From 3ce135ac2bb6bea2281dce42fbd6b1c231f7cbca Mon Sep 17 00:00:00 2001
From: Samuel Thibault <samuel.thibault@ens-lyon.org>
Date: Mon, 4 Apr 2022 20:28:09 +0200
Subject: [PATCH] Mark re-used buffers as undefined

These are global arrays reused several times. When using them msan and
valgrind thus believe they are always initialized, which reduces their
capacity to detect uninitialized values. We can however explicitly tell them
when they are reused, and thus to be considered as uninitialized.
---
 configure.ac                   |  2 ++
 src/libespeak-ng/compiledata.c |  5 +++++
 src/libespeak-ng/readclause.c  |  2 ++
 src/libespeak-ng/speech.h      | 15 +++++++++++++++
 src/libespeak-ng/wavegen.c     |  2 ++
 5 files changed, 26 insertions(+)

diff --git a/configure.ac b/configure.ac
index 098bf601..84caec35 100644
--- a/configure.ac
+++ b/configure.ac
@@ -250,6 +250,8 @@ else
         ])
 fi
 
+AC_CHECK_HEADERS([valgrind/memcheck.h])
+
 if test "$with_async" = "no" ; then
 	have_async=no
 else
diff --git a/src/libespeak-ng/compiledata.c b/src/libespeak-ng/compiledata.c
index 9d0d6190..8cc26899 100644
--- a/src/libespeak-ng/compiledata.c
+++ b/src/libespeak-ng/compiledata.c
@@ -2608,7 +2608,12 @@ espeak_ng_CompilePhonemeDataPath(long rate,
 	memset(ref_hash_tab, 0, sizeof(ref_hash_tab));
 
 	n_phoneme_tabs = 0;
+	MAKE_MEM_UNDEFINED(&n_phcodes_list, sizeof(n_phcodes_list));
+	MAKE_MEM_UNDEFINED(&phoneme_tab_list2, sizeof(phoneme_tab_list2));
+
 	stack_ix = 0;
+	MAKE_MEM_UNDEFINED(&stack, sizeof(stack));
+
 	StartPhonemeTable("base");
 	CompilePhonemeFiles();
 
diff --git a/src/libespeak-ng/readclause.c b/src/libespeak-ng/readclause.c
index de6cea56..e8dbc57d 100644
--- a/src/libespeak-ng/readclause.c
+++ b/src/libespeak-ng/readclause.c
@@ -997,7 +997,9 @@ void InitText2(void)
 	ungot_char2 = 0;
 
 	n_ssml_stack = 1;
+	MAKE_MEM_UNDEFINED(&ssml_stack[1], sizeof(ssml_stack) - sizeof(ssml_stack[0]));
 	n_param_stack = 1;
+	MAKE_MEM_UNDEFINED(&param_stack[1], sizeof(param_stack) - sizeof(param_stack[0]));
 	ssml_stack[0].tag_type = 0;
 
 	for (param = 0; param < N_SPEECH_PARAM; param++)
diff --git a/src/libespeak-ng/speech.h b/src/libespeak-ng/speech.h
index 31a7aa9c..5e2433b5 100644
--- a/src/libespeak-ng/speech.h
+++ b/src/libespeak-ng/speech.h
@@ -23,6 +23,21 @@
 #include <endian.h>               // for BYTE_ORDER, BIG_ENDIAN
 #include <espeak-ng/espeak_ng.h>
 
+#if defined(__has_feature)
+#  if __has_feature(memory_sanitizer)
+#    include <sanitizer/msan_interface.h>
+#    define MAKE_MEM_UNDEFINED(addr, len) __msan_unpoison(addr, len)
+#  endif
+#endif
+
+#ifndef MAKE_MEM_UNDEFINED
+#  ifdef HAVE_VALGRIND_MEMCHECK_H
+#    include <valgrind/memcheck.h>
+#    define MAKE_MEM_UNDEFINED(addr, len) VALGRIND_MAKE_MEM_UNDEFINED(addr, len)
+#  else
+#    define MAKE_MEM_UNDEFINED(addr, len) ((void) (addr, len))
+#  endif
+#endif
 
 #ifdef __cplusplus
 extern "C"
diff --git a/src/libespeak-ng/wavegen.c b/src/libespeak-ng/wavegen.c
index 2b3ede27..9441f201 100644
--- a/src/libespeak-ng/wavegen.c
+++ b/src/libespeak-ng/wavegen.c
@@ -45,6 +45,7 @@
 #endif
 
 #include "sintab.h"
+#include "speech.h"
 
 static void SetSynth(int length, int modn, frame_t *fr1, frame_t *fr2, voice_t *v);
 
@@ -271,6 +272,7 @@ void WcmdqInc()
 
 static void WcmdqIncHead()
 {
+	MAKE_MEM_UNDEFINED(&wcmdq[wcmdq_head], sizeof(wcmdq[wcmdq_head]));
 	wcmdq_head++;
 	if (wcmdq_head >= N_WCMDQ) wcmdq_head = 0;
 }