release/21.x: MC: Better handle backslash-escaped symbols

llvm/include/llvm/MC/MCContext.h

@@ -489,6 +489,10 @@ class MCContext {
   /// \param Name - The symbol name, which must be unique across all symbols.
   LLVM_ABI MCSymbol *getOrCreateSymbol(const Twine &Name);
 
+  /// Variant of getOrCreateSymbol that handles backslash-escaped symbols.
+  /// For example, parse "a\"b\\" as a"\.
+  LLVM_ABI MCSymbol *parseSymbol(const Twine &Name);
+
   /// Gets a symbol that will be defined to the final stack offset of a local
   /// variable after codegen.
   ///

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

@@ -279,6 +279,9 @@ class LLVM_ABI MCAsmParser {
   /// Res to the identifier contents.
   virtual bool parseIdentifier(StringRef &Res) = 0;
 
+  /// Parse identifier and get or create symbol for it.
+  bool parseSymbol(MCSymbol *&Res);
+
   /// Parse up to the end of statement and return the contents from the
   /// current token until the end of the statement; the current token on exit
   /// will be either the EndOfStatement or EOF.

llvm/lib/MC/MCContext.cpp

@@ -217,27 +217,6 @@ MCDataFragment *MCContext::allocInitialFragment(MCSection &Sec) {
 MCSymbol *MCContext::getOrCreateSymbol(const Twine &Name) {
   SmallString<128> NameSV;
   StringRef NameRef = Name.toStringRef(NameSV);
-  if (NameRef.contains('\\')) {
-    NameSV = NameRef;
-    size_t S = 0;
-    // Support escaped \\ and \" as in GNU Assembler. GAS issues a warning for
-    // other characters following \\, which we do not implement due to code
-    // structure.
-    for (size_t I = 0, E = NameSV.size(); I != E; ++I) {
-      char C = NameSV[I];
-      if (C == '\\' && I + 1 != E) {
-        switch (NameSV[I + 1]) {
-        case '"':
-        case '\\':
-          C = NameSV[++I];
-          break;
-        }
-      }
-      NameSV[S++] = C;
-    }
-    NameSV.resize(S);
-    NameRef = NameSV;
-  }
 
   assert(!NameRef.empty() && "Normal symbols cannot be unnamed!");
 
@@ -258,6 +237,34 @@ MCSymbol *MCContext::getOrCreateSymbol(const Twine &Name) {
   return Entry.second.Symbol;
 }
 
+MCSymbol *MCContext::parseSymbol(const Twine &Name) {
+  SmallString<128> SV;
+  StringRef NameRef = Name.toStringRef(SV);
+  if (NameRef.contains('\\')) {
+    SV = NameRef;
+    size_t S = 0;
+    // Support escaped \\ and \" as in GNU Assembler. GAS issues a warning for
+    // other characters following \\, which we do not implement due to code
+    // structure.
+    for (size_t I = 0, E = SV.size(); I != E; ++I) {
+      char C = SV[I];
+      if (C == '\\' && I + 1 != E) {
+        switch (SV[I + 1]) {
+        case '"':
+        case '\\':
+          C = SV[++I];
+          break;
+        }
+      }
+      SV[S++] = C;
+    }
+    SV.resize(S);
+    NameRef = SV;
+  }
+
+  return getOrCreateSymbol(NameRef);
+}
+
 MCSymbol *MCContext::getOrCreateFrameAllocSymbol(const Twine &FuncName,
                                                  unsigned Idx) {
   return getOrCreateSymbol(MAI->getPrivateGlobalPrefix() + FuncName +

llvm/lib/MC/MCParser/AsmParser.cpp

@@ -1222,8 +1222,8 @@ bool AsmParser::parsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc,
 
     MCSymbol *Sym = getContext().getInlineAsmLabel(SymbolName);
     if (!Sym)
-      Sym = getContext().getOrCreateSymbol(MAI.isHLASM() ? SymbolName.upper()
-                                                         : SymbolName);
+      Sym = getContext().parseSymbol(MAI.isHLASM() ? SymbolName.upper()
+                                                   : SymbolName);
 
