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

[tejohnson]

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.

[mehdi_amini]

LGTM

lib/AsmParser/LLLexer.cpp

#define KEYWORD(STR)                                                           \
   KEYWORD(caller);
   KEYWORD(within);
   KEYWORD(from);
   KEYWORD(tail);
   KEYWORD(musttail);
   KEYWORD(notail);
   KEYWORD(target);
   KEYWORD(triple);
+  KEYWORD(source_filename);
   KEYWORD(unwind);
   KEYWORD(deplibs);             // FIXME: Remove in 4.0.
   KEYWORD(datalayout);
   KEYWORD(volatile);
   KEYWORD(atomic);
   KEYWORD(unordered);
   KEYWORD(monotonic);
   KEYWORD(acquire);

lib/AsmParser/LLParser.h

bool ParseIndexList(SmallVectorImpl<unsigned> &Indices) {
       return false;
     }
 
     // Top-Level Entities
     bool ParseTopLevelEntities();
     bool ValidateEndOfModule();
     bool ParseTargetDefinition();
     bool ParseModuleAsm();
+    bool ParseSourceFileName();
     bool ParseDepLibs();        // FIXME: Remove in 4.0.
     bool ParseUnnamedType();
     bool ParseNamedType();
     bool ParseDeclare();
     bool ParseDefine();
 
     bool ParseGlobalType(bool &IsConstant);
     bool ParseUnnamedGlobal();

lib/AsmParser/LLParser.cpp

bool LLParser::ParseTopLevelEntities() {
   while (1) {
     switch (Lex.getKind()) {
     default:         return TokError("expected top-level entity");
     case lltok::Eof: return false;
     case lltok::kw_declare: if (ParseDeclare()) return true; break;
     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;
     case lltok::GlobalID:   if (ParseUnnamedGlobal()) return true; break;
     case lltok::GlobalVar:  if (ParseNamedGlobal()) return true; break;
     case lltok::ComdatVar:  if (parseComdat()) return true; break;
     case lltok::exclaim:    if (ParseStandaloneMetadata()) return true; break;
     case lltok::MetadataVar:if (ParseNamedMetadata()) return true; break;
if (ParseToken(lltok::equal, "expected '=' after target datalayout") ||
         ParseStringConstant(Str))
       return true;
     M->setDataLayout(Str);
     return false;
   }
 }
 
 /// 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)* ']'
 /// FIXME: Remove in 4.0. Currently parse, but ignore.
 bool LLParser::ParseDepLibs() {
   assert(Lex.getKind() == lltok::kw_deplibs);
   Lex.Lex();
   if (ParseToken(lltok::equal, "expected '=' after deplibs") ||
       ParseToken(lltok::lsquare, "expected '=' after deplibs"))

lib/AsmParser/LLToken.h

enum Kind {
     kw_caller,
     kw_within,
     kw_from,
     kw_tail,
     kw_musttail,
     kw_notail,
     kw_target,
     kw_triple,
+    kw_source_filename,
     kw_unwind,
     kw_deplibs,                 // FIXME: Remove in 4.0
     kw_datalayout,
     kw_volatile,
     kw_atomic,
     kw_unordered, kw_monotonic, kw_acquire, kw_release, kw_acq_rel, kw_seq_cst,
     kw_singlethread,
     kw_nnan,

lib/IR/AsmWriter.cpp

if (ShouldPreserveUseListOrder)
     UseListOrders = predictUseListOrder(M);
 
   if (!M->getModuleIdentifier().empty() &&
       // Don't print the ID if it will start a new line (which would
       // require a comment char before it).
       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";
   if (!M->getTargetTriple().empty())
     Out << "target triple = \"" << M->getTargetTriple() << "\"\n";
 
   if (!M->getModuleInlineAsm().empty()) {
     Out << '\n';

test/Assembler/source-filename.ll

+
+; 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"