[codeview] Emit S_BUILDINFO and LF_BUILDINFO with cwd and source file

[rnk]

Summary

We can fill in the command line and compiler path later if we want.

llvm/include/llvm/DebugInfo/CodeView/TypeRecord.h

public:
   BuildInfoRecord() = default;
   explicit BuildInfoRecord(TypeRecordKind Kind) : TypeRecord(Kind) {}
   BuildInfoRecord(ArrayRef<TypeIndex> ArgIndices)
       : TypeRecord(TypeRecordKind::BuildInfo),
         ArgIndices(ArgIndices.begin(), ArgIndices.end()) {}
 
   ArrayRef<TypeIndex> getArgs() const { return ArgIndices; }
 
-  SmallVector<TypeIndex, 4> ArgIndices;
+  /// Indices of known build info arguments.
+  enum BuildInfoArg {
+    CurrentDirectory, //< Absolute CWD path
+    BuildTool,        //< Absolute compiler path
+    SourceFile,       //< Path to main source file, relative or absolute
+    TypeServerPDB,    //< Absoulte path of type server PDB (/Fd)
+    CommandLine,      //< Full canonical command line (maybe -cc1)
+    MaxArgs
+  };
+
+  SmallVector<TypeIndex, MaxArgs> ArgIndices;
 };
 
 // LF_VFTABLE
 class VFTableRecord : public TypeRecord {
 public:
   VFTableRecord() = default;
   explicit VFTableRecord(TypeRecordKind Kind) : TypeRecord(Kind) {}
   VFTableRecord(TypeIndex CompleteClass, TypeIndex OverriddenVFTable,

llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.h

class LLVM_LIBRARY_VISIBILITY CodeViewDebug : public DebugHandlerBase {
   void emitCodeViewMagicVersion();
 
   void emitTypeInformation();
 
   void emitTypeGlobalHashes();
 
   void emitCompilerInformation();
 
+  void emitBuildInfo();
+
   void emitInlineeLinesSubsection();
 
   void emitDebugInfoForThunk(const Function *GV,
                              FunctionInfo &FI,
                              const MCSymbol *Fn);
 
   void emitDebugInfoForFunction(const Function *GV, FunctionInfo &FI);
 

llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.cpp

void CodeViewDebug::endModule() {
   // This subsection holds a file index to offset in string table table.
   OS.AddComment("File index to string table offset subsection");
   OS.EmitCVFileChecksumsDirective();
 
   // This subsection holds the string table.
   OS.AddComment("String table");
   OS.EmitCVStringTableDirective();
 
+  // Emit S_BUILDINFO, which points to LF_BUILDINFO. Put this in its own symbol
+  // subsection in the generic .debug$S section at the end. There is no
+  // particular reason for this ordering other than to match MSVC.
+  emitBuildInfo();
+
   // Emit type information and hashes last, so that any types we translate while
   // emitting function info are included.
   emitTypeInformation();
 
   if (EmitDebugGlobalHashes)
     emitTypeGlobalHashes();
 
   clear();
for (int N = 0; N < 4; ++N)
     OS.EmitIntValue(BackVer.Part[N], 2);
 
   OS.AddComment("Null-terminated compiler version string");
   emitNullTerminatedSymbolName(OS, CompilerVersion);
 
