1 files changed, 362 insertions, 74 deletions

diff --git a/compat/fsmonitor/fsm-listen-win32.c b/compat/fsmonitor/fsm-listen-win32.c
index 5b928ab..03df8d9 100644
--- a/compat/fsmonitor/fsm-listen-win32.c
+++ b/compat/fsmonitor/fsm-listen-win32.c
@@ -25,6 +25,9 @@ struct one_watch
 	DWORD count;
 
 	struct strbuf path;
+	wchar_t wpath_longname[MAX_PATH + 1];
+	DWORD wpath_longname_len;
+
 	HANDLE hDir;
 	HANDLE hEvent;
 	OVERLAPPED overlapped;
@@ -34,9 +37,24 @@ struct one_watch
 	 * need to later call GetOverlappedResult() and possibly CancelIoEx().
 	 */
 	BOOL is_active;
+
+	/*
+	 * Are shortnames enabled on the containing drive?  This is
+	 * always true for "C:/" drives and usually never true for
+	 * other drives.
+	 *
+	 * We only set this for the worktree because we only need to
+	 * convert shortname paths to longname paths for items we send
+	 * to clients.  (We don't care about shortname expansion for
+	 * paths inside a GITDIR because we never send them to
+	 * clients.)
+	 */
+	BOOL has_shortnames;
+	BOOL has_tilde;
+	wchar_t dotgit_shortname[16]; /* for 8.3 name */
 };
 
-struct fsmonitor_daemon_backend_data
+struct fsm_listen_data
 {
 	struct one_watch *watch_worktree;
 	struct one_watch *watch_gitdir;
@@ -51,17 +69,18 @@ struct fsmonitor_daemon_backend_data
 };
 
 /*
- * Convert the WCHAR path from the notification into UTF8 and
- * then normalize it.
+ * Convert the WCHAR path from the event into UTF8 and normalize it.
+ *
+ * `wpath_len` is in WCHARS not bytes.
  */
-static int normalize_path_in_utf8(FILE_NOTIFY_INFORMATION *info,
+static int normalize_path_in_utf8(wchar_t *wpath, DWORD wpath_len,
 				  struct strbuf *normalized_path)
 {
 	int reserve;
 	int len = 0;
 
 	strbuf_reset(normalized_path);
-	if (!info->FileNameLength)
+	if (!wpath_len)
 		goto normalize;
 
 	/*
@@ -70,12 +89,12 @@ static int normalize_path_in_utf8(FILE_NOTIFY_INFORMATION *info,
 	 * sequence of 2 UTF8 characters.  That should let us
 	 * avoid ERROR_INSUFFICIENT_BUFFER 99.9+% of the time.
 	 */
-	reserve = info->FileNameLength + 1;
+	reserve = 2 * wpath_len + 1;
 	strbuf_grow(normalized_path, reserve);
 
 	for (;;) {
-		len = WideCharToMultiByte(CP_UTF8, 0, info->FileName,
-					  info->FileNameLength / sizeof(WCHAR),
+		len = WideCharToMultiByte(CP_UTF8, 0,
+					  wpath, wpath_len,
 					  normalized_path->buf,
 					  strbuf_avail(normalized_path) - 1,
 					  NULL, NULL);
@@ -83,9 +102,7 @@ static int normalize_path_in_utf8(FILE_NOTIFY_INFORMATION *info,
 			goto normalize;
 		if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
 			error(_("[GLE %ld] could not convert path to UTF-8: '%.*ls'"),
-			      GetLastError(),
-			      (int)(info->FileNameLength / sizeof(WCHAR)),
-			      info->FileName);
+			      GetLastError(), (int)wpath_len, wpath);
 			return -1;
 		}
 
@@ -98,9 +115,176 @@ normalize:
 	return strbuf_normalize_path(normalized_path);
 }
 
