Index: lib/CodeGen/CGDeclCXX.cpp
===================================================================
--- lib/CodeGen/CGDeclCXX.cpp
+++ lib/CodeGen/CGDeclCXX.cpp
@@ -86,13 +86,18 @@
   llvm::Constant *function;
   llvm::Constant *argument;
 
-  // Special-case non-array C++ destructors, where there's a function
-  // with the right signature that we can just call.
-  const CXXRecordDecl *record = nullptr;
-  if (dtorKind == QualType::DK_cxx_destructor &&
-      (record = type->getAsCXXRecordDecl())) {
-    assert(!record->hasTrivialDestructor());
-    CXXDestructorDecl *dtor = record->getDestructor();
+  // Special-case non-array C++ destructors, if they have the right signature
+  // that can be directly registered with __cxa_atexit. If __cxa_atexit is
+  // disabled via a flag, a different helper function is generated anyway.
+  const CXXRecordDecl *Record = type->getAsCXXRecordDecl();
+  bool CanRegisterDestructor = Record &&
+                               !CGM.getCXXABI().HasThisReturn(GlobalDecl(
+                                   Record->getDestructor(), Dtor_Complete));
+
+  if (dtorKind == QualType::DK_cxx_destructor && Record &&
+      (CanRegisterDestructor || !CGM.getCodeGenOpts().CXAAtExit)) {
+    assert(!Record->hasTrivialDestructor());
+    CXXDestructorDecl *dtor = Record->getDestructor();
 
     function = CGM.getAddrOfCXXStructor(dtor, StructorType::Complete);
     argument = llvm::ConstantExpr::getBitCast(
Index: test/CodeGenCXX/runtimecc.cpp
===================================================================
--- test/CodeGenCXX/runtimecc.cpp
+++ test/CodeGenCXX/runtimecc.cpp
@@ -22,8 +22,13 @@
   A global;
 // CHECK-LABEL:    define internal void @__cxx_global_var_init()
 // CHECK:      call [[A]]* @_ZN5test01AC1Ev([[A]]* @_ZN5test06globalE)
-// CHECK-NEXT: call i32 @__cxa_atexit(void (i8*)* bitcast ([[A]]* ([[A]]*)* @_ZN5test01AD1Ev to void (i8*)*), i8* bitcast ([[A]]* @_ZN5test06globalE to i8*), i8* @__dso_handle) [[NOUNWIND:#[0-9]+]]
+// CHECK-NEXT: call i32 @__cxa_atexit(void (i8*)* @__cxx_global_array_dtor, i8* null, i8* @__dso_handle) [[NOUNWIND:#[0-9]+]]
 // CHECK-NEXT: ret void
+
+// CHECK-LABEL: define internal void @__cxx_global_array_dtor(i8*)
+// CHECK: call [[A]]* @_ZN5test01AD1Ev([[A]]* @_ZN5test06globalE)
+// CHECK-NEXT: ret void
+
 }
 
 // CHECK: declare i32 @__cxa_atexit(void (i8*)*, i8*, i8*) [[NOUNWIND]]
Index: test/CodeGenCXX/static-destructor.cpp
===================================================================
--- /dev/null
+++ test/CodeGenCXX/static-destructor.cpp
@@ -0,0 +1,30 @@
+// RUN: %clang_cc1 %s -triple=x86_64-pc-linux -emit-llvm -o - | FileCheck --check-prefix=X86 %s
+// RUN: %clang_cc1 %s -triple=wasm32 -emit-llvm -o - | FileCheck --check-prefix=WASM %s
+// RUN: %clang_cc1 %s -triple=armv7-apple-darwin9 -emit-llvm -o - | FileCheck --check-prefix=WASM %s
+
+// Test that destructors are not passed directly to __cxa_atexit when their
+// signatures do not match the type of its first argument.
+// e.g. ARM and WebAssembly have destructors that return this instead of void.
+
+
+class Foo {
+ public:
+  ~Foo() {
+  }
+};
+
+Foo global;
+
+// X86 destructors have void return, and are registered directly with __cxa_atexit.
+// X86: define internal void @__cxx_global_var_init()
+// X86-NEXT: entry:
+// X86-NEXT:   %0 = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%class.Foo*)* @_ZN3FooD1Ev to void (i8*)*), i8* getelementptr inbounds (%class.Foo, %class.Foo* @global, i32 0, i32 0), i8* @__dso_handle)
+
+// Wasm destructors return this, and use a wrapper function, which is registered
+// with __cxa_atexit.
+// WASM: define internal void @__cxx_global_var_init()
+// WASM-NEXT: entry:
+// WASM-NEXT: %0 = call i32 @__cxa_atexit(void (i8*)* @__cxx_global_array_dtor, i8* null, i8* @__dso_handle)
+
+// WASM: define internal void @__cxx_global_array_dtor(i8*)
+// WASM: %call = call %class.Foo* @_ZN3FooD1Ev(%class.Foo* @global)