Provide support for preserving assembly comments

Preserve assembly comments from input in output assembly and flags to
toggle property. This is on by default for inline assembly and off in
llvm-mc.

Parsed comments are emitted immediately before an EOL which generally
places them on the expected line.

Reviewers: rtrieu, dwmw2, rnk, majnemer

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D20020

llvm-svn: 275058

6 files changed, 72 insertions, 3 deletions

diff --git a/llvm/lib/CodeGen/LLVMTargetMachine.cpp b/llvm/lib/CodeGen/LLVMTargetMachine.cpp
index f6f9b740957..e62c94dfd0a 100644
--- a/llvm/lib/CodeGen/LLVMTargetMachine.cpp
+++ b/llvm/lib/CodeGen/LLVMTargetMachine.cpp
@@ -70,6 +70,8 @@ void LLVMTargetMachine::initAsmInfo() {
   if (Options.DisableIntegratedAS)
     TmpAsmInfo->setUseIntegratedAssembler(false);
 
+  TmpAsmInfo->setPreserveAsmComments(Options.MCOptions.PreserveAsmComments);
+
   if (Options.CompressDebugSections)
     TmpAsmInfo->setCompressDebugSections(DebugCompressionType::DCT_ZlibGnu);
 
diff --git a/llvm/lib/MC/MCAsmInfo.cpp b/llvm/lib/MC/MCAsmInfo.cpp
index fa83e395f8d..4a05175fdec 100644
--- a/llvm/lib/MC/MCAsmInfo.cpp
+++ b/llvm/lib/MC/MCAsmInfo.cpp
@@ -107,6 +107,7 @@ MCAsmInfo::MCAsmInfo() {
   //   architecture basis.
   //   - The target subclasses for AArch64, ARM, and X86 handle these cases
   UseIntegratedAssembler = false;
+  PreserveAsmComments = true;
 
   CompressDebugSections = DebugCompressionType::DCT_None;
 }
diff --git a/llvm/lib/MC/MCAsmStreamer.cpp b/llvm/lib/MC/MCAsmStreamer.cpp
index 3ff66ed395b..6b089bcd313 100644
--- a/llvm/lib/MC/MCAsmStreamer.cpp
+++ b/llvm/lib/MC/MCAsmStreamer.cpp
@@ -46,6 +46,7 @@ class MCAsmStreamer final : public MCStreamer {
   std::unique_ptr<MCCodeEmitter> Emitter;
   std::unique_ptr<MCAsmBackend> AsmBackend;
 
+  SmallString<128> ExplicitCommentToEmit;
   SmallString<128> CommentToEmit;
   raw_svector_ostream CommentStream;
 
@@ -73,6 +74,8 @@ public:
   }
 
   inline void EmitEOL() {
+    // Dump Explicit Comments here.
+    emitExplicitComments();
     // If we don't have any comments, just emit a \n.
     if (!IsVerboseAsm) {
       OS << '\n';
@@ -112,6 +115,9 @@ public:
 
   void emitRawComment(const Twine &T, bool TabPrefix = true) override;
 
+  void addExplicitComment(const Twine &T) override;
+  void emitExplicitComments() override;
+
   /// AddBlankLine - Emit a blank line to a .s file to pretty it up.
   void AddBlankLine() override {
     EmitEOL();
@@ -325,6 +331,49 @@ void MCAsmStreamer::emitRawComment(const Twine &T, bool TabPrefix) {
   EmitEOL();
 }
 