+/*
+ * See if the worktree root directory has shortnames enabled.
+ * This will help us decide if we need to do an expensive shortname
+ * to longname conversion on every notification event.
+ *
+ * We do not want to create a file to test this, so we assume that the
+ * root directory contains a ".git" file or directory.  (Our caller
+ * only calls us for the worktree root, so this should be fine.)
+ *
+ * Remember the spelling of the shortname for ".git" if it exists.
+ */
+static void check_for_shortnames(struct one_watch *watch)
+{
+	wchar_t buf_in[MAX_PATH + 1];
+	wchar_t buf_out[MAX_PATH + 1];
+	wchar_t *last;
+	wchar_t *p;
+
+	/* build L"<wt-root-path>/.git" */
+	swprintf(buf_in, ARRAY_SIZE(buf_in) - 1, L"%ls.git",
+		 watch->wpath_longname);
+
+	if (!GetShortPathNameW(buf_in, buf_out, ARRAY_SIZE(buf_out)))
+		return;
+
+	/*
+	 * Get the final filename component of the shortpath.
+	 * We know that the path does not have a final slash.
+	 */
+	for (last = p = buf_out; *p; p++)
+		if (*p == L'/' || *p == '\\')
+			last = p + 1;
+
+	if (!wcscmp(last, L".git"))
+		return;
+
+	watch->has_shortnames = 1;
+	wcsncpy(watch->dotgit_shortname, last,
+		ARRAY_SIZE(watch->dotgit_shortname));
+
+	/*
+	 * The shortname for ".git" is usually of the form "GIT~1", so
+	 * we should be able to avoid shortname to longname mapping on
+	 * every notification event if the source string does not
+	 * contain a "~".
+	 *
+	 * However, the documentation for GetLongPathNameW() says
+	 * that there are filesystems that don't follow that pattern
+	 * and warns against this optimization.
+	 *
+	 * Lets test this.
+	 */
+	if (wcschr(watch->dotgit_shortname, L'~'))
+		watch->has_tilde = 1;
+}
+
+enum get_relative_result {
+	GRR_NO_CONVERSION_NEEDED,
+	GRR_HAVE_CONVERSION,
+	GRR_SHUTDOWN,
+};
+
+/*
+ * Info notification paths are relative to the root of the watch.
+ * If our CWD is still at the root, then we can use relative paths
+ * to convert from shortnames to longnames.  If our process has a
+ * different CWD, then we need to construct an absolute path, do
+ * the conversion, and then return the root-relative portion.
+ *
+ * We use the longname form of the root as our basis and assume that
+ * it already has a trailing slash.
+ *
+ * `wpath_len` is in WCHARS not bytes.
+ */
+static enum get_relative_result get_relative_longname(
+	struct one_watch *watch,
+	const wchar_t *wpath, DWORD wpath_len,
+	wchar_t *wpath_longname, size_t bufsize_wpath_longname)
+{
+	wchar_t buf_in[2 * MAX_PATH + 1];
+	wchar_t buf_out[MAX_PATH + 1];
+	DWORD root_len;
+	DWORD out_len;
+
+	/*
+	 * Build L"<wt-root-path>/<event-rel-path>"
+	 * Note that the <event-rel-path> might not be null terminated
+	 * so we avoid swprintf() constructions.
+	 */
+	root_len = watch->wpath_longname_len;
+	if (root_len + wpath_len >= ARRAY_SIZE(buf_in)) {
+		/*
+		 * This should not happen.  We cannot append the observed
+		 * relative path onto the end of the worktree root path
+		 * without overflowing the buffer.  Just give up.
+		 */
+		return GRR_SHUTDOWN;
+	}
+	wcsncpy(buf_in, watch->wpath_longname, root_len);
+	wcsncpy(buf_in + root_len, wpath, wpath_len);
+	buf_in[root_len + wpath_len] = 0;
+
+	/*
+	 * We don't actually know if the source pathname is a
+	 * shortname or a longname.  This Windows routine allows
+	 * either to be given as input.
+	 */
+	out_len = GetLongPathNameW(buf_in, buf_out, ARRAY_SIZE(buf_out));
+	if (!out_len) {
+		/*
+		 * The shortname to longname conversion can fail for
+		 * various reasons, for example if the file has been
+		 * deleted.  (That is, if we just received a
+		 * delete-file notification event and the file is
+		 * already gone, we can't ask the file system to
+		 * lookup the longname for it.  Likewise, for moves
+		 * and renames where we are given the old name.)
+		 *
+		 * Since deleting or moving a file or directory by its
+		 * shortname is rather obscure, I'm going ignore the
+		 * failure and ask the caller to report the original
+		 * relative path.  This seems kinder than failing here
+		 * and forcing a resync.  Besides, forcing a resync on
+		 * every file/directory delete would effectively
+		 * cripple monitoring.
+		 *
+		 * We might revisit this in the future.
+		 */
+		return GRR_NO_CONVERSION_NEEDED;
+	}
+
+	if (!wcscmp(buf_in, buf_out)) {
+		/*
+		 * The path does not have a shortname alias.
+		 */
+		return GRR_NO_CONVERSION_NEEDED;
+	}
+
+	if (wcsncmp(buf_in, buf_out, root_len)) {
+		/*
+		 * The spelling of the root directory portion of the computed
+		 * longname has changed.  This should not happen.  Basically,
+		 * it means that we don't know where (without recomputing the
+		 * longname of just the root directory) to split out the
+		 * relative path.  Since this should not happen, I'm just
+		 * going to let this fail and force a shutdown (because all
+		 * subsequent events are probably going to see the same
+		 * mismatch).
+		 */
+		return GRR_SHUTDOWN;
+	}
+
+	if (out_len - root_len >= bufsize_wpath_longname) {
+		/*
+		 * This should not happen.  We cannot copy the root-relative
+		 * portion of the path into the provided buffer without an
+		 * overrun.  Just give up.
+		 */
+		return GRR_SHUTDOWN;
+	}
+
+	/* Return the worktree root-relative portion of the longname. */
+
+	wcscpy(wpath_longname, buf_out + root_len);
+	return GRR_HAVE_CONVERSION;
+}
+
 void fsm_listen__stop_async(struct fsmonitor_daemon_state *state)
 {
-	SetEvent(state->backend_data->hListener[LISTENER_SHUTDOWN]);
+	SetEvent(state->listen_data->hListener[LISTENER_SHUTDOWN]);
 }
 
