[WebAssembly] Added WasmAsmParser.

Summary:
This is to replace the ELFAsmParser that WebAssembly was using, which
so far was a stub that didn't do anything, and couldn't work correctly
with wasm.

This new class is there to implement generic directives related to
wasm as a binary format. Wasm target specific directives are still
parsed in WebAssemblyAsmParser as before. The two classes now
cooperate more correctly too.

Also implemented .result which was missing. Any unknown directives
will now result in errors.

Reviewers: dschuff, sbc100

Subscribers: mgorny, jgravelle-google, eraman, aheejin, sunfish, llvm-commits

Differential Revision: https://reviews.llvm.org/D54360

llvm-svn: 346700

lib/MC/MCParser/AsmParser.cpp

@@ -675,6 +675,7 @@ namespace llvm {
 extern MCAsmParserExtension *createDarwinAsmParser();
 extern MCAsmParserExtension *createELFAsmParser();
 extern MCAsmParserExtension *createCOFFAsmParser();
+extern MCAsmParserExtension *createWasmAsmParser();
 
 } // end namespace llvm
 
@@ -705,10 +706,7 @@ AsmParser::AsmParser(SourceMgr &SM, MCContext &Ctx, MCStreamer &Out,
     PlatformParser.reset(createELFAsmParser());
     break;
   case MCObjectFileInfo::IsWasm:
-    // TODO: WASM will need its own MCAsmParserExtension implementation, but
+    PlatformParser.reset(createWasmAsmParser());
-    // for now we can re-use the ELF one, since the directives can be the
-    // same for now.
-    PlatformParser.reset(createELFAsmParser());
     break;
   }
 
@@ -3921,7 +3919,7 @@ bool AsmParser::parseDirectiveCFIStartProc() {
         parseToken(AsmToken::EndOfStatement))
       return addErrorSuffix(" in '.cfi_startproc' directive");
   }
-  
+
   // TODO(kristina): Deal with a corner case of incorrect diagnostic context
   // being produced if this directive is emitted as part of preprocessor macro
   // expansion which can *ONLY* happen if Clang's cc1as is the API consumer.

lib/MC/MCParser/CMakeLists.txt

@@ -8,6 +8,7 @@ add_llvm_library(LLVMMCParser
   MCAsmParser.cpp
   MCAsmParserExtension.cpp
   MCTargetAsmParser.cpp
+  WasmAsmParser.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${LLVM_MAIN_INCLUDE_DIR}/llvm/MC/MCParser

