[CIR] Upstream Exception ThrowOp with subexpr

Author: AmrDeveloper

clang/include/clang/CIR/Dialect/IR/CIROps.td

@@ -4166,6 +4166,40 @@ def CIR_ThrowOp : CIR_Op<"throw"> {
   let hasVerifier = 1;
 }
 
+//===----------------------------------------------------------------------===//
+// AllocExceptionOp
+//===----------------------------------------------------------------------===//
+
+def CIR_AllocExceptionOp : CIR_Op<"alloc.exception"> {
+  let summary = "Allocates an exception according to Itanium ABI";
+  let description = [{
+    Implements a slightly higher level __cxa_allocate_exception:
+
+    `void *__cxa_allocate_exception(size_t thrown_size);`
+
+    If operation fails, program terminates, not throw.
+
+    Example:
+
+    ```mlir
+    // if (b == 0) {
+    //   ...
+    //   throw "...";
+    cir.if %10 {
+        %11 = cir.alloc_exception 8 -> !cir.ptr<!void>
+        ... // store exception content into %11
+        cir.throw %11 : !cir.ptr<!cir.ptr<!u8i>>, ...
+    ```
+  }];
+
+  let arguments = (ins I64Attr:$size);
+  let results = (outs Res<CIR_PointerType, "", [MemAlloc<DefaultResource>]>:$addr);
+
+  let assemblyFormat = [{
+    $size `->` qualified(type($addr)) attr-dict
+  }];
+}
+
 //===----------------------------------------------------------------------===//
 // Atomic operations
 //===----------------------------------------------------------------------===//

clang/lib/CIR/CodeGen/CIRGenCXXABI.h

@@ -113,6 +113,7 @@ class CIRGenCXXABI {
                                           CIRGenFunction &cgf) = 0;
 
   virtual void emitRethrow(CIRGenFunction &cgf, bool isNoReturn) = 0;
+  virtual void emitThrow(CIRGenFunction &cgf, const CXXThrowExpr *e) = 0;
 
   virtual mlir::Attribute getAddrOfRTTIDescriptor(mlir::Location loc,
                                                   QualType ty) = 0;

clang/lib/CIR/CodeGen/CIRGenCleanup.cpp

@@ -178,3 +178,36 @@ void CIRGenFunction::popCleanupBlocks(
     popCleanupBlock();
   }
 }
+
+void CIRGenFunction::deactivateCleanupBlock(
+    EHScopeStack::stable_iterator cleanup, mlir::Operation *dominatingIP) {
+  assert(cleanup != ehStack.stable_end() && "deactivating bottom of stack?");
+  EHCleanupScope &scope = cast<EHCleanupScope>(*ehStack.find(cleanup));
+  assert(scope.isActive() && "double deactivation");
+
+  // If it's the top of the stack, just pop it, but do so only if it belongs
+  // to the current RunCleanupsScope.
+  if (cleanup == ehStack.stable_begin() &&
+      currentCleanupStackDepth.strictlyEncloses(cleanup)) {
+
+    // Per comment below, checking EHAsynch is not really necessary
+    // it's there to assure zero-impact w/o EHAsynch option
+    if (!scope.isNormalCleanup() && getLangOpts().EHAsynch) {
+      cgm.errorNYI("deactivateCleanupBlock: EHAsynch & non-normal cleanup");
+      return;
+    }
+
+    // From LLVM: If it's a normal cleanup, we need to pretend that the
+    // fallthrough is unreachable.
+    // CIR remarks: LLVM uses an empty insertion point to signal behavior
+    // change to other codegen paths (triggered by PopCleanupBlock).
+    // CIRGen doesn't do that yet, but let's mimic just in case.
+    mlir::OpBuilder::InsertionGuard guard(builder);
+    builder.clearInsertionPoint();
+    popCleanupBlock();
+    return;
+  }
+
+  // Otherwise, follow the general case.
+  cgm.errorNYI("deactivateCleanupBlock: the general case");
+}

clang/lib/CIR/CodeGen/CIRGenCleanup.h

@@ -138,5 +138,13 @@ inline EHScopeStack::iterator EHScopeStack::begin() const {
   return iterator(startOfData);
 }
 
