DebugInfo: Added support for Checksum debug info feature (Clang part)

[aaboud]

Summary

Resolve Bug 30978.

This patch contains changes in Clang to support Checksum debug info feature.

[rnk]

lib/Basic/SourceManager.cpp

1447 ↗

(On Diff #80973)

Let's move this whole thing to CGDebugInfo::getOrCreateFile. SourceManager isn't caching or managing MD5 checksums at all in this CL.

1450–1451 ↗

(On Diff #80973)

If this can fail, we should not pretend to have an MD5 checksum in the debug info.

1461 ↗

(On Diff #80973)

This can use SmallString and stringifyResult() to avoid heap allocations.

lib/CodeGen/CGDebugInfo.cpp

376

We should only do this if CGM.getCodeGenOpts().EmitCodeView, or we will regress compile time on other platforms without any added functionality.

[probinson]

lib/CodeGen/CGDebugInfo.cpp

376

Eventually we'll want it for DWARF 5 also, but for now conditioning on CodeView is fine.

[aaboud]

Moved getChecksum from SourceManager to CGDebugInfo.
Also, now checksum is emitted only for CodeView.

[rnk]

test/CodeGen/debug-info-file-checksum.c

1

Instead of %s.source, you can do %S/Inputs/debug-info-file-checksum.c.

test/CodeGen/debug-info-file-checksum.c.source

1

This can live in test/CodeGen/Inputs/debug-info-file-checksum.c

[majnemer]

lib/CodeGen/CGDebugInfo.cpp

433–434

Formatting looks wrong

[aaboud]

Addressed comments by Reid and David.

[rnk]

This side looks good.

lib/CodeGen/CGDebugInfo.cpp

325

This is uncached. Maybe call it computeChecksum to indicate that it is expensive?

lib/CodeGen/CGDebugInfo.h

private:
   StringRef getCurrentDirname();
 
   /// Create new compile unit.
   void CreateCompileUnit();
 
   /// Remap a given path with the current debug prefix map
   std::string remapDIPath(StringRef) const;
 
+  /// Get the file checksum debug info for input file ID.
+  llvm::DIFile::ChecksumKind getChecksum(FileID FID,
+                                         SmallString<32> &Checksum) const;
+
   /// Get the file debug info descriptor for the input location.
   llvm::DIFile *getOrCreateFile(SourceLocation Loc);
 
   /// Get the file info for main compile unit.
   llvm::DIFile *getOrCreateMainFile();
 
   /// Get the type from the cache or create a new type if necessary.
   llvm::DIType *getOrCreateType(QualType Ty, llvm::DIFile *Fg);

lib/CodeGen/CGDebugInfo.cpp

 #include "llvm/ADT/StringExtras.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/FileSystem.h"
+#include "llvm/Support/MD5.h"
 #include "llvm/Support/Path.h"
 using namespace clang;
 using namespace clang::CodeGen;
 
 static uint32_t getTypeAlignIfRequired(const Type *Ty, const ASTContext &Ctx) {
   auto TI = Ctx.getTypeInfo(Ty);
   return TI.AlignIsRequired ? TI.Align : 0;
 }
if (CGM.getLangOpts().CPlusPlus) {
         return internString(UnnamedType);
       }
     }
   }
 
   return StringRef();
 }
 
+llvm::DIFile::ChecksumKind
+CGDebugInfo::getChecksum(FileID FID, SmallString<32> &Checksum) const {
+  Checksum.clear();
+
+  if (!CGM.getCodeGenOpts().EmitCodeView)
+    return llvm::DIFile::CSK_None;
+
+  SourceManager &SM = CGM.getContext().getSourceManager();
+  bool Invalid;
+  llvm::MemoryBuffer *MemBuffer = SM.getBuffer(FID, &Invalid);
+  if (Invalid)
+    return llvm::DIFile::CSK_None;
+
+  llvm::MD5 Hash;
+  llvm::MD5::MD5Result Result;
+
+  Hash.update(MemBuffer->getBuffer());
+  Hash.final(Result);
+
+  Hash.stringifyResult(Result, Checksum);
+  return llvm::DIFile::CSK_MD5;
+}
+
 llvm::DIFile *CGDebugInfo::getOrCreateFile(SourceLocation Loc) {
   if (!Loc.isValid())
     // If Location is not valid then use main input file.
     return DBuilder.createFile(remapDIPath(TheCU->getFilename()),
-                               remapDIPath(TheCU->getDirectory()));
+                               remapDIPath(TheCU->getDirectory()),
+                               TheCU->getFile()->getChecksumKind(),
+                               TheCU->getFile()->getChecksum());
 
   SourceManager &SM = CGM.getContext().getSourceManager();
   PresumedLoc PLoc = SM.getPresumedLoc(Loc);
 
   if (PLoc.isInvalid() || StringRef(PLoc.getFilename()).empty())
     // If the location is not valid then use main input file.
     return DBuilder.createFile(remapDIPath(TheCU->getFilename()),
-                               remapDIPath(TheCU->getDirectory()));
+                               remapDIPath(TheCU->getDirectory()),
+                               TheCU->getFile()->getChecksumKind(),
+                               TheCU->getFile()->getChecksum());
 