     // If this is an absolute variable reference, substitute it now to preserve
     // semantics in the face of reassignment.
@@ -1854,7 +1854,7 @@ bool AsmParser::parseStatement(ParseStatementInfo &Info,
                                        RewrittenLabel);
         IDVal = RewrittenLabel;
       }
-      Sym = getContext().getOrCreateSymbol(IDVal);
+      Sym = getContext().parseSymbol(IDVal);
     } else
       Sym = Ctx.createDirectionalLocalSymbol(LocalLabelVal);
     // End of Labels should be treated as end of line for lexing
@@ -3897,20 +3897,15 @@ bool AsmParser::parseDirectiveCVLoc() {
 /// ::= .cv_linetable FunctionId, FnStart, FnEnd
 bool AsmParser::parseDirectiveCVLinetable() {
   int64_t FunctionId;
-  StringRef FnStartName, FnEndName;
+  MCSymbol *FnStartSym, *FnEndSym;
   SMLoc Loc = getTok().getLoc();
   if (parseCVFunctionId(FunctionId, ".cv_linetable") || parseComma() ||
       parseTokenLoc(Loc) ||
-      check(parseIdentifier(FnStartName), Loc,
-            "expected identifier in directive") ||
+      check(parseSymbol(FnStartSym), Loc, "expected identifier in directive") ||
       parseComma() || parseTokenLoc(Loc) ||
-      check(parseIdentifier(FnEndName), Loc,
-            "expected identifier in directive"))
+      check(parseSymbol(FnEndSym), Loc, "expected identifier in directive"))
     return true;
 
-  MCSymbol *FnStartSym = getContext().getOrCreateSymbol(FnStartName);
-  MCSymbol *FnEndSym = getContext().getOrCreateSymbol(FnEndName);
-
   getStreamer().emitCVLinetableDirective(FunctionId, FnStartSym, FnEndSym);
   return false;
 }
@@ -3919,7 +3914,7 @@ bool AsmParser::parseDirectiveCVLinetable() {
 /// ::= .cv_inline_linetable PrimaryFunctionId FileId LineNum FnStart FnEnd
 bool AsmParser::parseDirectiveCVInlineLinetable() {
   int64_t PrimaryFunctionId, SourceFileId, SourceLineNum;
-  StringRef FnStartName, FnEndName;
+  MCSymbol *FnStartSym, *FnEndSym;
   SMLoc Loc = getTok().getLoc();
   if (parseCVFunctionId(PrimaryFunctionId, ".cv_inline_linetable") ||
       parseTokenLoc(Loc) ||
@@ -3929,16 +3924,14 @@ bool AsmParser::parseDirectiveCVInlineLinetable() {
       parseIntToken(SourceLineNum, "expected SourceLineNum") ||
       check(SourceLineNum < 0, Loc, "Line number less than zero") ||
       parseTokenLoc(Loc) ||
-      check(parseIdentifier(FnStartName), Loc, "expected identifier") ||
+      check(parseSymbol(FnStartSym), Loc, "expected identifier") ||
       parseTokenLoc(Loc) ||
-      check(parseIdentifier(FnEndName), Loc, "expected identifier"))
+      check(parseSymbol(FnEndSym), Loc, "expected identifier"))
     return true;
 
   if (parseEOL())
     return true;
 
-  MCSymbol *FnStartSym = getContext().getOrCreateSymbol(FnStartName);
-  MCSymbol *FnEndSym = getContext().getOrCreateSymbol(FnEndName);
   getStreamer().emitCVInlineLinetableDirective(PrimaryFunctionId, SourceFileId,
                                                SourceLineNum, FnStartSym,
                                                FnEndSym);
@@ -3959,16 +3952,14 @@ bool AsmParser::parseDirectiveCVDefRange() {
   std::vector<std::pair<const MCSymbol *, const MCSymbol *>> Ranges;
   while (getLexer().is(AsmToken::Identifier)) {
     Loc = getLexer().getLoc();
-    StringRef GapStartName;
-    if (parseIdentifier(GapStartName))
+    MCSymbol *GapStartSym;
+    if (parseSymbol(GapStartSym))
       return Error(Loc, "expected identifier in directive");
-    MCSymbol *GapStartSym = getContext().getOrCreateSymbol(GapStartName);
 
