[ThinLTO] Serialize the Module SourceFileName to/from LLVM assembly

Summary:
This change serializes out and in the SourceFileName to LLVM assembly
so that it is preserved through "llvm-dis | llvm-as". This is
necessary to ensure that the global identifiers created for local values
in the module summary index are the same even if the bitcode is
streamed out and read back from LLVM assembly.

Serializing the summary itself to LLVM assembly is in progress.

Reviewers: joker.eph

Subscribers: llvm-commits, joker.eph

Differential Revision: http://reviews.llvm.org/D18588

llvm-svn: 264869

lib/AsmParser/LLLexer.cpp

@@ -533,6 +533,7 @@ lltok::Kind LLLexer::LexIdentifier() {
   KEYWORD(notail);
   KEYWORD(target);
   KEYWORD(triple);
+  KEYWORD(source_filename);
   KEYWORD(unwind);
   KEYWORD(deplibs);             // FIXME: Remove in 4.0.
   KEYWORD(datalayout);

lib/AsmParser/LLParser.cpp

@@ -239,6 +239,10 @@ bool LLParser::ParseTopLevelEntities() {
     case lltok::kw_define:  if (ParseDefine()) return true; break;
     case lltok::kw_module:  if (ParseModuleAsm()) return true; break;
     case lltok::kw_target:  if (ParseTargetDefinition()) return true; break;
+    case lltok::kw_source_filename:
+      if (ParseSourceFileName())
+        return true;
+      break;
     case lltok::kw_deplibs: if (ParseDepLibs()) return true; break;
     case lltok::LocalVarID: if (ParseUnnamedType()) return true; break;
     case lltok::LocalVar:   if (ParseNamedType()) return true; break;
@@ -335,6 +339,19 @@ bool LLParser::ParseTargetDefinition() {
   }
 }
 
+/// toplevelentity
+///   ::= 'source_filename' '=' STRINGCONSTANT
+bool LLParser::ParseSourceFileName() {
+  assert(Lex.getKind() == lltok::kw_source_filename);
+  std::string Str;
+  Lex.Lex();
+  if (ParseToken(lltok::equal, "expected '=' after source_filename") ||
+      ParseStringConstant(Str))
+    return true;
+  M->setSourceFileName(Str);
+  return false;
+}
+
 /// toplevelentity
 ///   ::= 'deplibs' '=' '[' ']'
 ///   ::= 'deplibs' '=' '[' STRINGCONSTANT (',' STRINGCONSTANT)* ']'

lib/AsmParser/LLParser.h

@@ -261,6 +261,7 @@ namespace llvm {
     bool ValidateEndOfModule();
     bool ParseTargetDefinition();
     bool ParseModuleAsm();
+    bool ParseSourceFileName();
     bool ParseDepLibs();        // FIXME: Remove in 4.0.
     bool ParseUnnamedType();
     bool ParseNamedType();

lib/AsmParser/LLToken.h

@@ -59,6 +59,7 @@ namespace lltok {
     kw_notail,
     kw_target,
     kw_triple,
+    kw_source_filename,
     kw_unwind,
     kw_deplibs,                 // FIXME: Remove in 4.0
     kw_datalayout,

lib/IR/AsmWriter.cpp

@@ -2215,6 +2215,9 @@ void AssemblyWriter::printModule(const Module *M) {
       M->getModuleIdentifier().find('\n') == std::string::npos)
     Out << "; ModuleID = '" << M->getModuleIdentifier() << "'\n";
 
+  if (!M->getSourceFileName().empty())
+    Out << "source_filename = \"" << M->getSourceFileName() << "\"\n";
+
   const std::string &DL = M->getDataLayoutStr();
   if (!DL.empty())
     Out << "target datalayout = \"" << DL << "\"\n";

test/Assembler/source-filename.ll

@@ -0,0 +1,8 @@
+
+; Make sure that llvm-as/llvm-dis properly assemble/disassemble the
+; source_filename.
+
+; RUN: llvm-as < %s | llvm-dis | FileCheck %s
+
+; CHECK: source_filename = "test.cc"
+source_filename = "test.cc"