   // Cache the results.
   const char *fname = PLoc.getFilename();
   auto it = DIFileCache.find(fname);
 
   if (it != DIFileCache.end()) {
     // Verify that the information still exists.
     if (llvm::Metadata *V = it->second)
       return cast<llvm::DIFile>(V);
   }
 
+  SmallString<32> Checksum;
+  llvm::DIFile::ChecksumKind CSKind = getChecksum(SM.getFileID(Loc), Checksum);
+
   llvm::DIFile *F = DBuilder.createFile(remapDIPath(PLoc.getFilename()),
-                                        remapDIPath(getCurrentDirname()));
+                                        remapDIPath(getCurrentDirname()),
+                                        CSKind, Checksum);
 
   DIFileCache[fname].reset(F);
   return F;
 }
 
 llvm::DIFile *CGDebugInfo::getOrCreateMainFile() {
   return DBuilder.createFile(remapDIPath(TheCU->getFilename()),
-                             remapDIPath(TheCU->getDirectory()));
+                             remapDIPath(TheCU->getDirectory()),
+                             TheCU->getFile()->getChecksumKind(),
+                             TheCU->getFile()->getChecksum());
 }
 
 std::string CGDebugInfo::remapDIPath(StringRef Path) const {
   for (const auto &Entry : DebugPrefixMap)
     if (Path.startswith(Entry.first))
       return (Twine(Entry.second) + Path.substr(Entry.first.size())).str();
   return Path.str();
 }
StringRef CGDebugInfo::getCurrentDirname() {
   if (!CWDName.empty())
     return CWDName;
   SmallString<256> CWD;
   llvm::sys::fs::current_path(CWD);
   return CWDName = internString(CWD);
 }
 
 void CGDebugInfo::CreateCompileUnit() {
+   SmallString<32> Checksum;
+  llvm::DIFile::ChecksumKind CSKind = llvm::DIFile::CSK_None;
 
   // Should we be asking the SourceManager for the main file name, instead of
   // accepting it as an argument? This just causes the main file name to
   // mismatch with source locations and create extra lexical scopes or
   // mismatched debug info (a CU with a DW_AT_file of "-", because that's what
   // the driver passed, but functions/other things have DW_AT_file of "<stdin>"
   // because that's what the SourceManager says)
 
void CGDebugInfo::CreateCompileUnit() {
   std::string MainFileDir;
   if (const FileEntry *MainFile = SM.getFileEntryForID(SM.getMainFileID())) {
     MainFileDir = remapDIPath(MainFile->getDir()->getName());
     if (MainFileDir != ".") {
       llvm::SmallString<1024> MainFileDirSS(MainFileDir);
       llvm::sys::path::append(MainFileDirSS, MainFileName);
       MainFileName = MainFileDirSS.str();
     }
+    CSKind = getChecksum(SM.getMainFileID(), Checksum);
   }
 
   llvm::dwarf::SourceLanguage LangTag;
   const LangOptions &LO = CGM.getLangOpts();
   if (LO.CPlusPlus) {
     if (LO.ObjC1)
       LangTag = llvm::dwarf::DW_LANG_ObjC_plus_plus;
     else
case codegenoptions::FullDebugInfo:
     EmissionKind = llvm::DICompileUnit::FullDebug;
     break;
   }
 
   // Create new compile unit.
   // FIXME - Eliminate TheCU.
   TheCU = DBuilder.createCompileUnit(
       LangTag, DBuilder.createFile(remapDIPath(MainFileName),
-                                    remapDIPath(getCurrentDirname())),
+                                   remapDIPath(getCurrentDirname()), CSKind,
+                                   Checksum),
       Producer, LO.Optimize, CGM.getCodeGenOpts().DwarfDebugFlags, RuntimeVers,
       CGM.getCodeGenOpts().SplitDwarfFile, EmissionKind, 0 /* DWOid */,
       CGM.getCodeGenOpts().SplitDwarfInlining);
 }
 
 llvm::DIType *CGDebugInfo::CreateType(const BuiltinType *BT) {
   llvm::dwarf::TypeKind Encoding;
   StringRef BTName;

test/CodeGen/debug-info-file-checksum.c

+// RUN: %clang -emit-llvm -S -g -gcodeview -x c %s.source -o - | FileCheck %s
+
+// Check that "checksum" is created correctly for the compiled file.
+
+// CHECK: !DIFile(filename:{{.*}}, directory:{{.*}}, checksumkind: CSK_MD5, checksum: "a3b7d27af071accdeccaa933fc603608")

test/CodeGen/debug-info-file-checksum.c.source

+int foo(int x) {
+  return x+1;
+}