);
 	remove_index_entry_at(istate, nr);
 	add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
 }
@@ -270,20 +272,34 @@ static int ce_match_stat_basic(const struct cache_entry *ce, struct stat *st)
 	return changed;
 }
 
+static int is_racy_stat(const struct index_state *istate,
+			const struct stat_data *sd)
+{
+	return (istate->timestamp.sec &&
+#ifdef USE_NSEC
+		 /* nanosecond timestamped files can also be racy! */
+		(istate->timestamp.sec < sd->sd_mtime.sec ||
+		 (istate->timestamp.sec == sd->sd_mtime.sec &&
+		  istate->timestamp.nsec <= sd->sd_mtime.nsec))
+#else
+		istate->timestamp.sec <= sd->sd_mtime.sec
+#endif
+		);
+}
+
 static int is_racy_timestamp(const struct index_state *istate,
 			     const struct cache_entry *ce)
 {
 	return (!S_ISGITLINK(ce->ce_mode) &&
-		istate->timestamp.sec &&
+		is_racy_stat(istate, &ce->ce_stat_data));
-#ifdef USE_NSEC
+}
-		 /* nanosecond timestamped files can also be racy! */
+
-		(istate->timestamp.sec < ce->ce_stat_data.sd_mtime.sec ||
+int match_stat_data_racy(const struct index_state *istate,
-		 (istate->timestamp.sec == ce->ce_stat_data.sd_mtime.sec &&
+			 const struct stat_data *sd, struct stat *st)
-		  istate->timestamp.nsec <= ce->ce_stat_data.sd_mtime.nsec))
+{
-#else
+	if (is_racy_stat(istate, sd))
-		istate->timestamp.sec <= ce->ce_stat_data.sd_mtime.sec
+		return MTIME_CHANGED;
-#endif
+	return match_stat_data(sd, st);
-		 );
 }
 
 int ie_match_stat(const struct index_state *istate,
@@ -538,6 +554,7 @@ int remove_file_from_index(struct index_state *istate, const char *path)
 	if (pos < 0)
 		pos = -pos-1;
 	cache_tree_invalidate_path(istate, path);
+	untracked_cache_remove_from_index(istate, path);
 	while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
 		remove_index_entry_at(istate, pos);
 	return 0;
@@ -982,6 +999,8 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
 	}
 	pos = -pos-1;
 
+	untracked_cache_add_to_index(istate, ce->name);
+
 	/*
 	 * Inserting a merged entry ("stage 0") into the index
 	 * will always replace all non-merged entries..
@@ -1372,6 +1391,9 @@ static int read_index_extension(struct index_state *istate,
 		if (read_link_extension(istate, data, sz))
 			return -1;
 		break;
+	case CACHE_EXT_UNTRACKED:
+		istate->untracked = read_untracked_extension(data, sz);
+		break;
 	default:
 		if (*ext < 'A' || 'Z' < *ext)
 			return error("index uses %.4s extension, which we do not understand",
@@ -1667,6 +1689,8 @@ int discard_index(struct index_state *istate)
 	istate->cache = NULL;
 	istate->cache_alloc = 0;
 	discard_split_index(istate);
+	free_untracked_cache(istate->untracked);
+	istate->untracked = NULL;
 	return 0;
 }
 
@@ -2053,6 +2077,17 @@ static int do_write_index(struct index_state *istate, int newfd,
 		if (err)
 			return -1;
 	}
+	if (!strip_extensions && istate->untracked) {
+		struct strbuf sb = STRBUF_INIT;
+
+		write_untracked_extension(&sb, istate->untracked);
+		err = write_index_ext_header(&c, newfd, CACHE_EXT_UNTRACKED,
+					     sb.len) < 0 ||
+			ce_write(&c, newfd, sb.buf, sb.len) < 0;
+		strbuf_release(&sb);
+		if (err)
+			return -1;
+	}
 
 	if (ce_flush(&c, newfd, istate->sha1) || fstat(newfd, &st))
 		return -1;

split-index.c

@@ -41,13 +41,6 @@ int read_link_extension(struct index_state *istate,
 	return 0;
 }
 
