[binutils-gdb] Objdump: Add "-M annotate" option to the AArch64 disassembler.

https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=0166d3cedefcd8f60417427f7b72f46e74a35290

commit 0166d3cedefcd8f60417427f7b72f46e74a35290
Author: Nick Clifton <[email protected]>
Date:   Fri May 8 11:10:05 2026 +0100

    Objdump: Add "-M annotate" option to the AArch64 disassembler.

Diff:
---
 binutils/NEWS                                      |  4 +++
 binutils/doc/binutils.texi                         | 10 +++++-
 .../testsuite/binutils-all/aarch64/aarch64.exp     | 32 +++++++++++++++++
 .../testsuite/binutils-all/aarch64/objdumpM1.c     | 42 ++++++++++++++++++++++
 .../testsuite/binutils-all/aarch64/objdumpM2.c     |  5 +++
 opcodes/aarch64-dis.c                              | 39 ++++++++++++++++++--
 6 files changed, 129 insertions(+), 3 deletions(-)

diff --git a/binutils/NEWS b/binutils/NEWS
index 29821c96d0f..5532670b4a2 100644
--- a/binutils/NEWS
+++ b/binutils/NEWS
@@ -1,5 +1,9 @@
 -*- text -*-
 
+* The AArch64 disassembler now accepts a command line option of "-M annotate"
+  which displays the symbol associated with undefined instructions, should
+  there be one.
+  
 * The x86 and x86_64 disassemblers now accept a command line option of
   "-M annotate-immediates" which displays the symbol associated with immediate
   values, should there be one.
diff --git a/binutils/doc/binutils.texi b/binutils/doc/binutils.texi
index 45df92394b6..198ae8244ef 100644
--- a/binutils/doc/binutils.texi
+++ b/binutils/doc/binutils.texi
@@ -2691,7 +2691,15 @@ compilers.
 For AArch64 targets this switch can be used to set whether instructions are
 disassembled as the most general instruction using the @option{-M no-aliases}
 option or whether instruction notes should be generated as comments in the
-disasssembly using @option{-M notes}.
+disasssembly using @option{-M notes}.  In addition the @option{-M
+annotate} option can be used to customise the handling of undefined
+instructions when disassembling executables and shared libraries.
+Normally the disassembler will just show the hexadecimal value of tge
+undefined instruction, but if annotation is enabled it will first try
+to find a symbol whose value matches the instruction's encoding.  If
+there is a match then the symbol name will be displayed instead.  This
+can be useful when disassembling non-code sections which may contain
+function and data addresses.
 