 static struct one_watch *create_watch(struct fsmonitor_daemon_state *state,
@@ -111,7 +295,9 @@ static struct one_watch *create_watch(struct fsmonitor_daemon_state *state,
 	DWORD share_mode =
 		FILE_SHARE_WRITE | FILE_SHARE_READ | FILE_SHARE_DELETE;
 	HANDLE hDir;
-	wchar_t wpath[MAX_PATH];
+	DWORD len_longname;
+	wchar_t wpath[MAX_PATH + 1];
+	wchar_t wpath_longname[MAX_PATH + 1];
 
 	if (xutftowcs_path(wpath, path) < 0) {
 		error(_("could not convert to wide characters: '%s'"), path);
@@ -128,6 +314,21 @@ static struct one_watch *create_watch(struct fsmonitor_daemon_state *state,
 		return NULL;
 	}
 
+	len_longname = GetLongPathNameW(wpath, wpath_longname,
+					ARRAY_SIZE(wpath_longname));
+	if (!len_longname) {
+		error(_("[GLE %ld] could not get longname of '%s'"),
+		      GetLastError(), path);
+		CloseHandle(hDir);
+		return NULL;
+	}
+
+	if (wpath_longname[len_longname - 1] != L'/' &&
+	    wpath_longname[len_longname - 1] != L'\\') {
+		wpath_longname[len_longname++] = L'/';
+		wpath_longname[len_longname] = 0;
+	}
+
 	CALLOC_ARRAY(watch, 1);
 
 	watch->buf_len = sizeof(watch->buffer); /* assume full MAX_RDCW_BUF */
@@ -135,6 +336,9 @@ static struct one_watch *create_watch(struct fsmonitor_daemon_state *state,
 	strbuf_init(&watch->path, 0);
 	strbuf_addstr(&watch->path, path);
 
