[MC] Change AsmParser to leverage Assembler during evaluation

Teach AsmParser to check with Assembler for when evaluating constant
expressions.  This improves the handing of preprocessor expressions
that must be resolved at parse time. This idiom can be found as
assembling-time assertion checks in source-level assemblers. Note that
this relies on the MCStreamer to keep sufficient tabs on Section /
Fragment information which the MCAsmStreamer does not. As a result the
textual output may fail where the equivalent object generation would
pass. This can most easily be resolved by folding the MCAsmStreamer
and MCObjectStreamer together which is planned for in a separate
patch.

Currently, this feature is only enabled for assembly input, keeping IR
compilation consistent between assembly and object generation.

Reviewers: echristo, rnk, probinson, espindola, peter.smith

Reviewed By: peter.smith

Subscribers: eraman, peter.smith, arichardson, jyknight, hiraditya, llvm-commits

Differential Revision: https://reviews.llvm.org/D45164

llvm-svn: 331218

6 files changed, 43 insertions, 20 deletions

diff --git a/llvm/lib/CodeGen/AsmPrinter/AsmPrinterInlineAsm.cpp b/llvm/lib/CodeGen/AsmPrinter/AsmPrinterInlineAsm.cpp
index 04a72ba3d73..4159eb19423 100644
--- a/llvm/lib/CodeGen/AsmPrinter/AsmPrinterInlineAsm.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/AsmPrinterInlineAsm.cpp
@@ -132,6 +132,9 @@ void AsmPrinter::EmitInlineAsm(StringRef Str, const MCSubtargetInfo &STI,
   std::unique_ptr<MCAsmParser> Parser(
       createMCAsmParser(SrcMgr, OutContext, *OutStreamer, *MAI, BufNum));
 
+  // Do not use assembler-level information for parsing inline assembly.
+  OutStreamer->setUseAssemblerInfoForParsing(false);
+
   // We create a new MCInstrInfo here since we might be at the module level
   // and not have a MachineFunction to initialize the TargetInstrInfo from and
   // we only need MCInstrInfo for asm parsing. We create one unconditionally
diff --git a/llvm/lib/MC/MCAsmStreamer.cpp b/llvm/lib/MC/MCAsmStreamer.cpp
index 632a0308f29..d19c8c21dd0 100644
--- a/llvm/lib/MC/MCAsmStreamer.cpp
+++ b/llvm/lib/MC/MCAsmStreamer.cpp
@@ -78,6 +78,9 @@ public:
         InstPrinter->setCommentStream(CommentStream);
   }
 
+  MCAssembler &getAssembler() { return *Assembler; }
+  MCAssembler *getAssemblerPtr() override { return nullptr; }
+
   inline void EmitEOL() {
     // Dump Explicit Comments here.
     emitExplicitComments();
@@ -1656,10 +1659,10 @@ void MCAsmStreamer::AddEncodingComment(const MCInst &Inst,
   raw_svector_ostream VecOS(Code);
 
   // If we have no code emitter, don't emit code.
-  if (!Assembler->getEmitterPtr())
+  if (!getAssembler().getEmitterPtr())
     return;
 
-  Assembler->getEmitter().encodeInstruction(Inst, VecOS, Fixups, STI);
+  getAssembler().getEmitter().encodeInstruction(Inst, VecOS, Fixups, STI);
 