+inline EHScopeStack::iterator
+EHScopeStack::find(stable_iterator savePoint) const {
+  assert(savePoint.isValid() && "finding invalid savepoint");
+  assert(savePoint.size <= stable_begin().size &&
+         "finding savepoint after pop");
+  return iterator(endOfBuffer - savePoint.size);
+}
+
 } // namespace clang::CIRGen
 #endif // CLANG_LIB_CIR_CODEGEN_CIRGENCLEANUP_H

clang/lib/CIR/CodeGen/CIRGenException.cpp

@@ -31,11 +31,36 @@ void CIRGenFunction::emitCXXThrowExpr(const CXXThrowExpr *e) {
     if (throwType->isObjCObjectPointerType()) {
       cgm.errorNYI("emitCXXThrowExpr ObjCObjectPointerType");
       return;
-    } else {
-      cgm.errorNYI("emitCXXThrowExpr with subExpr");
-      return;
     }
-  } else {
-    cgm.getCXXABI().emitRethrow(*this, /*isNoReturn=*/true);
+
+    cgm.getCXXABI().emitThrow(*this, e);
+    return;
   }
+
+  cgm.getCXXABI().emitRethrow(*this, /*isNoReturn=*/true);
+}
+
+void CIRGenFunction::emitAnyExprToExn(const Expr *e, Address addr) {
+  // Make sure the exception object is cleaned up if there's an
+  // exception during initialization.
+  assert(!cir::MissingFeatures::ehCleanupScope());
+
+  // __cxa_allocate_exception returns a void*;  we need to cast this
+  // to the appropriate type for the object.
+  mlir::Type ty = convertTypeForMem(e->getType());
+  Address typedAddr = addr.withElementType(builder, ty);
+
+  // From LLVM's codegen:
+  // FIXME: this isn't quite right!  If there's a final unelided call
+  // to a copy constructor, then according to [except.terminate]p1 we
+  // must call std::terminate() if that constructor throws, because
+  // technically that copy occurs after the exception expression is
+  // evaluated but before the exception is caught.  But the best way
+  // to handle that is to teach EmitAggExpr to do the final copy
+  // differently if it can't be elided.
+  emitAnyExprToMem(e, typedAddr, e->getType().getQualifiers(),
+                   /*isInitializer=*/true);
+
+  // Deactivate the cleanup block.
+  assert(!cir::MissingFeatures::ehCleanupScope());
 }

clang/lib/CIR/CodeGen/CIRGenFunction.h

@@ -1090,6 +1090,11 @@ class CIRGenFunction : public CIRGenTypeCache {
   /// even if no aggregate location is provided.
   RValue emitAnyExprToTemp(const clang::Expr *e);
 
+  void emitAnyExprToExn(const Expr *e, Address addr);
+
+  void deactivateCleanupBlock(EHScopeStack::stable_iterator cleanup,
+                              mlir::Operation *dominatingIP);
+
   void emitArrayDestroy(mlir::Value begin, mlir::Value numElements,
                         QualType elementType, CharUnits elementAlign,
                         Destroyer *destroyer);

clang/lib/CIR/CodeGen/CIRGenItaniumCXXABI.cpp

@@ -70,6 +70,7 @@ class CIRGenItaniumCXXABI : public CIRGenCXXABI {
                           QualType thisTy) override;
 
   void emitRethrow(CIRGenFunction &cgf, bool isNoReturn) override;
+  void emitThrow(CIRGenFunction &cgf, const CXXThrowExpr *e) override;
 
   bool useThunkForDtorVariant(const CXXDestructorDecl *dtor,
                               CXXDtorType dt) const override {
@@ -1544,6 +1545,60 @@ void CIRGenItaniumCXXABI::emitRethrow(CIRGenFunction &cgf, bool isNoReturn) {
   }
 }
 
