[XCOFF] string constants handling for XCOFF

[shchenz]

Summary

This is from the code review of D99785. To make sure same file name in symbol table and in .dwinfo section, we need to change string constants generation for AIX.

Handle string constants for XCOFF according to https://www.ibm.com/docs/en/aix/7.2?topic=constants-string

[hubert.reinterpretcast]

LGTM with comments.

llvm/include/llvm/MC/MCAsmInfo.h

348–349

Suggested expanded description here.

llvm/lib/MC/MCAsmInfoXCOFF.cpp

25

Add period to the end of the sentence.

llvm/lib/MC/MCAsmStreamer.cpp

63–68

New member functions can be const?

[shchenz]

1: address @hubert.reinterpretcast comments

[shchenz]

Thanks for your review @hubert.reinterpretcast

llvm/lib/MC/MCAsmStreamer.cpp

63–68

Good idea

llvm/include/llvm/MC/MCAsmInfo.h

protected:
   /// Describes if the .lcomm directive for the target supports an alignment
   /// argument and how it is interpreted.  Defaults to NoAlignment.
   LCOMM::LCOMMType LCOMMDirectiveAlignmentType = LCOMM::NoAlignment;
 
   /// True if the target only has basename for .file directive. False if the
   /// target also needs the directory along with the basename. Default to true.
   bool HasBasenameOnlyForFileDirective = true;
 
+  /// Tue if the target represents string constant as mostly raw characters in
+  /// paired double quotation. Default to false.
+  bool HasPairedDoubleQuoteStringConstants = false;
+
   // True if the target allows .align directives on functions. This is true for
   // most targets, so defaults to true.
   bool HasFunctionAlignment = true;
 
   /// True if the target has .type and .size directives, this is true for most
   /// ELF targets.  Defaults to true.
   bool HasDotTypeDotSizeDirective = true;
 
public:
 
   LCOMM::LCOMMType getLCOMMDirectiveAlignmentType() const {
     return LCOMMDirectiveAlignmentType;
   }
 
   bool hasBasenameOnlyForFileDirective() const {
     return HasBasenameOnlyForFileDirective;
   }
+  bool hasPairedDoubleQuoteStringConstants() const {
+    return HasPairedDoubleQuoteStringConstants;
+  }
   bool hasFunctionAlignment() const { return HasFunctionAlignment; }
   bool hasDotTypeDotSizeDirective() const { return HasDotTypeDotSizeDirective; }
   bool hasSingleParameterDotFile() const { return HasSingleParameterDotFile; }
   bool hasIdentDirective() const { return HasIdentDirective; }
   bool hasNoDeadStrip() const { return HasNoDeadStrip; }
   bool hasAltEntry() const { return HasAltEntry; }
   const char *getWeakDirective() const { return WeakDirective; }
   const char *getWeakRefDirective() const { return WeakRefDirective; }

llvm/lib/MC/MCAsmInfoXCOFF.cpp

 extern cl::opt<cl::boolOrDefault> UseLEB128Directives;
 
 void MCAsmInfoXCOFF::anchor() {}
 
 MCAsmInfoXCOFF::MCAsmInfoXCOFF() {
   IsLittleEndian = false;
   HasVisibilityOnlyWithLinkage = true;
   HasBasenameOnlyForFileDirective = false;
+
+  // For XCOFF, string constant consists of any number of characters enclosed in
+  // "" (double quotation marks)
+  HasPairedDoubleQuoteStringConstants = true;
+
   PrivateGlobalPrefix = "L..";
   PrivateLabelPrefix = "L..";
   SupportsQuotedNames = false;
   UseDotAlignForAlignment = true;
   UsesDwarfFileAndLocDirectives = false;
   DwarfSectionSizeRequired = false;
   if (UseLEB128Directives == cl::BOU_UNSET)
     HasLEB128Directives = false;

llvm/lib/MC/MCAsmStreamer.cpp

class MCAsmStreamer final : public MCStreamer {
   raw_svector_ostream CommentStream;
   raw_null_ostream NullStream;
 
   unsigned IsVerboseAsm : 1;
   unsigned ShowInst : 1;
   unsigned UseDwarfDirectory : 1;
 
   void EmitRegisterName(int64_t Register);
+  void PrintQuotedString(StringRef Data, raw_ostream &OS);
+  void printDwarfFileDirective(unsigned FileNo, StringRef Directory,
+                               StringRef Filename,
+                               Optional<MD5::MD5Result> Checksum,
+                               Optional<StringRef> Source,
+                               bool UseDwarfDirectory, raw_svector_ostream &OS);
   void emitCFIStartProcImpl(MCDwarfFrameInfo &Frame) override;
   void emitCFIEndProcImpl(MCDwarfFrameInfo &Frame) override;
 