-static int write_strbuf(void *user_data, const void *data, size_t len)
-{
-	struct strbuf *sb = user_data;
-	strbuf_add(sb, data, len);
-	return len;
-}
-
 int write_link_extension(struct strbuf *sb,
 			 struct index_state *istate)
 {
@@ -55,8 +48,8 @@ int write_link_extension(struct strbuf *sb,
 	strbuf_add(sb, si->base_sha1, 20);
 	if (!si->delete_bitmap && !si->replace_bitmap)
 		return 0;
-	ewah_serialize_to(si->delete_bitmap, write_strbuf, sb);
+	ewah_serialize_strbuf(si->delete_bitmap, sb);
-	ewah_serialize_to(si->replace_bitmap, write_strbuf, sb);
+	ewah_serialize_strbuf(si->replace_bitmap, sb);
 	return 0;
 }
 

t/t7063-status-untracked-cache.sh

@@ -0,0 +1,353 @@
+#!/bin/sh
+
+test_description='test untracked cache'
+
+. ./test-lib.sh
+
+avoid_racy() {
+	sleep 1
+}
+
+git update-index --untracked-cache
+# It's fine if git update-index returns an error code other than one,
+# it'll be caught in the first test.
+if test $? -eq 1; then
+	skip_all='This system does not support untracked cache'
+	test_done
+fi
+
+test_expect_success 'setup' '
+	git init worktree &&
+	cd worktree &&
+	mkdir done dtwo dthree &&
+	touch one two three done/one dtwo/two dthree/three &&
+	git add one two done/one &&
+	: >.git/info/exclude &&
+	git update-index --untracked-cache
+'
+
+test_expect_success 'untracked cache is empty' '
+	test-dump-untracked-cache >../actual &&
+	cat >../expect <<EOF &&
+info/exclude 0000000000000000000000000000000000000000
+core.excludesfile 0000000000000000000000000000000000000000
+exclude_per_dir .gitignore
+flags 00000006
+EOF
+	test_cmp ../expect ../actual
+'
+
+cat >../status.expect <<EOF &&
+A  done/one
+A  one
+A  two
+?? dthree/
+?? dtwo/
+?? three
+EOF
+
+cat >../dump.expect <<EOF &&
+info/exclude e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
+core.excludesfile 0000000000000000000000000000000000000000
+exclude_per_dir .gitignore
+flags 00000006
+/ 0000000000000000000000000000000000000000 recurse valid
+dthree/
+dtwo/
+three
+/done/ 0000000000000000000000000000000000000000 recurse valid
+/dthree/ 0000000000000000000000000000000000000000 recurse check_only valid
+three
+/dtwo/ 0000000000000000000000000000000000000000 recurse check_only valid
+two
+EOF
+
+test_expect_success 'status first time (empty cache)' '
+	avoid_racy &&
+	: >../trace &&
+	GIT_TRACE_UNTRACKED_STATS="$TRASH_DIRECTORY/trace" \
+	git status --porcelain >../actual &&
+	test_cmp ../status.expect ../actual &&
+	cat >../trace.expect <<EOF &&
+node creation: 3
+gitignore invalidation: 1
+directory invalidation: 0
+opendir: 4
+EOF
+	test_cmp ../trace.expect ../trace
+'
+
+test_expect_success 'untracked cache after first status' '
+	test-dump-untracked-cache >../actual &&
+	test_cmp ../dump.expect ../actual
+'
+
+test_expect_success 'status second time (fully populated cache)' '
+	avoid_racy &&
+	: >../trace &&
+	GIT_TRACE_UNTRACKED_STATS="$TRASH_DIRECTORY/trace" \
+	git status --porcelain >../actual &&
+	test_cmp ../status.expect ../actual &&
+	cat >../trace.expect <<EOF &&
+node creation: 0
+gitignore invalidation: 0
+directory invalidation: 0
+opendir: 0
+EOF
+	test_cmp ../trace.expect ../trace
+'
+
+test_expect_success 'untracked cache after second status' '
+	test-dump-untracked-cache >../actual &&
+	test_cmp ../dump.expect ../actual
+'
+
+test_expect_success 'modify in root directory, one dir invalidation' '
+	avoid_racy &&
+	: >four &&
