[CIR] Upstream support for emitting constructors (#143639)

This change upstreams the code to emit simple constructor defintions.

Author: andykaylor

clang/include/clang/CIR/MissingFeatures.h

@@ -81,6 +81,7 @@ struct MissingFeatures {
   static bool opFuncCPUAndFeaturesAttributes() { return false; }
   static bool opFuncSection() { return false; }
   static bool opFuncSetComdat() { return false; }
+  static bool opFuncAttributesForDefinition() { return false; }
 
   // CallOp handling
   static bool opCallPseudoDtor() { return false; }
@@ -226,6 +227,9 @@ struct MissingFeatures {
   static bool implicitConstructorArgs() { return false; }
   static bool intrinsics() { return false; }
   static bool attributeNoBuiltin() { return false; }
+  static bool emitCtorPrologue() { return false; }
+  static bool thunks() { return false; }
+  static bool runCleanupsScope() { return false; }
 
   // Missing types
   static bool dataMemberType() { return false; }

clang/lib/CIR/CodeGen/CIRGenCXX.cpp

@@ -0,0 +1,40 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This contains code dealing with C++ code generation.
+//
+//===----------------------------------------------------------------------===//
+
+#include "CIRGenFunction.h"
+#include "CIRGenModule.h"
+
+#include "clang/AST/GlobalDecl.h"
+#include "clang/CIR/MissingFeatures.h"
+
+using namespace clang;
+using namespace clang::CIRGen;
+
+cir::FuncOp CIRGenModule::codegenCXXStructor(GlobalDecl gd) {
+  const CIRGenFunctionInfo &fnInfo =
+      getTypes().arrangeCXXStructorDeclaration(gd);
+  cir::FuncType funcType = getTypes().getFunctionType(fnInfo);
+  cir::FuncOp fn = getAddrOfCXXStructor(gd, &fnInfo, /*FnType=*/nullptr,
+                                        /*DontDefer=*/true, ForDefinition);
+  assert(!cir::MissingFeatures::opFuncLinkage());
+  CIRGenFunction cgf{*this, builder};
+  curCGF = &cgf;
+  {
+    mlir::OpBuilder::InsertionGuard guard(builder);
+    cgf.generateCode(gd, fn, funcType);
+  }
+  curCGF = nullptr;
+
+  setNonAliasAttributes(gd, fn);
+  assert(!cir::MissingFeatures::opFuncAttributesForDefinition());
+  return fn;
+}

clang/lib/CIR/CodeGen/CIRGenCXXABI.h

@@ -37,6 +37,10 @@ class CIRGenCXXABI {
 
   void setCXXABIThisValue(CIRGenFunction &cgf, mlir::Value thisPtr);
 
+  /// Emit a single constructor/destructor with the gen type from a C++
+  /// constructor/destructor Decl.
+  virtual void emitCXXStructor(clang::GlobalDecl gd) = 0;
+
 public:
   clang::ImplicitParamDecl *getThisDecl(CIRGenFunction &cgf) {
     return cgf.cxxabiThisDecl;
@@ -55,12 +59,19 @@ class CIRGenCXXABI {
     return md->getParent();
   }
 
+  /// Return whether the given global decl needs a VTT (virtual table table)
+  /// parameter.
+  virtual bool needsVTTParameter(clang::GlobalDecl gd) { return false; }
+
   /// Build a parameter variable suitable for 'this'.
   void buildThisParam(CIRGenFunction &cgf, FunctionArgList &params);
 
   /// Loads the incoming C++ this pointer as it was passed by the caller.
   mlir::Value loadIncomingCXXThis(CIRGenFunction &cgf);
 
+  /// Emit constructor variants required by this ABI.
+  virtual void emitCXXConstructors(const clang::CXXConstructorDecl *d) = 0;
+
   /// Returns true if the given constructor or destructor is one of the kinds
   /// that the ABI says returns 'this' (only applies when called non-virtually
   /// for destructors).

clang/lib/CIR/CodeGen/CIRGenCall.cpp

@@ -162,6 +162,47 @@ arrangeCIRFunctionInfo(CIRGenTypes &cgt, SmallVectorImpl<CanQualType> &prefix,
   return cgt.arrangeCIRFunctionInfo(resultType, prefix, required);
 }
 
