[mips] Replace custom parsing logic for data directives by the `addAliasForDirective`

[atanasyan]

Summary

The target independent AsmParser doesn't recognise .hword, .word, .dword which are required for Mips. Currently MipsAsmParser recognises these through dispatch to MipsAsmParser::parseDataDirective. This contains equivalent logic to AsmParser::parseDirectiveValue. This patch allows reuse of AsmParser::parseDirectiveValue by making use of addAliasForDirective to support .hword, .word and .dword.

Original patch provided by Alex Bradbury at D47001 was modified to fix handling of microMIPS symbols. The AsmParser::parseDirectiveValue calls either EmitIntValue or EmitValue. In this patch we override EmitIntValue in the MipsELFStreamer to clear a pending set of microMIPS symbols.

[asb]

Could you add a test that shows .4byte and .long are now correctly handled too? e.g. by extending micromips-label-test.s

[atanasyan]

• Add more tests to check .2byte, .4byte, .8byte, .long, .hword directives.

[asb]

Looks good to me.

[atanasyan]

Thanks for review.

lib/Target/Mips/AsmParser/MipsAsmParser.cpp

#include "MipsGenAsmMatcher.inc"
   bool parseSetMtDirective();
   bool parseSetNoMtDirective();
   bool parseSetNoCRCDirective();
   bool parseSetNoVirtDirective();
   bool parseSetNoGINVDirective();
 
   bool parseSetAssignment();
 
-  bool parseDataDirective(unsigned Size, SMLoc L);
   bool parseDirectiveGpWord();
   bool parseDirectiveGpDWord();
   bool parseDirectiveDtpRelWord();
   bool parseDirectiveDtpRelDWord();
   bool parseDirectiveTpRelWord();
   bool parseDirectiveTpRelDWord();
   bool parseDirectiveModule();
   bool parseDirectiveModuleFP();
#undef GET_OPERAND_DIAGNOSTIC_TYPES
   MipsAsmParser(const MCSubtargetInfo &sti, MCAsmParser &parser,
                 const MCInstrInfo &MII, const MCTargetOptions &Options)
     : MCTargetAsmParser(Options, sti, MII),
         ABI(MipsABIInfo::computeTargetABI(Triple(sti.getTargetTriple()),
                                           sti.getCPU(), Options)) {
     MCAsmParserExtension::Initialize(parser);
 
     parser.addAliasForDirective(".asciiz", ".asciz");
+    parser.addAliasForDirective(".hword", ".2byte");
+    parser.addAliasForDirective(".word", ".4byte");
+    parser.addAliasForDirective(".dword", ".8byte");
 
     // Initialize the set of available features.
     setAvailableFeatures(ComputeAvailableFeatures(getSTI().getFeatureBits()));
 
     // Remember the initial assembler options. The user can not modify these.
     AssemblerOptions.push_back(
         llvm::make_unique<MipsAssemblerOptions>(getSTI().getFeatureBits()));
 
if (IdVal == "ginv")
     return parseSetFeature(Mips::FeatureGINV);
   if (IdVal == "noginv")
     return parseSetNoGINVDirective();
 
   // It is just an identifier, look for an assignment.
   return parseSetAssignment();
 }
 
-/// parseDataDirective
-///  ::= .word [ expression (, expression)* ]
-bool MipsAsmParser::parseDataDirective(unsigned Size, SMLoc L) {
-  MCAsmParser &Parser = getParser();
-  if (getLexer().isNot(AsmToken::EndOfStatement)) {
-    while (true) {
-      const MCExpr *Value;
-      if (getParser().parseExpression(Value))
-        return true;
-
-      getParser().getStreamer().EmitValue(Value, Size);
-
-      if (getLexer().is(AsmToken::EndOfStatement))
-        break;
-
-      if (getLexer().isNot(AsmToken::Comma))
-        return Error(L, "unexpected token, expected comma");
-      Parser.Lex();
-    }
-  }
-
-  Parser.Lex();
-  return false;
-}
-
 /// parseDirectiveGpWord
 ///  ::= .gpword local_sym
 bool MipsAsmParser::parseDirectiveGpWord() {
   MCAsmParser &Parser = getParser();
   const MCExpr *Value;
   // EmitGPRel32Value requires an expression, so we are using base class
   // method to evaluate the expression.
   if (getParser().parseExpression(Value))
bool MipsAsmParser::ParseDirective(AsmToken DirectiveID) {
   if (IDVal == ".cpload") {
     parseDirectiveCpLoad(DirectiveID.getLoc());
     return false;
   }
   if (IDVal == ".cprestore") {
     parseDirectiveCpRestore(DirectiveID.getLoc());
     return false;
   }
-  if (IDVal == ".dword") {
-    parseDataDirective(8, DirectiveID.getLoc());
-    return false;
-  }
   if (IDVal == ".ent") {
     StringRef SymbolName;
 
     if (Parser.parseIdentifier(SymbolName)) {
       reportParseError("expected identifier after .ent");
       return false;
     }
 
if (IDVal == ".tprelword") {
     return false;
   }
 
   if (IDVal == ".tpreldword") {
     parseDirectiveTpRelDWord();
     return false;
   }
 
