Sync with 2.14.6

* maint-2.14: (28 commits)
  Git 2.14.6
  mingw: handle `subst`-ed "DOS drives"
  mingw: refuse to access paths with trailing spaces or periods
  mingw: refuse to access paths with illegal characters
  unpack-trees: let merged_entry() pass through do_add_entry()'s errors
  quote-stress-test: offer to test quoting arguments for MSYS2 sh
  t6130/t9350: prepare for stringent Win32 path validation
  quote-stress-test: allow skipping some trials
  quote-stress-test: accept arguments to test via the command-line
  tests: add a helper to stress test argument quoting
  mingw: fix quoting of arguments
  Disallow dubiously-nested submodule git directories
  protect_ntfs: turn on NTFS protection by default
  path: also guard `.gitmodules` against NTFS Alternate Data Streams
  is_ntfs_dotgit(): speed it up
  mingw: disallow backslash characters in tree objects' file names
  path: safeguard `.git` against NTFS Alternate Streams Accesses
  clone --recurse-submodules: prevent name squatting on Windows
  is_ntfs_dotgit(): only verify the leading segment
  test-path-utils: offer to run a protectNTFS/protectHFS benchmark
  ...

2 files changed, 112 insertions, 6 deletions

diff --git a/compat/mingw.c b/compat/mingw.c
index 2d44d21aca..725cd6cb50 100644
--- a/compat/mingw.c
+++ b/compat/mingw.c
@@ -333,6 +333,12 @@ int mingw_mkdir(const char *path, int mode)
 {
 	int ret;
 	wchar_t wpath[MAX_PATH];
+
+	if (!is_valid_win32_path(path)) {
+		errno = EINVAL;
+		return -1;
+	}
+
 	if (xutftowcs_path(wpath, path) < 0)
 		return -1;
 	ret = _wmkdir(wpath);
@@ -345,13 +351,18 @@ int mingw_open (const char *filename, int oflags, ...)
 {
 	va_list args;
 	unsigned mode;
-	int fd;
+	int fd, create = (oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL);
 	wchar_t wfilename[MAX_PATH];
 
 	va_start(args, oflags);
 	mode = va_arg(args, int);
 	va_end(args);
 
+	if (!is_valid_win32_path(filename)) {
+		errno = create ? EINVAL : ENOENT;
+		return -1;
+	}
+
 	if (filename && !strcmp(filename, "/dev/null"))
 		filename = "nul";
 
@@ -413,6 +424,11 @@ FILE *mingw_fopen (const char *filename, const char *otype)
 	int hide = needs_hiding(filename);
 	FILE *file;
 	wchar_t wfilename[MAX_PATH], wotype[4];
+	if (!is_valid_win32_path(filename)) {
+		int create = otype && strchr(otype, 'w');
+		errno = create ? EINVAL : ENOENT;
+		return NULL;
+	}
 	if (filename && !strcmp(filename, "/dev/null"))
 		filename = "nul";
 	if (xutftowcs_path(wfilename, filename) < 0 ||
@@ -435,6 +451,11 @@ FILE *mingw_freopen (const char *filename, const char *otype, FILE *stream)
 	int hide = needs_hiding(filename);
 	FILE *file;
 	wchar_t wfilename[MAX_PATH], wotype[4];
+	if (!is_valid_win32_path(filename)) {
+		int create = otype && strchr(otype, 'w');
+		errno = create ? EINVAL : ENOENT;
+		return NULL;
+	}
 	if (filename && !strcmp(filename, "/dev/null"))
 		filename = "nul";
 	if (xutftowcs_path(wfilename, filename) < 0 ||
@@ -872,7 +893,7 @@ static const char *quote_arg(const char *arg)
 				p++;
 				len++;
 			}
-			if (*p == '"')
+			if (*p == '"' || !*p)
 				n += count*2 + 1;
 			continue;
 		}
@@ -894,16 +915,19 @@ static const char *quote_arg(const char *arg)
 				count++;
 				*d++ = *arg++;
 			}
-			if (*arg == '"') {
+			if (*arg == '"' || !*arg) {
 				while (count-- > 0)
 					*d++ = '\\';
+				/* don't escape the surrounding end quote */
+				if (!*arg)
+					break;
 				*d++ = '\\';
 			}
 		}
 		*d++ = *arg++;
 	}
 	*d++ = '"';
-	*d++ = 0;
+	*d++ = '\0';
 	return q;
 }
 
