diff -rup binutils.orig/binutils/NEWS binutils-2.35/binutils/NEWS

--- binutils.orig/binutils/NEWS	2021-10-21 15:15:57.838969981 +0100

+++ binutils-2.35/binutils/NEWS	2021-10-21 15:39:14.475071663 +0100

@@ -122,6 +122,15 @@ Changes in 2.32:

 Changes in 2.31:

+* Tools which display names or strings (readelf, strings, nm, objdump)

+  have a new command line option which controls how unicode characters are

+  handled.  By default they are treated as normal for the tool.  Using

+  --unicode=locale will display them according to the current locale.

+  Using --unicode=hex will display them as hex byte values, whilst

+  --unicode=escape will display them as escape sequences.  In addition

+  using --unicode=highlight will display them as unicode escape sequences

+  highlighted in red (if supported by the output device).

+

 * Add support for disassembling netronome Flow Processor (NFP) firmware files.

 * The AArch64 port now supports showing disassembly notes which are emitted

diff -rup binutils.orig/binutils/doc/binutils.texi binutils-2.35/binutils/doc/binutils.texi

--- binutils.orig/binutils/doc/binutils.texi	2021-10-21 15:15:57.839969974 +0100

+++ binutils-2.35/binutils/doc/binutils.texi	2021-10-21 15:39:14.476071657 +0100

@@ -787,6 +787,7 @@ nm [@option{-A}|@option{-o}|@option{--pr

    [@option{-D}|@option{--dynamic}] [@option{-f}@var{format}|@option{--format=}@var{format}]

    [@option{-g}|@option{--extern-only}] [@option{-h}|@option{--help}]

    [@option{-l}|@option{--line-numbers}] [@option{--inlines}]

+   [@option{-U} @var{method}] [@option{--unicode=}@var{method}]

    [@option{-n}|@option{-v}|@option{--numeric-sort}]

    [@option{-P}|@option{--portability}] [@option{-p}|@option{--no-sort}]

    [@option{-r}|@option{--reverse-sort}] [@option{-S}|@option{--print-size}]

@@ -1075,6 +1076,21 @@ Use @var{radix} as the radix for printin

 @cindex undefined symbols

 Display only undefined symbols (those external to each object file).

+@item -U @var{[d|i|l|e|x|h]}

+@itemx --unicode=@var{[default|invalid|locale|escape|hex|highlight]}

+Controls the display of UTF-8 encoded mulibyte characters in strings.

+The default (@option{--unicode=default}) is to give them no special

+treatment.  The @option{--unicode=locale} option displays the sequence

+in the current locale, which may or may not support them.  The options

+@option{--unicode=hex} and @option{--unicode=invalid} display them as

+hex byte sequences enclosed by either angle brackets or curly braces.

+

+The @option{--unicode=escape} option displays them as escape sequences

+(@var{\uxxxx}) and the @option{--unicode=highlight} option displays

+them as escape sequences highlighted in red (if supported by the

+output device).  The colouring is intended to draw attention to the

+presence of unicode sequences where they might not be expected.

+

 @item -V

 @itemx --version

 Show the version number of @command{nm} and exit.

@@ -2176,6 +2192,7 @@ objdump [@option{-a}|@option{--archive-h

         [@option{--prefix-strip=}@var{level}]

         [@option{--insn-width=}@var{width}]

         [@option{--visualize-jumps[=color|=extended-color|=off]}

+        [@option{-U} @var{method}] [@option{--unicode=}@var{method}]

         [@option{-V}|@option{--version}]

         [@option{-H}|@option{--help}]

         @var{objfile}@dots{}

@@ -2843,6 +2860,21 @@ When displaying symbols include those wh

 special in some way and which would not normally be of interest to the

 user.

+@item -U @var{[d|i|l|e|x|h]}

+@itemx --unicode=@var{[default|invalid|locale|escape|hex|highlight]}

+Controls the display of UTF-8 encoded mulibyte characters in strings.