+void MCAsmStreamer::addExplicitComment(const Twine &T) {
+  StringRef c = T.getSingleStringRef();
+  if (c.equals(StringRef(MAI->getSeparatorString())))
+    return;
+  if (c.startswith(StringRef("//"))) {
+    ExplicitCommentToEmit.append("\t");
+    ExplicitCommentToEmit.append(MAI->getCommentString());
+    // drop //
+    ExplicitCommentToEmit.append(c.slice(2, c.size()).str());
+  } else if (c.startswith(StringRef("/*"))) {
+    size_t p = 2, len = c.size() - 2;
+    // emit each line in comment as separate newline.
+    do {
+      size_t newp = std::min(len, c.find_first_of("\r\n", p));
+      ExplicitCommentToEmit.append("\t");
+      ExplicitCommentToEmit.append(MAI->getCommentString());
+      ExplicitCommentToEmit.append(c.slice(p, newp).str());
+      // If we have another line in this comment add line
+      if (newp < len)
+        ExplicitCommentToEmit.append("\n");
+      p = newp + 1;
+    } while (p < len);
+  } else if (c.startswith(StringRef(MAI->getCommentString()))) {
+    ExplicitCommentToEmit.append("\t");
+    ExplicitCommentToEmit.append(c.str());
+  } else if (c.front() == '#') {
+    // # are comments for ## commentString. Output extra #.
+    ExplicitCommentToEmit.append("\t#");
+    ExplicitCommentToEmit.append(c.str());
+  } else
+    assert(false && "Unexpected Assembly Comment");
+  // full line comments immediately output
+  if (c.back() == '\n')
+    emitExplicitComments();
+}
+
+void MCAsmStreamer::emitExplicitComments() {
+  StringRef Comments = ExplicitCommentToEmit;
+  if (!Comments.empty())
+    OS << Comments;
+  ExplicitCommentToEmit.clear();
+}
+
 void MCAsmStreamer::ChangeSection(MCSection *Section,
                                   const MCExpr *Subsection) {
   assert(Section && "Cannot switch to a null section!");
@@ -510,8 +559,10 @@ void MCAsmStreamer::EmitSymbolDesc(MCSymbol *Symbol, unsigned DescValue) {
 }
 
 void MCAsmStreamer::EmitSyntaxDirective() {
-  if (MAI->getAssemblerDialect() == 1)
-    OS << "\t.intel_syntax noprefix\n";
+  if (MAI->getAssemblerDialect() == 1) {
+    OS << "\t.intel_syntax noprefix";
+    EmitEOL();
+  }
   // FIXME: Currently emit unprefix'ed registers.
   // The intel_syntax directive has one optional argument 
   // with may have a value of prefix or noprefix.
diff --git a/llvm/lib/MC/MCParser/AsmParser.cpp b/llvm/lib/MC/MCParser/AsmParser.cpp
index 9a331ec4458..d16f2452e13 100644
--- a/llvm/lib/MC/MCParser/AsmParser.cpp
+++ b/llvm/lib/MC/MCParser/AsmParser.cpp
@@ -626,9 +626,20 @@ const AsmToken &AsmParser::Lex() {
   if (Lexer.getTok().is(AsmToken::Error))
     Error(Lexer.getErrLoc(), Lexer.getErr());
 
+  // if it's a end of statement with a comment in it
+  if (getTok().is(AsmToken::EndOfStatement)) {
+    // if this is a line comment output it.
+    if (getTok().getString().front() != '\n' &&
+        getTok().getString().front() != '\r' && MAI.preserveAsmComments())
+      Out.addExplicitComment(Twine(getTok().getString()));
+  }
+
   const AsmToken *tok = &Lexer.Lex();
-  // Drop comments here.
+
+  // Parse comments here to be deferred until end of next statement.
   while (tok->is(AsmToken::Comment)) {
+    if (MAI.preserveAsmComments())
+      Out.addExplicitComment(Twine(tok->getString()));
     tok = &Lexer.Lex();
   }
 
diff --git a/llvm/lib/MC/MCParser/ELFAsmParser.cpp b/llvm/lib/MC/MCParser/ELFAsmParser.cpp
index 5650373a12d..533ae1f134b 100644
--- a/llvm/lib/MC/MCParser/ELFAsmParser.cpp
+++ b/llvm/lib/MC/MCParser/ELFAsmParser.cpp
@@ -188,6 +188,7 @@ bool ELFAsmParser::ParseSectionSwitch(StringRef Section, unsigned Type,
     if (getParser().parseExpression(Subsection))
       return true;
   }
+  Lex();
 
   getStreamer().SwitchSection(getContext().getELFSection(Section, Type, Flags),
                               Subsection);
diff --git a/llvm/lib/MC/MCStreamer.cpp b/llvm/lib/MC/MCStreamer.cpp
index 9ef96695e89..6c8828f71ba 100644
--- a/llvm/lib/MC/MCStreamer.cpp
+++ b/llvm/lib/MC/MCStreamer.cpp
@@ -70,6 +70,9 @@ raw_ostream &MCStreamer::GetCommentOS() {
 
 void MCStreamer::emitRawComment(const Twine &T, bool TabPrefix) {}
 
+void MCStreamer::addExplicitComment(const Twine &T) {}
+void MCStreamer::emitExplicitComments() {}
+
 void MCStreamer::generateCompactUnwindEncodings(MCAsmBackend *MAB) {
   for (auto &FI : DwarfFrameInfos)
     FI.CompactUnwindEncoding =