   OS.EmitLabel(CompilerEnd);
 }
 
+static TypeIndex getStringIdTypeIdx(GlobalTypeTableBuilder &TypeTable,
+                                    StringRef S) {
+  StringIdRecord SIR(TypeIndex(0x0), S);
+  return TypeTable.writeLeafType(SIR);
+}
+
+void CodeViewDebug::emitBuildInfo() {
+  // First, make LF_BUILDINFO. It's a sequence of strings with various bits of
+  // build info. The known prefix is:
+  // - Absolute path of current directory
+  // - Compiler path
+  // - Main source file path, relative to CWD or absolute
+  // - Type server PDB file
+  // - Canonical compiler command line
+  // If frontend and backend compilation are separated (think llc or LTO), it's
+  // not clear if the compiler path should refer to the executable for the
+  // frontend or the backend. Leave it blank for now.
+  TypeIndex BuildInfoArgs[BuildInfoRecord::MaxArgs] = {};
+  NamedMDNode *CUs = MMI->getModule()->getNamedMetadata("llvm.dbg.cu");
+  const MDNode *Node = *CUs->operands().begin(); // FIXME: Multiple CUs.
+  const auto *CU = cast<DICompileUnit>(Node);
+  const DIFile *MainSourceFile = CU->getFile();
+  BuildInfoArgs[BuildInfoRecord::CurrentDirectory] =
+      getStringIdTypeIdx(TypeTable, MainSourceFile->getDirectory());
+  BuildInfoArgs[BuildInfoRecord::SourceFile] =
+      getStringIdTypeIdx(TypeTable, MainSourceFile->getFilename());
+  // FIXME: Path to compiler and command line. PDB is intentionally blank unless
+  // we implement /Zi type servers.
+  BuildInfoRecord BIR(BuildInfoArgs);
+  TypeIndex BuildInfoIndex = TypeTable.writeLeafType(BIR);
+
+  // Make a new .debug$S subsection for the S_BUILDINFO record, which points
+  // from the module symbols into the type stream.
+  MCSymbol *BuildInfoEnd = beginCVSubsection(DebugSubsectionKind::Symbols);
+  OS.AddComment("Record length");
+  OS.EmitIntValue(6, 2);
+  OS.AddComment("Record kind: S_BUILDINFO");
+  OS.EmitIntValue(unsigned(SymbolKind::S_BUILDINFO), 2);
+  OS.AddComment("LF_BUILDINFO index");
+  OS.EmitIntValue(BuildInfoIndex.getIndex(), 4);
+  endCVSubsection(BuildInfoEnd);
+}
+
 void CodeViewDebug::emitInlineeLinesSubsection() {
   if (InlinedSubprograms.empty())
     return;
 
   OS.AddComment("Inlinee lines subsection");
   MCSymbol *InlineEnd = beginCVSubsection(DebugSubsectionKind::InlineeLines);
 
   // We emit the checksum info for files.  This is used by debuggers to

llvm/test/DebugInfo/COFF/build-info.ll

+; RUN: llc -filetype=obj -mtriple i686-pc-windows-msvc %s -o %t.o
+; RUN: llvm-pdbutil dump %t.o -symbols -types | FileCheck %s
+
+; CHECK: [[INFO_IDX:0x[^ ]*]] | LF_BUILDINFO
+; CHECK-NEXT:          0x{{.*}}: `D:\src\scopes\clang`
+; CHECK-NEXT:          <no type>: ``
+; CHECK-NEXT:          0x{{.*}}: `D:\src\scopes\foo.cpp`
+; CHECK-NEXT:          <no type>: ``
+; CHECK-NEXT:          <no type>: ``
+
+; CHECK: {{.*}} | S_BUILDINFO [size = 8] BuildId = `[[INFO_IDX]]`
+
+; ModuleID = 'D:\src\scopes\foo.cpp'
+source_filename = "D:\5Csrc\5Cscopes\5Cfoo.cpp"
+target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
+target triple = "i686-pc-windows-msvc19.0.23918"
+
+; Function Attrs: nounwind sspstrong
+define i32 @"\01?foo@@YAHXZ"() #0 !dbg !10 {
+entry:
+  ret i32 42, !dbg !14
+}
+
+attributes #0 = { nounwind sspstrong "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="pentium4" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!7, !8}
+!llvm.ident = !{!9}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 4.0.0 ", isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !2)
+; One .debug$S section should contain an S_COMPILE3 record that identifies the
+; source language and the version of the compiler based on the DICompileUnit.
+!1 = !DIFile(filename: "D:\5Csrc\5Cscopes\5Cfoo.cpp", directory: "D:\5Csrc\5Cscopes\5Cclang")
+!2 = !{}
+!7 = !{i32 2, !"CodeView", i32 1}
+!8 = !{i32 2, !"Debug Info Version", i32 3}
+!9 = !{!"clang version 4.0.0 "}
+!10 = distinct !DISubprogram(name: "foo", linkageName: "\01?foo@@YAHXZ", scope: !1, file: !1, line: 1, type: !11, isLocal: false, isDefinition: true, scopeLine: 1, flags: DIFlagPrototyped, isOptimized: false, unit: !0, retainedNodes: !2)
+!11 = !DISubroutineType(types: !12)
+!12 = !{!13}
+!13 = !DIBasicType(name: "int", size: 32, align: 32, encoding: DW_ATE_signed)
+!14 = !DILocation(line: 2, scope: !10)