+The default (@option{--unicode=default}) is to give them no special

+treatment.  The @option{--unicode=locale} option displays the sequence

+in the current locale, which may or may not support them.  The options

+@option{--unicode=hex} and @option{--unicode=invalid} display them as

+hex byte sequences enclosed by either angle brackets or curly braces.

+

+The @option{--unicode=escape} option displays them as escape sequences

+(@var{\uxxxx}) and the @option{--unicode=highlight} option displays

+them as escape sequences highlighted in red (if supported by the

+output device).  The colouring is intended to draw attention to the

+presence of unicode sequences where they might not be expected.

+

 @item -V

 @itemx --version

 Print the version number of @command{objdump} and exit.

@@ -3119,6 +3151,7 @@ strings [@option{-afovV}] [@option{-}@va

         [@option{-n} @var{min-len}] [@option{--bytes=}@var{min-len}]

         [@option{-t} @var{radix}] [@option{--radix=}@var{radix}]

         [@option{-e} @var{encoding}] [@option{--encoding=}@var{encoding}]

+        [@option{-U} @var{method}] [@option{--unicode=}@var{method}]

         [@option{-}] [@option{--all}] [@option{--print-file-name}]

         [@option{-T} @var{bfdname}] [@option{--target=}@var{bfdname}]

         [@option{-w}] [@option{--include-all-whitespace}]

@@ -3210,6 +3243,28 @@ single-8-bit-byte characters, @samp{b} =

 littleendian.  Useful for finding wide character strings. (@samp{l}

 and @samp{b} apply to, for example, Unicode UTF-16/UCS-2 encodings).

+@item -U @var{[d|i|l|e|x|h]}

+@itemx --unicode=@var{[default|invalid|locale|escape|hex|highlight]}

+Controls the display of UTF-8 encoded mulibyte characters in strings.

+The default (@option{--unicode=default}) is to give them no special

+treatment, and instead rely upon the setting of the

+@option{--encoding} option.  The other values for this option

+automatically enable @option{--encoding=S}.

+

+The @option{--unicode=invalid} option treats them as non-graphic

+characters and hence not part of a valid string.  All the remaining

+options treat them as valid string characters.

+

+The @option{--unicode=locale} option displays them in the current

+locale, which may or may not support UTF-8 encoding.  The

+@option{--unicode=hex} option displays them as hex byte sequences

+enclosed between @var{<>} characters.  The @option{--unicode=escape}

+option displays them as escape sequences (@var{\uxxxx}) and the

+@option{--unicode=highlight} option displays them as escape sequences

+highlighted in red (if supported by the output device).  The colouring

+is intended to draw attention to the presence of unicode sequences

+where they might not be expected.

+

 @item -T @var{bfdname}

 @itemx --target=@var{bfdname}

 @cindex object code format

@@ -4728,6 +4783,7 @@ readelf [@option{-a}|@option{--all}]

         [@option{-W}|@option{--wide}]

         [@option{-T}|@option{--silent-truncation}]

         [@option{-H}|@option{--help}]

+        [@option{-U} @var{method}|@option{--unicode=}@var{method}]

         @var{elffile}@dots{}

 @c man end

 @end smallexample

@@ -4817,6 +4873,28 @@ Displays the entries in dynamic symbol t

 has one.  The output format is the same as the format used by the

 @option{--syms} option.

+@item -U @var{[d|i|l|e|x|h]}

+@itemx --unicode=[default|invalid|locale|escape|hex|highlight]

+Controls the display of non-ASCII characters in identifier names.

+The default (@option{--unicode=locale} or @option{--unicode=default}) is

+to treat them as multibyte characters and display them in the current

+locale.  All other versions of this option treat the bytes as UTF-8

+encoded values and attempt to interpret them.  If they cannot be

+interpreted or if the @option{--unicode=invalid} option is used then

+they are displayed as a sequence of hex bytes, encloses in curly

+parethesis characters.

