diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -4316,9 +4316,11 @@
     }
 
     // If value is passed via pointer - do a load.
-    if (VA.getLocInfo() == CCValAssign::Indirect && !Ins[I].Flags.isByVal())
+    if (VA.getLocInfo() == CCValAssign::Indirect &&
+        !(Ins[I].Flags.isByVal() && VA.isRegLoc())) {
       ArgValue =
           DAG.getLoad(VA.getValVT(), dl, Chain, ArgValue, MachinePointerInfo());
+    }
 
     InVals.push_back(ArgValue);
   }
diff --git a/llvm/test/CodeGen/X86/win64-byval.ll b/llvm/test/CodeGen/X86/win64-byval.ll
--- a/llvm/test/CodeGen/X86/win64-byval.ll
+++ b/llvm/test/CodeGen/X86/win64-byval.ll
@@ -87,3 +87,13 @@
   call void @foo2(ptr byval({ float, double }) @G, ptr byval({ float, double }) @G, ptr byval({ float, double }) @G, ptr byval({ float, double }) @G, ptr byval({ float, double }) @G, i64 10)
   ret void
 }
+
+define i64 @receive_byval_arg_via_stack_arg(i64* byval(i64), i64* byval(i64), i64* byval(i64), i64* byval(i64), i64* byval(i64) %x) {
+; CHECK-LABEL: receive_byval_arg_via_stack_arg:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    movq {{[0-9]+}}(%rsp), %rax
+; CHECK-NEXT:    movq (%rax), %rax
+; CHECK-NEXT:    retq
+  %r = load i64, i64* %x
+  ret i64 %r
+}