[CIR] Add support for runtime data member pointer access (#171510)

This adds support for a CIR operation to represent runtime data member
access.

Author: andykaylor

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

@@ -3559,6 +3559,63 @@ def CIR_ArrayDtor : CIR_ArrayInitDestroy<"array.dtor"> {
   }];
 }
 
+//===----------------------------------------------------------------------===//
+// GetRuntimeMemberOp
+//===----------------------------------------------------------------------===//
+
+def CIR_GetRuntimeMemberOp : CIR_Op<"get_runtime_member"> {
+  let summary = "Get the address of a member of a record";
+  let description = [{
+    The `cir.get_runtime_member` operation gets the address of a member from
+    the input record. The target member is given by a value of type
+    `!cir.data_member` (i.e. a pointer-to-data-member value).
+
+    This operation differs from `cir.get_member` in when the target member can
+    be determined. For the `cir.get_member` operation, the target member is
+    specified as a constant index so the member it returns access to is known
+    when the operation is constructed. For the `cir.get_runtime_member`
+    operation, the target member is given through a pointer-to-data-member
+    value which is unknown until the program being compiled is executed. In
+    other words, `cir.get_member` represents a normal member access through the
+    `.` operator in C/C++:
+
+    ```cpp
+    struct Foo { int x; };
+    Foo f;
+    (void)f.x;  // cir.get_member
+    ```
+
+    And `cir.get_runtime_member` represents a member access through the `.*` or
+    the `->*` operator in C++:
+
+    ```cpp
+    struct Foo { int x; }
+    Foo f;
+    Foo *p;
+    int Foo::*member;
+
+    (void)f.*member;   // cir.get_runtime_member
+    (void)p->*member;  // cir.get_runtime_member
+    ```
+
+    This operation expects a pointer to the base record as well as the pointer
+    to the target member.
+  }];
+
+  let arguments = (ins
+    Arg<CIR_PtrToRecordType, "address of the record object", [MemRead]>:$addr,
+    Arg<CIR_DataMemberType, "pointer to the target member">:$member);
+
+  let results = (outs Res<CIR_PointerType, "">:$result);
+
+  let assemblyFormat = [{
+    $addr `[` $member `:` qualified(type($member)) `]` attr-dict
+    `:` qualified(type($addr)) `->` qualified(type($result))
+  }];
+
+  let hasVerifier = 1;
+}
+
 //===----------------------------------------------------------------------===//
 // VecCreate
 //===----------------------------------------------------------------------===//

clang/lib/CIR/CodeGen/CIRGenBuilder.h

@@ -529,6 +529,19 @@ class CIRGenBuilderTy : public cir::CIRBaseBuilderTy {
                    addr.getAlignment()};
   }
 
+  cir::GetRuntimeMemberOp createGetIndirectMember(mlir::Location loc,
+                                                  mlir::Value objectPtr,
+                                                  mlir::Value memberPtr) {
+    auto memberPtrTy = mlir::cast<cir::DataMemberType>(memberPtr.getType());
+
+    // TODO(cir): consider address space.
+    assert(!cir::MissingFeatures::addressSpace());
+    cir::PointerType resultTy = getPointerTo(memberPtrTy.getMemberTy());
+
+    return cir::GetRuntimeMemberOp::create(*this, loc, resultTy, objectPtr,
+                                           memberPtr);
+  }
+
   /// Create a cir.ptr_stride operation to get access to an array element.
   /// \p idx is the index of the element to access, \p shouldDecay is true if
   /// the result should decay to a pointer to the element type.

clang/lib/CIR/CodeGen/CIRGenClass.cpp

@@ -584,6 +584,25 @@ void CIRGenFunction::emitInitializerForField(FieldDecl *field, LValue lhs,
   assert(!cir::MissingFeatures::requiresCleanups());
 }
 
+Address CIRGenFunction::emitCXXMemberDataPointerAddress(
+    const Expr *e, Address base, mlir::Value memberPtr,
+    const MemberPointerType *memberPtrType, LValueBaseInfo *baseInfo) {
+  assert(!cir::MissingFeatures::cxxABI());
+
+  cir::GetRuntimeMemberOp op = builder.createGetIndirectMember(
+      getLoc(e->getSourceRange()), base.getPointer(), memberPtr);
+
+  QualType memberType = memberPtrType->getPointeeType();
+  assert(!cir::MissingFeatures::opTBAA());
+  CharUnits memberAlign = cgm.getNaturalTypeAlignment(memberType, baseInfo);
+  memberAlign = cgm.getDynamicOffsetAlignment(
+      base.getAlignment(), memberPtrType->getMostRecentCXXRecordDecl(),
+      memberAlign);
+
+  return Address(op, convertTypeForMem(memberPtrType->getPointeeType()),
+                 memberAlign);
+}
+
 CharUnits
 CIRGenModule::getDynamicOffsetAlignment(CharUnits actualBaseAlign,
                                         const CXXRecordDecl *baseDecl,

clang/lib/CIR/CodeGen/CIRGenExpr.cpp

@@ -683,6 +683,29 @@ RValue CIRGenFunction::emitLoadOfExtVectorElementLValue(LValue lv) {
   return RValue::get(resultVec);
 }
 
