From 69d643ba20a7ab34f13273bb29a286eef0bea6bf Mon Sep 17 00:00:00 2001
From: Kevin Enderby <enderby@apple.com>
Date: Tue, 23 Feb 2010 21:41:24 +0000
Subject: [PATCH] This is the second patch to allow x86 code to be aligned with
 optimal nops. With the compiler changed to use EmitCodeAlignment() it does
 change the functionality.  But X86 assembly code assembled with llvm-mc does
 not change its output.  For that we will eventually change the assembler
 frontend to detect a '.align x, 0x90' when used in a section that
 'hasInstructions' and use EmitCodeAlignment, but will wait until we have
 better target hooks.

llvm-svn: 96988
---
 lib/MC/MCAssembler.cpp | 49 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 47 insertions(+), 2 deletions(-)

diff --git a/lib/MC/MCAssembler.cpp b/lib/MC/MCAssembler.cpp
index 2c698e76f92..96227dbee50 100644
--- a/lib/MC/MCAssembler.cpp
+++ b/lib/MC/MCAssembler.cpp
@@ -1066,9 +1066,54 @@ void MCAssembler::LayoutSection(MCSectionData &SD) {
 ///
 /// FIXME this is X86 32-bit specific and should move to a better place.
 static uint64_t WriteNopData(uint64_t Count, MachObjectWriter &MOW) {
-  // FIXME for now just use the 0x90 nop opcode byte.
+  static const uint8_t Nops[16][16] = {
+    // nop
+    {0x90},
+    // xchg %ax,%ax
+    {0x66, 0x90},
+    // nopl (%[re]ax)
+    {0x0f, 0x1f, 0x00},
+    // nopl 0(%[re]ax)
+    {0x0f, 0x1f, 0x40, 0x00},
+    // nopl 0(%[re]ax,%[re]ax,1)
+    {0x0f, 0x1f, 0x44, 0x00, 0x00},
+    // nopw 0(%[re]ax,%[re]ax,1)
+    {0x66, 0x0f, 0x1f, 0x44, 0x00, 0x00},
+    // nopl 0L(%[re]ax)
+    {0x0f, 0x1f, 0x80, 0x00, 0x00, 0x00, 0x00},
+    // nopl 0L(%[re]ax,%[re]ax,1)
+    {0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00},
+    // nopw 0L(%[re]ax,%[re]ax,1)
+    {0x66, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00},
+    // nopw %cs:0L(%[re]ax,%[re]ax,1)
+    {0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00},
+    // nopl 0(%[re]ax,%[re]ax,1)
+    // nopw 0(%[re]ax,%[re]ax,1)
+    {0x0f, 0x1f, 0x44, 0x00, 0x00,
+     0x66, 0x0f, 0x1f, 0x44, 0x00, 0x00},
+    // nopw 0(%[re]ax,%[re]ax,1)
+    // nopw 0(%[re]ax,%[re]ax,1)
+    {0x66, 0x0f, 0x1f, 0x44, 0x00, 0x00,
+     0x66, 0x0f, 0x1f, 0x44, 0x00, 0x00},
+    // nopw 0(%[re]ax,%[re]ax,1)
+    // nopl 0L(%[re]ax) */
+    {0x66, 0x0f, 0x1f, 0x44, 0x00, 0x00,
+     0x0f, 0x1f, 0x80, 0x00, 0x00, 0x00, 0x00},
+    // nopl 0L(%[re]ax)
+    // nopl 0L(%[re]ax)
+    {0x0f, 0x1f, 0x80, 0x00, 0x00, 0x00, 0x00,
+     0x0f, 0x1f, 0x80, 0x00, 0x00, 0x00, 0x00},
+    // nopl 0L(%[re]ax)
+    // nopl 0L(%[re]ax,%[re]ax,1)
+    {0x0f, 0x1f, 0x80, 0x00, 0x00, 0x00, 0x00,
+     0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00}
+  };
+
+  if (Count > 15)
+    return 0;
+
   for (uint64_t i = 0; i < Count; i++)
-    MOW.Write8 (uint8_t(0x90));
+    MOW.Write8 (uint8_t(Nops[Count - 1][i]));
 
   return Count;
 }