+

+Using the @option{--unicode=escape} option will display the characters

+as as unicode escape sequences (@var{\uxxxx}).  Using the

+@option{--unicode=hex} will display the characters as hex byte

+sequences enclosed between angle brackets.

+

+Using the @option{--unicode=highlight} will display the characters as 

+unicode escape sequences but it will also highlighted them in red,

+assuming that colouring is supported by the output device.  The

+colouring is intended to draw attention to the presence of unicode

+sequences when they might not be expected.

+

 @item -e

 @itemx --headers

 Display all the headers in the file.  Equivalent to @option{-h -l -S}.

diff -rup binutils.orig/binutils/nm.c binutils-2.35/binutils/nm.c

--- binutils.orig/binutils/nm.c	2021-10-21 15:15:57.835970002 +0100

+++ binutils-2.35/binutils/nm.c	2021-10-21 15:39:14.476071657 +0100

@@ -38,6 +38,11 @@

 #include "bucomm.h"

 #include "plugin-api.h"

 #include "plugin.h"

+#include "safe-ctype.h"

+

+#ifndef streq

+#define streq(a,b) (strcmp ((a),(b)) == 0)

+#endif

 /* When sorting by size, we use this structure to hold the size and a

    pointer to the minisymbol.  */

@@ -186,6 +191,18 @@ static const char *plugin_target = NULL;

 static bfd *lineno_cache_bfd;

 static bfd *lineno_cache_rel_bfd;

+typedef enum unicode_display_type

+{

+  unicode_default = 0,

+  unicode_locale,

+  unicode_escape,

+  unicode_hex,

+  unicode_highlight,

+  unicode_invalid

+} unicode_display_type;

+

+static unicode_display_type unicode_display = unicode_default;

+

 enum long_option_values

 {

   OPTION_TARGET = 200,

@@ -225,6 +242,7 @@ static struct option long_options[] =

   {"target", required_argument, 0, OPTION_TARGET},

   {"defined-only", no_argument, &defined_only, 1},

   {"undefined-only", no_argument, &undefined_only, 1},

+  {"unicode", required_argument, NULL, 'U'},

   {"version", no_argument, &show_version, 1},

   {"with-symbol-versions", no_argument, &with_symbol_versions, 1},

   {0, no_argument, 0, 0}

@@ -274,6 +292,8 @@ usage (FILE *stream, int status)

   -t, --radix=RADIX      Use RADIX for printing symbol values\n\

       --target=BFDNAME   Specify the target object format as BFDNAME\n\

   -u, --undefined-only   Display only undefined symbols\n\

+  -U {d|s|i|x|e|h}       Specify how to treat UTF-8 encoded unicode characters\n\

+      --unicode={default|show|invalid|hex|escape|highlight}\n\

       --with-symbol-versions  Display version strings after symbol names\n\

   -X 32_64               (ignored)\n\

   @FILE                  Read options from FILE\n\

@@ -389,6 +409,189 @@ get_coff_symbol_type (const struct inter

   return bufp;

 }

+/* Convert a potential UTF-8 encoded sequence in IN into characters in OUT.

+   The conversion format is controlled by the unicode_display variable.

+   Returns the number of characters added to OUT.

+   Returns the number of bytes consumed from IN in CONSUMED.

+   Always consumes at least one byte and displays at least one character.  */

+   

+static unsigned int

+display_utf8 (const unsigned char * in, char * out, unsigned int * consumed)

+{

+  char *        orig_out = out;

+  unsigned int  nchars = 0;

+

+  if (unicode_display == unicode_default)

+    goto invalid;

+

+  if (in[0] < 0xc0)

+    goto invalid;

+

+  if ((in[1] & 0xc0) != 0x80)

+    goto invalid;

+

+  if ((in[0] & 0x20) == 0)

+    {

+      nchars = 2;

+      goto valid;