lib/MC/MCParser/WasmAsmParser.cpp

@@ -0,0 +1,145 @@
+//===- WasmAsmParser.cpp - Wasm Assembly Parser -----------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+// --
+//
+// Note, this is for wasm, the binary format (analogous to ELF), not wasm,
+// the instruction set (analogous to x86), for which parsing code lives in
+// WebAssemblyAsmParser.
+//
+// This file contains processing for generic directives implemented using
+// MCTargetStreamer, the ones that depend on WebAssemblyTargetStreamer are in
+// WebAssemblyAsmParser.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/BinaryFormat/Wasm.h"
+#include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCParser/MCAsmLexer.h"
+#include "llvm/MC/MCParser/MCAsmParser.h"
+#include "llvm/MC/MCParser/MCAsmParserExtension.h"
+#include "llvm/MC/MCStreamer.h"
+#include "llvm/MC/MCSymbol.h"
+#include "llvm/MC/MCSymbolWasm.h"
+#include "llvm/Support/MachineValueType.h"
+
+using namespace llvm;
+
+namespace {
+
+class WasmAsmParser : public MCAsmParserExtension {
+  MCAsmParser *Parser;
+  MCAsmLexer *Lexer;
+
+  template<bool (WasmAsmParser::*HandlerMethod)(StringRef, SMLoc)>
+  void addDirectiveHandler(StringRef Directive) {
+    MCAsmParser::ExtensionDirectiveHandler Handler = std::make_pair(
+        this, HandleDirective<WasmAsmParser, HandlerMethod>);
+
+    getParser().addDirectiveHandler(Directive, Handler);
+  }
+
+public:
+  WasmAsmParser() : Parser(nullptr), Lexer(nullptr) {
+    BracketExpressionsSupported = true;
+  }
+
+  void Initialize(MCAsmParser &P) override {
+    Parser = &P;
+    Lexer = &Parser->getLexer();
+    // Call the base implementation.
+    this->MCAsmParserExtension::Initialize(*Parser);
+
+    addDirectiveHandler<&WasmAsmParser::parseSectionDirectiveText>(".text");
+    addDirectiveHandler<&WasmAsmParser::parseSectionDirective>(".section");
+    addDirectiveHandler<&WasmAsmParser::parseDirectiveSize>(".size");
+    addDirectiveHandler<&WasmAsmParser::parseDirectiveType>(".type");
+  }
+
+  bool Error(const StringRef &msg, const AsmToken &tok) {
+    return Parser->Error(tok.getLoc(), msg + tok.getString());
+  }
+
+  bool IsNext(AsmToken::TokenKind Kind) {
+    auto ok = Lexer->is(Kind);
+    if (ok) Lex();
+    return ok;
+  }
+
+  bool Expect(AsmToken::TokenKind Kind, const char *KindName) {
+    if (!IsNext(Kind))
+      return Error(std::string("Expected ") + KindName + ", instead got: ",
+                   Lexer->getTok());
+    return false;
+  }
+
+  bool parseSectionDirectiveText(StringRef, SMLoc) {
+    // FIXME: .text currently no-op.
+    return false;
+  }
+
+  bool parseSectionDirective(StringRef, SMLoc) {
+    // FIXME: .section currently no-op.
+    while (Lexer->isNot(AsmToken::EndOfStatement)) Parser->Lex();
+    return false;
+  }
+
+  // TODO: This function is almost the same as ELFAsmParser::ParseDirectiveSize
+  // so maybe could be shared somehow.
+  bool parseDirectiveSize(StringRef, SMLoc) {
+    StringRef Name;
+    if (Parser->parseIdentifier(Name))
+      return TokError("expected identifier in directive");
+    auto Sym = getContext().getOrCreateSymbol(Name);
+    if (Lexer->isNot(AsmToken::Comma))
+      return TokError("unexpected token in directive");
+    Lex();
+    const MCExpr *Expr;
+    if (Parser->parseExpression(Expr))
+      return true;
+    if (Lexer->isNot(AsmToken::EndOfStatement))
+      return TokError("unexpected token in directive");
+    Lex();
+    // MCWasmStreamer implements this.
+    getStreamer().emitELFSize(Sym, Expr);
+    return false;
+  }
+
+  bool parseDirectiveType(StringRef, SMLoc) {
+    // This could be the start of a function, check if followed by
+    // "label,@function"
+    if (!Lexer->is(AsmToken::Identifier))
+      return Error("Expected label after .type directive, got: ",
+                   Lexer->getTok());
+    auto WasmSym = cast<MCSymbolWasm>(
+                     getStreamer().getContext().getOrCreateSymbol(
+                       Lexer->getTok().getString()));
+    Lex();
+    if (!(IsNext(AsmToken::Comma) && IsNext(AsmToken::At) &&
+          Lexer->is(AsmToken::Identifier)))
+      return Error("Expected label,@type declaration, got: ", Lexer->getTok());
+    auto TypeName = Lexer->getTok().getString();
+    if (TypeName == "function")
+      WasmSym->setType(wasm::WASM_SYMBOL_TYPE_FUNCTION);
+    else if (TypeName == "global")
+      WasmSym->setType(wasm::WASM_SYMBOL_TYPE_GLOBAL);
+    else
+      return Error("Unknown WASM symbol type: ", Lexer->getTok());
+    Lex();
+    return Expect(AsmToken::EndOfStatement, "EOL");
+  }
+};
+
+} // end anonymous namespace
+
+namespace llvm {
+
+MCAsmParserExtension *createWasmAsmParser() {
+  return new WasmAsmParser;
+}
+
+} // end namespace llvm

lib/Target/WebAssembly/AsmParser/WebAssemblyAsmParser.cpp

@@ -132,13 +132,12 @@ struct WebAssemblyOperand : public MCParsedAsmOperand {
 class WebAssemblyAsmParser final : public MCTargetAsmParser {
   MCAsmParser &Parser;
   MCAsmLexer &Lexer;
-  MCSymbolWasm *LastSymbol;
 