+	: >../trace &&
+	GIT_TRACE_UNTRACKED_STATS="$TRASH_DIRECTORY/trace" \
+	git status --porcelain >../actual &&
+	cat >../status.expect <<EOF &&
+A  done/one
+A  one
+A  two
+?? dthree/
+?? dtwo/
+?? four
+?? three
+EOF
+	test_cmp ../status.expect ../actual &&
+	cat >../trace.expect <<EOF &&
+node creation: 0
+gitignore invalidation: 0
+directory invalidation: 1
+opendir: 1
+EOF
+	test_cmp ../trace.expect ../trace
+
+'
+
+test_expect_success 'verify untracked cache dump' '
+	test-dump-untracked-cache >../actual &&
+	cat >../expect <<EOF &&
+info/exclude e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
+core.excludesfile 0000000000000000000000000000000000000000
+exclude_per_dir .gitignore
+flags 00000006
+/ 0000000000000000000000000000000000000000 recurse valid
+dthree/
+dtwo/
+four
+three
+/done/ 0000000000000000000000000000000000000000 recurse valid
+/dthree/ 0000000000000000000000000000000000000000 recurse check_only valid
+three
+/dtwo/ 0000000000000000000000000000000000000000 recurse check_only valid
+two
+EOF
+	test_cmp ../expect ../actual
+'
+
+test_expect_success 'new .gitignore invalidates recursively' '
+	avoid_racy &&
+	echo four >.gitignore &&
+	: >../trace &&
+	GIT_TRACE_UNTRACKED_STATS="$TRASH_DIRECTORY/trace" \
+	git status --porcelain >../actual &&
+	cat >../status.expect <<EOF &&
+A  done/one
+A  one
+A  two
+?? .gitignore
+?? dthree/
+?? dtwo/
+?? three
+EOF
+	test_cmp ../status.expect ../actual &&
+	cat >../trace.expect <<EOF &&
+node creation: 0
+gitignore invalidation: 1
+directory invalidation: 1
+opendir: 4
+EOF
+	test_cmp ../trace.expect ../trace
+
+'
+
+test_expect_success 'verify untracked cache dump' '
+	test-dump-untracked-cache >../actual &&
+	cat >../expect <<EOF &&
+info/exclude e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
+core.excludesfile 0000000000000000000000000000000000000000
+exclude_per_dir .gitignore
+flags 00000006
+/ e6fcc8f2ee31bae321d66afd183fcb7237afae6e recurse valid
+.gitignore
+dthree/
+dtwo/
+three
+/done/ 0000000000000000000000000000000000000000 recurse valid
+/dthree/ 0000000000000000000000000000000000000000 recurse check_only valid
+three
+/dtwo/ 0000000000000000000000000000000000000000 recurse check_only valid
+two
+EOF
+	test_cmp ../expect ../actual
+'
+
+test_expect_success 'new info/exclude invalidates everything' '
+	avoid_racy &&
+	echo three >>.git/info/exclude &&
+	: >../trace &&
+	GIT_TRACE_UNTRACKED_STATS="$TRASH_DIRECTORY/trace" \
+	git status --porcelain >../actual &&
+	cat >../status.expect <<EOF &&
+A  done/one
+A  one
+A  two
+?? .gitignore
+?? dtwo/
+EOF
+	test_cmp ../status.expect ../actual &&
+	cat >../trace.expect <<EOF &&
+node creation: 0
+gitignore invalidation: 1
+directory invalidation: 0
+opendir: 4
+EOF
+	test_cmp ../trace.expect ../trace
+'
+
+test_expect_success 'verify untracked cache dump' '
+	test-dump-untracked-cache >../actual &&
+	cat >../expect <<EOF &&
+info/exclude 13263c0978fb9fad16b2d580fb800b6d811c3ff0
+core.excludesfile 0000000000000000000000000000000000000000
+exclude_per_dir .gitignore
+flags 00000006
+/ e6fcc8f2ee31bae321d66afd183fcb7237afae6e recurse valid
+.gitignore
+dtwo/
+/done/ 0000000000000000000000000000000000000000 recurse valid
+/dthree/ 0000000000000000000000000000000000000000 recurse check_only valid
+/dtwo/ 0000000000000000000000000000000000000000 recurse check_only valid
+two
+EOF
+	test_cmp ../expect ../actual
+'
