opcodes/aarch64: split off creation of comment text in disassembler

The function aarch64_print_operand (aarch64-opc.c) is responsible for
converting an instruction operand into the textual representation of
that operand.

In some cases, a comment is included in the operand representation,
though this (currently) only happens for the last operand of the
instruction.

In a future commit I would like to enable the new libopcodes styling
for AArch64, this will allow objdump and GDB[1] to syntax highlight
the disassembler output, however, having operands and comments
combined in a single string like this makes such styling harder.

In this commit, I propose to extend aarch64_print_operand to take a
second buffer.  Any comments for the instruction are written into this
extra buffer.  The two callers of aarch64_print_operand are then
updated to pass an extra buffer, and print any resulting comment.

In this commit no styling is added, that will come later.  However, I
have adjusted the output slightly.  Before this commit some comments
would be separated from the instruction operands with a tab character,
while in other cases the comment was separated with two single spaces.

After this commit I use a single tab character in all cases.  This
means a few test cases needed updated.  If people would prefer me to
move everyone to use the two spaces, then just let me know.  Or maybe
there was a good reason why we used a mix of styles, I could probably
figure out a way to maintain the old output exactly if that is
critical.

Other than that, there should be no user visible changes after this
commit.

[1] GDB patches have not been merged yet, but have been posted to the
GDB mailing list:
https://sourceware.org/pipermail/gdb-patches/2022-June/190142.html

gas/config/tc-aarch64.c

@@ -5358,6 +5358,7 @@ print_operands (char *buf, const aarch64_opcode *opcode,
   for (i = 0; i < AARCH64_MAX_OPND_NUM; ++i)
     {
       char str[128];
+      char cmt[128];
 
       /* We regard the opcode operand info more, however we also look into
 	 the inst->operands to support the disassembling of the optional
@@ -5370,7 +5371,7 @@ print_operands (char *buf, const aarch64_opcode *opcode,
 
       /* Generate the operand string in STR.  */
       aarch64_print_operand (str, sizeof (str), 0, opcode, opnds, i, NULL, NULL,
-			     NULL, cpu_variant);
+			     NULL, cmt, sizeof (cmt), cpu_variant);
 
       /* Delimiter.  */
       if (str[0] != '\0')
@@ -5378,6 +5379,15 @@ print_operands (char *buf, const aarch64_opcode *opcode,
 
       /* Append the operand string.  */
       strcat (buf, str);
+
+      /* Append a comment.  This works because only the last operand ever
+	 adds a comment.  If that ever changes then we'll need to be
+	 smarter here.  */
+      if (cmt[0] != '\0')
+	{
+	  strcat (buf, "\t// ");
+	  strcat (buf, cmt);
+	}
     }
 }
 

include/opcode/aarch64.h

@@ -1371,7 +1371,7 @@ aarch64_get_opcode (enum aarch64_op);
 extern void
 aarch64_print_operand (char *, size_t, bfd_vma, const aarch64_opcode *,
 		       const aarch64_opnd_info *, int, int *, bfd_vma *,
-		       char **,
+		       char **, char *, size_t,
 		       aarch64_feature_set features);
 
 /* Miscellaneous interface.  */

opcodes/aarch64-dis.c

@@ -3287,6 +3287,8 @@ print_operands (bfd_vma pc, const aarch64_opcode *opcode,
   for (i = 0, num_printed = 0; i < AARCH64_MAX_OPND_NUM; ++i)
     {
       char str[128];
+      char cmt[128];
+
       /* We regard the opcode operand info more, however we also look into
 	 the inst->operands to support the disassembling of the optional
 	 operand.
@@ -3298,7 +3300,8 @@ print_operands (bfd_vma pc, const aarch64_opcode *opcode,
 
       /* Generate the operand string in STR.  */
       aarch64_print_operand (str, sizeof (str), pc, opcode, opnds, i, &pcrel_p,
-			     &info->target, &notes, arch_variant);
+			     &info->target, &notes, cmt, sizeof (cmt),
+			     arch_variant);
 
       /* Print the delimiter (taking account of omitted operand(s)).  */
       if (str[0] != '\0')
@@ -3309,7 +3312,15 @@ print_operands (bfd_vma pc, const aarch64_opcode *opcode,
       if (pcrel_p)
 	(*info->print_address_func) (info->target, info);
       else
+	{
 	  (*info->fprintf_func) (info->stream, "%s", str);
+
+	  /* Print the comment.  This works because only the last operand
+	     ever adds a comment.  If that ever changes then we'll need to
+	     be smarter here.  */
+	  if (cmt[0] != '\0')
+	    (*info->fprintf_func) (info->stream, "\t// %s", cmt);
+	}
     }
 
     if (notes && !no_notes)

opcodes/aarch64-opc.c

@@ -3229,6 +3229,7 @@ aarch64_print_operand (char *buf, size_t size, bfd_vma pc,
 		       const aarch64_opcode *opcode,
 		       const aarch64_opnd_info *opnds, int idx, int *pcrel_p,
 		       bfd_vma *address, char** notes,
+		       char *comment, size_t comment_size,
 		       aarch64_feature_set features)
 {
   unsigned int i, num_conds;
@@ -3237,6 +3238,14 @@ aarch64_print_operand (char *buf, size_t size, bfd_vma pc,
   enum aarch64_modifier_kind kind;
   uint64_t addr, enum_value;
 
+  if (comment != NULL)
+    {
+      assert (comment_size > 0);
+      comment[0] = '\0';
+    }
+  else
+    assert (comment_size == 0);
+
   buf[0] = '\0';
   if (pcrel_p)
     *pcrel_p = 0;
@@ -3572,12 +3581,13 @@ aarch64_print_operand (char *buf, size_t size, bfd_vma pc,
 	case 4:	/* e.g. MOV Wd, #<imm32>.  */
 	    {
 	      int imm32 = opnd->imm.value;
-	      snprintf (buf, size, "#0x%-20x\t// #%d", imm32, imm32);
+	      snprintf (buf, size, "#0x%-20x", imm32);
+	      snprintf (comment, comment_size, "#%d", imm32);
 	    }
 	  break;
 	case 8:	/* e.g. MOV Xd, #<imm64>.  */
-	  snprintf (buf, size, "#0x%-20" PRIx64 "\t// #%" PRIi64,
-		    opnd->imm.value, opnd->imm.value);
+	  snprintf (buf, size, "#0x%-20" PRIx64, opnd->imm.value);
+	  snprintf (comment, comment_size, "#%" PRIi64, opnd->imm.value);
 	  break;
 	default:
 	  snprintf (buf, size, "<invalid>");
@@ -3675,12 +3685,12 @@ aarch64_print_operand (char *buf, size_t size, bfd_vma pc,
       num_conds = ARRAY_SIZE (opnd->cond->names);
       for (i = 1; i < num_conds && opnd->cond->names[i]; ++i)
 	{
-	  size_t len = strlen (buf);
+	  size_t len = comment != NULL ? strlen (comment) : 0;
 	  if (i == 1)
-	    snprintf (buf + len, size - len, "  // %s = %s",
+	    snprintf (comment + len, comment_size - len, "%s = %s",
 		      opnd->cond->names[0], opnd->cond->names[i]);
 	  else
-	    snprintf (buf + len, size - len, ", %s",
+	    snprintf (comment + len, comment_size - len, ", %s",
 		      opnd->cond->names[i]);
 	}
       break;