+    }

+

+  if ((in[2] & 0xc0) != 0x80)

+    goto invalid;

+

+  if ((in[0] & 0x10) == 0)

+    {

+      nchars = 3;

+      goto valid;

+    }

+

+  if ((in[3] & 0xc0) != 0x80)

+    goto invalid;

+

+  nchars = 4;

+

+ valid:

+  switch (unicode_display)

+    {

+    case unicode_locale:

+      /* Copy the bytes into the output buffer as is.  */

+      memcpy (out, in, nchars);

+      out += nchars;

+      break;

+

+    case unicode_invalid:

+    case unicode_hex:

+      {

+      unsigned int j;

+

+      out += sprintf (out, "%c", unicode_display == unicode_hex ? '<' : '{');

+      for (j = 0; j < nchars; j++)

+	out += sprintf (out, "%02x", in [j]);

+      out += sprintf (out, "%c", unicode_display == unicode_hex ? '>' : '}');

+      }

+      break;

+      

+    case unicode_highlight:

+      if (isatty (1))

+	out += sprintf (out, "\x1B[31;47m"); /* Red.  */

+      /* Fall through.  */

+    case unicode_escape:

+      switch (nchars)

+	{

+	case 2:

+	  out += sprintf (out, "\\u%02x%02x",

+		  ((in[0] & 0x1c) >> 2), 

+		  ((in[0] & 0x03) << 6) | (in[1] & 0x3f));

+	  break;

+

+	case 3:

+	  out += sprintf (out, "\\u%02x%02x",

+		  ((in[0] & 0x0f) << 4) | ((in[1] & 0x3c) >> 2),

+		  ((in[1] & 0x03) << 6) | ((in[2] & 0x3f)));

+	  break;

+

+	case 4:

+	  out += sprintf (out, "\\u%02x%02x%02x",

+		  ((in[0] & 0x07) << 6) | ((in[1] & 0x3c) >> 2),

+		  ((in[1] & 0x03) << 6) | ((in[2] & 0x3c) >> 2),

+		  ((in[2] & 0x03) << 6) | ((in[3] & 0x3f)));

+	  break;

+	default:

+	  /* URG.  */

+	  break;

+	}

+

+      if (unicode_display == unicode_highlight && isatty (1))

+	out += sprintf (out, "\033[0m"); /* Default colour.  */

+      break;

+

+    default:

+      /* URG */

+      break;

+    }

+

+  * consumed = nchars;

+  return out - orig_out;

+

+ invalid:

+  /* Not a valid UTF-8 sequence.  */

+  *out = *in;

+  * consumed = 1;

+  return 1;

+}

+

+/* Convert any UTF-8 encoded characters in NAME into the form specified by

+   unicode_display.  Also converts control characters.  Returns a static

+   buffer if conversion was necessary.

+   Code stolen from objdump.c:sanitize_string().  */

+

+static const char *

+convert_utf8 (const char * in)

+{

+  static char *  buffer = NULL;

+  static size_t  buffer_len = 0;

+  const char *   original = in;

+  char *         out;

+

+  /* Paranoia.  */

+  if (in == NULL)

+    return "";

+

+  /* See if any conversion is necessary.

+     In the majority of cases it will not be needed.  */

+  do

+    {

+      unsigned char c = *in++;

+

+      if (c == 0)

+	return original;

+

+      if (ISCNTRL (c))

+	break;

+

+      if (unicode_display != unicode_default && c >= 0xc0)

+	break;

+    }

+  while (1);

+

+  /* Copy the input, translating as needed.  */

+  in = original;

+  if (buffer_len < (strlen (in) * 9))

+    {

+      free ((void *) buffer);

+      buffer_len = strlen (in) * 9;

+      buffer = xmalloc (buffer_len + 1);

+    }

+

+  out = buffer;

+  do

+    {

+      unsigned char c = *in++;

+

+      if (c == 0)

+	break;