+
+test_expect_success 'move two from tracked to untracked' '
+	git rm --cached two &&
+	test-dump-untracked-cache >../actual &&
+	cat >../expect <<EOF &&
+info/exclude 13263c0978fb9fad16b2d580fb800b6d811c3ff0
+core.excludesfile 0000000000000000000000000000000000000000
+exclude_per_dir .gitignore
+flags 00000006
+/ e6fcc8f2ee31bae321d66afd183fcb7237afae6e recurse
+/done/ 0000000000000000000000000000000000000000 recurse valid
+/dthree/ 0000000000000000000000000000000000000000 recurse check_only valid
+/dtwo/ 0000000000000000000000000000000000000000 recurse check_only valid
+two
+EOF
+	test_cmp ../expect ../actual
+'
+
+test_expect_success 'status after the move' '
+	: >../trace &&
+	GIT_TRACE_UNTRACKED_STATS="$TRASH_DIRECTORY/trace" \
+	git status --porcelain >../actual &&
+	cat >../status.expect <<EOF &&
+A  done/one
+A  one
+?? .gitignore
+?? dtwo/
+?? two
+EOF
+	test_cmp ../status.expect ../actual &&
+	cat >../trace.expect <<EOF &&
+node creation: 0
+gitignore invalidation: 0
+directory invalidation: 0
+opendir: 1
+EOF
+	test_cmp ../trace.expect ../trace
+'
+
+test_expect_success 'verify untracked cache dump' '
+	test-dump-untracked-cache >../actual &&
+	cat >../expect <<EOF &&
+info/exclude 13263c0978fb9fad16b2d580fb800b6d811c3ff0
+core.excludesfile 0000000000000000000000000000000000000000
+exclude_per_dir .gitignore
+flags 00000006
+/ e6fcc8f2ee31bae321d66afd183fcb7237afae6e recurse valid
+.gitignore
+dtwo/
+two
+/done/ 0000000000000000000000000000000000000000 recurse valid
+/dthree/ 0000000000000000000000000000000000000000 recurse check_only valid
+/dtwo/ 0000000000000000000000000000000000000000 recurse check_only valid
+two
+EOF
+	test_cmp ../expect ../actual
+'
+
+test_expect_success 'move two from untracked to tracked' '
+	git add two &&
+	test-dump-untracked-cache >../actual &&
+	cat >../expect <<EOF &&
+info/exclude 13263c0978fb9fad16b2d580fb800b6d811c3ff0
+core.excludesfile 0000000000000000000000000000000000000000
+exclude_per_dir .gitignore
+flags 00000006
+/ e6fcc8f2ee31bae321d66afd183fcb7237afae6e recurse
+/done/ 0000000000000000000000000000000000000000 recurse valid
+/dthree/ 0000000000000000000000000000000000000000 recurse check_only valid
+/dtwo/ 0000000000000000000000000000000000000000 recurse check_only valid
+two
+EOF
+	test_cmp ../expect ../actual
+'
+
+test_expect_success 'status after the move' '
+	: >../trace &&
+	GIT_TRACE_UNTRACKED_STATS="$TRASH_DIRECTORY/trace" \
+	git status --porcelain >../actual &&
+	cat >../status.expect <<EOF &&
+A  done/one
+A  one
+A  two
+?? .gitignore
+?? dtwo/
+EOF
+	test_cmp ../status.expect ../actual &&
+	cat >../trace.expect <<EOF &&
+node creation: 0
+gitignore invalidation: 0
+directory invalidation: 0
+opendir: 1
+EOF
+	test_cmp ../trace.expect ../trace
+'
+
+test_expect_success 'verify untracked cache dump' '
+	test-dump-untracked-cache >../actual &&
+	cat >../expect <<EOF &&
+info/exclude 13263c0978fb9fad16b2d580fb800b6d811c3ff0
+core.excludesfile 0000000000000000000000000000000000000000
+exclude_per_dir .gitignore
+flags 00000006
+/ e6fcc8f2ee31bae321d66afd183fcb7237afae6e recurse valid
+.gitignore
+dtwo/
+/done/ 0000000000000000000000000000000000000000 recurse valid
+/dthree/ 0000000000000000000000000000000000000000 recurse check_only valid
+/dtwo/ 0000000000000000000000000000000000000000 recurse check_only valid
+two
+EOF
+	test_cmp ../expect ../actual
+'
+
+test_done

