[Clang][CodeGen] Add more tests.

Author: dtcxzyw

clang/lib/CodeGen/CGBuilder.h

@@ -215,19 +215,25 @@ class CGBuilderTy : public CGBuilderBaseTy {
   ///
   /// This API assumes that drilling into a struct like this is always an
   /// inbounds and nuw operation.
+  /// Specifically, inbounds flag will not be set if \p IsBaseConstantNull is
+  /// true.
   using CGBuilderBaseTy::CreateStructGEP;
   Address CreateStructGEP(Address Addr, unsigned Index,
-                          const llvm::Twine &Name = "") {
+                          const llvm::Twine &Name = "",
+                          bool IsBaseConstantNull = false) {
     llvm::StructType *ElTy = cast<llvm::StructType>(Addr.getElementType());
     const llvm::DataLayout &DL = BB->getDataLayout();
     const llvm::StructLayout *Layout = DL.getStructLayout(ElTy);
     auto Offset = CharUnits::fromQuantity(Layout->getElementOffset(Index));
 
-    return Address(CreateStructGEP(Addr.getElementType(), Addr.getBasePointer(),
-                                   Index, Name),
-                   ElTy->getElementType(Index),
-                   Addr.getAlignment().alignmentAtOffset(Offset),
-                   Addr.isKnownNonNull());
+    llvm::GEPNoWrapFlags NWFlags = llvm::GEPNoWrapFlags::noUnsignedWrap();
+    if (!IsBaseConstantNull)
+      NWFlags |= llvm::GEPNoWrapFlags::inBounds();
+    return Address(
+        CreateConstGEP2_32(Addr.getElementType(), Addr.getBasePointer(), 0,
+                           Index, Name, NWFlags),
+        ElTy->getElementType(Index),
+        Addr.getAlignment().alignmentAtOffset(Offset), Addr.isKnownNonNull());
   }
 
   /// Given

clang/lib/CodeGen/CGExpr.cpp

@@ -4778,6 +4778,9 @@ LValue CodeGenFunction::EmitMemberExpr(const MemberExpr *E) {
   }
 
   Expr *BaseExpr = E->getBase();
+  // Check whether the underlying base pointer is a constant null.
+  // If so, we do not set inbounds flag for GEP to avoid breaking some old-style
+  // offsetof idioms.
   Expr *UnderlyingBaseExpr = BaseExpr;
   while (auto *BaseMemberExpr = dyn_cast<MemberExpr>(UnderlyingBaseExpr))
     UnderlyingBaseExpr = BaseMemberExpr->getBase();
@@ -4916,9 +4919,8 @@ static Address emitAddrOfFieldStorage(CodeGenFunction &CGF, Address base,
   unsigned idx =
     CGF.CGM.getTypes().getCGRecordLayout(rec).getLLVMFieldNo(field);
 
-  if (IsBaseConstantNull)
-    return CGF.Builder.CreateConstGEP(base, idx, field->getName());
-  return CGF.Builder.CreateStructGEP(base, idx, field->getName());
+  return CGF.Builder.CreateStructGEP(base, idx, field->getName(),
+                                     IsBaseConstantNull);
 }
 
 static Address emitPreserveStructAccess(CodeGenFunction &CGF, LValue base,

clang/test/CodeGenCXX/catch-nullptr-and-nonzero-offset-in-offsetof-idiom.cpp

@@ -16,6 +16,32 @@ uintptr_t get_offset_of_y_naively() {
   return ((uintptr_t)(&(((S *)nullptr)->y)));
 }
 
+struct Empty {};
+
+struct T {
+  int a;
+  S s;
+  [[no_unique_address]] Empty e1;
+  int b;
+  [[no_unique_address]] Empty e2;
+};
+
+// CHECK-LABEL: @_Z30get_offset_of_y_naively_nestedv(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    ret i64 ptrtoint (ptr getelementptr nuw ([[STRUCT_S:%.*]], ptr getelementptr nuw ([[STRUCT_T:%.*]], ptr null, i32 0, i32 1), i32 0, i32 1) to i64)
+//
+uintptr_t get_offset_of_y_naively_nested() {
+  return ((uintptr_t)(&(((T *)nullptr)->s.y)));
+}
+
+// CHECK-LABEL: @_Z26get_offset_of_zero_storagev(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    ret i64 ptrtoint (ptr getelementptr (i8, ptr null, i64 16) to i64)
+//
+uintptr_t get_offset_of_zero_storage() {
+  return ((uintptr_t)(&(((T *)nullptr)->e2)));
+}
+
 // CHECK-LABEL: @_Z27get_offset_of_y_via_builtinv(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    ret i64 4