From b3722dea3bff1e177104180661fc283610c3c22b Mon Sep 17 00:00:00 2001
From: Shengchen Kan <shengchen.kan@intel.com>
Date: Sun, 1 Mar 2020 16:02:41 +0800
Subject: [PATCH] [X86] Add a private member function determinePaddingPrefix
 for X86AsmBackend

Summary: X86 can reduce the bytes of NOP by padding instructions with prefixes to get a better peformance in some cases. So a private member function `determinePaddingPrefix` is added to determine which prefix is the most suitable.

Reviewers: annita.zhang, reames, MaskRay, craig.topper, LuoYuanke, jyknight

Reviewed By: reames

Subscribers: llvm-commits, dexonsmith, hiraditya

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D75357
---
 llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp | 79 ++++++++++++++++++++++
 llvm/lib/Target/X86/MCTargetDesc/X86BaseInfo.h     | 10 +++
 2 files changed, 89 insertions(+)

diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
index 7633e46..8fa0b25 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
@@ -126,6 +126,8 @@ class X86AsmBackend : public MCAsmBackend {
   X86AlignBranchKind AlignBranchType;
   Align AlignBoundary;
 
+  uint8_t determinePaddingPrefix(const MCInst &Inst) const;
+
   bool isMacroFused(const MCInst &Cmp, const MCInst &Jcc) const;
 
   bool needAlign(MCObjectStreamer &OS) const;
@@ -340,6 +342,83 @@ static bool isFirstMacroFusibleInst(const MCInst &Inst,
   return FIK != X86::FirstMacroFusionInstKind::Invalid;
 }
 
+/// X86 can reduce the bytes of NOP by padding instructions with prefixes to
+/// get a better peformance in some cases. Here, we determine which prefix is
+/// the most suitable.
+///
+/// If the instruction has a segment override prefix, use the existing one.
+/// If the target is 64-bit, use the CS.
+/// If the target is 32-bit,
+///   - If the instruction has a ESP/EBP base register, use SS.
+///   - Otherwise use DS.
+uint8_t X86AsmBackend::determinePaddingPrefix(const MCInst &Inst) const {
+  assert((STI.hasFeature(X86::Mode32Bit) || STI.hasFeature(X86::Mode64Bit)) &&
+         "Prefixes can be added only in 32-bit or 64-bit mode.");
+  const MCInstrDesc &Desc = MCII->get(Inst.getOpcode());
+  uint64_t TSFlags = Desc.TSFlags;
+
+  // Determine where the memory operand starts, if present.
+  int MemoryOperand = X86II::getMemoryOperandNo(TSFlags);
+  if (MemoryOperand != -1)
+    MemoryOperand += X86II::getOperandBias(Desc);
+
+  unsigned SegmentReg = 0;
+  if (MemoryOperand >= 0) {
+    // Check for explicit segment override on memory operand.
+    SegmentReg = Inst.getOperand(MemoryOperand + X86::AddrSegmentReg).getReg();
+  }
+
+  switch (TSFlags & X86II::FormMask) {
+  default:
+    break;
+  case X86II::RawFrmDstSrc: {
+    // Check segment override opcode prefix as needed (not for %ds).
+    if (Inst.getOperand(2).getReg() != X86::DS)
+      SegmentReg = Inst.getOperand(2).getReg();
+    break;
+  }
+  case X86II::RawFrmSrc: {
+    // Check segment override opcode prefix as needed (not for %ds).
+    if (Inst.getOperand(1).getReg() != X86::DS)
+      SegmentReg = Inst.getOperand(1).getReg();
+    break;
+  }
+  case X86II::RawFrmMemOffs: {
+    // Check segment override opcode prefix as needed.
+    SegmentReg = Inst.getOperand(1).getReg();
+    break;
+  }
+  }
+
+  switch (SegmentReg) {
+  case 0:
+    break;
+  case X86::CS:
+    return X86::CS_Encoding;
+  case X86::DS:
+    return X86::DS_Encoding;
+  case X86::ES:
+    return X86::ES_Encoding;
+  case X86::FS:
+    return X86::FS_Encoding;
+  case X86::GS:
+    return X86::GS_Encoding;
+  case X86::SS:
+    return X86::SS_Encoding;
+  }
+
+  if (STI.hasFeature(X86::Mode64Bit))
+    return X86::CS_Encoding;
+
+  if (MemoryOperand >= 0) {
+    unsigned BaseRegNum = MemoryOperand + X86::AddrBaseReg;
+    unsigned BaseReg = Inst.getOperand(BaseRegNum).getReg();
+    if (BaseReg == X86::ESP || BaseReg == X86::EBP)
+      return X86::SS_Encoding;
+  }
+  return X86::DS_Encoding;
+}
+
 /// Check if the two instructions will be macro-fused on the target cpu.
 bool X86AsmBackend::isMacroFused(const MCInst &Cmp, const MCInst &Jcc) const {
   const MCInstrDesc &InstDesc = MCII->get(Jcc.getOpcode());
diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86BaseInfo.h b/llvm/lib/Target/X86/MCTargetDesc/X86BaseInfo.h
index b9758e2..c006c3f 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86BaseInfo.h
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86BaseInfo.h
@@ -383,6 +383,16 @@ namespace X86 {
     AlignBranchRet = 1U << 4,
     AlignBranchIndirect = 1U << 5
   };
+
+  /// Defines the encoding values for segment override prefix.
+  enum EncodingOfSegmentOverridePrefix : uint8_t {
+    CS_Encoding = 0x2E,
+    DS_Encoding = 0x3E,
+    ES_Encoding = 0x26,
+    FS_Encoding = 0x64,
+    GS_Encoding = 0x65,
+    SS_Encoding = 0x36
+  };
 } // end namespace X86;
 
 /// X86II - This namespace holds all of the target specific flags that
-- 
2.7.4