Index: lib/CodeGen/CGCXXABI.h
===================================================================
--- lib/CodeGen/CGCXXABI.h
+++ lib/CodeGen/CGCXXABI.h
@@ -106,6 +106,16 @@
 
   virtual bool hasMostDerivedReturn(GlobalDecl GD) const { return false; }
 
+  /// Returns true if the target allows calling a function through a pointer
+  /// with a different signature than the actual function (or equivalently,
+  /// bitcasting a function or function pointer to a different function type).
+  /// In principle in the most general case this could depend on the target, the
+  /// calling convention, and the actual types of the arguments and return
+  /// value. Here it just means whether the signature mismatch could *ever* be
+  /// allowed; in other words, does the target do strict checking of signatures
+  /// for all calls.
+  virtual bool canCallMismatchedFunctionType() const { return true; }
+
   /// If the C++ ABI requires the given type be returned in a particular way,
   /// this method sets RetAI and returns true.
   virtual bool classifyReturnType(CGFunctionInfo &FI) const = 0;
Index: lib/CodeGen/CGDeclCXX.cpp
===================================================================
--- lib/CodeGen/CGDeclCXX.cpp
+++ lib/CodeGen/CGDeclCXX.cpp
@@ -86,13 +86,21 @@
   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.
+  // Under some ABIs, destructors return this instead of void, and cannot be
+  // passed directly to __cxa_atexit if the target does not allow this mismatch.
+  const CXXRecordDecl *Record = type->getAsCXXRecordDecl();
+  bool CanRegisterDestructor =
+      Record && (!CGM.getCXXABI().HasThisReturn(
+                     GlobalDecl(Record->getDestructor(), Dtor_Complete)) ||
+                 CGM.getCXXABI().canCallMismatchedFunctionType());
+  // If __cxa_atexit is disabled via a flag, a different helper function is
+  // generated elsewhere which uses atexit instead, and it takes the destructor
+  // directly.
+  bool UsingExternalHelper = !CGM.getCodeGenOpts().CXAAtExit;
+  if (Record && (CanRegisterDestructor || UsingExternalHelper)) {
+    assert(!Record->hasTrivialDestructor());
+    CXXDestructorDecl *dtor = Record->getDestructor();
 
     function = CGM.getAddrOfCXXStructor(dtor, StructorType::Complete);
     argument = llvm::ConstantExpr::getBitCast(
Index: lib/CodeGen/ItaniumCXXABI.cpp
===================================================================
--- lib/CodeGen/ItaniumCXXABI.cpp
+++ lib/CodeGen/ItaniumCXXABI.cpp
@@ -443,6 +443,7 @@
            (isa<CXXDestructorDecl>(GD.getDecl()) &&
             GD.getDtorType() != Dtor_Deleting);
   }
+  bool canCallMismatchedFunctionType() const override { return false; }
 };
 }
 
Index: test/CodeGenCXX/static-destructor.cpp
===================================================================
--- /dev/null
+++ test/CodeGenCXX/static-destructor.cpp
@@ -0,0 +1,36 @@
+// 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=ARM %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)
+
+// ARM destructors return this, but can be registered directly with __cxa_atexit
+// because the calling conventions tolerate the mismatch.
+// ARM: define internal void @__cxx_global_var_init()
+// ARM-NEXT: entry:
+// ARM-NEXT:   %0 = call i32 @__cxa_atexit(void (i8*)* bitcast (%class.Foo* (%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)