[ms] [llvm-ml] Use default RIP-relative addressing for x64 MASM.

Summary:
When parsing 64-bit MASM, treat memory operands with unspecified base register as RIP-based.

Documented in several places, including https://software.intel.com/en-us/articles/introduction-to-x64-assembly: "Unfortunately, MASM does not allow this form of opcode, but other assemblers like FASM and YASM do. Instead, MASM embeds RIP-relative addressing implicitly."

Reviewed By: thakis

Differential Revision: https://reviews.llvm.org/D73227

Author: ericastor

llvm/include/llvm/MC/MCParser/MCAsmParser.h

@@ -168,6 +168,8 @@ class MCAsmParser {
   virtual void setParsingMSInlineAsm(bool V) = 0;
   virtual bool isParsingMSInlineAsm() = 0;
 
+  virtual bool isParsingMasm() const { return false; }
+
   /// Parse MS-style inline assembly.
   virtual bool parseMSInlineAsm(
       void *AsmLoc, std::string &AsmString, unsigned &NumOutputs,

llvm/lib/MC/MCParser/MasmParser.cpp

@@ -245,6 +245,8 @@ class MasmParser : public MCAsmParser {
   }
   bool isParsingMSInlineAsm() override { return ParsingMSInlineAsm; }
 
+  bool isParsingMasm() const override { return true; }
+
   bool parseMSInlineAsm(void *AsmLoc, std::string &AsmString,
                         unsigned &NumOutputs, unsigned &NumInputs,
                         SmallVectorImpl<std::pair<void *,bool>> &OpDecls,

llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp

@@ -1509,8 +1509,9 @@ std::unique_ptr<X86Operand> X86AsmParser::CreateMemForMSInlineAsm(
   } else {
     BaseReg = BaseReg ? BaseReg : 1;
     return X86Operand::CreateMem(getPointerWidth(), SegReg, Disp, BaseReg,
-                                 IndexReg, Scale, Start, End, Size, Identifier,
-                                 Decl, FrontendSize);
+                                 IndexReg, Scale, Start, End, Size,
+                                 /*DefaultBaseReg=*/X86::RIP, Identifier, Decl,
+                                 FrontendSize);
   }
 }
 
@@ -2073,6 +2074,14 @@ std::unique_ptr<X86Operand> X86AsmParser::ParseIntelOperand() {
     return CreateMemForMSInlineAsm(RegNo, Disp, BaseReg, IndexReg, Scale, Start,
                                    End, Size, SM.getSymName(),
                                    SM.getIdentifierInfo());
+
+  // When parsing x64 MS-style assembly, all memory operands default to
+  // RIP-relative when interpreted as non-absolute references.
+  if (Parser.isParsingMasm() && is64BitMode())
+    return X86Operand::CreateMem(getPointerWidth(), RegNo, Disp, BaseReg,
+                                 IndexReg, Scale, Start, End, Size,
+                                 /*DefaultBaseReg=*/X86::RIP);
+
   if (!(BaseReg || IndexReg || RegNo))
     return X86Operand::CreateMem(getPointerWidth(), Disp, Start, End, Size);
   return X86Operand::CreateMem(getPointerWidth(), RegNo, Disp,

llvm/lib/Target/X86/AsmParser/X86Operand.h

@@ -58,6 +58,7 @@ struct X86Operand final : public MCParsedAsmOperand {
     unsigned SegReg;
     const MCExpr *Disp;
     unsigned BaseReg;
+    unsigned DefaultBaseReg;
     unsigned IndexReg;
     unsigned Scale;
     unsigned Size;
@@ -182,6 +183,10 @@ struct X86Operand final : public MCParsedAsmOperand {
     assert(Kind == Memory && "Invalid access!");
     return Mem.BaseReg;
   }
+  unsigned getMemDefaultBaseReg() const {
+    assert(Kind == Memory && "Invalid access!");
+    return Mem.DefaultBaseReg;
+  }
   unsigned getMemIndexReg() const {
     assert(Kind == Memory && "Invalid access!");
     return Mem.IndexReg;
@@ -546,7 +551,10 @@ struct X86Operand final : public MCParsedAsmOperand {
 
   void addMemOperands(MCInst &Inst, unsigned N) const {
     assert((N == 5) && "Invalid number of operands!");
-    Inst.addOperand(MCOperand::createReg(getMemBaseReg()));
+    if (getMemBaseReg())
+      Inst.addOperand(MCOperand::createReg(getMemBaseReg()));
+    else
+      Inst.addOperand(MCOperand::createReg(getMemDefaultBaseReg()));
     Inst.addOperand(MCOperand::createImm(getMemScale()));
     Inst.addOperand(MCOperand::createReg(getMemIndexReg()));
     addExpr(Inst, getMemDisp());
@@ -639,6 +647,7 @@ struct X86Operand final : public MCParsedAsmOperand {
     Res->Mem.SegReg   = 0;
     Res->Mem.Disp     = Disp;
     Res->Mem.BaseReg  = 0;
+    Res->Mem.DefaultBaseReg = 0;
     Res->Mem.IndexReg = 0;
     Res->Mem.Scale    = 1;
     Res->Mem.Size     = Size;
@@ -654,11 +663,14 @@ struct X86Operand final : public MCParsedAsmOperand {
   static std::unique_ptr<X86Operand>
   CreateMem(unsigned ModeSize, unsigned SegReg, const MCExpr *Disp,
             unsigned BaseReg, unsigned IndexReg, unsigned Scale, SMLoc StartLoc,
-            SMLoc EndLoc, unsigned Size = 0, StringRef SymName = StringRef(),
-            void *OpDecl = nullptr, unsigned FrontendSize = 0) {
+            SMLoc EndLoc, unsigned Size = 0,
+            unsigned DefaultBaseReg = X86::NoRegister,
+            StringRef SymName = StringRef(), void *OpDecl = nullptr,
+            unsigned FrontendSize = 0) {
     // We should never just have a displacement, that should be parsed as an
     // absolute memory operand.
-    assert((SegReg || BaseReg || IndexReg) && "Invalid memory operand!");
+    assert((SegReg || BaseReg || IndexReg || DefaultBaseReg) &&
+           "Invalid memory operand!");
 
     // The scale should always be one of {1,2,4,8}.
     assert(((Scale == 1 || Scale == 2 || Scale == 4 || Scale == 8)) &&
@@ -667,6 +679,7 @@ struct X86Operand final : public MCParsedAsmOperand {
     Res->Mem.SegReg   = SegReg;
     Res->Mem.Disp     = Disp;
     Res->Mem.BaseReg  = BaseReg;
+    Res->Mem.DefaultBaseReg = DefaultBaseReg;
     Res->Mem.IndexReg = IndexReg;
     Res->Mem.Scale    = Scale;
     Res->Mem.Size     = Size;

llvm/test/tools/llvm-ml/rip-relative-addressing.test

@@ -0,0 +1,8 @@
+# RUN: llvm-ml -m32 -filetype=asm %s | FileCheck %s --check-prefix=CHECK-32
+# RUN: llvm-ml -m64 -filetype=asm %s | FileCheck %s --check-prefix=CHECK-64
+
+.code
+mov eax, [4]
+; CHECK-32: mov eax, dword ptr [4]
+; CHECK-64: mov eax, dword ptr [rip + 4]
+END