+	wcscpy(watch->wpath_longname, wpath_longname);
+	watch->wpath_longname_len = len_longname;
+
 	watch->hDir = hDir;
 	watch->hEvent = CreateEvent(NULL, TRUE, FALSE, NULL);
 
@@ -155,7 +359,7 @@ static void destroy_watch(struct one_watch *watch)
 	free(watch);
 }
 
-static int start_rdcw_watch(struct fsmonitor_daemon_backend_data *data,
+static int start_rdcw_watch(struct fsm_listen_data *data,
 			    struct one_watch *watch)
 {
 	DWORD dwNotifyFilter =
@@ -220,12 +424,22 @@ static int recv_rdcw_watch(struct one_watch *watch)
 	}
 
 	/*
-	 * NEEDSWORK: If an external <gitdir> is deleted, the above
-	 * returns an error.  I'm not sure that there's anything that
-	 * we can do here other than failing -- the <worktree>/.git
-	 * link file would be broken anyway.  We might try to check
-	 * for that and return a better error message, but I'm not
-	 * sure it is worth it.
+	 * GetOverlappedResult() fails if the watched directory is
+	 * deleted while we were waiting for an overlapped IO to
+	 * complete.  The documentation did not list specific errors,
+	 * but I observed ERROR_ACCESS_DENIED (0x05) errors during
+	 * testing.
+	 *
+	 * Note that we only get notificaiton events for events
+	 * *within* the directory, not *on* the directory itself.
+	 * (These might be properies of the parent directory, for
+	 * example).
+	 *
+	 * NEEDSWORK: We might try to check for the deleted directory
+	 * case and return a better error message, but I'm not sure it
+	 * is worth it.
+	 *
+	 * Shutdown if we get any error.
 	 */
 
 	error(_("GetOverlappedResult failed on '%s' [GLE %ld]"),
@@ -259,6 +473,62 @@ static void cancel_rdcw_watch(struct one_watch *watch)
 }
 
 /*
+ * Process a single relative pathname event.
+ * Return 1 if we should shutdown.
+ */
+static int process_1_worktree_event(
+	struct string_list *cookie_list,
+	struct fsmonitor_batch **batch,
+	const struct strbuf *path,
+	enum fsmonitor_path_type t,
+	DWORD info_action)
+{
+	const char *slash;
+
+	switch (t) {
+	case IS_INSIDE_DOT_GIT_WITH_COOKIE_PREFIX:
+		/* special case cookie files within .git */
+
+		/* Use just the filename of the cookie file. */
+		slash = find_last_dir_sep(path->buf);
+		string_list_append(cookie_list,
+				   slash ? slash + 1 : path->buf);
+		break;
+
+	case IS_INSIDE_DOT_GIT:
+		/* ignore everything inside of "<worktree>/.git/" */
+		break;
+
+	case IS_DOT_GIT:
+		/* "<worktree>/.git" was deleted (or renamed away) */
+		if ((info_action == FILE_ACTION_REMOVED) ||
+		    (info_action == FILE_ACTION_RENAMED_OLD_NAME)) {
+			trace2_data_string("fsmonitor", NULL,
+					   "fsm-listen/dotgit",
+					   "removed");
+			return 1;
+		}
+		break;
+
+	case IS_WORKDIR_PATH:
+		/* queue normal pathname */
+		if (!*batch)
+			*batch = fsmonitor_batch__new();
+		fsmonitor_batch__add_path(*batch, path->buf);
+		break;
+
+	case IS_GITDIR:
+	case IS_INSIDE_GITDIR:
+	case IS_INSIDE_GITDIR_WITH_COOKIE_PREFIX:
+	default:
+		BUG("unexpected path classification '%d' for '%s'",
+		    t, path->buf);
+	}
+
+	return 0;
+}
+
+/*
  * Process filesystem events that happen anywhere (recursively) under the
  * <worktree> root directory.  For a normal working directory, this includes
  * both version controlled files and the contents of the .git/ directory.
@@ -268,12 +538,13 @@ static void cancel_rdcw_watch(struct one_watch *watch)
  */
 static int process_worktree_events(struct fsmonitor_daemon_state *state)
 {
-	struct fsmonitor_daemon_backend_data *data = state->backend_data;
+	struct fsm_listen_data *data = state->listen_data;
 	struct one_watch *watch = data->watch_worktree;
 	struct strbuf path = STRBUF_INIT;
 	struct string_list cookie_list = STRING_LIST_INIT_DUP;
 	struct fsmonitor_batch *batch = NULL;
 	const char *p = watch->buffer;
+	wchar_t wpath_longname[MAX_PATH + 1];
 