+void CIRGenFunction::emitDelegateCallArg(CallArgList &args,
+                                         const VarDecl *param,
+                                         SourceLocation loc) {
+  // StartFunction converted the ABI-lowered parameter(s) into a local alloca.
+  // We need to turn that into an r-value suitable for emitCall
+  Address local = getAddrOfLocalVar(param);
+
+  QualType type = param->getType();
+
+  if (const auto *rd = type->getAsCXXRecordDecl()) {
+    cgm.errorNYI(param->getSourceRange(),
+                 "emitDelegateCallArg: record argument");
+    return;
+  }
+
+  // GetAddrOfLocalVar returns a pointer-to-pointer for references, but the
+  // argument needs to be the original pointer.
+  if (type->isReferenceType()) {
+    args.add(
+        RValue::get(builder.createLoad(getLoc(param->getSourceRange()), local)),
+        type);
+  } else if (getLangOpts().ObjCAutoRefCount) {
+    cgm.errorNYI(param->getSourceRange(),
+                 "emitDelegateCallArg: ObjCAutoRefCount");
+    // For the most part, we just need to load the alloca, except that aggregate
+    // r-values are actually pointers to temporaries.
+  } else {
+    cgm.errorNYI(param->getSourceRange(),
+                 "emitDelegateCallArg: convertTempToRValue");
+  }
+
+  // Deactivate the cleanup for the callee-destructed param that was pushed.
+  assert(!cir::MissingFeatures::thunks());
+  if (type->isRecordType() &&
+      type->castAs<RecordType>()->getDecl()->isParamDestroyedInCallee() &&
+      param->needsDestruction(getContext())) {
+    cgm.errorNYI(param->getSourceRange(),
+                 "emitDelegateCallArg: callee-destructed param");
+  }
+}
+
 static const CIRGenFunctionInfo &
 arrangeFreeFunctionLikeCall(CIRGenTypes &cgt, CIRGenModule &cgm,
                             const CallArgList &args,

clang/lib/CIR/CodeGen/CIRGenClass.cpp

@@ -21,6 +21,87 @@
 using namespace clang;
 using namespace clang::CIRGen;
 
+/// Checks whether the given constructor is a valid subject for the
+/// complete-to-base constructor delegation optimization, i.e. emitting the
+/// complete constructor as a simple call to the base constructor.
+bool CIRGenFunction::isConstructorDelegationValid(
+    const CXXConstructorDecl *ctor) {
+  // Currently we disable the optimization for classes with virtual bases
+  // because (1) the address of parameter variables need to be consistent across
+  // all initializers but (2) the delegate function call necessarily creates a
+  // second copy of the parameter variable.
+  //
+  // The limiting example (purely theoretical AFAIK):
+  //   struct A { A(int &c) { c++; } };
+  //   struct A : virtual A {
+  //     B(int count) : A(count) { printf("%d\n", count); }
+  //   };
+  // ...although even this example could in principle be emitted as a delegation
+  // since the address of the parameter doesn't escape.
+  if (ctor->getParent()->getNumVBases())
+    return false;
+
+  // We also disable the optimization for variadic functions because it's
+  // impossible to "re-pass" varargs.
+  if (ctor->getType()->castAs<FunctionProtoType>()->isVariadic())
+    return false;
+
+  // FIXME: Decide if we can do a delegation of a delegating constructor.
+  if (ctor->isDelegatingConstructor())
+    return false;
+
+  return true;
+}
+
+Address CIRGenFunction::loadCXXThisAddress() {
+  assert(curFuncDecl && "loading 'this' without a func declaration?");
+  assert(isa<CXXMethodDecl>(curFuncDecl));
+
+  // Lazily compute CXXThisAlignment.
+  if (cxxThisAlignment.isZero()) {
+    // Just use the best known alignment for the parent.
+    // TODO: if we're currently emitting a complete-object ctor/dtor, we can
+    // always use the complete-object alignment.
+    auto rd = cast<CXXMethodDecl>(curFuncDecl)->getParent();
+    cxxThisAlignment = cgm.getClassPointerAlignment(rd);
+  }
+
+  return Address(loadCXXThis(), cxxThisAlignment);
+}
+
+void CIRGenFunction::emitDelegateCXXConstructorCall(
+    const CXXConstructorDecl *ctor, CXXCtorType ctorType,
+    const FunctionArgList &args, SourceLocation loc) {
+  CallArgList delegateArgs;
+
+  FunctionArgList::const_iterator i = args.begin(), e = args.end();
+  assert(i != e && "no parameters to constructor");
+
+  // this
+  Address thisAddr = loadCXXThisAddress();
+  delegateArgs.add(RValue::get(thisAddr.getPointer()), (*i)->getType());
+  ++i;
+
+  // FIXME: The location of the VTT parameter in the parameter list is specific
+  // to the Itanium ABI and shouldn't be hardcoded here.
+  if (cgm.getCXXABI().needsVTTParameter(curGD)) {
+    cgm.errorNYI(loc, "emitDelegateCXXConstructorCall: VTT parameter");
+    return;
+  }
+
+  // Explicit arguments.
+  for (; i != e; ++i) {
+    const VarDecl *param = *i;
+    // FIXME: per-argument source location
+    emitDelegateCallArg(delegateArgs, param, loc);
+  }
+
+  assert(!cir::MissingFeatures::sanitizers());
+
+  emitCXXConstructorCall(ctor, ctorType, /*ForVirtualBase=*/false,
+                         /*Delegating=*/true, thisAddr, delegateArgs, loc);
+}
+
 Address CIRGenFunction::getAddressOfBaseClass(
     Address value, const CXXRecordDecl *derived,
     llvm::iterator_range<CastExpr::path_const_iterator> path,