 public:
   WebAssemblyAsmParser(const MCSubtargetInfo &STI, MCAsmParser &Parser,
                        const MCInstrInfo &MII, const MCTargetOptions &Options)
       : MCTargetAsmParser(Options, STI, MII), Parser(Parser),
-        Lexer(Parser.getLexer()), LastSymbol(nullptr) {
+        Lexer(Parser.getLexer()) {
     setAvailableFeatures(ComputeAvailableFeatures(STI.getFeatureBits()));
   }
 
@@ -191,6 +190,19 @@ public:
         .Default({MVT::INVALID_SIMPLE_VALUE_TYPE, wasm::WASM_TYPE_NORESULT});
   }
 
+  bool ParseRegTypeList(std::vector<MVT> &Types) {
+    while (Lexer.is(AsmToken::Identifier)) {
+      auto RegType = ParseRegType(Lexer.getTok().getString()).first;
+      if (RegType == MVT::INVALID_SIMPLE_VALUE_TYPE)
+        return true;
+      Types.push_back(RegType);
+      Parser.Lex();
+      if (!IsNext(AsmToken::Comma))
+        break;
+    }
+    return Expect(AsmToken::EndOfStatement, "EOL");
+  }
+
   void ParseSingleInteger(bool IsNegative, OperandVector &Operands) {
     auto &Int = Lexer.getTok();
     int64_t Val = Int.getIntVal();
@@ -314,10 +326,9 @@ public:
     return false;
   }
 