+LValue
+CIRGenFunction::emitPointerToDataMemberBinaryExpr(const BinaryOperator *e) {
+  assert((e->getOpcode() == BO_PtrMemD || e->getOpcode() == BO_PtrMemI) &&
+         "unexpected binary operator opcode");
+
+  Address baseAddr = Address::invalid();
+  if (e->getOpcode() == BO_PtrMemD)
+    baseAddr = emitLValue(e->getLHS()).getAddress();
+  else
+    baseAddr = emitPointerWithAlignment(e->getLHS());
+
+  const auto *memberPtrTy = e->getRHS()->getType()->castAs<MemberPointerType>();
+
+  mlir::Value memberPtr = emitScalarExpr(e->getRHS());
+
+  LValueBaseInfo baseInfo;
+  assert(!cir::MissingFeatures::opTBAA());
+  Address memberAddr = emitCXXMemberDataPointerAddress(e, baseAddr, memberPtr,
+                                                       memberPtrTy, &baseInfo);
+
+  return makeAddrLValue(memberAddr, memberPtrTy->getPointeeType(), baseInfo);
+}
+
 /// Generates lvalue for partial ext_vector access.
 Address CIRGenFunction::emitExtVectorElementLValue(LValue lv,
                                                    mlir::Location loc) {
@@ -1762,10 +1785,8 @@ LValue CIRGenFunction::emitBinaryOperatorLValue(const BinaryOperator *e) {
     return emitLValue(e->getRHS());
   }
 
-  if (e->getOpcode() == BO_PtrMemD || e->getOpcode() == BO_PtrMemI) {
-    cgm.errorNYI(e->getSourceRange(), "member pointers");
-    return {};
-  }
+  if (e->getOpcode() == BO_PtrMemD || e->getOpcode() == BO_PtrMemI)
+    return emitPointerToDataMemberBinaryExpr(e);
 
   assert(e->getOpcode() == BO_Assign && "unexpected binary l-value");
 

clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp

@@ -1338,13 +1338,11 @@ class ScalarExprEmitter : public StmtVisitor<ScalarExprEmitter, mlir::Value> {
   }
 
   mlir::Value VisitBinPtrMemD(const BinaryOperator *e) {
-    cgf.cgm.errorNYI(e->getSourceRange(), "ScalarExprEmitter: ptr mem d");
-    return {};
+    return emitLoadOfLValue(e);
   }
 
   mlir::Value VisitBinPtrMemI(const BinaryOperator *e) {
-    cgf.cgm.errorNYI(e->getSourceRange(), "ScalarExprEmitter: ptr mem i");
-    return {};
+    return emitLoadOfLValue(e);
   }
 
   // Other Operators.

clang/lib/CIR/CodeGen/CIRGenFunction.h

@@ -1514,6 +1514,10 @@ class CIRGenFunction : public CIRGenTypeCache {
   RValue emitCXXMemberCallExpr(const clang::CXXMemberCallExpr *e,
                                ReturnValueSlot returnValue);
 
+  Address emitCXXMemberDataPointerAddress(
+      const Expr *e, Address base, mlir::Value memberPtr,
+      const MemberPointerType *memberPtrType, LValueBaseInfo *baseInfo);
+
   RValue emitCXXMemberOrOperatorCall(
       const clang::CXXMethodDecl *md, const CIRGenCallee &callee,
       ReturnValueSlot returnValue, mlir::Value thisPtr,
@@ -1696,6 +1700,8 @@ class CIRGenFunction : public CIRGenTypeCache {
 
   mlir::Value emitOpOnBoolExpr(mlir::Location loc, const clang::Expr *cond);
 
+  LValue emitPointerToDataMemberBinaryExpr(const BinaryOperator *e);
+
   mlir::LogicalResult emitLabel(const clang::LabelDecl &d);
   mlir::LogicalResult emitLabelStmt(const clang::LabelStmt &s);
 

clang/lib/CIR/Dialect/IR/CIRDialect.cpp

@@ -2485,6 +2485,21 @@ LogicalResult cir::CopyOp::verify() {
   return mlir::success();
 }
 