clang/lib/CIR/CodeGen/CIRGenFunction.cpp

@@ -465,7 +465,7 @@ cir::FuncOp CIRGenFunction::generateCode(clang::GlobalDecl gd, cir::FuncOp fn,
     if (isa<CXXDestructorDecl>(funcDecl))
       getCIRGenModule().errorNYI(bodyRange, "C++ destructor definition");
     else if (isa<CXXConstructorDecl>(funcDecl))
-      getCIRGenModule().errorNYI(bodyRange, "C++ constructor definition");
+      emitConstructorBody(args);
     else if (getLangOpts().CUDA && !getLangOpts().CUDAIsDevice &&
              funcDecl->hasAttr<CUDAGlobalAttr>())
       getCIRGenModule().errorNYI(bodyRange, "CUDA kernel");
@@ -496,6 +496,54 @@ cir::FuncOp CIRGenFunction::generateCode(clang::GlobalDecl gd, cir::FuncOp fn,
   return fn;
 }
 
+void CIRGenFunction::emitConstructorBody(FunctionArgList &args) {
+  assert(!cir::MissingFeatures::sanitizers());
+  const auto *ctor = cast<CXXConstructorDecl>(curGD.getDecl());
+  CXXCtorType ctorType = curGD.getCtorType();
+
+  assert((cgm.getTarget().getCXXABI().hasConstructorVariants() ||
+          ctorType == Ctor_Complete) &&
+         "can only generate complete ctor for this ABI");
+
+  if (ctorType == Ctor_Complete && isConstructorDelegationValid(ctor) &&
+      cgm.getTarget().getCXXABI().hasConstructorVariants()) {
+    emitDelegateCXXConstructorCall(ctor, Ctor_Base, args, ctor->getEndLoc());
+    return;
+  }
+
+  const FunctionDecl *definition = nullptr;
+  Stmt *body = ctor->getBody(definition);
+  assert(definition == ctor && "emitting wrong constructor body");
+
+  if (isa_and_nonnull<CXXTryStmt>(body)) {
+    cgm.errorNYI(ctor->getSourceRange(), "emitConstructorBody: try body");
+    return;
+  }
+
+  assert(!cir::MissingFeatures::incrementProfileCounter());
+  assert(!cir::MissingFeatures::runCleanupsScope());
+
+  // TODO: in restricted cases, we can emit the vbase initializers of a
+  // complete ctor and then delegate to the base ctor.
+
+  assert(!cir::MissingFeatures::emitCtorPrologue());
+  if (ctor->isDelegatingConstructor()) {
+    // This will be handled in emitCtorPrologue, but we should emit a diagnostic
+    // rather than silently fail to delegate.
+    cgm.errorNYI(ctor->getSourceRange(),
+                 "emitConstructorBody: delegating ctor");
+    return;
+  }
+
+  // TODO(cir): propagate this result via mlir::logical result. Just unreachable
+  // now just to have it handled.
+  if (mlir::failed(emitStmt(body, true))) {
+    cgm.errorNYI(ctor->getSourceRange(),
+                 "emitConstructorBody: emit body statement failed.");
+    return;
+  }
+}
+
 /// Given a value of type T* that may not be to a complete object, construct
 /// an l-vlaue withi the natural pointee alignment of T.
 LValue CIRGenFunction::makeNaturalAlignPointeeAddrLValue(mlir::Value val,
@@ -522,16 +570,16 @@ clang::QualType CIRGenFunction::buildFunctionArgList(clang::GlobalDecl gd,
     cgm.getCXXABI().buildThisParam(*this, args);
   }
 