 	/*
 	 * If the kernel gets more events than will fit in the kernel
@@ -306,54 +577,64 @@ static int process_worktree_events(struct fsmonitor_daemon_state *state)
 	 */
 	for (;;) {
 		FILE_NOTIFY_INFORMATION *info = (void *)p;
-		const char *slash;
+		wchar_t *wpath = info->FileName;
+		DWORD wpath_len = info->FileNameLength / sizeof(WCHAR);
 		enum fsmonitor_path_type t;
+		enum get_relative_result grr;
+
+		if (watch->has_shortnames) {
+			if (!wcscmp(wpath, watch->dotgit_shortname)) {
+				/*
+				 * This event exactly matches the
+				 * spelling of the shortname of
+				 * ".git", so we can skip some steps.
+				 *
+				 * (This case is odd because the user
+				 * can "rm -rf GIT~1" and we cannot
+				 * use the filesystem to map it back
+				 * to ".git".)
+				 */
+				strbuf_reset(&path);
+				strbuf_addstr(&path, ".git");
+				t = IS_DOT_GIT;
+				goto process_it;
+			}
 
-		strbuf_reset(&path);
-		if (normalize_path_in_utf8(info, &path) == -1)
-			goto skip_this_path;
-
-		t = fsmonitor_classify_path_workdir_relative(path.buf);
-
-		switch (t) {
-		case IS_INSIDE_DOT_GIT_WITH_COOKIE_PREFIX:
-			/* special case cookie files within .git */
-
-			/* Use just the filename of the cookie file. */
-			slash = find_last_dir_sep(path.buf);
-			string_list_append(&cookie_list,
-					   slash ? slash + 1 : path.buf);
-			break;
-
-		case IS_INSIDE_DOT_GIT:
-			/* ignore everything inside of "<worktree>/.git/" */
-			break;
+			if (watch->has_tilde && !wcschr(wpath, L'~')) {
+				/*
+				 * Shortnames on this filesystem have tildes
+				 * and the notification path does not have
+				 * one, so we assume that it is a longname.
+				 */
+				goto normalize_it;
+			}
 
-		case IS_DOT_GIT:
-			/* "<worktree>/.git" was deleted (or renamed away) */
-			if ((info->Action == FILE_ACTION_REMOVED) ||
-			    (info->Action == FILE_ACTION_RENAMED_OLD_NAME)) {
-				trace2_data_string("fsmonitor", NULL,
-						   "fsm-listen/dotgit",
-						   "removed");
+			grr = get_relative_longname(watch, wpath, wpath_len,
+						    wpath_longname,
+						    ARRAY_SIZE(wpath_longname));
+			switch (grr) {
+			case GRR_NO_CONVERSION_NEEDED: /* use info buffer as is */
+				break;
+			case GRR_HAVE_CONVERSION:
+				wpath = wpath_longname;
+				wpath_len = wcslen(wpath);
+				break;
+			default:
+			case GRR_SHUTDOWN:
 				goto force_shutdown;
 			}
-			break;
+		}
 
-		case IS_WORKDIR_PATH:
-			/* queue normal pathname */
-			if (!batch)
-				batch = fsmonitor_batch__new();
-			fsmonitor_batch__add_path(batch, path.buf);
-			break;
+normalize_it:
+		if (normalize_path_in_utf8(wpath, wpath_len, &path) == -1)
+			goto skip_this_path;
 
