Re-commit r192758 - MC: quote tricky symbol names in asm output

The reason this got reverted was that the @feat.00 symbol which was emitted
for every TU became quoted, and on cygwin/mingw we use the gas assembler which
couldn't handle the quotes.

This commit fixes the problem by only emitting @feat.00 for win32, where we use
clang -cc1as to assemble. gas would just drop this symbol anyway, so there is no
loss there.

With @feat.00 gone, there shouldn't be quoted symbols showing up on cygwin since
it uses the Itanium ABI, which doesn't put these funny characters in symbols.

> Because of win32 mangling, we produce symbol and section names with
> funny characters in them, most notably @ characters.
>
> MC would choke on trying to parse its own assembly output. This patch addresses
> that by:
>
> - Making @ trigger quoting of symbol names
> - Also quote section names in the same way
> - Just parse section names like other identifiers (to allow for quotes)
> - Don't assume @ signifies a symbol variant if it is in a string.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192859 91177308-0d34-0410-b5e6-96231b3b80d8

9 files changed, 67 insertions, 25 deletions

diff --git a/lib/MC/MCParser/AsmParser.cpp b/lib/MC/MCParser/AsmParser.cpp
index 9a362563a7..75f5c78b70 100644
--- a/lib/MC/MCParser/AsmParser.cpp
+++ b/lib/MC/MCParser/AsmParser.cpp
@@ -792,19 +792,25 @@ 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 (Split.first.size() != Identifier.size() &&
+        FirstTokenKind != AsmToken::String) {
+      SymbolName = Split.first;
+      StringRef VariantName = Split.second;
+
+      // Lookup the symbol variant.
+      Variant = MCSymbolRefExpr::getVariantKindForName(VariantName);
       if (Variant == MCSymbolRefExpr::VK_Invalid) {
         Variant = MCSymbolRefExpr::VK_None;
-        return TokError("invalid variant '" + Split.second + "'");
+        return TokError("invalid variant '" + VariantName + "'");
       }
     }
 
+    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())) {
diff --git a/lib/MC/MCParser/COFFAsmParser.cpp b/lib/MC/MCParser/COFFAsmParser.cpp
index df1794c979..b3c094366a 100644
--- a/lib/MC/MCParser/COFFAsmParser.cpp
+++ b/lib/MC/MCParser/COFFAsmParser.cpp
@@ -295,12 +295,7 @@ bool COFFAsmParser::ParseSectionSwitch(StringRef Section,
 }
 
 bool COFFAsmParser::ParseSectionName(StringRef &SectionName) {
-  if (!getLexer().is(AsmToken::Identifier))
-    return true;
-
-  SectionName = getTok().getIdentifier();
-  Lex();
-  return false;
+  return getParser().parseIdentifier(SectionName);
 }
 
 // .section name [, "flags"]
diff --git a/lib/MC/MCSectionCOFF.cpp b/lib/MC/MCSectionCOFF.cpp
index 64aa2c5c49..a8f5db095b 100644
--- a/lib/MC/MCSectionCOFF.cpp
+++ b/lib/MC/MCSectionCOFF.cpp
@@ -39,6 +39,22 @@ void MCSectionCOFF::setSelection(int Selection,
   Characteristics |= COFF::IMAGE_SCN_LNK_COMDAT;
 }
 
+static bool isAcceptableSectionNameChar(char C) {
+  return (C >= 'a' && C <= 'z') ||
+         (C >= 'A' && C <= 'Z') ||
+         (C >= '0' && C <= '9') ||
+         C == '_' || C == '$' || C == '.';
+}
+
+/// NameNeedsQuoting - Return true if the identifier \p Str needs quotes to be
+/// syntactically correct.
+static bool sectionNameNeedsQuoting(StringRef Name) {
+  for (unsigned i = 0, e = Name.size(); i != e; ++i)
+    if (!isAcceptableSectionNameChar(Name[i]))
+      return true;
+  return false;
+}
+
 void MCSectionCOFF::PrintSwitchToSection(const MCAsmInfo &MAI,
                                          raw_ostream &OS,
                                          const MCExpr *Subsection) const {
@@ -49,7 +65,10 @@ void MCSectionCOFF::PrintSwitchToSection(const MCAsmInfo &MAI,
     return;
   }
 
-  OS << "\t.section\t" << getSectionName() << ",\"";
+  if (sectionNameNeedsQuoting(getSectionName()))
+    OS << "\t.section\t" << '"' << getSectionName() << '"' << ",\"";
+  else
+    OS << "\t.section\t" << getSectionName() << ",\"";
   if (getKind().isText())
     OS << 'x';
   if (getKind().isWriteable())
diff --git a/lib/MC/MCSymbol.cpp b/lib/MC/MCSymbol.cpp
index b973c57f7b..f386c3bc90 100644
--- a/lib/MC/MCSymbol.cpp
+++ b/lib/MC/MCSymbol.cpp
@@ -18,12 +18,10 @@ const MCSection *MCSymbol::AbsolutePseudoSection =
   reinterpret_cast<const MCSection *>(1);
 
 static bool isAcceptableChar(char C) {
-  if ((C < 'a' || C > 'z') &&
-      (C < 'A' || C > 'Z') &&
-      (C < '0' || C > '9') &&
-      C != '_' && C != '$' && C != '.' && C != '@')
-    return false;
-  return true;
+  return (C >= 'a' && C <= 'z') ||
+         (C >= 'A' && C <= 'Z') ||
+         (C >= '0' && C <= '9') ||
+         C == '_' || C == '$' || C == '.';
 }
 
