Reapply#3 "[RemoveDIs] Load into new debug info format by default in LLVM (llvm#89799)"

Reapplies commit 91446e2, which was reverted due to a downstream error,
discussed on the pull request. The error could not be reproduced
upstream, and cannot be reproduced downstream as-of current main, so
until the error can be confirmed to still exist this patch should
return.

This reverts commit 23f8fac.

Author: SLTozer

clang/test/CodeGen/instrument-objc-method.m

@@ -11,16 +11,16 @@ @implementation ObjCClass
 + (void)initialize {
 }
 
-// PREINLINE: declare void @llvm.dbg.declare(metadata, metadata, metadata) #1
-// BARE: @"\01+[ObjCClass load]"{{\(.*\)}} #2
+// BARE: @"\01+[ObjCClass load]"{{\(.*\)}} #1
 + (void)load __attribute__((no_instrument_function)) {
 }
 
-// PREINLINE: @"\01-[ObjCClass dealloc]"{{\(.*\)}} #2
-// BARE: @"\01-[ObjCClass dealloc]"{{\(.*\)}} #2
+// PREINLINE: @"\01-[ObjCClass dealloc]"{{\(.*\)}} #1
+// BARE: @"\01-[ObjCClass dealloc]"{{\(.*\)}} #1
 - (void)dealloc __attribute__((no_instrument_function)) {
 }
 
+// PREINLINE: declare void @llvm.dbg.declare(metadata, metadata, metadata) #2
 // PREINLINE: attributes #0 = { {{.*}}"instrument-function-entry"="__cyg_profile_func_enter"
 // PREINLINE-NOT: attributes #0 = { {{.*}}"instrument-function-entry"="__cyg_profile_func_enter_bare"
 // PREINLINE-NOT: attributes #2 = { {{.*}}"__cyg_profile_func_enter"

llvm/docs/ReleaseNotes.rst

@@ -225,6 +225,13 @@ Changes to the Metadata Info
 Changes to the Debug Info
 ---------------------------------
 
+* LLVM has switched from using debug intrinsics internally to using debug
+  records by default. This should happen transparently when using the DIBuilder
+  to construct debug variable information, but will require changes for any code
+  that interacts with debug intrinsics directly. Debug intrinsics will only be
+  supported on a best-effort basis from here onwards; for more information, see
+  the `migration docs <https://llvm.org/docs/RemoveDIsDebugInfo.html>`_.
+
 Changes to the LLVM tools
 ---------------------------------
 * llvm-nm and llvm-objdump can now print symbol information from linked

llvm/include/llvm/AsmParser/LLParser.h

@@ -337,7 +337,6 @@ namespace llvm {
 
     // Top-Level Entities
     bool parseTopLevelEntities();
-    bool finalizeDebugInfoFormat(Module *M);
     void dropUnknownMetadataReferences();
     bool validateEndOfModule(bool UpgradeDebugInfo);
     bool validateEndOfIndex();

llvm/lib/AsmParser/LLParser.cpp

@@ -74,23 +74,6 @@ static std::string getTypeString(Type *T) {
   return Tmp.str();
 }
 
-// Whatever debug info format we parsed, we should convert to the expected debug
-// info format immediately afterwards.
-bool LLParser::finalizeDebugInfoFormat(Module *M) {
-  // We should have already returned an error if we observed both intrinsics and
-  // records in this IR.
-  assert(!(SeenNewDbgInfoFormat && SeenOldDbgInfoFormat) &&
-         "Mixed debug intrinsics/records seen without a parsing error?");
-  if (PreserveInputDbgFormat == cl::boolOrDefault::BOU_TRUE) {
-    UseNewDbgInfoFormat = SeenNewDbgInfoFormat;
-    WriteNewDbgInfoFormatToBitcode = SeenNewDbgInfoFormat;
-    WriteNewDbgInfoFormat = SeenNewDbgInfoFormat;
-  } else if (M) {
-    M->setIsNewDbgInfoFormat(false);
-  }
-  return false;
-}
-
 /// Run: module ::= toplevelentity*
 bool LLParser::Run(bool UpgradeDebugInfo,
                    DataLayoutCallbackTy DataLayoutCallback) {
@@ -108,7 +91,7 @@ bool LLParser::Run(bool UpgradeDebugInfo,
   }
 
   return parseTopLevelEntities() || validateEndOfModule(UpgradeDebugInfo) ||
-         validateEndOfIndex() || finalizeDebugInfoFormat(M);
+         validateEndOfIndex();
 }
 
 bool LLParser::parseStandaloneConstantValue(Constant *&C,
@@ -207,6 +190,18 @@ void LLParser::dropUnknownMetadataReferences() {
 bool LLParser::validateEndOfModule(bool UpgradeDebugInfo) {
   if (!M)
     return false;
+
+  // We should have already returned an error if we observed both intrinsics and
+  // records in this IR.
+  assert(!(SeenNewDbgInfoFormat && SeenOldDbgInfoFormat) &&
+         "Mixed debug intrinsics/records seen without a parsing error?");
+  if (PreserveInputDbgFormat == cl::boolOrDefault::BOU_TRUE) {
+    UseNewDbgInfoFormat = SeenNewDbgInfoFormat;
+    WriteNewDbgInfoFormatToBitcode = SeenNewDbgInfoFormat;
+    WriteNewDbgInfoFormat = SeenNewDbgInfoFormat;
+    M->setNewDbgInfoFormatFlag(SeenNewDbgInfoFormat);
+  }
+
   // Handle any function attribute group forward references.
   for (const auto &RAG : ForwardRefAttrGroups) {
     Value *V = RAG.first;
@@ -439,6 +434,9 @@ bool LLParser::validateEndOfModule(bool UpgradeDebugInfo) {
   UpgradeModuleFlags(*M);
   UpgradeSectionAttributes(*M);
 
