Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -2657,6 +2657,14 @@
         Hi = Lo;
     } else if (Size == 128 ||
                (isNamedArg && Size <= getNativeVectorSizeForAVXABI(AVXLevel))) {
+      QualType ElementType = VT->getElementType();
+
+      // gcc passes 256 and 512 bit <X x int128> vectors in memory. :(
+      if (Size != 128 &&
+          (ElementType->isSpecificBuiltinType(BuiltinType::Int128) ||
+           ElementType->isSpecificBuiltinType(BuiltinType::UInt128)))
+        return;
+
       // Arguments of 256-bits are split into four eightbyte chunks. The
       // least significant one belongs to class SSE and all the others to class
       // SSEUP. The original Lo and Hi design considers that types can't be
@@ -2899,6 +2907,10 @@
     unsigned LargestVector = getNativeVectorSizeForAVXABI(AVXLevel);
     if (Size <= 64 || Size > LargestVector)
       return true;
+    QualType EltTy = VecTy->getElementType();
+    if (EltTy->isSpecificBuiltinType(BuiltinType::Int128) ||
+        EltTy->isSpecificBuiltinType(BuiltinType::UInt128))
+      return true;
   }
 
   return false;
@@ -2972,8 +2984,11 @@
   if (const Type *InnerTy = isSingleElementStruct(Ty, getContext()))
     Ty = QualType(InnerTy, 0);
 
+  // Don't pass vXi128 vectors in their native type, the backend can't
+  // legalize them.
   llvm::Type *IRType = CGT.ConvertType(Ty);
-  if (isa<llvm::VectorType>(IRType) ||
+  if ((isa<llvm::VectorType>(IRType) &&
+       !IRType->getVectorElementType()->isIntegerTy(128)) ||
       IRType->getTypeID() == llvm::Type::FP128TyID)
     return IRType;