   // If we are showing fixups, create symbolic markers in the encoded
   // representation. We do this by making a per-bit map to the fixup item index,
@@ -1672,7 +1675,7 @@ void MCAsmStreamer::AddEncodingComment(const MCInst &Inst,
   for (unsigned i = 0, e = Fixups.size(); i != e; ++i) {
     MCFixup &F = Fixups[i];
     const MCFixupKindInfo &Info =
-        Assembler->getBackend().getFixupKindInfo(F.getKind());
+        getAssembler().getBackend().getFixupKindInfo(F.getKind());
     for (unsigned j = 0; j != Info.TargetSize; ++j) {
       unsigned Index = F.getOffset() * 8 + Info.TargetOffset + j;
       assert(Index < Code.size() * 8 && "Invalid offset in fixup!");
@@ -1737,7 +1740,7 @@ void MCAsmStreamer::AddEncodingComment(const MCInst &Inst,
   for (unsigned i = 0, e = Fixups.size(); i != e; ++i) {
     MCFixup &F = Fixups[i];
     const MCFixupKindInfo &Info =
-        Assembler->getBackend().getFixupKindInfo(F.getKind());
+        getAssembler().getBackend().getFixupKindInfo(F.getKind());
     OS << "  fixup " << char('A' + i) << " - " << "offset: " << F.getOffset()
        << ", value: " << *F.getValue() << ", kind: " << Info.Name << "\n";
   }
diff --git a/llvm/lib/MC/MCExpr.cpp b/llvm/lib/MC/MCExpr.cpp
index 4dcfa85d520..2ad19a793ad 100644
--- a/llvm/lib/MC/MCExpr.cpp
+++ b/llvm/lib/MC/MCExpr.cpp
@@ -441,6 +441,10 @@ bool MCExpr::evaluateAsAbsolute(int64_t &Res, const MCAssembler &Asm) const {
   return evaluateAsAbsolute(Res, &Asm, nullptr, nullptr);
 }
 
+bool MCExpr::evaluateAsAbsolute(int64_t &Res, const MCAssembler *Asm) const {
+  return evaluateAsAbsolute(Res, Asm, nullptr, nullptr);
+}
+
 bool MCExpr::evaluateKnownAbsolute(int64_t &Res,
                                    const MCAsmLayout &Layout) const {
   return evaluateAsAbsolute(Res, &Layout.getAssembler(), &Layout, nullptr,
@@ -494,7 +498,7 @@ static void AttemptToFoldSymbolOffsetDifference(
     return;
 
   if (SA.getFragment() == SB.getFragment() && !SA.isVariable() &&
-      !SB.isVariable()) {
+      !SA.isUnset() && !SB.isVariable() && !SB.isUnset()) {
     Addend += (SA.getOffset() - SB.getOffset());
 
     // Pointers to Thumb symbols need to have their low-bit set to allow
diff --git a/llvm/lib/MC/MCObjectStreamer.cpp b/llvm/lib/MC/MCObjectStreamer.cpp
index 19c41df473c..ebedd9bf815 100644
--- a/llvm/lib/MC/MCObjectStreamer.cpp
+++ b/llvm/lib/MC/MCObjectStreamer.cpp
@@ -35,6 +35,15 @@ MCObjectStreamer::MCObjectStreamer(MCContext &Context,
 
 MCObjectStreamer::~MCObjectStreamer() {}
 
+// AssemblerPtr is used for evaluation of expressions and causes
+// difference between asm and object outputs. Return nullptr to in
+// inline asm mode to limit divergence to assembly inputs.
+MCAssembler *MCObjectStreamer::getAssemblerPtr() {
+  if (getUseAssemblerInfoForParsing())
+    return Assembler.get();
+  return nullptr;
+}
+
 void MCObjectStreamer::flushPendingLabels(MCFragment *F, uint64_t FOffset) {
   if (PendingLabels.empty())
     return;
@@ -155,7 +164,7 @@ void MCObjectStreamer::EmitValueImpl(const MCExpr *Value, unsigned Size,
 