 public:
   MCAsmStreamer(MCContext &Context, std::unique_ptr<formatted_raw_ostream> os,
                 bool isVerboseAsm, bool useDwarfDirectory,
                 MCInstPrinter *printer, std::unique_ptr<MCCodeEmitter> emitter,
                 std::unique_ptr<MCAsmBackend> asmbackend, bool showInst)
printCharacterList(printOneCharacterFor([&OS](char C) {
       const char AsmCharLitBuf[2] = {'\'', C};
       OS << StringRef(AsmCharLitBuf, sizeof(AsmCharLitBuf));
     }));
     return;
   }
   llvm_unreachable("Invalid AsmCharLiteralSyntax value!");
 }
 
-static void PrintQuotedString(StringRef Data, raw_ostream &OS) {
+void MCAsmStreamer::PrintQuotedString(StringRef Data, raw_ostream &OS) {
   OS << '"';
 
+  if (MAI->hasPairedDoubleQuoteStringConstants()) {
+    for (unsigned i = 0, e = Data.size(); i != e; ++i) {
+      unsigned char C = Data[i];
+      if (C == '"')
+        OS << "\"\"";
+      else
+        OS << (char)C;
+    }
+  } else {
     for (unsigned i = 0, e = Data.size(); i != e; ++i) {
       unsigned char C = Data[i];
       if (C == '"' || C == '\\') {
         OS << '\\' << (char)C;
         continue;
       }
 
       if (isPrint((unsigned char)C)) {
         OS << (char)C;
         continue;
       }
 
       switch (C) {
-      case '\b': OS << "\\b"; break;
-      case '\f': OS << "\\f"; break;
-      case '\n': OS << "\\n"; break;
-      case '\r': OS << "\\r"; break;
-      case '\t': OS << "\\t"; break;
+      case '\b':
+        OS << "\\b";
+        break;
+      case '\f':
+        OS << "\\f";
+        break;
+      case '\n':
+        OS << "\\n";
+        break;
+      case '\r':
+        OS << "\\r";
+        break;
+      case '\t':
+        OS << "\\t";
+        break;
       default:
         OS << '\\';
         OS << toOctal(C >> 6);
         OS << toOctal(C >> 3);
         OS << toOctal(C >> 0);
         break;
       }
     }
+  }
 
   OS << '"';
 }
 
 void MCAsmStreamer::emitBytes(StringRef Data) {
   assert(getCurrentSectionOnly() &&
          "Cannot emit contents before setting section!");
   if (Data.empty()) return;

 
 void MCAsmStreamer::emitFileDirective(StringRef Filename) {
   assert(MAI->hasSingleParameterDotFile());
   OS << "\t.file\t";
   PrintQuotedString(Filename, OS);
   EmitEOL();
 }
 
-static void printDwarfFileDirective(unsigned FileNo, StringRef Directory,
-                                    StringRef Filename,
-                                    Optional<MD5::MD5Result> Checksum,
-                                    Optional<StringRef> Source,
-                                    bool UseDwarfDirectory,
-                                    raw_svector_ostream &OS) {
+void MCAsmStreamer::printDwarfFileDirective(
+    unsigned FileNo, StringRef Directory, StringRef Filename,
+    Optional<MD5::MD5Result> Checksum, Optional<StringRef> Source,
+    bool UseDwarfDirectory, raw_svector_ostream &OS) {
   SmallString<128> FullPathName;
 
   if (!UseDwarfDirectory && !Directory.empty()) {
     if (sys::path::is_absolute(Filename))
       Directory = "";
     else {
       FullPathName = Directory;
       sys::path::append(FullPathName, Filename);

llvm/test/CodeGen/PowerPC/aix-filename-special-character-double-quotation.ll

+; RUN: llc -verify-machineinstrs -mtriple powerpc-ibm-aix-xcoff < %s \
+; RUN:   | FileCheck %s
+; RUN: llc -verify-machineinstrs -mtriple powerpc64-ibm-aix-xcoff < %s \
+; RUN:   | FileCheck %s
+
+; CHECK: .file "1""2.c"
+
+source_filename = "1\222.c"

llvm/test/CodeGen/PowerPC/aix-filename-special-character-single-quotation.ll

+; RUN: llc -verify-machineinstrs -mtriple powerpc-ibm-aix-xcoff < %s \
+; RUN:   | FileCheck %s
+; RUN: llc -verify-machineinstrs -mtriple powerpc64-ibm-aix-xcoff < %s \
+; RUN:   | FileCheck %s
+
+; CHECK: .file "1'2.c"
+
+source_filename = "1'2.c"