+

+      if (ISCNTRL (c))

+	{

+	  *out++ = '^';

+	  *out++ = c + 0x40;

+	}

+      else if (unicode_display != unicode_default && c >= 0xc0)

+	{

+	  unsigned int num_consumed;

+

+	  out += display_utf8 ((const unsigned char *)(in - 1), out, & num_consumed);

+	  in += num_consumed - 1;

+	}

+      else

+	*out++ = c;

+    }

+  while (1);

+

+  *out = 0;

+  return buffer;

+}

+

 /* Print symbol name NAME, read from ABFD, with printf format FORM,

    demangling it if requested.  */

@@ -410,6 +613,9 @@ print_symname (const char *form, struct

 	}

     }

+  if (unicode_display != unicode_default)

+    name = convert_utf8 (name);

+

   printf (form, name);

   if (info != NULL && info->elfinfo)

     {

@@ -1726,7 +1932,7 @@ main (int argc, char **argv)

     fatal (_("fatal error: libbfd ABI mismatch"));

   set_default_bfd_target ();

-  while ((c = getopt_long (argc, argv, "aABCDef:gHhlnopPrSst:uvVvX:",

+  while ((c = getopt_long (argc, argv, "aABCDef:gHhlnopPrSst:uU:vVvX:",

 			   long_options, (int *) 0)) != EOF)

     {

       switch (c)

@@ -1813,6 +2019,24 @@ main (int argc, char **argv)

 	case 'u':

 	  undefined_only = 1;

 	  break;

+

+	case 'U':

+	  if (streq (optarg, "default") || streq (optarg, "d"))

+	    unicode_display = unicode_default;

+	  else if (streq (optarg, "locale") || streq (optarg, "l"))

+	    unicode_display = unicode_locale;

+	  else if (streq (optarg, "escape") || streq (optarg, "e"))

+	    unicode_display = unicode_escape;

+	  else if (streq (optarg, "invalid") || streq (optarg, "i"))

+	    unicode_display = unicode_invalid;

+	  else if (streq (optarg, "hex") || streq (optarg, "x"))

+	    unicode_display = unicode_hex;

+	  else if (streq (optarg, "highlight") || streq (optarg, "h"))

+	    unicode_display = unicode_highlight;

+	  else

+	    fatal (_("invalid argument to -U/--unicode: %s"), optarg);

+	  break;

+

 	case 'V':

 	  show_version = 1;

 	  break;

diff -rup binutils.orig/binutils/objdump.c binutils-2.35/binutils/objdump.c

--- binutils.orig/binutils/objdump.c	2021-10-21 15:15:57.836969995 +0100

+++ binutils-2.35/binutils/objdump.c	2021-10-21 15:40:27.689549518 +0100

@@ -205,6 +205,18 @@ static const struct objdump_private_desc

 /* The list of detected jumps inside a function.  */

 static struct jump_info *detected_jumps = NULL;

+

+typedef enum unicode_display_type

+{

+  unicode_default = 0,

+  unicode_locale,

+  unicode_escape,

+  unicode_hex,

+  unicode_highlight,

+  unicode_invalid

+} unicode_display_type;

+

+static unicode_display_type unicode_display = unicode_default;

 static void usage (FILE *, int) ATTRIBUTE_NORETURN;

 static void

@@ -247,6 +259,9 @@ usage (FILE *stream, int status)

   -r, --reloc              Display the relocation entries in the file\n\

   -R, --dynamic-reloc      Display the dynamic relocation entries in the file\n\

   @<file>                  Read options from <file>\n\

+  -U[d|l|i|x|e|h]          Controls the display of UTF-8 unicode characters\n\

+  --unicode=[default|locale|invalid|hex|escape|highlight]\n"));

