gdb: disassembler opcode display formatting

This commit changes the format of 'disassemble /r' to match GNU
objdump.  Specifically, GDB will now display the instruction bytes in
as 'objdump --wide --disassemble' does.

Here is an example for RISC-V before this patch:

  (gdb) disassemble /r 0x0001018e,0x0001019e
  Dump of assembler code from 0x1018e to 0x1019e:
     0x0001018e <call_me+66>:     03 26 84 fe     lw      a2,-24(s0)
     0x00010192 <call_me+70>:     83 25 c4 fe     lw      a1,-20(s0)
     0x00010196 <call_me+74>:     61 65   lui     a0,0x18
     0x00010198 <call_me+76>:     13 05 85 6a     addi    a0,a0,1704
     0x0001019c <call_me+80>:     f1 22   jal     0x10368 <printf>
  End of assembler dump.

And here's an example after this patch:

  (gdb) disassemble /r 0x0001018e,0x0001019e
  Dump of assembler code from 0x1018e to 0x1019e:
     0x0001018e <call_me+66>:     fe842603                lw      a2,-24(s0)
     0x00010192 <call_me+70>:     fec42583                lw      a1,-20(s0)
     0x00010196 <call_me+74>:     6561                    lui     a0,0x18
     0x00010198 <call_me+76>:     6a850513                addi    a0,a0,1704
     0x0001019c <call_me+80>:     22f1                    jal     0x10368 <printf>
  End of assembler dump.

There are two differences here.  First, the instruction bytes after
the patch are grouped based on the size of the instruction, and are
byte-swapped to little-endian order.

Second, after the patch, GDB now uses the bytes-per-line hint from
libopcodes to add whitespace padding after the opcode bytes, this
means that in most cases the instructions are nicely aligned.

It is still possible for a very long instruction to intrude into the
disassembled text space.  The next example is x86-64, before the
patch:

  (gdb) disassemble /r main
  Dump of assembler code for function main:
     0x0000000000401106 <+0>:     55      push   %rbp
     0x0000000000401107 <+1>:     48 89 e5        mov    %rsp,%rbp
     0x000000000040110a <+4>:     c7 87 d8 00 00 00 01 00 00 00   movl   $0x1,0xd8(%rdi)
     0x0000000000401114 <+14>:    b8 00 00 00 00  mov    $0x0,%eax
     0x0000000000401119 <+19>:    5d      pop    %rbp
     0x000000000040111a <+20>:    c3      ret
  End of assembler dump.

And after the patch:

  (gdb) disassemble /r main
  Dump of assembler code for function main:
     0x0000000000401106 <+0>:     55                      push   %rbp
     0x0000000000401107 <+1>:     48 89 e5                mov    %rsp,%rbp
     0x000000000040110a <+4>:     c7 87 d8 00 00 00 01 00 00 00   movl   $0x1,0xd8(%rdi)
     0x0000000000401114 <+14>:    b8 00 00 00 00          mov    $0x0,%eax
     0x0000000000401119 <+19>:    5d                      pop    %rbp
     0x000000000040111a <+20>:    c3                      ret
  End of assembler dump.

Most instructions are aligned, except for the very long instruction.
Notice too that for x86-64 libopcodes doesn't request that GDB group
the instruction bytes.  This matches the behaviour of objdump.

In case the user really wants the old behaviour, I have added a new
modifier 'disassemble /b', this displays the instruction byte at a
time.  For x86-64, which never groups instruction bytes, /b and /r are
equivalent, but for RISC-V, using /b gets the old layout back (except
that the whitespace for alignment is still present).  Consider our
original RISC-V example, this time using /b:

  (gdb) disassemble /b 0x0001018e,0x0001019e
  Dump of assembler code from 0x1018e to 0x1019e:
     0x0001018e <call_me+66>:     03 26 84 fe             lw      a2,-24(s0)
     0x00010192 <call_me+70>:     83 25 c4 fe             lw      a1,-20(s0)
     0x00010196 <call_me+74>:     61 65                   lui     a0,0x18
     0x00010198 <call_me+76>:     13 05 85 6a             addi    a0,a0,1704
     0x0001019c <call_me+80>:     f1 22                   jal     0x10368 <printf>
  End of assembler dump.