@@ -1965,6 +1989,30 @@ pid_t waitpid(pid_t pid, int *status, int options)
 	return -1;
 }
 
+int mingw_has_dos_drive_prefix(const char *path)
+{
+	int i;
+
+	/*
+	 * Does it start with an ASCII letter (i.e. highest bit not set),
+	 * followed by a colon?
+	 */
+	if (!(0x80 & (unsigned char)*path))
+		return *path && path[1] == ':' ? 2 : 0;
+
+	/*
+	 * While drive letters must be letters of the English alphabet, it is
+	 * possible to assign virtually _any_ Unicode character via `subst` as
+	 * a drive letter to "virtual drives". Even `1`, or `ä`. Or fun stuff
+	 * like this:
+	 *
+	 *      subst ֍: %USERPROFILE%\Desktop
+	 */
+	for (i = 1; i < 4 && (0x80 & (unsigned char)path[i]); i++)
+		; /* skip first UTF-8 character */
+	return path[i] == ':' ? i + 1 : 0;
+}
+
 int mingw_skip_dos_drive_prefix(char **path)
 {
 	int ret = has_dos_drive_prefix(*path);
@@ -2106,6 +2154,50 @@ static void setup_windows_environment(void)
 		setenv("TERM", "cygwin", 1);
 }
 
+int is_valid_win32_path(const char *path)
+{
+	int preceding_space_or_period = 0, i = 0, periods = 0;
+
+	if (!protect_ntfs)
+		return 1;
+
+	skip_dos_drive_prefix((char **)&path);
+
+	for (;;) {
+		char c = *(path++);
+		switch (c) {
+		case '\0':
+		case '/': case '\\':
+			/* cannot end in ` ` or `.`, except for `.` and `..` */
+			if (preceding_space_or_period &&
+			    (i != periods || periods > 2))
+				return 0;
+			if (!c)
+				return 1;
+
+			i = periods = preceding_space_or_period = 0;
+			continue;
+		case '.':
+			periods++;
+			/* fallthru */
+		case ' ':
+			preceding_space_or_period = 1;
+			i++;
+			continue;
+		case ':': /* DOS drive prefix was already skipped */
+		case '<': case '>': case '"': case '|': case '?': case '*':
+			/* illegal character */
+			return 0;
+		default:
+			if (c > '\0' && c < '\x20')
+				/* illegal character */
+				return 0;
+		}
+		preceding_space_or_period = 0;
+		i++;
+	}
+}
+
 /*
  * Disable MSVCRT command line wildcard expansion (__getmainargs called from
  * mingw startup code, see init.c in mingw runtime).
diff --git a/compat/mingw.h b/compat/mingw.h
index e03aecfe2e..17064665d9 100644
--- a/compat/mingw.h
+++ b/compat/mingw.h
@@ -394,8 +394,8 @@ HANDLE winansi_get_osfhandle(int fd);
  * git specific compatibility
  */
 
-#define has_dos_drive_prefix(path) \
-	(isalpha(*(path)) && (path)[1] == ':' ? 2 : 0)
+int mingw_has_dos_drive_prefix(const char *path);
+#define has_dos_drive_prefix mingw_has_dos_drive_prefix
 int mingw_skip_dos_drive_prefix(char **path);
 #define skip_dos_drive_prefix mingw_skip_dos_drive_prefix
 static inline int mingw_is_dir_sep(int c)
@@ -429,6 +429,20 @@ int mingw_offset_1st_component(const char *path);
 #endif
 
 /**
+ * Verifies that the given path is a valid one on Windows.
+ *
+ * In particular, path segments are disallowed which
+ *
+ * - end in a period or a space (except the special directories `.` and `..`).
+ *
+ * - contain any of the reserved characters, e.g. `:`, `;`, `*`, etc
+ *
+ * Returns 1 upon success, otherwise 0.
+ */
+int is_valid_win32_path(const char *path);
+#define is_valid_path(path) is_valid_win32_path(path)
+
+/**
  * Converts UTF-8 encoded string to UTF-16LE.
  *
  * To support repositories with legacy-encoded file names, invalid UTF-8 bytes