+void CIRGenItaniumCXXABI::emitThrow(CIRGenFunction &cgf,
+                                    const CXXThrowExpr *e) {
+  // This differs a bit from LLVM codegen, CIR has native operations for some
+  // cxa functions, and defers allocation size computation, always pass the dtor
+  // symbol, etc. CIRGen also does not use getAllocateExceptionFn / getThrowFn.
+
+  // Now allocate the exception object.
+  CIRGenBuilderTy &builder = cgf.getBuilder();
+  QualType clangThrowType = e->getSubExpr()->getType();
+  cir::PointerType throwTy =
+      builder.getPointerTo(cgf.convertType(clangThrowType));
+  uint64_t typeSize =
+      cgf.getContext().getTypeSizeInChars(clangThrowType).getQuantity();
+  mlir::Location subExprLoc = cgf.getLoc(e->getSubExpr()->getSourceRange());
+
+  // Defer computing allocation size to some later lowering pass.
+  mlir::TypedValue<cir::PointerType> exceptionPtr =
+      cir::AllocExceptionOp::create(builder, subExprLoc, throwTy,
+                                    builder.getI64IntegerAttr(typeSize))
+          .getAddr();
+
+  // Build expression and store its result into exceptionPtr.
+  CharUnits exnAlign = cgf.getContext().getExnObjectAlignment();
+  cgf.emitAnyExprToExn(e->getSubExpr(), Address(exceptionPtr, exnAlign));
+
+  // Get the RTTI symbol address.
+  auto typeInfo = mlir::dyn_cast_if_present<cir::GlobalViewAttr>(
+      cgm.getAddrOfRTTIDescriptor(subExprLoc, clangThrowType,
+                                  /*ForEH=*/true));
+  assert(typeInfo && "expected GlobalViewAttr typeinfo");
+  assert(!typeInfo.getIndices() && "expected no indirection");
+
+  // The address of the destructor.
+  //
+  // Note: LLVM codegen already optimizes out the dtor if the
+  // type is a record with trivial dtor (by passing down a
+  // null dtor). In CIR, we forward this info and allow for
+  // Lowering pass to skip passing the trivial function.
+  //
+  if (const RecordType *recordTy = clangThrowType->getAs<RecordType>()) {
+    CXXRecordDecl *rec =
+        cast<CXXRecordDecl>(recordTy->getOriginalDecl()->getDefinition());
+    assert(!cir::MissingFeatures::isTrivialCtorOrDtor());
+    if (!rec->hasTrivialDestructor()) {
+      cgm.errorNYI("emitThrow: non-trivial destructor");
+      return;
+    }
+  }
+
+  // Now throw the exception.
+  mlir::Location loc = cgf.getLoc(e->getSourceRange());
+  insertThrowAndSplit(builder, loc, exceptionPtr, typeInfo.getSymbol());
+}
+
 CIRGenCXXABI *clang::CIRGen::CreateCIRGenItaniumCXXABI(CIRGenModule &cgm) {
   switch (cgm.getASTContext().getCXXABIKind()) {
   case TargetCXXABI::GenericItanium:

clang/lib/CIR/CodeGen/EHScopeStack.h

@@ -175,6 +175,10 @@ class EHScopeStack {
     return stable_iterator(endOfBuffer - startOfData);
   }
 
+  /// Turn a stable reference to a scope depth into a unstable pointer
+  /// to the EH stack.
+  iterator find(stable_iterator savePoint) const;
+
   /// Create a stable reference to the bottom of the EH stack.
   static stable_iterator stable_end() { return stable_iterator(0); }
 };

clang/lib/CIR/Lowering/DirectToLLVM/LowerToLLVM.cpp

@@ -2581,22 +2581,69 @@ void createLLVMFuncOpIfNotExist(mlir::ConversionPatternRewriter &rewriter,
 mlir::LogicalResult CIRToLLVMThrowOpLowering::matchAndRewrite(
     cir::ThrowOp op, OpAdaptor adaptor,
     mlir::ConversionPatternRewriter &rewriter) const {
-  if (op.rethrows()) {
-    auto voidTy = mlir::LLVM::LLVMVoidType::get(getContext());
-    auto funcTy =
-        mlir::LLVM::LLVMFunctionType::get(getContext(), voidTy, {}, false);
+  mlir::Location loc = op.getLoc();
+  auto voidTy = mlir::LLVM::LLVMVoidType::get(getContext());
 
