MC asm parser: allow ?'s in symbol names, and handle @'s in names in MS asm

This is another (final?) stab at making us able to parse our own asm output
on Windows.

Symbols on Windows often contain @'s and ?'s in their names. Our asm parser
didn't like this. ?'s were not allowed, and @'s were intepreted as trying to
reference PLT/GOT/etc.

We can't just add quotes around the bad names, since e.g. for MinGW, we use gas
to assemble, and it doesn't like quotes in some places (notably in .def
directives).

This commit makes us allow ?'s in symbol names, and @'s in symbol names for MS
assembly.

Differential Revision: http://llvm-reviews.chandlerc.com/D1978

llvm-svn: 193000

4 files changed, 23 insertions, 13 deletions

diff --git a/llvm/lib/MC/MCAsmInfo.cpp b/llvm/lib/MC/MCAsmInfo.cpp
index 6112ad1fcac..0eea75ef04e 100644
--- a/llvm/lib/MC/MCAsmInfo.cpp
+++ b/llvm/lib/MC/MCAsmInfo.cpp
@@ -53,6 +53,7 @@ MCAsmInfo::MCAsmInfo() {
   AllowQuotesInName = false;
   AllowNameToStartWithDigit = false;
   AllowPeriodsInName = true;
+  AllowAtInName = false;
   AllowUTF8 = true;
   UseDataRegionDirectives = false;
   ZeroDirective = "\t.zero\t";
diff --git a/llvm/lib/MC/MCParser/AsmLexer.cpp b/llvm/lib/MC/MCParser/AsmLexer.cpp
index 1ce0cc2a1d7..b49dd010479 100644
--- a/llvm/lib/MC/MCParser/AsmLexer.cpp
+++ b/llvm/lib/MC/MCParser/AsmLexer.cpp
@@ -138,9 +138,9 @@ AsmToken AsmLexer::LexHexFloatLiteral(bool NoIntDigits) {
   return AsmToken(AsmToken::Real, StringRef(TokStart, CurPtr - TokStart));
 }
 
-/// LexIdentifier: [a-zA-Z_.][a-zA-Z0-9_$.@]*
+/// LexIdentifier: [a-zA-Z_.][a-zA-Z0-9_$.@?]*
 static bool IsIdentifierChar(char c) {
-  return isalnum(c) || c == '_' || c == '$' || c == '.' || c == '@';
+  return isalnum(c) || c == '_' || c == '$' || c == '.' || c == '@' || c == '?';
 }
 AsmToken AsmLexer::LexIdentifier() {
   // Check for floating point literals.
diff --git a/llvm/lib/MC/MCParser/AsmParser.cpp b/llvm/lib/MC/MCParser/AsmParser.cpp
index 9a362563a7e..1fb8480b057 100644
--- a/llvm/lib/MC/MCParser/AsmParser.cpp
+++ b/llvm/lib/MC/MCParser/AsmParser.cpp
@@ -769,6 +769,7 @@ bool AsmParser::parsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc) {
     Res = MCUnaryExpr::CreateLNot(Res, getContext());
     return false;
   case AsmToken::Dollar:
+  case AsmToken::At:
   case AsmToken::String:
   case AsmToken::Identifier: {
     StringRef Identifier;
@@ -792,19 +793,25 @@ bool AsmParser::parsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc) {
     EndLoc = SMLoc::getFromPointer(Identifier.end());
 
     // This is a symbol reference.
+    StringRef SymbolName = Identifier;
+    MCSymbolRefExpr::VariantKind Variant = MCSymbolRefExpr::VK_None;
     std::pair<StringRef, StringRef> Split = Identifier.split('@');
-    MCSymbol *Sym = getContext().GetOrCreateSymbol(Split.first);
 
     // Lookup the symbol variant if used.
-    MCSymbolRefExpr::VariantKind Variant = MCSymbolRefExpr::VK_None;
     if (Split.first.size() != Identifier.size()) {
       Variant = MCSymbolRefExpr::getVariantKindForName(Split.second);
-      if (Variant == MCSymbolRefExpr::VK_Invalid) {
+      if (Variant != MCSymbolRefExpr::VK_Invalid) {
+        SymbolName = Split.first;
+      } else if (MAI.doesAllowAtInName()) {
+        Variant = MCSymbolRefExpr::VK_None;
+      } else {
         Variant = MCSymbolRefExpr::VK_None;
         return TokError("invalid variant '" + Split.second + "'");
       }
     }
 
+    MCSymbol *Sym = getContext().GetOrCreateSymbol(SymbolName);
+
     // If this is an absolute variable reference, substitute it now to preserve
     // semantics in the face of reassignment.
     if (Sym->isVariable() && isa<MCConstantExpr>(Sym->getVariableValue())) {
@@ -2105,25 +2112,25 @@ bool AsmParser::parseAssignment(StringRef Name, bool allow_redef,
 ///   ::= string
 bool AsmParser::parseIdentifier(StringRef &Res) {
   // The assembler has relaxed rules for accepting identifiers, in particular we
-  // allow things like '.globl $foo', which would normally be separate
-  // tokens. At this level, we have already lexed so we cannot (currently)
+  // allow things like '.globl $foo' and '.def @feat.00', which would normally be
+  // separate tokens. At this level, we have already lexed so we cannot (currently)
   // handle this as a context dependent token, instead we detect adjacent tokens
   // and return the combined identifier.
-  if (Lexer.is(AsmToken::Dollar)) {
-    SMLoc DollarLoc = getLexer().getLoc();
+  if (Lexer.is(AsmToken::Dollar) || Lexer.is(AsmToken::At)) {
+    SMLoc PrefixLoc = getLexer().getLoc();
 
-    // Consume the dollar sign, and check for a following identifier.
+    // Consume the prefix character, and check for a following identifier.
     Lex();
     if (Lexer.isNot(AsmToken::Identifier))
       return true;
 
-    // We have a '$' followed by an identifier, make sure they are adjacent.
-    if (DollarLoc.getPointer() + 1 != getTok().getLoc().getPointer())
+    // We have a '$' or '@' followed by an identifier, make sure they are adjacent.
+    if (PrefixLoc.getPointer() + 1 != getTok().getLoc().getPointer())
       return true;
 
     // Construct the joined identifier and consume the token.
     Res =
-        StringRef(DollarLoc.getPointer(), getTok().getIdentifier().size() + 1);
+        StringRef(PrefixLoc.getPointer(), getTok().getIdentifier().size() + 1);
     Lex();
     return false;
   }
diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp b/llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp
index d3f5258a8df..3861e1ce290 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp
@@ -135,6 +135,8 @@ X86MCAsmInfoMicrosoft::X86MCAsmInfoMicrosoft(const Triple &Triple) {
   AssemblerDialect = AsmWriterFlavor;
 
   TextAlignFillValue = 0x90;
+
+  AllowAtInName = true;
 }
 
 void X86MCAsmInfoGNUCOFF::anchor() { }