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

This patch enables parsing and creating modules directly into the new
debug info format. Prior to this patch, all modules were constructed
with the old debug info format by default, and would be converted into
the new format just before running LLVM passes. This is an important
milestone, in that this means that every tool will now be exposed to
debug records, rather than those that run LLVM passes. As far as I've
tested, all LLVM tools/projects now either handle debug records, or
convert them to the old intrinsic format.

There are a few unit tests that need updating for this patch; these are
either cases of tests that previously needed to set the debug info
format to function, or tests that depend on the old debug info format in
some way. There should be no visible change in the output of any LLVM
tool as a result of this patch, although the likelihood of this patch
breaking downstream code means an NFC tag might be a little misleading,
if not technically incorrect:

This will probably break some downstream tools that don't already handle
debug records. If your downstream code breaks as a result of this
change, the simplest fix is to convert the module in question to the old
debug format before you process it, using
`Module::convertFromNewDbgValues()`. For more information about how to
handle debug records or about what has changed, see the migration
document:
  https://llvm.org/docs/RemoveDIsDebugInfo.html

5 files changed, 24 insertions, 22 deletions

diff --git a/llvm/lib/AsmParser/LLParser.cpp b/llvm/lib/AsmParser/LLParser.cpp
index 2902bd9..34053a5 100644
--- a/llvm/lib/AsmParser/LLParser.cpp
+++ b/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.
diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index 0b7fcd8..73fe63b 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -4319,7 +4319,7 @@ 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);
diff --git a/llvm/lib/IR/BasicBlock.cpp b/llvm/lib/IR/BasicBlock.cpp
index 29f2cbf..aea9425 100644
--- a/llvm/lib/IR/BasicBlock.cpp
+++ b/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);
diff --git a/llvm/lib/IR/Function.cpp b/llvm/lib/IR/Function.cpp
index 6901840..e42248d 100644
--- a/llvm/lib/IR/Function.cpp
+++ b/llvm/lib/IR/Function.cpp
@@ -83,6 +83,8 @@ static cl::opt<unsigned> 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) {
@@ -438,7 +440,7 @@ 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);
diff --git a/llvm/lib/IR/Module.cpp b/llvm/lib/IR/Module.cpp
index a8696ed..915fa50 100644
--- a/llvm/lib/IR/Module.cpp
+++ b/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);
 }