+//===----------------------------------------------------------------------===//
+// GetRuntimeMemberOp Definitions
+//===----------------------------------------------------------------------===//
+
+LogicalResult cir::GetRuntimeMemberOp::verify() {
+  auto recordTy = mlir::cast<RecordType>(getAddr().getType().getPointee());
+  cir::DataMemberType memberPtrTy = getMember().getType();
+
+  if (recordTy != memberPtrTy.getClassTy())
+    return emitError() << "record type does not match the member pointer type";
+  if (getType().getPointee() != memberPtrTy.getMemberTy())
+    return emitError() << "result type does not match the member pointer type";
+  return mlir::success();
+}
+
 //===----------------------------------------------------------------------===//
 // GetMemberOp Definitions
 //===----------------------------------------------------------------------===//

clang/lib/CIR/Dialect/Transforms/TargetLowering/CIRCXXABI.h

@@ -15,6 +15,7 @@
 #define CLANG_LIB_CIR_DIALECT_TRANSFORMS_TARGETLOWERING_CIRCXXABI_H
 
 #include "mlir/Transforms/DialectConversion.h"
+#include "clang/CIR/Dialect/IR/CIRDialect.h"
 #include "clang/CIR/Dialect/IR/CIRTypes.h"
 
 namespace cir {
@@ -45,6 +46,13 @@ class CIRCXXABI {
   lowerDataMemberConstant(cir::DataMemberAttr attr,
                           const mlir::DataLayout &layout,
                           const mlir::TypeConverter &typeConverter) const = 0;
+
+  /// Lower the given cir.get_runtime_member op to a sequence of more
+  /// "primitive" CIR operations that act on the ABI types.
+  virtual mlir::Operation *
+  lowerGetRuntimeMember(cir::GetRuntimeMemberOp op, mlir::Type loweredResultTy,
+                        mlir::Value loweredAddr, mlir::Value loweredMember,
+                        mlir::OpBuilder &builder) const = 0;
 };
 
 /// Creates an Itanium-family ABI.

clang/lib/CIR/Dialect/Transforms/TargetLowering/LowerItaniumCXXABI.cpp

@@ -42,6 +42,11 @@ class LowerItaniumCXXABI : public CIRCXXABI {
   mlir::TypedAttr lowerDataMemberConstant(
       cir::DataMemberAttr attr, const mlir::DataLayout &layout,
       const mlir::TypeConverter &typeConverter) const override;
+
+  mlir::Operation *
+  lowerGetRuntimeMember(cir::GetRuntimeMemberOp op, mlir::Type loweredResultTy,
+                        mlir::Value loweredAddr, mlir::Value loweredMember,
+                        mlir::OpBuilder &builder) const override;
 };
 
 } // namespace
@@ -87,4 +92,20 @@ mlir::TypedAttr LowerItaniumCXXABI::lowerDataMemberConstant(
   return cir::IntAttr::get(abiTy, memberOffset);
 }
 
+mlir::Operation *LowerItaniumCXXABI::lowerGetRuntimeMember(
+    cir::GetRuntimeMemberOp op, mlir::Type loweredResultTy,
+    mlir::Value loweredAddr, mlir::Value loweredMember,
+    mlir::OpBuilder &builder) const {
+  auto byteTy = cir::IntType::get(op.getContext(), 8, true);
+  auto bytePtrTy = cir::PointerType::get(
+      byteTy,
+      mlir::cast<cir::PointerType>(op.getAddr().getType()).getAddrSpace());
+  auto objectBytesPtr = cir::CastOp::create(
+      builder, op.getLoc(), bytePtrTy, cir::CastKind::bitcast, op.getAddr());
+  auto memberBytesPtr = cir::PtrStrideOp::create(
+      builder, op.getLoc(), bytePtrTy, objectBytesPtr, loweredMember);
+  return cir::CastOp::create(builder, op.getLoc(), op.getType(),
+                             cir::CastKind::bitcast, memberBytesPtr);
+}
+
 } // namespace cir

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

@@ -3231,6 +3231,17 @@ mlir::LogicalResult CIRToLLVMGetMemberOpLowering::matchAndRewrite(
   }
 }
 
+mlir::LogicalResult CIRToLLVMGetRuntimeMemberOpLowering::matchAndRewrite(
+    cir::GetRuntimeMemberOp op, OpAdaptor adaptor,
+    mlir::ConversionPatternRewriter &rewriter) const {
+  assert(lowerMod && "lowering module is not available");
+  mlir::Type llvmResTy = getTypeConverter()->convertType(op.getType());
+  mlir::Operation *llvmOp = lowerMod->getCXXABI().lowerGetRuntimeMember(
+      op, llvmResTy, adaptor.getAddr(), adaptor.getMember(), rewriter);
+  rewriter.replaceOp(op, llvmOp);
+  return mlir::success();
+}
+
 mlir::LogicalResult CIRToLLVMUnreachableOpLowering::matchAndRewrite(
     cir::UnreachableOp op, OpAdaptor adaptor,
     mlir::ConversionPatternRewriter &rewriter) const {