   // Avoid fixups when possible.
   int64_t AbsValue;
-  if (Value->evaluateAsAbsolute(AbsValue, getAssembler())) {
+  if (Value->evaluateAsAbsolute(AbsValue, getAssemblerPtr())) {
     if (!isUIntN(8 * Size, AbsValue) && !isIntN(8 * Size, AbsValue)) {
       getContext().reportError(
           Loc, "value evaluated as " + Twine(AbsValue) + " is out of range.");
@@ -217,7 +226,7 @@ void MCObjectStreamer::EmitLabel(MCSymbol *Symbol, SMLoc Loc, MCFragment *F) {
 
 void MCObjectStreamer::EmitULEB128Value(const MCExpr *Value) {
   int64_t IntValue;
-  if (Value->evaluateAsAbsolute(IntValue, getAssembler())) {
+  if (Value->evaluateAsAbsolute(IntValue, getAssemblerPtr())) {
     EmitULEB128IntValue(IntValue);
     return;
   }
@@ -226,7 +235,7 @@ void MCObjectStreamer::EmitULEB128Value(const MCExpr *Value) {
 
 void MCObjectStreamer::EmitSLEB128Value(const MCExpr *Value) {
   int64_t IntValue;
-  if (Value->evaluateAsAbsolute(IntValue, getAssembler())) {
+  if (Value->evaluateAsAbsolute(IntValue, getAssemblerPtr())) {
     EmitSLEB128IntValue(IntValue);
     return;
   }
@@ -254,7 +263,7 @@ bool MCObjectStreamer::changeSectionImpl(MCSection *Section,
 
   int64_t IntSubsection = 0;
   if (Subsection &&
-      !Subsection->evaluateAsAbsolute(IntSubsection, getAssembler()))
+      !Subsection->evaluateAsAbsolute(IntSubsection, getAssemblerPtr()))
     report_fatal_error("Cannot evaluate subsection number");
   if (IntSubsection < 0 || IntSubsection > 8192)
     report_fatal_error("Subsection number out of range");
@@ -400,7 +409,7 @@ void MCObjectStreamer::EmitDwarfAdvanceLineAddr(int64_t LineDelta,
   }
   const MCExpr *AddrDelta = buildSymbolDiff(*this, Label, LastLabel);
   int64_t Res;
-  if (AddrDelta->evaluateAsAbsolute(Res, getAssembler())) {
+  if (AddrDelta->evaluateAsAbsolute(Res, getAssemblerPtr())) {
     MCDwarfLineAddr::Emit(this, Assembler->getDWARFLinetableParams(), LineDelta,
                           Res);
     return;
@@ -412,7 +421,7 @@ void MCObjectStreamer::EmitDwarfAdvanceFrameAddr(const MCSymbol *LastLabel,
                                                  const MCSymbol *Label) {
   const MCExpr *AddrDelta = buildSymbolDiff(*this, Label, LastLabel);
   int64_t Res;
-  if (AddrDelta->evaluateAsAbsolute(Res, getAssembler())) {
+  if (AddrDelta->evaluateAsAbsolute(Res, getAssemblerPtr())) {
     MCDwarfFrameEmitter::EmitAdvanceLoc(*this, Res);
     return;
   }
@@ -608,7 +617,7 @@ void MCObjectStreamer::emitFill(const MCExpr &NumBytes, uint64_t FillValue,
 void MCObjectStreamer::emitFill(const MCExpr &NumValues, int64_t Size,
                                 int64_t Expr, SMLoc Loc) {
   int64_t IntNumValues;
-  if (!NumValues.evaluateAsAbsolute(IntNumValues, getAssembler())) {
+  if (!NumValues.evaluateAsAbsolute(IntNumValues, getAssemblerPtr())) {
     getContext().reportError(Loc, "expected absolute expression");
     return;
   }
diff --git a/llvm/lib/MC/MCParser/AsmParser.cpp b/llvm/lib/MC/MCParser/AsmParser.cpp
index 7ee8e1b3e84..c2410413a62 100644
--- a/llvm/lib/MC/MCParser/AsmParser.cpp
+++ b/llvm/lib/MC/MCParser/AsmParser.cpp
@@ -775,7 +775,7 @@ bool AsmParser::processIncbinFile(const std::string &Filename, int64_t Skip,
   Bytes = Bytes.drop_front(Skip);
   if (Count) {
     int64_t Res;
-    if (!Count->evaluateAsAbsolute(Res))
+    if (!Count->evaluateAsAbsolute(Res, getStreamer().getAssemblerPtr()))
       return Error(Loc, "expected absolute expression");
     if (Res < 0)
       return Warning(Loc, "negative count has no effect");
@@ -1378,7 +1378,8 @@ bool AsmParser::parseExpression(const MCExpr *&Res, SMLoc &EndLoc) {
     Lex();
   }
 