-  if (isa<CXXConstructorDecl>(fd))
-    cgm.errorNYI(fd->getSourceRange(),
-                 "buildFunctionArgList: CXXConstructorDecl");
+  if (const auto *cd = dyn_cast<CXXConstructorDecl>(fd))
+    if (cd->getInheritedConstructor())
+      cgm.errorNYI(fd->getSourceRange(),
+                   "buildFunctionArgList: inherited constructor");
 
   for (auto *param : fd->parameters())
     args.push_back(param);
 
   if (md && (isa<CXXConstructorDecl>(md) || isa<CXXDestructorDecl>(md)))
-    cgm.errorNYI(fd->getSourceRange(),
-                 "buildFunctionArgList: implicit structor params");
+    assert(!cir::MissingFeatures::cxxabiStructorImplicitParam());
 
   return retTy;
 }

clang/lib/CIR/CodeGen/CIRGenFunction.h

@@ -66,6 +66,7 @@ class CIRGenFunction : public CIRGenTypeCache {
   ImplicitParamDecl *cxxabiThisDecl = nullptr;
   mlir::Value cxxabiThisValue = nullptr;
   mlir::Value cxxThisValue = nullptr;
+  clang::CharUnits cxxThisAlignment;
 
   // Holds the Decl for the current outermost non-closure context
   const clang::Decl *curFuncDecl = nullptr;
@@ -473,6 +474,9 @@ class CIRGenFunction : public CIRGenTypeCache {
 
   bool shouldNullCheckClassCastValue(const CastExpr *ce);
 
+  static bool
+  isConstructorDelegationValid(const clang::CXXConstructorDecl *ctor);
+
   LValue makeNaturalAlignPointeeAddrLValue(mlir::Value v, clang::QualType t);
 
   /// Construct an address with the natural alignment of T. If a pointer to T
@@ -517,6 +521,7 @@ class CIRGenFunction : public CIRGenTypeCache {
     assert(cxxThisValue && "no 'this' value for this function");
     return cxxThisValue;
   }
+  Address loadCXXThisAddress();
 
   /// Get an appropriate 'undef' rvalue for the given type.
   /// TODO: What's the equivalent for MLIR? Currently we're only using this for
@@ -753,6 +758,8 @@ class CIRGenFunction : public CIRGenTypeCache {
 
   LValue emitCompoundAssignmentLValue(const clang::CompoundAssignOperator *e);
 
+  void emitConstructorBody(FunctionArgList &args);
+
   mlir::LogicalResult emitContinueStmt(const clang::ContinueStmt &s);
 
   void emitCXXConstructExpr(const clang::CXXConstructExpr *e,
@@ -841,6 +848,17 @@ class CIRGenFunction : public CIRGenTypeCache {
                                       mlir::Type condType,
                                       bool buildingTopLevelCase);
 
+  void emitDelegateCXXConstructorCall(const clang::CXXConstructorDecl *ctor,
+                                      clang::CXXCtorType ctorType,
+                                      const FunctionArgList &args,
+                                      clang::SourceLocation loc);
+
+  /// We are performing a delegate call; that is, the current function is
+  /// delegating to another one. Produce a r-value suitable for passing the
+  /// given parameter.
+  void emitDelegateCallArg(CallArgList &args, const clang::VarDecl *param,
+                           clang::SourceLocation loc);
+
   /// Emit an `if` on a boolean condition to the specified blocks.
   /// FIXME: Based on the condition, this might try to simplify the codegen of
   /// the conditional based on the branch.