-    auto mlirModule = op->getParentOfType<mlir::ModuleOp>();
-    rewriter.setInsertionPointToStart(&mlirModule.getBodyRegion().front());
+  if (op.rethrows()) {
+    auto funcTy = mlir::LLVM::LLVMFunctionType::get(voidTy, {});
 
+    // Get or create `declare void @__cxa_rethrow()`
     const llvm::StringRef functionName = "__cxa_rethrow";
     createLLVMFuncOpIfNotExist(rewriter, op, functionName, funcTy);
 
-    rewriter.setInsertionPointAfter(op.getOperation());
-    rewriter.replaceOpWithNewOp<mlir::LLVM::CallOp>(
-        op, mlir::TypeRange{}, functionName, mlir::ValueRange{});
+    auto cxaRethrow = mlir::LLVM::CallOp::create(
+        rewriter, loc, mlir::TypeRange{}, functionName);
+
+    rewriter.replaceOp(op, cxaRethrow);
+    return mlir::success();
   }
 
+  auto llvmPtrTy = mlir::LLVM::LLVMPointerType::get(rewriter.getContext());
+  auto fnTy = mlir::LLVM::LLVMFunctionType::get(
+      voidTy, {llvmPtrTy, llvmPtrTy, llvmPtrTy});
+
+  // Get or create `declare void @__cxa_throw(ptr, ptr, ptr)`
+  const llvm::StringRef fnName = "__cxa_throw";
+  createLLVMFuncOpIfNotExist(rewriter, op, fnName, fnTy);
+
+  mlir::Value typeInfo = mlir::LLVM::AddressOfOp::create(
+      rewriter, loc, mlir::LLVM::LLVMPointerType::get(rewriter.getContext()),
+      adaptor.getTypeInfoAttr());
+
+  mlir::Value dtor;
+  if (op.getDtor()) {
+    dtor = mlir::LLVM::AddressOfOp::create(rewriter, loc, llvmPtrTy,
+                                           adaptor.getDtorAttr());
+  } else {
+    dtor = mlir::LLVM::ZeroOp::create(rewriter, loc, llvmPtrTy);
+  }
+
+  auto cxaThrowCall = mlir::LLVM::CallOp::create(
+      rewriter, loc, mlir::TypeRange{}, fnName,
+      mlir::ValueRange{adaptor.getExceptionPtr(), typeInfo, dtor});
+
+  rewriter.replaceOp(op, cxaThrowCall);
+  return mlir::success();
+}
+
+mlir::LogicalResult CIRToLLVMAllocExceptionOpLowering::matchAndRewrite(
+    cir::AllocExceptionOp op, OpAdaptor adaptor,
+    mlir::ConversionPatternRewriter &rewriter) const {
+  // Get or create `declare ptr @__cxa_allocate_exception(i64)`
+  StringRef fnName = "__cxa_allocate_exception";
+  auto llvmPtrTy = mlir::LLVM::LLVMPointerType::get(rewriter.getContext());
+  auto int64Ty = mlir::IntegerType::get(rewriter.getContext(), 64);
+  auto fnTy = mlir::LLVM::LLVMFunctionType::get(llvmPtrTy, {int64Ty});
+
+  createLLVMFuncOpIfNotExist(rewriter, op, fnName, fnTy);
+  auto exceptionSize = mlir::LLVM::ConstantOp::create(rewriter, op.getLoc(),
+                                                      adaptor.getSizeAttr());
+
+  auto allocaExceptionCall = mlir::LLVM::CallOp::create(
+      rewriter, op.getLoc(), mlir::TypeRange{llvmPtrTy}, fnName,
+      mlir::ValueRange{exceptionSize});
+
+  rewriter.replaceOp(op, allocaExceptionCall);
   return mlir::success();
 }
 

clang/test/CIR/CodeGen/throws.cpp

@@ -5,7 +5,7 @@
 // RUN: %clang_cc1 -std=c++20 -triple x86_64-unknown-linux-gnu -fcxx-exceptions -fexceptions -emit-llvm %s -o %t.ll
 // RUN: FileCheck --input-file=%t.ll %s -check-prefix=OGCG
 
