clean: do not traverse mount points

It seems to be not exactly rare on Windows to install NTFS junction
points (the equivalent of "bind mounts" on Linux/Unix) in worktrees,
e.g. to map some development tools into a subdirectory.

In such a scenario, it is pretty horrible if `git clean -dfx` traverses
into the mapped directory and starts to "clean up".

Let's just not do that. Let's make sure before we traverse into a
directory that it is not a mount point (or junction).

This addresses #607

Signed-off-by: Johannes Schindelin <[email protected]>

Author: dscho

builtin/clean.c

@@ -34,6 +34,8 @@ static const char *msg_remove = N_("Removing %s\n");
 static const char *msg_would_remove = N_("Would remove %s\n");
 static const char *msg_skip_git_dir = N_("Skipping repository %s\n");
 static const char *msg_would_skip_git_dir = N_("Would skip repository %s\n");
+static const char *msg_skip_mount_point = N_("Skipping mount point %s\n");
+static const char *msg_would_skip_mount_point = N_("Would skip mount point %s\n");
 static const char *msg_warn_remove_failed = N_("failed to remove %s");
 static const char *msg_warn_lstat_failed = N_("could not lstat %s\n");
 static const char *msg_skip_cwd = N_("Refusing to remove current working directory\n");
@@ -175,6 +177,18 @@ static int remove_dirs(struct strbuf *path, const char *prefix, int force_flag,
 		goto out;
 	}
 
+	if (is_mount_point(path)) {
+		if (!quiet) {
+			quote_path(path->buf, prefix, &quoted, 0);
+			printf(dry_run ?
+			       _(msg_would_skip_mount_point) :
+			       _(msg_skip_mount_point), quoted.buf);
+		}
+		*dir_gone = 0;
+
+		goto out;
+	}
+
 	dir = opendir(path->buf);
 	if (!dir) {
 		/* an empty dir could be removed even if it is unreadble */

cache.h

@@ -1289,6 +1289,7 @@ int normalize_path_copy_len(char *dst, const char *src, int *prefix_len);
 int normalize_path_copy(char *dst, const char *src);
 int longest_ancestor_length(const char *path, struct string_list *prefixes);
 char *strip_path_suffix(const char *path, const char *suffix);
+int is_mount_point_via_stat(struct strbuf *path);
 int daemon_avoid_alias(const char *path);
 
 /*

compat/mingw.c

@@ -2509,6 +2509,28 @@ pid_t waitpid(pid_t pid, int *status, int options)
 	return -1;
 }
 
+int mingw_is_mount_point(struct strbuf *path)
+{
+	WIN32_FIND_DATAW findbuf = { 0 };
+	HANDLE handle;
+	wchar_t wfilename[MAX_PATH];
+	int wlen = xutftowcs_path(wfilename, path->buf);
+	if (wlen < 0)
+		die(_("could not get long path for '%s'"), path->buf);
+
+	/* remove trailing slash, if any */
+	if (wlen > 0 && wfilename[wlen - 1] == L'/')
+		wfilename[--wlen] = L'\0';
+
+	handle = FindFirstFileW(wfilename, &findbuf);
+	if (handle == INVALID_HANDLE_VALUE)
+		return 0;
+	FindClose(handle);
+
+	return (findbuf.dwFileAttributes & FILE_ATTRIBUTE_REPARSE_POINT) &&
+		(findbuf.dwReserved0 == IO_REPARSE_TAG_MOUNT_POINT);
+}
+
 int xutftowcsn(wchar_t *wcs, const char *utfs, size_t wcslen, int utflen)
 {
 	int upos = 0, wpos = 0;

compat/mingw.h

@@ -449,6 +449,9 @@ static inline void convert_slashes(char *path)
 		if (*path == '\\')
 			*path = '/';
 }
+struct strbuf;
+int mingw_is_mount_point(struct strbuf *path);
+#define is_mount_point mingw_is_mount_point
 #define PATH_SEP ';'
 char *mingw_query_user_email(void);
 #define query_user_email mingw_query_user_email

git-compat-util.h

@@ -548,6 +548,10 @@ static inline int git_has_dir_sep(const char *path)
 #define has_dir_sep(path) git_has_dir_sep(path)
 #endif
 
+#ifndef is_mount_point
+#define is_mount_point is_mount_point_via_stat
+#endif
+
 #ifndef query_user_email
 #define query_user_email() NULL
 #endif

path.c

@@ -1306,6 +1306,45 @@ char *strip_path_suffix(const char *path, const char *suffix)
 	return offset == -1 ? NULL : xstrndup(path, offset);
 }
 
+int is_mount_point_via_stat(struct strbuf *path)
+{
+	size_t len = path->len;
+	unsigned int current_dev;
+	struct stat st;
+
+	if (!strcmp("/", path->buf))
+		return 1;
+
+	strbuf_addstr(path, "/.");
+	if (lstat(path->buf, &st)) {
+		/*
+		 * If we cannot access the current directory, we cannot say
+		 * that it is a bind mount.
+		 */
+		strbuf_setlen(path, len);
+		return 0;
+	}
+	current_dev = st.st_dev;
+
+	/* Now look at the parent directory */
+	strbuf_addch(path, '.');
+	if (lstat(path->buf, &st)) {
+		/*
+		 * If we cannot access the parent directory, we cannot say
+		 * that it is a bind mount.
+		 */
+		strbuf_setlen(path, len);
+		return 0;
+	}
+	strbuf_setlen(path, len);
+
+	/*
+	 * If the device ID differs between current and parent directory,
+	 * then it is a bind mount.
+	 */
+	return current_dev != st.st_dev;
+}
+
 int daemon_avoid_alias(const char *p)
 {
 	int sl, ndot;

t/t7300-clean.sh

@@ -789,4 +789,13 @@ test_expect_success 'traverse into directories that may have ignored entries' '
 	)
 '
 
+test_expect_success MINGW 'clean does not traverse mount points' '
+	mkdir target &&
+	>target/dont-clean-me &&
+	git init with-mountpoint &&
+	cmd //c "mklink /j with-mountpoint\\mountpoint target" &&
+	git -C with-mountpoint clean -dfx &&
+	test_path_is_file target/dont-clean-me
+'
+
 test_done