-  void onLabelParsed(MCSymbol *Symbol) override {
+  // This function processes wasm-specific directives streamed to
-    LastSymbol = cast<MCSymbolWasm>(Symbol);
+  // WebAssemblyTargetStreamer, all others go to the generic parser
-  }
+  // (see WasmAsmParser).
-
   bool ParseDirective(AsmToken DirectiveID) override {
     // This function has a really weird return value behavior that is different
     // from all the other parsing functions:
@@ -331,44 +342,7 @@ public:
         reinterpret_cast<WebAssemblyTargetStreamer &>(*Out.getTargetStreamer());
     // TODO: any time we return an error, at least one token must have been
     // consumed, otherwise this will not signal an error to the caller.
-    if (DirectiveID.getString() == ".type") {
+    if (DirectiveID.getString() == ".globaltype") {
-      // This could be the start of a function, check if followed by
-      // "label,@function"
-      if (!Lexer.is(AsmToken::Identifier))
-        return Error("Expected label after .type directive, got: ",
-                     Lexer.getTok());
-      auto WasmSym = cast<MCSymbolWasm>(
-                       TOut.getStreamer().getContext().getOrCreateSymbol(
-                         Lexer.getTok().getString()));
-      Parser.Lex();
-      if (!(IsNext(AsmToken::Comma) && IsNext(AsmToken::At) &&
-            Lexer.is(AsmToken::Identifier)))
-        return Error("Expected label,@type declaration, got: ", Lexer.getTok());
-      auto TypeName = Lexer.getTok().getString();
-      if (TypeName == "function")
-        WasmSym->setType(wasm::WASM_SYMBOL_TYPE_FUNCTION);
-      else if (TypeName == "global")
-        WasmSym->setType(wasm::WASM_SYMBOL_TYPE_GLOBAL);
-      else
-        return Error("Unknown WASM symbol type: ", Lexer.getTok());
-      Parser.Lex();
-      return Expect(AsmToken::EndOfStatement, "EOL");
-    } else if (DirectiveID.getString() == ".size") {
-      if (!Lexer.is(AsmToken::Identifier))
-        return Error("Expected label after .size directive, got: ",
-                     Lexer.getTok());
-      auto WasmSym = cast<MCSymbolWasm>(
-                       TOut.getStreamer().getContext().getOrCreateSymbol(
-                         Lexer.getTok().getString()));
-      Parser.Lex();
-      if (!IsNext(AsmToken::Comma))
-        return Error("Expected `,`, got: ", Lexer.getTok());
-      const MCExpr *Exp;
-      if (Parser.parseExpression(Exp))
-        return Error("Cannot parse .size expression: ", Lexer.getTok());
-      WasmSym->setSize(Exp);
-      return Expect(AsmToken::EndOfStatement, "EOL");
-    } else if (DirectiveID.getString() == ".globaltype") {
       if (!Lexer.is(AsmToken::Identifier))
         return Error("Expected symbol name after .globaltype directive, got: ",
                      Lexer.getTok());
@@ -392,40 +366,23 @@ public:
       // And emit the directive again.
       TOut.emitGlobalType(WasmSym);
       return Expect(AsmToken::EndOfStatement, "EOL");
-    } else if (DirectiveID.getString() == ".param" ||
+    } else if (DirectiveID.getString() == ".param") {
-               DirectiveID.getString() == ".local") {
-      // Track the number of locals, needed for correct virtual register
-      // assignment elsewhere.
-      // Also output a directive to the streamer.
       std::vector<MVT> Params;
+      if (ParseRegTypeList(Params)) return true;
+      TOut.emitParam(nullptr /* unused */, Params);
+      return false;
+    } else if (DirectiveID.getString() == ".result") {
+      std::vector<MVT> Results;
+      if (ParseRegTypeList(Results)) return true;
+      TOut.emitResult(nullptr /* unused */, Results);
+      return false;
+    } else if (DirectiveID.getString() == ".local") {
       std::vector<MVT> Locals;
-      while (Lexer.is(AsmToken::Identifier)) {
+      if (ParseRegTypeList(Locals)) return true;
-        auto RegType = ParseRegType(Lexer.getTok().getString()).first;
-        if (RegType == MVT::INVALID_SIMPLE_VALUE_TYPE)
-          return true;
-        if (DirectiveID.getString() == ".param") {
-          Params.push_back(RegType);
-        } else {
-          Locals.push_back(RegType);
-        }
-        Parser.Lex();
-        if (!IsNext(AsmToken::Comma))
-          break;
-      }
-      assert(LastSymbol);
-      // TODO: LastSymbol isn't even used by emitParam, so could be removed.
-      TOut.emitParam(LastSymbol, Params);
       TOut.emitLocal(Locals);
-      return Expect(AsmToken::EndOfStatement, "EOL");
+      return false;
-    } else {
-      // TODO: remove.
-      while (Lexer.isNot(AsmToken::EndOfStatement))
-        Parser.Lex();
-      return Expect(AsmToken::EndOfStatement, "EOL");
     }
-    // TODO: current ELF directive parsing is broken, fix this is a followup.
+    return true;  // We didn't process this directive.
-    //return true;  // We didn't process this directive.
-    return false;
   }
 
   bool MatchAndEmitInstruction(SMLoc IDLoc, unsigned & /*Opcode*/,

test/CodeGen/WebAssembly/inline-asm-roundtrip.ll

@@ -22,6 +22,7 @@ target triple = "wasm32-unknown-unknown"
 
 ; CHECK-LABEL: main:
 ; CHECK-NEXT:	.param  	i32, i32
+; CHECK-NEXT: .result   i32
 ; CHECK-NEXT:	.local  	i32
 ; CHECK-NEXT:	i32.const	1
 ; CHECK-NEXT:	set_local	[[SRC:[0-9]+]]

test/MC/WebAssembly/basic-assembly.s

@@ -3,10 +3,12 @@
 # RUN: llvm-mc -triple=wasm32-unknown-unknown -filetype=obj -mattr=+simd128,+nontrapping-fptoint,+exception-handling < %s
 
     .text
+    .section .text.main,"",@
     .type    test0,@function
 test0:
     # Test all types:
     .param      i32, i64
+    .result     i32
     .local      f32, f64, v128, v128
     # Explicit getlocal/setlocal:
     get_local   2
@@ -65,6 +67,7 @@ test0:
 # CHECK:           .text
 # CHECK-LABEL: test0:
 # CHECK-NEXT:      .param      i32, i64
+# CHECK-NEXT:      .result     i32
 # CHECK-NEXT:      .local      f32, f64
 # CHECK-NEXT:      get_local   2
 # CHECK-NEXT:      set_local   2