diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -4358,15 +4358,10 @@
 
 Address WinX86_64ABIInfo::EmitVAArg(CodeGenFunction &CGF, Address VAListAddr,
                                     QualType Ty) const {
-
-  bool IsIndirect = false;
-
   // MS x64 ABI requirement: "Any argument that doesn't fit in 8 bytes, or is
   // not 1, 2, 4, or 8 bytes, must be passed by reference."
-  if (isAggregateTypeForABI(Ty) || Ty->isMemberPointerType()) {
-    uint64_t Width = getContext().getTypeSize(Ty);
-    IsIndirect = Width > 64 || !llvm::isPowerOf2_64(Width);
-  }
+  uint64_t Width = getContext().getTypeSize(Ty);
+  bool IsIndirect = Width > 64 || !llvm::isPowerOf2_64(Width);
 
   return emitVoidPtrVAArg(CGF, VAListAddr, Ty, IsIndirect,
                           CGF.getContext().getTypeInfoInChars(Ty),
diff --git a/clang/test/CodeGen/mingw-long-double.c b/clang/test/CodeGen/mingw-long-double.c
--- a/clang/test/CodeGen/mingw-long-double.c
+++ b/clang/test/CodeGen/mingw-long-double.c
@@ -45,3 +45,19 @@
 // GNU32: declare dso_local void @__mulxc3
 // GNU64: declare dso_local void @__mulxc3
 // MSC64: declare dso_local void @__muldc3
+
+void VarArgLD(int a, ...) {
+  // GNU32-LABEL: define{{.*}} void @VarArgLD
+  // GNU64-LABEL: define{{.*}} void @VarArgLD
+  // MSC64-LABEL: define{{.*}} void @VarArgLD
+  __builtin_va_list ap;
+  __builtin_va_start(ap, a);
+  long double LD = __builtin_va_arg(ap, long double);
+  // GNU32-NOT: load x86_fp80*, x86_fp80**
+  // GNU32: load x86_fp80, x86_fp80*
+  // GNU64: load x86_fp80*, x86_fp80**
+  // GNU64: load x86_fp80, x86_fp80*
+  // MSC64-NOT: load double*, double**
+  // MSC64: load double, double*
+  __builtin_va_end(ap);
+}
diff --git a/clang/test/CodeGen/win64-i128.c b/clang/test/CodeGen/win64-i128.c
--- a/clang/test/CodeGen/win64-i128.c
+++ b/clang/test/CodeGen/win64-i128.c
@@ -14,3 +14,16 @@
 
 // GNU64: define dso_local <2 x i64> @bar(i128* %0, i128* %1)
 // MSC64: define dso_local <2 x i64> @bar(i128* %0, i128* %1)
+
+void vararg(int a, ...) {
+  // GNU64-LABEL: define{{.*}} void @vararg
+  // MSC64-LABEL: define{{.*}} void @vararg
+  __builtin_va_list ap;
+  __builtin_va_start(ap, a);
+  int128_t i = __builtin_va_arg(ap, int128_t);
+  // GNU64: load i128*, i128**
+  // GNU64: load i128, i128*
+  // MSC64: load i128*, i128**
+  // MSC64: load i128, i128*
+  __builtin_va_end(ap);
+}
diff --git a/clang/test/CodeGenCXX/ext-int.cpp b/clang/test/CodeGenCXX/ext-int.cpp
--- a/clang/test/CodeGenCXX/ext-int.cpp
+++ b/clang/test/CodeGenCXX/ext-int.cpp
@@ -164,10 +164,11 @@
   // LIN: store i92 %[[LOAD1]], i92*
 
   // WIN: %[[CUR1:.+]] = load i8*, i8** %[[ARGS]]
-  // WIN: %[[NEXT1:.+]] = getelementptr inbounds i8, i8* %[[CUR1]], i64 16
+  // WIN: %[[NEXT1:.+]] = getelementptr inbounds i8, i8* %[[CUR1]], i64 8
   // WIN: store i8* %[[NEXT1]], i8** %[[ARGS]]
-  // WIN: %[[BC1:.+]] = bitcast i8* %[[CUR1]] to i92*
-  // WIN: %[[LOADV1:.+]] = load i92, i92* %[[BC1]]
+  // WIN: %[[BC1:.+]] = bitcast i8* %[[CUR1]] to i92**
+  // WIN: %[[LOADP1:.+]] = load i92*, i92** %[[BC1]]
+  // WIN: %[[LOADV1:.+]] = load i92, i92* %[[LOADP1]]
   // WIN: store i92 %[[LOADV1]], i92*
 
   _ExtInt(31) B = __builtin_va_arg(args, _ExtInt(31));
@@ -215,10 +216,11 @@
   // LIN: store i129 %[[LOAD4]], i129*
 
   // WIN: %[[CUR4:.+]] = load i8*, i8** %[[ARGS]]
-  // WIN: %[[NEXT4:.+]] = getelementptr inbounds i8, i8* %[[CUR4]], i64 24
+  // WIN: %[[NEXT4:.+]] = getelementptr inbounds i8, i8* %[[CUR4]], i64 8
   // WIN: store i8* %[[NEXT4]], i8** %[[ARGS]]
-  // WIN: %[[BC4:.+]] = bitcast i8* %[[CUR4]] to i129*
-  // WIN: %[[LOADV4:.+]] = load i129, i129* %[[BC4]]
+  // WIN: %[[BC4:.+]] = bitcast i8* %[[CUR4]] to i129**
+  // WIN: %[[LOADP4:.+]] = load i129*, i129** %[[BC4]]
+  // WIN: %[[LOADV4:.+]] = load i129, i129* %[[LOADP4]]
   // WIN: store i129 %[[LOADV4]], i129*
 
   _ExtInt(16777200) E = __builtin_va_arg(args, _ExtInt(16777200));
@@ -232,10 +234,11 @@
   // LIN: store i16777200 %[[LOAD5]], i16777200*
 
   // WIN: %[[CUR5:.+]] = load i8*, i8** %[[ARGS]]
-  // WIN: %[[NEXT5:.+]] = getelementptr inbounds i8, i8* %[[CUR5]], i64 2097152
+  // WIN: %[[NEXT5:.+]] = getelementptr inbounds i8, i8* %[[CUR5]], i64 8
   // WIN: store i8* %[[NEXT5]], i8** %[[ARGS]]
-  // WIN: %[[BC5:.+]] = bitcast i8* %[[CUR5]] to i16777200*
-  // WIN: %[[LOADV5:.+]] = load i16777200, i16777200* %[[BC5]]
+  // WIN: %[[BC5:.+]] = bitcast i8* %[[CUR5]] to i16777200**
+  // WIN: %[[LOADP5:.+]] = load i16777200*, i16777200** %[[BC5]]
+  // WIN: %[[LOADV5:.+]] = load i16777200, i16777200* %[[LOADP5]]
   // WIN: store i16777200 %[[LOADV5]], i16777200*
 
   __builtin_va_end(args);