Index: lib/CodeGen/ItaniumCXXABI.cpp
===================================================================
--- lib/CodeGen/ItaniumCXXABI.cpp
+++ lib/CodeGen/ItaniumCXXABI.cpp
@@ -2463,10 +2463,12 @@
     CGM.SetLLVMFunctionAttributesForDefinition(nullptr, Wrapper);
 
   // Always resolve references to the wrapper at link time.
-  if (!Wrapper->hasLocalLinkage() && !(isThreadWrapperReplaceable(VD, CGM) &&
-      !llvm::GlobalVariable::isLinkOnceLinkage(Wrapper->getLinkage()) &&
-      !llvm::GlobalVariable::isWeakODRLinkage(Wrapper->getLinkage())))
-    Wrapper->setVisibility(llvm::GlobalValue::HiddenVisibility);
+  if (!Wrapper->hasLocalLinkage())
+    if (!isThreadWrapperReplaceable(VD, CGM) ||
+        llvm::GlobalVariable::isLinkOnceLinkage(Wrapper->getLinkage()) ||
+        llvm::GlobalVariable::isWeakODRLinkage(Wrapper->getLinkage()) ||
+        VD->getVisibility() == HiddenVisibility)
+      Wrapper->setVisibility(llvm::GlobalValue::HiddenVisibility);
 
   if (isThreadWrapperReplaceable(VD, CGM)) {
     Wrapper->setCallingConv(llvm::CallingConv::CXX_FAST_TLS);
Index: test/CodeGenCXX/cxx11-thread-local-visibility.cpp
===================================================================
--- test/CodeGenCXX/cxx11-thread-local-visibility.cpp
+++ test/CodeGenCXX/cxx11-thread-local-visibility.cpp
@@ -0,0 +1,17 @@
+// RUN: %clang_cc1 -std=c++11 -emit-llvm %s -o - -triple x86_64-linux-gnu | FileCheck --check-prefix=LINUX %s
+// RUN: %clang_cc1 -std=c++11 -emit-llvm %s -o - -triple x86_64-apple-darwin12 | FileCheck --check-prefix=DARWIN %s
+
+// Regression test for PR40327
+
+// LINUX: @default_tls = thread_local global i32
+// LINUX: @hidden_tls = hidden thread_local global i32
+// LINUX: define weak_odr hidden i32* @_ZTW11default_tls()
+// LINUX: define weak_odr hidden i32* @_ZTW10hidden_tls()
+//
+// DARWIN: @default_tls = internal thread_local global i32
+// DARWIN: @hidden_tls = internal thread_local global i32
+// DARWIN: define cxx_fast_tlscc i32* @_ZTW11default_tls()
+// DARWIN: define hidden cxx_fast_tlscc i32* @_ZTW10hidden_tls()
+
+__attribute__((visibility("default"))) thread_local int default_tls;
+__attribute__((visibility("hidden"))) thread_local int hidden_tls;
Index: test/CodeGenCXX/cxx11-thread-local.cpp
===================================================================
--- test/CodeGenCXX/cxx11-thread-local.cpp
+++ test/CodeGenCXX/cxx11-thread-local.cpp
@@ -318,7 +318,7 @@
 // CHECK-NOT: call void @[[V_M_INIT]]()
 
 
-// LIUNX: define weak_odr hidden i32* @_ZTW1a() {
+// LINUX: define weak_odr hidden i32* @_ZTW1a()
 // DARWIN: define cxx_fast_tlscc i32* @_ZTW1a()
 // LINUX:   call void @_ZTH1a()
 // DARWIN: call cxx_fast_tlscc void @_ZTH1a()