[clang] Return larger CXX records in memory

We incorrectly return CXX records in AVX registers when they should be
returned in memory. This is violation of x86-64 psABI.

Detailed discussion is here: https://groups.google.com/g/x86-64-abi/c/BjOOyihHuqg/m/KurXdUcWAgAJ

Author: pranavk

clang/include/clang/Basic/LangOptions.h

@@ -245,6 +245,7 @@ class LangOptionsBase {
     ///   construction vtable because it hasn't added 'type' as a substitution.
     ///   - Skip mangling enclosing class templates of member-like friend
     ///   function templates.
+    ///   - Incorrectly return C++ records in AVX registers on x86_64.
     Ver19,
 
     /// Conform to the underlying platform's C and C++ ABIs as closely

clang/lib/CodeGen/Targets/X86.cpp

@@ -1334,6 +1334,16 @@ class X86_64ABIInfo : public ABIInfo {
     return T.isOSLinux() || T.isOSNetBSD();
   }
 
+  bool returnCXXRecordGreaterThan128InMem() const {
+    // Clang <= 19.0 did not do this.
+    if (getContext().getLangOpts().getClangABICompat() <=
+        LangOptions::ClangABI::Ver19)
+      return false;
+
+    const llvm::Triple &T = getTarget().getTriple();
+    return T.isOSLinux() || T.isOSNetBSD();
+  }
+
   X86AVXABILevel AVXLevel;
   // Some ABIs (e.g. X32 ABI and Native Client OS) use 32 bit pointers on
   // 64-bit hardware.
@@ -2067,6 +2077,13 @@ void X86_64ABIInfo::classify(QualType Ty, uint64_t OffsetBase, Class &Lo,
         classify(I.getType(), Offset, FieldLo, FieldHi, isNamedArg);
         Lo = merge(Lo, FieldLo);
         Hi = merge(Hi, FieldHi);
+        if (returnCXXRecordGreaterThan128InMem() &&
+            (Size > 128 && (Size != getContext().getTypeSize(I.getType()) ||
+                            Size > getNativeVectorSizeForAVXABI(AVXLevel)))) {
+          // The only case a 256(or 512)-bit wide vector could be used to return
+          // is when CXX record contains a single 256(or 512)-bit element.
+          Lo = Memory;
+        }
         if (Lo == Memory || Hi == Memory) {
           postMerge(Size, Lo, Hi);
           return;

clang/test/CodeGen/X86/avx-cxx-record.cpp

@@ -0,0 +1,23 @@
+// RUN: %clang %s -S --target=x86_64-unknown-linux-gnu -emit-llvm -O2 -march=x86-64-v3 -o - | FileCheck %s
+
+using UInt64x2 = unsigned long long __attribute__((__vector_size__(16), may_alias));
+
+template<int id>
+struct XMM1 {
+    UInt64x2 x;
+};
+
+struct XMM2 : XMM1<0>, XMM1<1> {
+};
+
+// CHECK: define{{.*}} @_Z3foov({{.*}} [[ARG:%.*]]){{.*}}
+// CHECK-NEXT: entry:
+// CHECK-NEXT: store {{.*}}, ptr [[ARG]]{{.*}}
+// CHECK-NEXT: [[TMP1:%.*]] = getelementptr {{.*}}, ptr [[ARG]]{{.*}}
+// CHECK-NEXT: store {{.*}}, ptr [[TMP1]]{{.*}}
+XMM2 foo() {
+  XMM2 result;
+  ((XMM1<0>*)&result)->x = UInt64x2{1, 2};
+  ((XMM1<1>*)&result)->x = UInt64x2{3, 4};
+  return result;
+}