[PATCH v2] precompose_utf8: use a flex array for d_name

[Ihar Hrachyshka <ihar.hrachyshka@gmail.com>]

On macOS, git status may abort while reading a directory entry
whose UTF-8 name grows past NAME_MAX bytes:

  __chk_fail_overflow
  __strlcpy_chk
  precompose_utf8_readdir
  read_directory_recursive
  wt_status_collect
  cmd_status

The precompose wrapper already reallocates dirent_prec_psx for
long names, but d_name is declared as char[NAME_MAX + 1]. A
fortified libc can still see that declared object size and reject a
larger strlcpy bound, even though the allocation was grown.

Make d_name a FLEX_ARRAY and size allocations from offsetof(). That
matches the actual object layout with the dynamic allocation, so the
fortified copy sees a destination whose size can grow with max_name_len.

Add a regression test that creates an over-NAME_MAX non-ASCII basename
and runs status with core.precomposeunicode enabled.

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
---

Changes in v2:
- Drop perl from the regression test and use printf/tr instead.
- Use the minimal 256-byte filename that reproduces the crash.

 compat/precompose_utf8.c     | 12 ++++++++----
 compat/precompose_utf8.h     |  9 +++++----
 t/t3910-mac-os-precompose.sh | 16 ++++++++++++++++
 3 files changed, 29 insertions(+), 8 deletions(-)

diff --git a/compat/precompose_utf8.c b/compat/precompose_utf8.c
index 1711794..8077f62 100644
--- a/compat/precompose_utf8.c
+++ b/compat/precompose_utf8.c
@@ -19,6 +19,11 @@ typedef char *iconv_ibp;
 static const char *repo_encoding = "UTF-8";
 static const char *path_encoding = "UTF-8-MAC";
 
+static size_t dirent_prec_psx_size(size_t max_name_len)
+{
+	return st_add(offsetof(dirent_prec_psx, d_name), max_name_len);
+}
+
 static size_t has_non_ascii(const char *s, size_t maxlen, size_t *strlen_c)
 {
 	const uint8_t *ptr = (const uint8_t *)s;
@@ -114,8 +119,8 @@ const char *precompose_argv_prefix(int argc, const char **argv, const char *pref
 PREC_DIR *precompose_utf8_opendir(const char *dirname)
 {
 	PREC_DIR *prec_dir = xmalloc(sizeof(PREC_DIR));
-	prec_dir->dirent_nfc = xmalloc(sizeof(dirent_prec_psx));
-	prec_dir->dirent_nfc->max_name_len = sizeof(prec_dir->dirent_nfc->d_name);
+	prec_dir->dirent_nfc = xmalloc(dirent_prec_psx_size(NAME_MAX + 1));
+	prec_dir->dirent_nfc->max_name_len = NAME_MAX + 1;
 
 	prec_dir->dirp = opendir(dirname);
 	if (!prec_dir->dirp) {
@@ -145,8 +150,7 @@ struct dirent_prec_psx *precompose_utf8_readdir(PREC_DIR *prec_dir)
 		int ret_errno = errno;
 
 		if (new_maxlen > prec_dir->dirent_nfc->max_name_len) {
-			size_t new_len = sizeof(dirent_prec_psx) + new_maxlen -
-				sizeof(prec_dir->dirent_nfc->d_name);
+			size_t new_len = dirent_prec_psx_size(new_maxlen);
 
 			prec_dir->dirent_nfc = xrealloc(prec_dir->dirent_nfc, new_len);
 			prec_dir->dirent_nfc->max_name_len = new_maxlen;
diff --git a/compat/precompose_utf8.h b/compat/precompose_utf8.h
index fea06cf..c7c3cc2 100644
--- a/compat/precompose_utf8.h
+++ b/compat/precompose_utf8.h
@@ -14,11 +14,12 @@ typedef struct dirent_prec_psx {
 
 	/*
 	 * See http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/dirent.h.html
-	 * NAME_MAX + 1 should be enough, but some systems have
-	 * NAME_MAX=255 and strlen(d_name) may return 508 or 510
-	 * Solution: allocate more when needed, see precompose_utf8_readdir()
+	 * Start with room for NAME_MAX + 1 bytes, but keep d_name as a
+	 * flexible array. Some systems have NAME_MAX=255 while strlen(d_name)
+	 * from readdir() may return 508 or 510 bytes. Grow the allocation as
+	 * needed in precompose_utf8_readdir().
 	 */
-	char   d_name[NAME_MAX+1];
+	char   d_name[FLEX_ARRAY];
 } dirent_prec_psx;
 
 
diff --git a/t/t3910-mac-os-precompose.sh b/t/t3910-mac-os-precompose.sh
index 6d5918c..ea75fb4 100755
--- a/t/t3910-mac-os-precompose.sh
+++ b/t/t3910-mac-os-precompose.sh
@@ -207,6 +207,22 @@ test_expect_success "Add long precomposed filename" '
 	git commit -m "Long filename"
 '
 
+test_expect_success "status with long non-ASCII filename" '
+	test_when_finished "rm -rf long-utf8-status" &&
+	git init long-utf8-status &&
+	(
+		cd long-utf8-status &&
+		test "$(git config --bool core.precomposeunicode)" = true &&
+		long_utf8_name=$(
+			printf "%253s\342\200\224" "" |
+			tr " " a
+		) &&
+		test "$(printf "%s" "$long_utf8_name" | wc -c | tr -d " ")" = 256 &&
+		printf "content\n" >"$long_utf8_name" &&
+		git status --porcelain=v1 >actual
+	)
+'
+
 test_expect_failure 'handle existing decomposed filenames' '
 	echo content >"verbatim.$Adiarnfd" &&
 	git -c core.precomposeunicode=false add "verbatim.$Adiarnfd" &&
-- 
2.54.0