Obviously, this patch is a potentially significant change to the
behaviour or /r.  I could have added /b with the new behaviour and
left /r alone.  However, personally, I feel the new behaviour is
significantly better than the old, hence, I made /r be what I consider
the "better" behaviour.

The reason I prefer the new behaviour is that, when I use /r, I almost
always want to manually decode the instruction for some reason, and
having the bytes displayed in "instruction order" rather than memory
order, just makes this easier.

The 'record instruction-history' command also takes a /r modifier, and
has been modified in the same way as disassemble; /r gets the new
behaviour, and /b has been added to retain the old behaviour.

Finally, the MI command -data-disassemble, is unchanged in behaviour,
this command now requests the raw bytes of the instruction, which is
equivalent to the /b modifier.  This means that the MI output will
remain backward compatible.

1 files changed, 40 insertions, 3 deletions

diff --git a/gdb/disasm.c b/gdb/disasm.c
index ba6ac2d..b5e503f 100644
--- a/gdb/disasm.c
+++ b/gdb/disasm.c
@@ -457,7 +457,7 @@ gdb_pretty_print_disassembler::pretty_print_insn (const struct disasm_insn *insn
 	throw ex;
       }
 
-    if (flags & DISASSEMBLY_RAW_INSN)
+    if ((flags & (DISASSEMBLY_RAW_INSN | DISASSEMBLY_RAW_BYTES)) != 0)
       {
 	/* Build the opcodes using a temporary stream so we can
 	   write them out in a single go for the MI.  */
@@ -467,14 +467,51 @@ gdb_pretty_print_disassembler::pretty_print_insn (const struct disasm_insn *insn
 	m_opcode_data.resize (size);
 	read_code (pc, m_opcode_data.data (), size);
 
-	for (int i = 0; i < size; ++i)
+	/* The disassembler provides information about the best way to
+	   display the instruction bytes to the user.  We provide some sane
+	   defaults in case the disassembler gets it wrong.  */
+	const struct disassemble_info *di = m_di.disasm_info ();
+	int bytes_per_line = std::max (di->bytes_per_line, size);
+	int bytes_per_chunk = std::max (di->bytes_per_chunk, 1);
+
+	/* If the user has requested the instruction bytes be displayed
+	   byte at a time, then handle that here.  Also, if the instruction
+	   is not a multiple of the chunk size (which probably indicates a
+	   disassembler problem) then avoid that causing display problems
+	   by switching to byte at a time mode.  */
+	if ((flags & DISASSEMBLY_RAW_BYTES) != 0
+	    || (size % bytes_per_chunk) != 0)
+	  bytes_per_chunk = 1;
+
+	/* Print the instruction opcodes bytes, grouped into chunks.  */
+	for (int i = 0; i < size; i += bytes_per_chunk)
 	  {
 	    if (i > 0)
 	      m_opcode_stb.puts (" ");
-	    m_opcode_stb.printf ("%02x", (unsigned) m_opcode_data[i]);
+
+	    if (di->display_endian == BFD_ENDIAN_LITTLE)
+	      {
+		for (int k = bytes_per_chunk; k-- != 0; )
+		  m_opcode_stb.printf ("%02x", (unsigned) m_opcode_data[i + k]);
+	      }
+	    else
+	      {
+		for (int k = 0; k < bytes_per_chunk; k++)
+		  m_opcode_stb.printf ("%02x", (unsigned) m_opcode_data[i + k]);
+	      }
+	  }
+
+	/* Calculate required padding.  */
+	int nspaces = 0;
+	for (int i = size; i < bytes_per_line; i += bytes_per_chunk)
+	  {
+	    if (i > size)
+	      nspaces++;
+	    nspaces += bytes_per_chunk * 2;
 	  }
 
 	m_uiout->field_stream ("opcodes", m_opcode_stb);
+	m_uiout->spaces (nspaces);
 	m_uiout->text ("\t");
       }