Sync with 2.19.3

* maint-2.19: (34 commits)
  Git 2.19.3
  Git 2.18.2
  Git 2.17.3
  Git 2.16.6
  test-drop-caches: use `has_dos_drive_prefix()`
  Git 2.15.4
  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
  ...

3 files changed, 256 insertions, 6 deletions

diff --git a/t/helper/test-drop-caches.c b/t/helper/test-drop-caches.c
index f65e301f9d..7b4278462b 100644
--- a/t/helper/test-drop-caches.c
+++ b/t/helper/test-drop-caches.c
@@ -8,18 +8,21 @@ static int cmd_sync(void)
 {
 	char Buffer[MAX_PATH];
 	DWORD dwRet;
-	char szVolumeAccessPath[] = "\\\\.\\X:";
+	char szVolumeAccessPath[] = "\\\\.\\XXXX:";
 	HANDLE hVolWrite;
-	int success = 0;
+	int success = 0, dos_drive_prefix;
 
 	dwRet = GetCurrentDirectory(MAX_PATH, Buffer);
 	if ((0 == dwRet) || (dwRet > MAX_PATH))
 		return error("Error getting current directory");
 
-	if (!has_dos_drive_prefix(Buffer))
+	dos_drive_prefix = has_dos_drive_prefix(Buffer);
+	if (!dos_drive_prefix)
 		return error("'%s': invalid drive letter", Buffer);
 
-	szVolumeAccessPath[4] = Buffer[0];
+	memcpy(szVolumeAccessPath, Buffer, dos_drive_prefix);
+	szVolumeAccessPath[dos_drive_prefix] = '\0';
+
 	hVolWrite = CreateFile(szVolumeAccessPath, GENERIC_READ | GENERIC_WRITE,
 		FILE_SHARE_READ | FILE_SHARE_WRITE, NULL, OPEN_EXISTING, 0, NULL);
 	if (INVALID_HANDLE_VALUE == hVolWrite)
diff --git a/t/helper/test-path-utils.c b/t/helper/test-path-utils.c
index ae091d9b3e..e737a941d3 100644
--- a/t/helper/test-path-utils.c
+++ b/t/helper/test-path-utils.c
@@ -177,6 +177,99 @@ static int is_dotgitmodules(const char *path)
 	return is_hfs_dotgitmodules(path) || is_ntfs_dotgitmodules(path);
 }
 