-		case IS_GITDIR:
-		case IS_INSIDE_GITDIR:
-		case IS_INSIDE_GITDIR_WITH_COOKIE_PREFIX:
-		default:
-			BUG("unexpected path classification '%d' for '%s'",
-			    t, path.buf);
-		}
+		t = fsmonitor_classify_path_workdir_relative(path.buf);
+
+process_it:
+		if (process_1_worktree_event(&cookie_list, &batch, &path, t,
+					     info->Action))
+			goto force_shutdown;
 
 skip_this_path:
 		if (!info->NextEntryOffset)
@@ -382,10 +663,13 @@ force_shutdown:
  * Note that we DO NOT get filesystem events on the external <gitdir>
  * itself (it is not inside something that we are watching).  In particular,
  * we do not get an event if the external <gitdir> is deleted.
+ *
+ * Also, we do not care about shortnames within the external <gitdir>, since
+ * we never send these paths to clients.
  */
 static int process_gitdir_events(struct fsmonitor_daemon_state *state)
 {
-	struct fsmonitor_daemon_backend_data *data = state->backend_data;
+	struct fsm_listen_data *data = state->listen_data;
 	struct one_watch *watch = data->watch_gitdir;
 	struct strbuf path = STRBUF_INIT;
 	struct string_list cookie_list = STRING_LIST_INIT_DUP;
@@ -403,8 +687,10 @@ static int process_gitdir_events(struct fsmonitor_daemon_state *state)
 		const char *slash;
 		enum fsmonitor_path_type t;
 
-		strbuf_reset(&path);
-		if (normalize_path_in_utf8(info, &path) == -1)
+		if (normalize_path_in_utf8(
+			    info->FileName,
+			    info->FileNameLength / sizeof(WCHAR),
+			    &path) == -1)
 			goto skip_this_path;
 
 		t = fsmonitor_classify_path_gitdir_relative(path.buf);
@@ -441,11 +727,11 @@ skip_this_path:
 
 void fsm_listen__loop(struct fsmonitor_daemon_state *state)
 {
-	struct fsmonitor_daemon_backend_data *data = state->backend_data;
+	struct fsm_listen_data *data = state->listen_data;
 	DWORD dwWait;
 	int result;
 
-	state->error_code = 0;
+	state->listen_error_code = 0;
 
 	if (start_rdcw_watch(data, data->watch_worktree) == -1)
 		goto force_error_stop;
@@ -510,7 +796,7 @@ void fsm_listen__loop(struct fsmonitor_daemon_state *state)
 	}
 
 force_error_stop:
-	state->error_code = -1;
+	state->listen_error_code = -1;
 
 force_shutdown:
 	/*
@@ -527,7 +813,7 @@ clean_shutdown:
 
 int fsm_listen__ctor(struct fsmonitor_daemon_state *state)
 {
-	struct fsmonitor_daemon_backend_data *data;
+	struct fsm_listen_data *data;
 
 	CALLOC_ARRAY(data, 1);
 
@@ -538,6 +824,8 @@ int fsm_listen__ctor(struct fsmonitor_daemon_state *state)
 	if (!data->watch_worktree)
 		goto failed;
 
+	check_for_shortnames(data->watch_worktree);
+
 	if (state->nr_paths_watching > 1) {
 		data->watch_gitdir = create_watch(state,
 						  state->path_gitdir_watch.buf);
@@ -558,7 +846,7 @@ int fsm_listen__ctor(struct fsmonitor_daemon_state *state)
 		data->nr_listener_handles++;
 	}
 
-	state->backend_data = data;
+	state->listen_data = data;
 	return 0;
 
 failed:
@@ -571,16 +859,16 @@ failed:
 
 void fsm_listen__dtor(struct fsmonitor_daemon_state *state)
 {
-	struct fsmonitor_daemon_backend_data *data;
+	struct fsm_listen_data *data;
 
-	if (!state || !state->backend_data)
+	if (!state || !state->listen_data)
 		return;
 
-	data = state->backend_data;
+	data = state->listen_data;
 
 	CloseHandle(data->hEventShutdown);
 	destroy_watch(data->watch_worktree);
 	destroy_watch(data->watch_gitdir);
 
-	FREE_AND_NULL(state->backend_data);
+	FREE_AND_NULL(state->listen_data);
 }