PR 31283 windmc: Parse input correctly on big endian hosts

On big endian hosts (eg. s390x) the windmc tool fails to parse even
trivial files:

  $ cat test.mc
  ;
  $ ./binutils/windmc ./test.mc
  In test.mc at line 1: parser: syntax error.
  In test.mc at line 1: fatal: syntax error.

The tool starts by reading the input as Windows CP1252 and then
converting it internally into an array of UTF-16LE, which it then
processes as an array of unsigned short (typedef unichar).

There are lots of ways this is wrong, but in the specific case of big
endian machines the little endian pairs of bytes are byte-swapped.

For example, the ';' character in the input above is first converted
to UTF16-LE byte sequence { 0x3b, 0x00 }, which is then cast to
unsigned short.  On a big endian machine the first unichar appears to
be 0x3b00.  The lexer is unable to recognize this as the comment
character ((unichar)';') and so parsing fails.

The simple fix is to convert the input to UTF-16BE on big endian
machines (and do the reverse conversion when writing the output).

Fixes: https://sourceware.org/bugzilla/show_bug.cgi?id=31283
Signed-off-by: Richard W.M. Jones <rjones@redhat.com>
(cherry picked from commit 3f8f9745c75b333515f399fc2908ede2ed8014e9)

4 files changed, 259 insertions, 4 deletions

diff --git a/binutils/config.in b/binutils/config.in
index a9a9f71..ee148c7 100644
--- a/binutils/config.in
+++ b/binutils/config.in
@@ -7,6 +7,9 @@
 #endif
 #define __CONFIG_H__ 1
 
+/* Define if building universal (internal helper macro) */
+#undef AC_APPLE_UNIVERSAL_BUILD
+
 /* Should ar and ranlib use -D behavior by default? */
 #undef DEFAULT_AR_DETERMINISTIC
 
@@ -256,6 +259,18 @@
 /* Version number of package */
 #undef VERSION
 
+/* Define WORDS_BIGENDIAN to 1 if your processor stores words with the most
+   significant byte first (like Motorola and SPARC, unlike Intel). */
+#if defined AC_APPLE_UNIVERSAL_BUILD
+# if defined __BIG_ENDIAN__
+#  define WORDS_BIGENDIAN 1
+# endif
+#else
+# ifndef WORDS_BIGENDIAN
+#  undef WORDS_BIGENDIAN
+# endif
+#endif
+
 /* Define to 1 if `lex' declares `yytext' as a `char *' by default, not a
    `char[]'. */
 #undef YYTEXT_POINTER
diff --git a/binutils/configure b/binutils/configure
index 90476f1..a109273 100755
--- a/binutils/configure
+++ b/binutils/configure
@@ -4725,6 +4725,231 @@ $as_echo "$ac_cv_safe_to_define___extensions__" >&6; }
 
 
 
+ { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether byte ordering is bigendian" >&5
+$as_echo_n "checking whether byte ordering is bigendian... " >&6; }
+if ${ac_cv_c_bigendian+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  ac_cv_c_bigendian=unknown
+    # See if we're dealing with a universal compiler.
+    cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#ifndef __APPLE_CC__
+	       not a universal capable compiler
+	     #endif
+	     typedef int dummy;
+
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+
+	# Check for potential -arch flags.  It is not universal unless
+	# there are at least two -arch flags with different values.
+	ac_arch=
+	ac_prev=
+	for ac_word in $CC $CFLAGS $CPPFLAGS $LDFLAGS; do
+	 if test -n "$ac_prev"; then
+	   case $ac_word in
+	     i?86 | x86_64 | ppc | ppc64)
+	       if test -z "$ac_arch" || test "$ac_arch" = "$ac_word"; then
+		 ac_arch=$ac_word
+	       else
+		 ac_cv_c_bigendian=universal
+		 break
+	       fi
+	       ;;
+	   esac
+	   ac_prev=
+	 elif test "x$ac_word" = "x-arch"; then
+	   ac_prev=arch
+	 fi
+       done
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+    if test $ac_cv_c_bigendian = unknown; then
+      # See if sys/param.h defines the BYTE_ORDER macro.
+      cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <sys/types.h>
+	     #include <sys/param.h>
+
+int
+main ()
+{
+#if ! (defined BYTE_ORDER && defined BIG_ENDIAN \
+		     && defined LITTLE_ENDIAN && BYTE_ORDER && BIG_ENDIAN \
+		     && LITTLE_ENDIAN)
+	      bogus endian macros
+	     #endif
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  # It does; now see whether it defined to BIG_ENDIAN or not.
+	 cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <sys/types.h>
+		#include <sys/param.h>
+
+int
+main ()
+{
+#if BYTE_ORDER != BIG_ENDIAN
+		 not big endian
+		#endif
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  ac_cv_c_bigendian=yes
+else
+  ac_cv_c_bigendian=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+    fi
+    if test $ac_cv_c_bigendian = unknown; then
+      # See if <limits.h> defines _LITTLE_ENDIAN or _BIG_ENDIAN (e.g., Solaris).
+      cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <limits.h>
+
+int
+main ()
+{
+#if ! (defined _LITTLE_ENDIAN || defined _BIG_ENDIAN)
+	      bogus endian macros
+	     #endif
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  # It does; now see whether it defined to _BIG_ENDIAN or not.
+	 cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <limits.h>
+
+int
+main ()
+{
+#ifndef _BIG_ENDIAN
+		 not big endian
+		#endif
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  ac_cv_c_bigendian=yes
+else
+  ac_cv_c_bigendian=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+    fi
+    if test $ac_cv_c_bigendian = unknown; then
+      # Compile a test program.
+      if test "$cross_compiling" = yes; then :
+  # Try to guess by grepping values from an object file.
+	 cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+short int ascii_mm[] =
+		  { 0x4249, 0x4765, 0x6E44, 0x6961, 0x6E53, 0x7953, 0 };
+		short int ascii_ii[] =
+		  { 0x694C, 0x5454, 0x656C, 0x6E45, 0x6944, 0x6E61, 0 };
+		int use_ascii (int i) {
+		  return ascii_mm[i] + ascii_ii[i];
+		}
+		short int ebcdic_ii[] =
+		  { 0x89D3, 0xE3E3, 0x8593, 0x95C5, 0x89C4, 0x9581, 0 };
+		short int ebcdic_mm[] =
+		  { 0xC2C9, 0xC785, 0x95C4, 0x8981, 0x95E2, 0xA8E2, 0 };
+		int use_ebcdic (int i) {
+		  return ebcdic_mm[i] + ebcdic_ii[i];
+		}
+		extern int foo;
+
+int
+main ()
+{
+return use_ascii (foo) == use_ebcdic (foo);
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  if grep BIGenDianSyS conftest.$ac_objext >/dev/null; then
+	      ac_cv_c_bigendian=yes
+	    fi
+	    if grep LiTTleEnDian conftest.$ac_objext >/dev/null ; then
+	      if test "$ac_cv_c_bigendian" = unknown; then
+		ac_cv_c_bigendian=no
+	      else
+		# finding both strings is unlikely to happen, but who knows?
+		ac_cv_c_bigendian=unknown
+	      fi
+	    fi
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+else
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+$ac_includes_default
+int
+main ()
+{
+
+	     /* Are we little or big endian?  From Harbison&Steele.  */
+	     union
+	     {
+	       long int l;
+	       char c[sizeof (long int)];
+	     } u;
+	     u.l = 1;
+	     return u.c[sizeof (long int) - 1] == 1;
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_run "$LINENO"; then :
+  ac_cv_c_bigendian=no
+else
+  ac_cv_c_bigendian=yes
+fi
+rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext \
+  conftest.$ac_objext conftest.beam conftest.$ac_ext
+fi
+
+    fi
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_c_bigendian" >&5
+$as_echo "$ac_cv_c_bigendian" >&6; }
+ case $ac_cv_c_bigendian in #(
+   yes)
+     $as_echo "#define WORDS_BIGENDIAN 1" >>confdefs.h
+;; #(
+   no)
+      ;; #(
+   universal)
+
+$as_echo "#define AC_APPLE_UNIVERSAL_BUILD 1" >>confdefs.h
+
+     ;; #(
+   *)
+     as_fn_error $? "unknown endianness
+ presetting ac_cv_c_bigendian=no (or yes) will help" "$LINENO" 5 ;;
+ esac
+
+
 case `pwd` in
   *\ * | *\	*)
     { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: Libtool does not cope well with whitespace in \`pwd\`" >&5
@@ -10858,7 +11083,7 @@ else
   lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2
   lt_status=$lt_dlunknown
   cat > conftest.$ac_ext <<_LT_EOF
-#line 10861 "configure"
+#line 11086 "configure"
 #include "confdefs.h"
 
 #if HAVE_DLFCN_H
@@ -10964,7 +11189,7 @@ else
   lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2
   lt_status=$lt_dlunknown
   cat > conftest.$ac_ext <<_LT_EOF
-#line 10967 "configure"
+#line 11192 "configure"
 #include "confdefs.h"
 
 #if HAVE_DLFCN_H
@@ -16532,6 +16757,7 @@ if test -z "${am__fastdepCC_TRUE}" && test -z "${am__fastdepCC_FALSE}"; then
   as_fn_error $? "conditional \"am__fastdepCC\" was never defined.
 Usually this means the macro was only invoked conditionally." "$LINENO" 5
 fi
+
 if test -z "${ENABLE_LIBCTF_TRUE}" && test -z "${ENABLE_LIBCTF_FALSE}"; then
   as_fn_error $? "conditional \"ENABLE_LIBCTF\" was never defined.
 Usually this means the macro was only invoked conditionally." "$LINENO" 5
diff --git a/binutils/configure.ac b/binutils/configure.ac
index b03e36c..dac72c1 100644
--- a/binutils/configure.ac
+++ b/binutils/configure.ac
@@ -31,6 +31,8 @@ AC_PROG_CC
 AC_GNU_SOURCE
 AC_USE_SYSTEM_EXTENSIONS
 
+AC_C_BIGENDIAN
+
 LT_INIT
 ACX_LARGEFILE
 
diff --git a/binutils/winduni.c b/binutils/winduni.c
index 5b65976..f19de4f 100644
--- a/binutils/winduni.c
+++ b/binutils/winduni.c
@@ -771,7 +771,13 @@ wind_MultiByteToWideChar (rc_uint_type cp, const char *mb,
 
   if (!mb || !iconv_name)
     return 0;
-  iconv_t cd = iconv_open ("UTF-16LE", iconv_name);
+  iconv_t cd = iconv_open (
+#if WORDS_BIGENDIAN
+			   "UTF-16BE",
+#else
+			   "UTF-16LE",
+#endif
+			   iconv_name);
 
   while (1)
     {
@@ -844,7 +850,13 @@ wind_WideCharToMultiByte (rc_uint_type cp, const unichar *u, char *mb, rc_uint_t
 
   if (!u || !iconv_name)
     return 0;
-  iconv_t cd = iconv_open (iconv_name, "UTF-16LE");
+  iconv_t cd = iconv_open (iconv_name,
+#if WORDS_BIGENDIAN
+			   "UTF-16BE"
+#else
+			   "UTF-16LE"
+#endif
+			   );
 
   while (1)
     {