+/*
+ * A very simple, reproducible pseudo-random generator. Copied from
+ * `test-genrandom.c`.
+ */
+static uint64_t my_random_value = 1234;
+
+static uint64_t my_random(void)
+{
+	my_random_value = my_random_value * 1103515245 + 12345;
+	return my_random_value;
+}
+
+/*
+ * A fast approximation of the square root, without requiring math.h.
+ *
+ * It uses Newton's method to approximate the solution of 0 = x^2 - value.
+ */
+static double my_sqrt(double value)
+{
+	const double epsilon = 1e-6;
+	double x = value;
+
+	if (value == 0)
+		return 0;
+
+	for (;;) {
+		double delta = (value / x - x) / 2;
+		if (delta < epsilon && delta > -epsilon)
+			return x + delta;
+		x += delta;
+	}
+}
+
+static int protect_ntfs_hfs_benchmark(int argc, const char **argv)
+{
+	size_t i, j, nr, min_len = 3, max_len = 20;
+	char **names;
+	int repetitions = 15, file_mode = 0100644;
+	uint64_t begin, end;
+	double m[3][2], v[3][2];
+	uint64_t cumul;
+	double cumul2;
+
+	if (argc > 1 && !strcmp(argv[1], "--with-symlink-mode")) {
+		file_mode = 0120000;
+		argc--;
+		argv++;
+	}
+
+	nr = argc > 1 ? strtoul(argv[1], NULL, 0) : 1000000;
+	ALLOC_ARRAY(names, nr);
+
+	if (argc > 2) {
+		min_len = strtoul(argv[2], NULL, 0);
+		if (argc > 3)
+			max_len = strtoul(argv[3], NULL, 0);
+		if (min_len > max_len)
+			die("min_len > max_len");
+	}
+
+	for (i = 0; i < nr; i++) {
+		size_t len = min_len + (my_random() % (max_len + 1 - min_len));
+
+		names[i] = xmallocz(len);
+		while (len > 0)
+			names[i][--len] = (char)(' ' + (my_random() % ('\x7f' - ' ')));
+	}
+
+	for (protect_ntfs = 0; protect_ntfs < 2; protect_ntfs++)
+		for (protect_hfs = 0; protect_hfs < 2; protect_hfs++) {
+			cumul = 0;
+			cumul2 = 0;
+			for (i = 0; i < repetitions; i++) {
+				begin = getnanotime();
+				for (j = 0; j < nr; j++)
+					verify_path(names[j], file_mode);
+				end = getnanotime();
+				printf("protect_ntfs = %d, protect_hfs = %d: %lfms\n", protect_ntfs, protect_hfs, (end-begin) / (double)1e6);
+				cumul += end - begin;
+				cumul2 += (end - begin) * (end - begin);
+			}
+			m[protect_ntfs][protect_hfs] = cumul / (double)repetitions;
+			v[protect_ntfs][protect_hfs] = my_sqrt(cumul2 / (double)repetitions - m[protect_ntfs][protect_hfs] * m[protect_ntfs][protect_hfs]);
+			printf("mean: %lfms, stddev: %lfms\n", m[protect_ntfs][protect_hfs] / (double)1e6, v[protect_ntfs][protect_hfs] / (double)1e6);
+		}
+
+	for (protect_ntfs = 0; protect_ntfs < 2; protect_ntfs++)
+		for (protect_hfs = 0; protect_hfs < 2; protect_hfs++)
+			printf("ntfs=%d/hfs=%d: %lf%% slower\n", protect_ntfs, protect_hfs, (m[protect_ntfs][protect_hfs] - m[0][0]) * 100 / m[0][0]);
+
+	return 0;
+}
+
 int cmd__path_utils(int argc, const char **argv)
 {
 	if (argc == 3 && !strcmp(argv[1], "normalize_path_copy")) {
@@ -291,6 +384,26 @@ int cmd__path_utils(int argc, const char **argv)
 		return !!res;
 	}
 
+	if (argc > 1 && !strcmp(argv[1], "protect_ntfs_hfs"))
+		return !!protect_ntfs_hfs_benchmark(argc - 1, argv + 1);
+
+	if (argc > 1 && !strcmp(argv[1], "is_valid_path")) {
+		int res = 0, expect = 1, i;
+
+		for (i = 2; i < argc; i++)
+			if (!strcmp("--not", argv[i]))
+				expect = 0;
+			else if (expect != is_valid_path(argv[i]))
+				res = error("'%s' is%s a valid path",
+					    argv[i], expect ? " not" : "");
+			else
+				fprintf(stderr,
+					"'%s' is%s a valid path\n",
+					argv[i], expect ? "" : " not");
+
+		return !!res;
+	}
+
 	fprintf(stderr, "%s: unknown function name: %s\n", argv[0],
 		argv[1] ? argv[1] : "(there was none)");
 	return 1;
diff --git a/t/helper/test-run-command.c b/t/helper/test-run-command.c
index 2cc93bb69c..8579b1f7d1 100644
--- a/t/helper/test-run-command.c
+++ b/t/helper/test-run-command.c
@@ -13,8 +13,8 @@
 #include "run-command.h"
 #include "argv-array.h"
 #include "strbuf.h"
-#include <string.h>
-#include <errno.h>
+#include "gettext.h"
+#include "parse-options.h"
 
 static int number_callbacks;
 static int parallel_next(struct child_process *cp,
@@ -50,11 +50,145 @@ static int task_finished(int result,
 	return 1;
 }
 