+      fprintf (stream, _("\

   -v, --version            Display this program's version number\n\

   -i, --info               List object formats and architectures supported\n\

   -H, --help               Display this information\n\

@@ -395,6 +410,7 @@ static struct option long_options[]=

   {"stop-address", required_argument, NULL, OPTION_STOP_ADDRESS},

   {"syms", no_argument, NULL, 't'},

   {"target", required_argument, NULL, 'b'},

+  {"unicode", required_argument, NULL, 'U'},

   {"version", no_argument, NULL, 'V'},

   {"wide", no_argument, NULL, 'w'},

   {"prefix", required_argument, NULL, OPTION_PREFIX},

@@ -414,10 +430,124 @@ nonfatal (const char *msg)

   bfd_nonfatal (msg);

   exit_status = 1;

 }

+

+/* Convert a potential UTF-8 encoded sequence in IN into characters in OUT.

+   The conversion format is controlled by the unicode_display variable.

+   Returns the number of characters added to OUT.

+   Returns the number of bytes consumed from IN in CONSUMED.

+   Always consumes at least one byte and displays at least one character.  */

+   

+static unsigned int

+display_utf8 (const unsigned char * in, char * out, unsigned int * consumed)

+{

+  char *        orig_out = out;

+  unsigned int  nchars = 0;

+

+  if (unicode_display == unicode_default)

+    goto invalid;

+

+  if (in[0] < 0xc0)

+    goto invalid;

+

+  if ((in[1] & 0xc0) != 0x80)

+    goto invalid;

+

+  if ((in[0] & 0x20) == 0)

+    {

+      nchars = 2;

+      goto valid;

+    }

+

+  if ((in[2] & 0xc0) != 0x80)

+    goto invalid;

+

+  if ((in[0] & 0x10) == 0)

+    {

+      nchars = 3;

+      goto valid;

+    }

+

+  if ((in[3] & 0xc0) != 0x80)

+    goto invalid;

+

+  nchars = 4;

+

+ valid:

+  switch (unicode_display)

+    {

+    case unicode_locale:

+      /* Copy the bytes into the output buffer as is.  */

+      memcpy (out, in, nchars);

+      out += nchars;

+      break;

+

+    case unicode_invalid:

+    case unicode_hex:

+      {

+      unsigned int j;

+

+      out += sprintf (out, "%c", unicode_display == unicode_hex ? '<' : '{');

+      for (j = 0; j < nchars; j++)

+	out += sprintf (out, "%02x", in [j]);

+      out += sprintf (out, "%c", unicode_display == unicode_hex ? '>' : '}');

+      }

+      break;

+      

+    case unicode_highlight:

+      if (isatty (1))

+	out += sprintf (out, "\x1B[31;47m"); /* Red.  */

+      /* Fall through.  */

+    case unicode_escape:

+      switch (nchars)

+	{

+	case 2:

+	  out += sprintf (out, "\\u%02x%02x",

+		  ((in[0] & 0x1c) >> 2), 

+		  ((in[0] & 0x03) << 6) | (in[1] & 0x3f));

+	  break;

+

+	case 3:

+	  out += sprintf (out, "\\u%02x%02x",

+		  ((in[0] & 0x0f) << 4) | ((in[1] & 0x3c) >> 2),

+		  ((in[1] & 0x03) << 6) | ((in[2] & 0x3f)));

+	  break;

+

+	case 4:

+	  out += sprintf (out, "\\u%02x%02x%02x",

+		  ((in[0] & 0x07) << 6) | ((in[1] & 0x3c) >> 2),

+		  ((in[1] & 0x03) << 6) | ((in[2] & 0x3c) >> 2),

+		  ((in[2] & 0x03) << 6) | ((in[3] & 0x3f)));

+	  break;

+	default:

+	  /* URG.  */

+	  break;

+	}

+

+      if (unicode_display == unicode_highlight && isatty (1))

+	out += sprintf (out, "\033[0m"); /* Default colour.  */

+      break;

+

+    default:

+      /* URG */

+      break;

+    }

+

+  * consumed = nchars;

+  return out - orig_out;

+

+ invalid:

+  /* Not a valid UTF-8 sequence.  */

+  *out = *in;

+  * consumed = 1;

+  return 1;

+}

 /* Returns a version of IN with any control characters

    replaced by escape sequences.  Uses a static buffer

-   if necessary.  */

+   if necessary.