-  if (IDVal == ".word") {
-    parseDataDirective(4, DirectiveID.getLoc());
-    return false;
-  }
-
-  if (IDVal == ".hword") {
-    parseDataDirective(2, DirectiveID.getLoc());
-    return false;
-  }
-
   if (IDVal == ".option") {
     parseDirectiveOption();
     return false;
   }
 
   if (IDVal == ".abicalls") {
     getTargetStreamer().emitDirectiveAbiCalls();
     if (Parser.getTok().isNot(AsmToken::EndOfStatement)) {

lib/Target/Mips/MCTargetDesc/MipsELFStreamer.h

public:
   /// EmitInstruction.
   void EmitLabel(MCSymbol *Symbol, SMLoc Loc = SMLoc()) override;
 
   /// Overriding this function allows us to dismiss all labels that are
   /// candidates for marking as microMIPS when .section directive is processed.
   void SwitchSection(MCSection *Section,
                      const MCExpr *Subsection = nullptr) override;
 
-  /// Overriding this function allows us to dismiss all labels that are
-  /// candidates for marking as microMIPS when .word directive is emitted.
+  /// Overriding these functions allows us to dismiss all labels that are
+  /// candidates for marking as microMIPS when .word/.long/.4byte etc
+  /// directives are emitted.
   void EmitValueImpl(const MCExpr *Value, unsigned Size, SMLoc Loc) override;
+  void EmitIntValue(uint64_t Value, unsigned Size) override;
 
   /// Emits all the option records stored up until the point it's called.
   void EmitMipsOptionRecords();
 
   /// Mark labels as microMIPS, if necessary for the subtarget.
   void createPendingLabelRelocs();
 };
 
 MCELFStreamer *createMipsELFStreamer(MCContext &Context,
                                      std::unique_ptr<MCAsmBackend> MAB,
                                      std::unique_ptr<MCObjectWriter> OW,
                                      std::unique_ptr<MCCodeEmitter> Emitter,
                                      bool RelaxAll);
 } // end namespace llvm
 
 #endif // LLVM_LIB_TARGET_MIPS_MCTARGETDESC_MIPSELFSTREAMER_H

lib/Target/Mips/MCTargetDesc/MipsELFStreamer.cpp

 }
 
 void MipsELFStreamer::EmitValueImpl(const MCExpr *Value, unsigned Size,
                                     SMLoc Loc) {
   MCELFStreamer::EmitValueImpl(Value, Size, Loc);
   Labels.clear();
 }
 
+void MipsELFStreamer::EmitIntValue(uint64_t Value, unsigned Size) {
+  MCELFStreamer::EmitIntValue(Value, Size);
+  Labels.clear();
+}
+
 void MipsELFStreamer::EmitMipsOptionRecords() {
   for (const auto &I : MipsOptionRecords)
     I->EmitMipsOptionRecord();
 }
 
 MCELFStreamer *llvm::createMipsELFStreamer(
     MCContext &Context, std::unique_ptr<MCAsmBackend> MAB,
     std::unique_ptr<MCObjectWriter> OW, std::unique_ptr<MCCodeEmitter> Emitter,
     bool RelaxAll) {
   return new MipsELFStreamer(Context, std::move(MAB), std::move(OW),
                              std::move(Emitter));
 }

test/MC/Mips/micromips-label-test.s

 # RUN: llvm-mc %s -triple=mipsel-unknown-linux -mcpu=mips32r2 \
 # RUN:   -mattr=+micromips -filetype=obj -o - | llvm-readobj -t | FileCheck %s
   .text
   .set nomicromips
 f:
   nop
 g:
   .set micromips
   nop
 h:
   .word 0
+k:
+  .long 0
+l:
+  .hword 0
+m:
+  .2byte 0
+n:
+  .4byte 0
+o:
+  .8byte 0
 i:
   nop
 j:
   .set nomicromips
   nop
 # CHECK: Symbols [
 # CHECK:   Symbol {
 # CHECK:     Name: f

 # CHECK:   }
 # CHECK:   Symbol {
 # CHECK:     Name: j
 # CHECK:     Binding: Local
 # CHECK:     Type: None
 # CHECK:     Other: 0
 # CHECK:     Section: .text
 # CHECK:   }
+# CHECK:   Symbol {
+# CHECK:     Name: k
+# CHECK:     Binding: Local
+# CHECK:     Type: None
+# CHECK:     Other: 0
+# CHECK:     Section: .text
+# CHECK:   }
+# CHECK:   Symbol {
+# CHECK:     Name: l
+# CHECK:     Binding: Local
+# CHECK:     Type: None
+# CHECK:     Other: 0
+# CHECK:     Section: .text
+# CHECK:   }
+# CHECK:   Symbol {
+# CHECK:     Name: m
+# CHECK:     Binding: Local
+# CHECK:     Type: None
+# CHECK:     Other: 0
+# CHECK:     Section: .text
+# CHECK:   }
+# CHECK:   Symbol {
+# CHECK:     Name: n
+# CHECK:     Binding: Local
+# CHECK:     Type: None
+# CHECK:     Other: 0
+# CHECK:     Section: .text
+# CHECK:   }
+# CHECK:   Symbol {
+# CHECK:     Name: o
+# CHECK:     Binding: Local
+# CHECK:     Type: None
+# CHECK:     Other: 0
+# CHECK:     Section: .text
+# CHECK:   }
 # CHECK: ]
-