-void foo() {
+void rethrow() {
   throw;
 }
 
@@ -18,7 +18,7 @@ void foo() {
 // OGCG: call void @__cxa_rethrow()
 // OGCG: unreachable
 
-int foo1(int a, int b) {
+int rethrow_from_block(int a, int b) {
   if (b == 0)
     throw;
   return a / b;
@@ -83,3 +83,43 @@ int foo1(int a, int b) {
 // OGCG:  %[[TMP_B:.*]] = load i32, ptr %[[B_ADDR]], align 4
 // OGCG:  %[[DIV_A_B:.*]] = sdiv i32 %[[TMP_A]], %[[TMP_B]]
 // OGCG:  ret i32 %[[DIV_A_B]]
+
+void throw_scalar() { 
+  throw 1;
+}
+
+// CIR: %[[EXCEPTION_ADDR:.*]] = cir.alloc.exception 4 -> !cir.ptr<!s32i>
+// CIR: %[[EXCEPTION_VALUE:.*]] = cir.const #cir.int<1> : !s32i
+// CIR: cir.store{{.*}} %[[EXCEPTION_VALUE]], %[[EXCEPTION_ADDR]] : !s32i, !cir.ptr<!s32i>
+// CIR: cir.throw %[[EXCEPTION_ADDR]] : !cir.ptr<!s32i>, @_ZTIi
+// CIR: cir.unreachable
+
+// LLVM: %[[EXCEPTION_ADDR:.*]] = call ptr @__cxa_allocate_exception(i64 4)
+// LLVM: store i32 1, ptr %[[EXCEPTION_ADDR]], align 16
+// LLVM: call void @__cxa_throw(ptr %[[EXCEPTION_ADDR]], ptr @_ZTIi, ptr null)
+// LLVM: unreachable
+
+// OGCG: %[[EXCEPTION_ADDR:.*]] = call ptr @__cxa_allocate_exception(i64 4)
+// OGCG: store i32 1, ptr %[[EXCEPTION_ADDR]], align 16
+// OGCG: call void @__cxa_throw(ptr %[[EXCEPTION_ADDR]], ptr @_ZTIi, ptr null)
+// OGCG: unreachable
+
+void paren_expr() { (throw 0, 1 + 2); }
+
+// CIR:   %[[EXCEPTION_ADDR:.*]] = cir.alloc.exception 4 -> !cir.ptr<!s32i>
+// CIR:   %[[EXCEPTION_VALUE:.*]] = cir.const #cir.int<0> : !s32i
+// CIR:   cir.store{{.*}} %[[EXCEPTION_VALUE]], %[[EXCEPTION_ADDR]] : !s32i, !cir.ptr<!s32i>
+// CIR:   cir.throw %[[EXCEPTION_ADDR]] : !cir.ptr<!s32i>, @_ZTIi
+// CIR:   cir.unreachable
+// CIR: ^bb1:
+// CIR:   %[[CONST_1:.*]] = cir.const #cir.int<1> : !s32i
+// CIR:   %[[CONST_2:.*]] = cir.const #cir.int<2> : !s32i
+// CIR:   %[[ADD:.*]] = cir.binop(add, %[[CONST_1]], %[[CONST_2]]) nsw : !s32i
+
+// LLVM: %[[EXCEPTION_ADDR:.*]] = call ptr @__cxa_allocate_exception(i64 4)
+// LLVM: store i32 0, ptr %[[EXCEPTION_ADDR]], align 16
+// LLVM: call void @__cxa_throw(ptr %[[EXCEPTION_ADDR]], ptr @_ZTIi, ptr null)
+
+// OGCG: %[[EXCEPTION_ADDR:.*]] = call ptr @__cxa_allocate_exception(i64 4)
+// OGCG: store i32 0, ptr %[[EXCEPTION_ADDR]], align 16
+// OGCG: call void @__cxa_throw(ptr %[[EXCEPTION_ADDR]], ptr @_ZTIi, ptr null)