+

+   If unicode display is enabled, then also handles the

+   conversion of unicode characters.  */

 static const char *

 sanitize_string (const char * in)

@@ -435,40 +565,50 @@ sanitize_string (const char * in)

      of cases it will not be needed.  */

   do

     {

-      char c = *in++;

+      unsigned char c = *in++;

       if (c == 0)

 	return original;

       if (ISCNTRL (c))

 	break;

+

+      if (unicode_display != unicode_default && c >= 0xc0)

+	break;

     }

   while (1);

   /* Copy the input, translating as needed.  */

   in = original;

-  if (buffer_len < (strlen (in) * 2))

+  if (buffer_len < (strlen (in) * 9))

     {

       free ((void *) buffer);

-      buffer_len = strlen (in) * 2;

+      buffer_len = strlen (in) * 9;

       buffer = xmalloc (buffer_len + 1);

     }

   out = buffer;

   do

     {

-      char c = *in++;

+      unsigned char c = *in++;

       if (c == 0)

 	break;

-      if (!ISCNTRL (c))

-	*out++ = c;

-      else

+      if (ISCNTRL (c))

 	{

 	  *out++ = '^';

 	  *out++ = c + 0x40;

 	}

+      else if (unicode_display != unicode_default && c >= 0xc0)

+	{

+	  unsigned int num_consumed;

+

+	  out += display_utf8 ((const unsigned char *)(in - 1), out, & num_consumed);

+	  in += num_consumed - 1;

+	}

+      else

+	*out++ = c;

     }

   while (1);

@@ -476,7 +616,6 @@ sanitize_string (const char * in)

   return buffer;

 }

-

 /* Returns TRUE if the specified section should be dumped.  */

 static bfd_boolean

@@ -1055,6 +1194,8 @@ objdump_print_symname (bfd *abfd, struct

   name = sanitize_string (name);

+  name = sanitize_string (name);

+

   if (inf != NULL)

     {

       (*inf->fprintf_func) (inf->stream, "%s", name);

@@ -3136,7 +3277,7 @@ disassemble_section (bfd *abfd, asection

   if (!bfd_malloc_and_get_section (abfd, section, &data))

     {

       non_fatal (_("Reading section %s failed because: %s"),

-		 section->name, bfd_errmsg (bfd_get_error ()));

+		 sanitize_string (section->name), bfd_errmsg (bfd_get_error ()));

       return;

     }

@@ -4307,7 +4448,7 @@ dump_section (bfd *abfd, asection *secti

   if (!bfd_get_full_section_contents (abfd, section, &data))

     {

       non_fatal (_("Reading section %s failed because: %s"),

-		 section->name, bfd_errmsg (bfd_get_error ()));

+		 sanitize_string (section->name), bfd_errmsg (bfd_get_error ()));

       return;

     }

@@ -4447,6 +4588,24 @@ dump_symbols (bfd *abfd ATTRIBUTE_UNUSED

 		  free (alloc);

 		}

 	    }

+	  else if (unicode_display != unicode_default

+		   && name != NULL && *name != '\0')

+	    {

+	      const char * sanitized_name;

+

+	      /* If we want to sanitize the name, we do it here, and

+		 temporarily clobber it while calling bfd_print_symbol.

+		 FIXME: This is a gross hack.  */

+	      sanitized_name = sanitize_string (name);

+	      if (sanitized_name != name)

+		(*current)->name = sanitized_name;

+	      else

+		sanitized_name = NULL;

+	      bfd_print_symbol (cur_bfd, stdout, *current,

+				bfd_print_symbol_all);

+	      if (sanitized_name != NULL)