 /// NameNeedsQuoting - Return true if the identifier \p Str needs quotes to be
diff --git a/lib/Target/X86/X86AsmPrinter.cpp b/lib/Target/X86/X86AsmPrinter.cpp
index 7d7a1add22..d7f7c3e55d 100644
--- a/lib/Target/X86/X86AsmPrinter.cpp
+++ b/lib/Target/X86/X86AsmPrinter.cpp
@@ -519,9 +519,11 @@ void X86AsmPrinter::EmitStartOfAsmFile(Module &M) {
   if (Subtarget->isTargetEnvMacho())
     OutStreamer.SwitchSection(getObjFileLowering().getTextSection());
 
-  if (Subtarget->isTargetCOFF()) {
+  if (Subtarget->isTargetCOFF() && Subtarget->isTargetWindows()) {
     // Emit an absolute @feat.00 symbol.  This appears to be some kind of
     // compiler features bitfield read by link.exe.
+    // We only do this on win32, since on cygwin etc. we use the GNU assembler,
+    // which doesn't handle this symbol.
     if (!Subtarget->is64Bit()) {
       MCSymbol *S = MMI->getContext().GetOrCreateSymbol(StringRef("@feat.00"));
       OutStreamer.BeginCOFFSymbolDef(S);
diff --git a/test/CodeGen/X86/coff-feat00.ll b/test/CodeGen/X86/coff-feat00.ll
index 1dcd427639..048aa34345 100644
--- a/test/CodeGen/X86/coff-feat00.ll
+++ b/test/CodeGen/X86/coff-feat00.ll
@@ -1,7 +1,9 @@
-; RUN: llc -O0 -mtriple=i386-pc-win32 -filetype=asm -o - %s | FileCheck %s
+; RUN: llc -O0 -mtriple=i386-pc-win32 -filetype=asm -o - %s | FileCheck %s --check-prefix=WIN32
+; RUN: llc -O0 -mtriple=i386-pc-cygwin -filetype=asm -o - %s | FileCheck %s --check-prefix=CYGWIN
 
 define i32 @foo() {
   ret i32 0
 }
 
-; CHECK: @feat.00 = 1
+; WIN32: "@feat.00" = 1
+; CYGWIN-NOT: "@feat.00" = 1
diff --git a/test/CodeGen/X86/fastcall-correct-mangling.ll b/test/CodeGen/X86/fastcall-correct-mangling.ll
index 3569d36541..17addbc3e1 100644
--- a/test/CodeGen/X86/fastcall-correct-mangling.ll
+++ b/test/CodeGen/X86/fastcall-correct-mangling.ll
@@ -3,7 +3,7 @@
 ; Check that a fastcall function gets correct mangling
 
 define x86_fastcallcc void @func(i64 %X, i8 %Y, i8 %G, i16 %Z) {
-; CHECK: @func@20:
+; CHECK: "@func@20":
         ret void
 }
 
diff --git a/test/CodeGen/X86/stdcall.ll b/test/CodeGen/X86/stdcall.ll
index 73826ed0b2..34f90c5ee3 100644
--- a/test/CodeGen/X86/stdcall.ll
+++ b/test/CodeGen/X86/stdcall.ll
@@ -5,7 +5,7 @@
 
 define internal x86_stdcallcc void @MyFunc() nounwind {
 entry:
-; CHECK: MyFunc@0:
+; CHECK: "_MyFunc@0":
 ; CHECK: ret
   ret void
 }
@@ -20,5 +20,5 @@ entry:
 
 @B = global %0 { void (...)* bitcast (void ()* @MyFunc to void (...)*) }, align 4
 ; CHECK: _B:
-; CHECK: .long _MyFunc@0
+; CHECK: .long "_MyFunc@0"
 
diff --git a/test/MC/COFF/quoted-names.ll b/test/MC/COFF/quoted-names.ll
new file mode 100644
index 0000000000..920035f555
--- /dev/null
+++ b/test/MC/COFF/quoted-names.ll
@@ -0,0 +1,20 @@
+; Check that certain symbol and section names are quoted in the asm output.
+; RUN: llc -mtriple=i686-pc-win32 %s -o - | FileCheck %s
+
+; Check that the symbol and section names can round-trip through the assembler.
+; RUN: llc -mtriple=i686-pc-win32 %s -o - | llvm-mc -triple i686-pc-win32 -filetype=obj | llvm-readobj -s -section-symbols | FileCheck %s --check-prefix=READOBJ
+
+@"\01??__E_Generic_object@?$_Error_objects@H@std@@YAXXZ" = global i32 0
+
+define weak i32 @"\01??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51"() section ".text" {
+  %res = load i32* @"\01??__E_Generic_object@?$_Error_objects@H@std@@YAXXZ"
+  ret i32 %res
+}
+
+; CHECK: .section ".text$??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51","xr"
+; CHECK: .globl "??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51"
+; CHECK: "??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51"
+
+; READOBJ: Symbol
+; READOBJ: Name: ??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51
+; READOBJ: Section: .text$??_B?$num_put@_WV?$back_insert_iterator@V?$basic_string@_WU?$char_traits@_W@std@@V?$allocator@_W@2@@std@@@std@@@std@@51