test-dump-untracked-cache.c

@@ -0,0 +1,62 @@
+#include "cache.h"
+#include "dir.h"
+
+static int compare_untracked(const void *a_, const void *b_)
+{
+	const char *const *a = a_;
+	const char *const *b = b_;
+	return strcmp(*a, *b);
+}
+
+static int compare_dir(const void *a_, const void *b_)
+{
+	const struct untracked_cache_dir *const *a = a_;
+	const struct untracked_cache_dir *const *b = b_;
+	return strcmp((*a)->name, (*b)->name);
+}
+
+static void dump(struct untracked_cache_dir *ucd, struct strbuf *base)
+{
+	int i, len;
+	qsort(ucd->untracked, ucd->untracked_nr, sizeof(*ucd->untracked),
+	      compare_untracked);
+	qsort(ucd->dirs, ucd->dirs_nr, sizeof(*ucd->dirs),
+	      compare_dir);
+	len = base->len;
+	strbuf_addf(base, "%s/", ucd->name);
+	printf("%s %s", base->buf,
+	       sha1_to_hex(ucd->exclude_sha1));
+	if (ucd->recurse)
+		fputs(" recurse", stdout);
+	if (ucd->check_only)
+		fputs(" check_only", stdout);
+	if (ucd->valid)
+		fputs(" valid", stdout);
+	printf("\n");
+	for (i = 0; i < ucd->untracked_nr; i++)
+		printf("%s\n", ucd->untracked[i]);
+	for (i = 0; i < ucd->dirs_nr; i++)
+		dump(ucd->dirs[i], base);
+	strbuf_setlen(base, len);
+}
+
+int main(int ac, char **av)
+{
+	struct untracked_cache *uc;
+	struct strbuf base = STRBUF_INIT;
+	setup_git_directory();
+	if (read_cache() < 0)
+		die("unable to read index file");
+	uc = the_index.untracked;
+	if (!uc) {
+		printf("no untracked cache\n");
+		return 0;
+	}
+	printf("info/exclude %s\n", sha1_to_hex(uc->ss_info_exclude.sha1));
+	printf("core.excludesfile %s\n", sha1_to_hex(uc->ss_excludes_file.sha1));
+	printf("exclude_per_dir %s\n", uc->exclude_per_dir);
+	printf("flags %08x\n", uc->dir_flags);
+	if (uc->root)
+		dump(uc->root, &base);
+	return 0;
+}

unpack-trees.c

@@ -9,6 +9,7 @@
 #include "refs.h"
 #include "attr.h"
 #include "split-index.h"
+#include "dir.h"
 
 /*
  * Error messages expected by scripts out of plumbing commands such as
@@ -1259,8 +1260,10 @@ static int verify_uptodate_sparse(const struct cache_entry *ce,
 static void invalidate_ce_path(const struct cache_entry *ce,
 			       struct unpack_trees_options *o)
 {
-	if (ce)
+	if (!ce)
-		cache_tree_invalidate_path(o->src_index, ce->name);
+		return;
+	cache_tree_invalidate_path(o->src_index, ce->name);
+	untracked_cache_invalidate_path(o->src_index, ce->name);
 }
 
 /*

wt-status.c

@@ -585,6 +585,8 @@ static void wt_status_collect_untracked(struct wt_status *s)
 			DIR_SHOW_OTHER_DIRECTORIES | DIR_HIDE_EMPTY_DIRECTORIES;
 	if (s->show_ignored_files)
 		dir.flags |= DIR_SHOW_IGNORED_TOO;
+	else
+		dir.untracked = the_index.untracked;
 	setup_standard_excludes(&dir);
 
 	fill_directory(&dir, &s->pathspec);