-  // Try to constant fold it up front, if possible.
+  // Try to constant fold it up front, if possible. Do not exploit
+  // assembler here.
   int64_t Value;
   if (Res->evaluateAsAbsolute(Value))
     Res = MCConstantExpr::create(Value, getContext());
@@ -1419,7 +1420,7 @@ bool AsmParser::parseAbsoluteExpression(int64_t &Res) {
   if (parseExpression(Expr))
     return true;
 
-  if (!Expr->evaluateAsAbsolute(Res))
+  if (!Expr->evaluateAsAbsolute(Res, getStreamer().getAssemblerPtr()))
     return Error(StartLoc, "expected absolute expression");
 
   return false;
@@ -2616,7 +2617,8 @@ bool AsmParser::parseMacroArguments(const MCAsmMacro *M,
         Lex();
         if (parseExpression(AbsoluteExp, EndLoc))
           return false;
-        if (!AbsoluteExp->evaluateAsAbsolute(Value))
+        if (!AbsoluteExp->evaluateAsAbsolute(Value,
+                                             getStreamer().getAssemblerPtr()))
           return Error(StrLoc, "expected absolute expression");
         const char *StrChar = StrLoc.getPointer();
         const char *EndChar = EndLoc.getPointer();
@@ -2916,8 +2918,9 @@ bool AsmParser::parseDirectiveReloc(SMLoc DirectiveLoc) {
   if (parseExpression(Offset))
     return true;
 
-  if (check(!Offset->evaluateAsAbsolute(OffsetValue), OffsetLoc,
-            "expression is not a constant value") ||
+  if (check(!Offset->evaluateAsAbsolute(OffsetValue,
+                                        getStreamer().getAssemblerPtr()),
+            OffsetLoc, "expression is not a constant value") ||
       check(OffsetValue < 0, OffsetLoc, "expression is negative") ||
       parseToken(AsmToken::Comma, "expected comma") ||
       check(getTok().isNot(AsmToken::Identifier), "expected relocation name"))
@@ -5344,7 +5347,7 @@ bool AsmParser::parseDirectiveRept(SMLoc DirectiveLoc, StringRef Dir) {
     return true;
 
   int64_t Count;
-  if (!CountExpr->evaluateAsAbsolute(Count)) {
+  if (!CountExpr->evaluateAsAbsolute(Count, getStreamer().getAssemblerPtr())) {
     return Error(CountLoc, "unexpected token in '" + Dir + "' directive");
   }
 
diff --git a/llvm/lib/MC/MCStreamer.cpp b/llvm/lib/MC/MCStreamer.cpp
index 776569894a5..89d418d6743 100644
--- a/llvm/lib/MC/MCStreamer.cpp
+++ b/llvm/lib/MC/MCStreamer.cpp
@@ -75,7 +75,8 @@ void MCTargetStreamer::emitValue(const MCExpr *Value) {
 void MCTargetStreamer::emitAssignment(MCSymbol *Symbol, const MCExpr *Value) {}
 
 MCStreamer::MCStreamer(MCContext &Ctx)
-    : Context(Ctx), CurrentWinFrameInfo(nullptr) {
+    : Context(Ctx), CurrentWinFrameInfo(nullptr),
+      UseAssemblerInfoForParsing(false) {
   SectionStack.push_back(std::pair<MCSectionSubPair, MCSectionSubPair>());
 }