 For the x86, some of the options duplicate functions of the @option{-m}
 switch, but allow finer grained control.
diff --git a/binutils/testsuite/binutils-all/aarch64/aarch64.exp b/binutils/testsuite/binutils-all/aarch64/aarch64.exp
index 05edcf53203..9699df54894 100644
--- a/binutils/testsuite/binutils-all/aarch64/aarch64.exp
+++ b/binutils/testsuite/binutils-all/aarch64/aarch64.exp
@@ -28,3 +28,35 @@ foreach t $test_list {
     verbose [file rootname $t]
     run_dump_test [file rootname $t]
 }
+
+# Test objdump -M annotate
+
+proc test_objdump_M_annotate { } {
+    global srcdir
+    global subdir
+    global OBJDUMP
+    global OBJDUMPFLAGS
+
+    set test "objdump -M annotate"
+
+    set result [target_compile "$srcdir/$subdir/objdumpM1.c $srcdir/$subdir/objdumpM2.c" tmpdir/objdumpM executable debug]
+    if { $result != "" } {
+	unsupported "$test (build): compile result: $result"
+	return
+    }
+
+    set got [binutils_run $OBJDUMP "$OBJDUMPFLAGS -D -M annotate tmpdir/objdumpM"]
+
+    # Look for something like this in the disassembly:
+    #   420020:	00400780 .inst	0x00400780 ; [func1]
+    set want "; \[func1\]"
+
+    if [regexp $want $got] then {
+	pass $test
+	# file delete objdumpM
+    } else {
+	fail $test
+    }
+}
+
+test_objdump_M_annotate
diff --git a/binutils/testsuite/binutils-all/aarch64/objdumpM1.c b/binutils/testsuite/binutils-all/aarch64/objdumpM1.c
new file mode 100644
index 00000000000..1b7c8604f9b
--- /dev/null
+++ b/binutils/testsuite/binutils-all/aarch64/objdumpM1.c
@@ -0,0 +1,42 @@
+int datum = 22;
+
+extern int func1 (int);
+extern int func2 (int);
+extern int func3 (int);
+extern int func4 (int);
+extern int func5 (int);
+
+/* Create an array of function pointers in the .data section.  */
+struct ptrs
+{
+  int (* fptr)(int);
+  int field;
+}
+fred [5] =
+{
+  { func1, 1 },
+  { func2, 2 },
+  { func3, 3 },
+  { func4, 4 },
+  { func5, 5 }
+};
+
+int main (int arg)
+{
+  /* FIXME: We want a way to make sure that undefined instructions that
+     are inserted via the .inst directive are not annotated.  (Since the .inst
+     directive is used explicitly for instructions and the user does not care
+     if they happen to match a symbolic value).
+     
+     Unfortunately the .inst directive only supports constant expressions so
+     we cannot use an unresolved symbolic value.  Inserting a symbolic value
+     via one of the data directives does not work since they are labeled as
+     data (via the MAP_DATA mapping state) and hence they become eligible
+     for annotation.
+
+     So for now we are stuck.  */
+
+  /* Stop the compiler from optimizing away the function pointer array
+     by using it in a non-predictable manner.  */
+  return fred[arg].fptr (fred[arg].field * datum);
+}
diff --git a/binutils/testsuite/binutils-all/aarch64/objdumpM2.c b/binutils/testsuite/binutils-all/aarch64/objdumpM2.c
new file mode 100644
index 00000000000..a4e8dee4365
--- /dev/null
+++ b/binutils/testsuite/binutils-all/aarch64/objdumpM2.c
@@ -0,0 +1,5 @@
+int func1 (int arg) { return arg * 2; }
+int func2 (int arg) { return arg * 3; }
+int func3 (int arg) { return arg * 4; }
+int func4 (int arg) { return arg * 5; }
+int func5 (int arg) { return arg * 6; }
diff --git a/opcodes/aarch64-dis.c b/opcodes/aarch64-dis.c
index 8544ce4b6d4..a7a170661b2 100644
--- a/opcodes/aarch64-dis.c
+++ b/opcodes/aarch64-dis.c
@@ -49,6 +49,7 @@ static enum map_type last_type;
 static int last_mapping_sym = -1;
 static bfd_vma last_stop_offset = 0;
 static bfd_vma last_mapping_addr = 0;
+static bool annotate_undefined_insns = false;
 
 /* Other options */
 static int no_aliases = 0;	/* If set disassemble as most general inst.  */
@@ -91,6 +92,18 @@ parse_aarch64_dis_option (const char *option, unsigned int len ATTRIBUTE_UNUSED)
       return;
     }
 
+  if (startswith (option, "annotate"))
+    {
+      annotate_undefined_insns = true;
+      return;
+    }
+
+  if (startswith (option, "no-annotate"))
+    {
+      annotate_undefined_insns = false;
+      return;
+    }
+
 #ifdef DEBUG_AARCH64
   if (startswith (option, "debug_dump"))
     {
@@ -4260,8 +4273,24 @@ print_insn_aarch64_word (bfd_vma pc,
 				    ".inst\t");
       (*info->fprintf_styled_func) (info->stream, dis_style_immediate,
 				    "0x%08x", word);
-      (*info->fprintf_styled_func) (info->stream, dis_style_comment_start,
-				    " ; %s", err_msg[ret]);
+      asymbol * sym = NULL;
+      /* See if this "instruction" is actually the address of something.  */
+      if (annotate_undefined_insns
+	  /* Skip values that have been explicitly tagged as code.  */
+	  && last_type == MAP_DATA
+	  /* Skip static object files as symbol values have not be resolved yet.  */
+	  && info->section != NULL
+	  && info->section->owner != NULL
+	  && (info->section->owner->flags & (EXEC_P | DYNAMIC)))
+	{
+	  sym = info->symbol_at_address_func (word, info);
+	  if (sym != NULL)
+	    info->fprintf_styled_func (info->stream, dis_style_symbol,
+				       " ; [%s]", sym->name);
+	}
+      if (sym == NULL)
+	info->fprintf_styled_func (info->stream, dis_style_comment_start,
+				   " ; %s", err_msg[ret]);
       break;
     case ERR_OK:
       user_friendly_fixup (&inst);
@@ -4595,6 +4624,12 @@ with the -M switch (multiple options should be separated by commas):\n"));
   fprintf (stream, _("\n\
   notes            Do print instruction notes.\n"));
 
+  fprintf (stream, _("\n\
+  annotate         Display symbol names for undefined instructions.\n"));
+
+  fprintf (stream, _("\n\
+  no-annotate       Do not display symbol names for undefined instructions.\n"));
+
 #ifdef DEBUG_AARCH64
   fprintf (stream, _("\n\
   debug_dump         Temp switch for debug trace.\n"));