+static uint64_t my_random_next = 1234;
+
+static uint64_t my_random(void)
+{
+	uint64_t res = my_random_next;
+	my_random_next = my_random_next * 1103515245 + 12345;
+	return res;
+}
+
+static int quote_stress_test(int argc, const char **argv)
+{
+	/*
+	 * We are running a quote-stress test.
+	 * spawn a subprocess that runs quote-stress with a
+	 * special option that echoes back the arguments that
+	 * were passed in.
+	 */
+	char special[] = ".?*\\^_\"'`{}()[]<>@~&+:;$%"; // \t\r\n\a";
+	int i, j, k, trials = 100, skip = 0, msys2 = 0;
+	struct strbuf out = STRBUF_INIT;
+	struct argv_array args = ARGV_ARRAY_INIT;
+	struct option options[] = {
+		OPT_INTEGER('n', "trials", &trials, "Number of trials"),
+		OPT_INTEGER('s', "skip", &skip, "Skip <n> trials"),
+		OPT_BOOL('m', "msys2", &msys2, "Test quoting for MSYS2's sh"),
+		OPT_END()
+	};
+	const char * const usage[] = {
+		"test-tool run-command quote-stress-test <options>",
+		NULL
+	};
+
+	argc = parse_options(argc, argv, NULL, options, usage, 0);
+
+	setenv("MSYS_NO_PATHCONV", "1", 0);
+
+	for (i = 0; i < trials; i++) {
+		struct child_process cp = CHILD_PROCESS_INIT;
+		size_t arg_count, arg_offset;
+		int ret = 0;
+
+		argv_array_clear(&args);
+		if (msys2)
+			argv_array_pushl(&args, "sh", "-c",
+					 "printf %s\\\\0 \"$@\"", "skip", NULL);
+		else
+			argv_array_pushl(&args, "test-tool", "run-command",
+					 "quote-echo", NULL);
+		arg_offset = args.argc;
+
+		if (argc > 0) {
+			trials = 1;
+			arg_count = argc;
+			for (j = 0; j < arg_count; j++)
+				argv_array_push(&args, argv[j]);
+		} else {
+			arg_count = 1 + (my_random() % 5);
+			for (j = 0; j < arg_count; j++) {
+				char buf[20];
+				size_t min_len = 1;
+				size_t arg_len = min_len +
+					(my_random() % (ARRAY_SIZE(buf) - min_len));
+
+				for (k = 0; k < arg_len; k++)
+					buf[k] = special[my_random() %
+						ARRAY_SIZE(special)];
+				buf[arg_len] = '\0';
+
+				argv_array_push(&args, buf);
+			}
+		}
+
+		if (i < skip)
+			continue;
+
+		cp.argv = args.argv;
+		strbuf_reset(&out);
+		if (pipe_command(&cp, NULL, 0, &out, 0, NULL, 0) < 0)
+			return error("Failed to spawn child process");
+
+		for (j = 0, k = 0; j < arg_count; j++) {
+			const char *arg = args.argv[j + arg_offset];
+
+			if (strcmp(arg, out.buf + k))
+				ret = error("incorrectly quoted arg: '%s', "
+					    "echoed back as '%s'",
+					     arg, out.buf + k);
+			k += strlen(out.buf + k) + 1;
+		}
+
+		if (k != out.len)
+			ret = error("got %d bytes, but consumed only %d",
+				     (int)out.len, (int)k);
+
+		if (ret) {
+			fprintf(stderr, "Trial #%d failed. Arguments:\n", i);
+			for (j = 0; j < arg_count; j++)
+				fprintf(stderr, "arg #%d: '%s'\n",
+					(int)j, args.argv[j + arg_offset]);
+
+			strbuf_release(&out);
+			argv_array_clear(&args);
+
+			return ret;
+		}
+
+		if (i && (i % 100) == 0)
+			fprintf(stderr, "Trials completed: %d\n", (int)i);
+	}
+
+	strbuf_release(&out);
+	argv_array_clear(&args);
+
+	return 0;
+}
+
+static int quote_echo(int argc, const char **argv)
+{
+	while (argc > 1) {
+		fwrite(argv[1], strlen(argv[1]), 1, stdout);
+		fputc('\0', stdout);
+		argv++;
+		argc--;
+	}
+
+	return 0;
+}
+
 int cmd__run_command(int argc, const char **argv)
 {
 	struct child_process proc = CHILD_PROCESS_INIT;
 	int jobs;
 
+	if (argc >= 2 && !strcmp(argv[1], "quote-stress-test"))
+		return !!quote_stress_test(argc - 1, argv + 1);
+
+	if (argc >= 2 && !strcmp(argv[1], "quote-echo"))
+		return !!quote_echo(argc - 1, argv + 1);
+
 	if (argc < 3)
 		return 1;
 	while (!strcmp(argv[1], "env")) {