+  if (PreserveInputDbgFormat != cl::boolOrDefault::BOU_TRUE)
+    M->setIsNewDbgInfoFormat(UseNewDbgInfoFormat);
+
   if (!Slots)
     return false;
   // Initialize the slot mapping.

llvm/lib/Bitcode/Reader/BitcodeReader.cpp

@@ -4355,7 +4355,7 @@ Error BitcodeReader::parseModule(uint64_t ResumeBit,
   if (PreserveInputDbgFormat != cl::boolOrDefault::BOU_TRUE) {
     TheModule->IsNewDbgInfoFormat =
         UseNewDbgInfoFormat &&
-        LoadBitcodeIntoNewDbgInfoFormat == cl::boolOrDefault::BOU_TRUE;
+        LoadBitcodeIntoNewDbgInfoFormat != cl::boolOrDefault::BOU_FALSE;
   }
 
   this->ValueTypeCallback = std::move(Callbacks.ValueType);

llvm/lib/IR/BasicBlock.cpp

@@ -181,7 +181,7 @@ template class llvm::SymbolTableListTraits<Instruction,
 BasicBlock::BasicBlock(LLVMContext &C, const Twine &Name, Function *NewParent,
                        BasicBlock *InsertBefore)
     : Value(Type::getLabelTy(C), Value::BasicBlockVal),
-      IsNewDbgInfoFormat(false), Parent(nullptr) {
+      IsNewDbgInfoFormat(UseNewDbgInfoFormat), Parent(nullptr) {
 
   if (NewParent)
     insertInto(NewParent, InsertBefore);

llvm/lib/IR/DebugProgramInstruction.cpp

@@ -366,8 +366,8 @@ void DbgVariableRecord::setKillLocation() {
 }
 
 bool DbgVariableRecord::isKillLocation() const {
-  return (getNumVariableLocationOps() == 0 &&
-          !getExpression()->isComplex()) ||
+  return (!hasArgList() && isa<MDNode>(getRawLocation())) ||
+         (getNumVariableLocationOps() == 0 && !getExpression()->isComplex()) ||
          any_of(location_ops(), [](Value *V) { return isa<UndefValue>(V); });
 }
 

llvm/lib/IR/Function.cpp

@@ -83,6 +83,8 @@ static cl::opt<int> NonGlobalValueMaxNameSize(
     "non-global-value-max-name-size", cl::Hidden, cl::init(1024),
     cl::desc("Maximum size for the name of non-global values."));
 
+extern cl::opt<bool> UseNewDbgInfoFormat;
+
 void Function::convertToNewDbgValues() {
   IsNewDbgInfoFormat = true;
   for (auto &BB : *this) {
@@ -441,7 +443,7 @@ Function::Function(FunctionType *Ty, LinkageTypes Linkage, unsigned AddrSpace,
     : GlobalObject(Ty, Value::FunctionVal,
                    OperandTraits<Function>::op_begin(this), 0, Linkage, name,
                    computeAddrSpace(AddrSpace, ParentModule)),
-      NumArgs(Ty->getNumParams()), IsNewDbgInfoFormat(false) {
+      NumArgs(Ty->getNumParams()), IsNewDbgInfoFormat(UseNewDbgInfoFormat) {
   assert(FunctionType::isValidReturnType(getReturnType()) &&
          "invalid return type");
   setGlobalObjectSubClassData(0);

llvm/lib/IR/Module.cpp

@@ -54,6 +54,8 @@
 
 using namespace llvm;
 
+extern cl::opt<bool> UseNewDbgInfoFormat;
+
 //===----------------------------------------------------------------------===//
 // Methods to implement the globals and functions lists.
 //
@@ -72,7 +74,7 @@ template class llvm::SymbolTableListTraits<GlobalIFunc>;
 Module::Module(StringRef MID, LLVMContext &C)
     : Context(C), ValSymTab(std::make_unique<ValueSymbolTable>(-1)),
       ModuleID(std::string(MID)), SourceFileName(std::string(MID)), DL(""),
-      IsNewDbgInfoFormat(false) {
+      IsNewDbgInfoFormat(UseNewDbgInfoFormat) {
   Context.addModule(this);
 }
 

llvm/tools/llvm-as/llvm-as.cpp

@@ -142,11 +142,10 @@ int main(int argc, char **argv) {
   }
 
   // Convert to new debug format if requested.
-  assert(!M->IsNewDbgInfoFormat && "Unexpectedly in new debug mode");
-  if (UseNewDbgInfoFormat && WriteNewDbgInfoFormatToBitcode) {
-    M->convertToNewDbgValues();
+  M->setIsNewDbgInfoFormat(UseNewDbgInfoFormat &&
+                           WriteNewDbgInfoFormatToBitcode);
+  if (M->IsNewDbgInfoFormat)
     M->removeDebugIntrinsicDeclarations();
-  }
 
   std::unique_ptr<ModuleSummaryIndex> Index = std::move(ModuleAndIndex.Index);