     Loc = getLexer().getLoc();
-    StringRef GapEndName;
-    if (parseIdentifier(GapEndName))
+    MCSymbol *GapEndSym;
+    if (parseSymbol(GapEndSym))
       return Error(Loc, "expected identifier in directive");
-    MCSymbol *GapEndSym = getContext().getOrCreateSymbol(GapEndName);
 
     Ranges.push_back({GapStartSym, GapEndSym});
   }
@@ -4105,12 +4096,11 @@ bool AsmParser::parseDirectiveCVFileChecksumOffset() {
 /// ::= .cv_fpo_data procsym
 bool AsmParser::parseDirectiveCVFPOData() {
   SMLoc DirLoc = getLexer().getLoc();
-  StringRef ProcName;
-  if (parseIdentifier(ProcName))
+  MCSymbol *ProcSym;
+  if (parseSymbol(ProcSym))
     return TokError("expected symbol name");
   if (parseEOL())
     return true;
-  MCSymbol *ProcSym = getContext().getOrCreateSymbol(ProcName);
   getStreamer().emitCVFPOData(ProcSym, DirLoc);
   return false;
 }
@@ -4329,15 +4319,12 @@ bool AsmParser::parseDirectiveCFIPersonalityOrLsda(bool IsPersonality) {
   if (Encoding == dwarf::DW_EH_PE_omit)
     return false;
 
-  StringRef Name;
+  MCSymbol *Sym;
   if (check(!isValidEncoding(Encoding), "unsupported encoding.") ||
       parseComma() ||
-      check(parseIdentifier(Name), "expected identifier in directive") ||
-      parseEOL())
+      check(parseSymbol(Sym), "expected identifier in directive") || parseEOL())
     return true;
 
-  MCSymbol *Sym = getContext().getOrCreateSymbol(Name);
-
   if (IsPersonality)
     getStreamer().emitCFIPersonality(Sym, Encoding);
   else
@@ -4966,7 +4953,7 @@ bool AsmParser::parseDirectiveSymbolAttribute(MCSymbolAttr Attr) {
     if (discardLTOSymbol(Name))
       return false;
 
-    MCSymbol *Sym = getContext().getOrCreateSymbol(Name);
+    MCSymbol *Sym = getContext().parseSymbol(Name);
 
     // Assembler local symbols don't make any sense here, except for directives
     // that the symbol should be tagged.
@@ -4988,13 +4975,10 @@ bool AsmParser::parseDirectiveComm(bool IsLocal) {
     return true;
 
   SMLoc IDLoc = getLexer().getLoc();
-  StringRef Name;
-  if (parseIdentifier(Name))
+  MCSymbol *Sym;
+  if (parseSymbol(Sym))
     return TokError("expected identifier in directive");
 
-  // Handle the identifier as the key symbol.
-  MCSymbol *Sym = getContext().getOrCreateSymbol(Name);
-
   if (parseComma())
     return true;
 
@@ -5827,10 +5811,9 @@ bool AsmParser::parseDirectiveAddrsig() {
 }
 
 bool AsmParser::parseDirectiveAddrsigSym() {
-  StringRef Name;
-  if (check(parseIdentifier(Name), "expected identifier") || parseEOL())
+  MCSymbol *Sym;
+  if (check(parseSymbol(Sym), "expected identifier") || parseEOL())
     return true;
-  MCSymbol *Sym = getContext().getOrCreateSymbol(Name);
   getStreamer().emitAddrsigSym(Sym);
   return false;
 }
@@ -6230,7 +6213,7 @@ bool HLASMAsmParser::parseAsHLASMLabel(ParseStatementInfo &Info,
     return Error(LabelLoc,
                  "Cannot have just a label for an HLASM inline asm statement");
 
-  MCSymbol *Sym = getContext().getOrCreateSymbol(
+  MCSymbol *Sym = getContext().parseSymbol(
       getContext().getAsmInfo()->isHLASM() ? LabelVal.upper() : LabelVal);
 
   // Emit the label.
@@ -6357,7 +6340,7 @@ bool parseAssignmentExpression(StringRef Name, bool allow_redef,
     Parser.getStreamer().emitValueToOffset(Value, 0, EqualLoc);
     return false;
   } else
-    Sym = Parser.getContext().getOrCreateSymbol(Name);
+    Sym = Parser.getContext().parseSymbol(Name);
 
   Sym->setRedefinable(allow_redef);