From 2ace1b68ac717fc284b64944a38705ff57871ba2 Mon Sep 17 00:00:00 2001
From: Rafael Espindola <rafael.espindola@gmail.com>
Date: Thu, 25 Nov 2010 17:14:16 +0000
Subject: [PATCH] Use multiple 0x66 prefixes so that all nops up to 15 bytes
 are a single instruction.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120147 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/X86/X86AsmBackend.cpp   | 32 ++++++++----------------------
 test/MC/MachO/x86_32-optimal_nop.s |  2 +-
 2 files changed, 9 insertions(+), 25 deletions(-)

diff --git a/lib/Target/X86/X86AsmBackend.cpp b/lib/Target/X86/X86AsmBackend.cpp
index fd823bf5244..ab8f6287452 100644
--- a/lib/Target/X86/X86AsmBackend.cpp
+++ b/lib/Target/X86/X86AsmBackend.cpp
@@ -211,10 +211,8 @@ void X86AsmBackend::RelaxInstruction(const MCInst &Inst, MCInst &Res) const {
 /// WriteNopData - Write optimal nops to the output file for the \arg Count
 /// bytes.  This returns the number of bytes written.  It may return 0 if
 /// the \arg Count is more than the maximum optimal nops.
-///
-/// FIXME this is X86 32-bit specific and should move to a better place.
 bool X86AsmBackend::WriteNopData(uint64_t Count, MCObjectWriter *OW) const {
-  static const uint8_t Nops[16][16] = {
+  static const uint8_t Nops[10][10] = {
     // nop
     {0x90},
     // xchg %ax,%ax
@@ -235,30 +233,16 @@ bool X86AsmBackend::WriteNopData(uint64_t Count, MCObjectWriter *OW) const {
     {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},
-    // nopw %cs:0L(%[re]ax,%[re]ax,1)
-    {0x66, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 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}
   };
 
   // Write an optimal sequence for the first 15 bytes.
-  uint64_t OptimalCount = (Count < 16) ? Count : 15;
-  for (uint64_t i = 0, e = OptimalCount; i != e; i++)
-    OW->Write8(Nops[OptimalCount - 1][i]);
+  const uint64_t OptimalCount = (Count < 16) ? Count : 15;
+  const uint64_t Prefixes = OptimalCount <= 10 ? 0 : OptimalCount - 10;
+  for (uint64_t i = 0, e = Prefixes; i != e; i++)
+    OW->Write8(0x66);
+  const uint64_t Rest = OptimalCount - Prefixes;
+  for (uint64_t i = 0, e = Rest; i != e; i++)
+    OW->Write8(Nops[Rest - 1][i]);
 
   // Finish with single byte nops.
   for (uint64_t i = OptimalCount, e = Count; i != e; ++i)
diff --git a/test/MC/MachO/x86_32-optimal_nop.s b/test/MC/MachO/x86_32-optimal_nop.s
index 09c541f5603..31cf2402834 100644
--- a/test/MC/MachO/x86_32-optimal_nop.s
+++ b/test/MC/MachO/x86_32-optimal_nop.s
@@ -192,7 +192,7 @@ f0:
 // CHECK:    ),
 // CHECK:   ('_relocations', [
 // CHECK:   ])
-// CHECK:   ('_section_data', 'c390c300 00000000 00000000 00000000 c3c36690 c3000000 00000000 00000000 c30f1f00 c3000000 00000000 00000000 c3c3c3c3 0f1f4000 c3000000 00000000 c3c3c30f 1f440000 c3000000 00000000 c3c3660f 1f440000 c3000000 00000000 c30f1f80 00000000 c3000000 00000000 c3c3c3c3 c3c3c3c3 c3000000 00000000 c3c3c3c3 c3c3c366 0f1f8400 00000000 c3000000 00000000 00000000 00000000 c3c3c3c3 c3c3c366 0f1f8400 00000000 c3000000 00000000 00000000 00000000 c3c3c3c3 c366662e 0f1f8400 00000000 c3000000 00000000 00000000 00000000 c3c3c3c3 660f1f44 0000660f 1f440000 c3000000 00000000 00000000 00000000 c3c3c366 0f1f4400 000f1f80 00000000 c3000000 00000000 00000000 00000000 c3c30f1f 80000000 000f1f80 00000000 c3000000 00000000 00000000 00000000 c30f1f80 00000000 0f1f8400 00000000 c3')
+// CHECK:   ('_section_data', 'c390c300 00000000 00000000 00000000 c3c36690 c3000000 00000000 00000000 c30f1f00 c3000000 00000000 00000000 c3c3c3c3 0f1f4000 c3000000 00000000 c3c3c30f 1f440000 c3000000 00000000 c3c3660f 1f440000 c3000000 00000000 c30f1f80 00000000 c3000000 00000000 c3c3c3c3 c3c3c3c3 c3000000 00000000 c3c3c3c3 c3c3c366 0f1f8400 00000000 c3000000 00000000 00000000 00000000 c3c3c3c3 c3c3c366 0f1f8400 00000000 c3000000 00000000 00000000 00000000 c3c3c3c3 c366662e 0f1f8400 00000000 c3000000 00000000 00000000 00000000 c3c3c3c3 6666662e 0f1f8400 00000000 c3000000 00000000 00000000 00000000 c3c3c366 6666662e 0f1f8400 00000000 c3000000 00000000 00000000 00000000 c3c36666 6666662e 0f1f8400 00000000 c3000000 00000000 00000000 00000000 c3666666 6666662e 0f1f8400 00000000 c3')
 // CHECK:     # Section 1
 // CHECK:    (('section_name', '__const\x00\x00\x00\x00\x00\x00\x00\x00\x00')
 // CHECK:     ('segment_name', '__TEXT\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00')
-- 
2.34.1