Index: lib/Sema/SemaCoroutine.cpp
===================================================================
--- lib/Sema/SemaCoroutine.cpp
+++ lib/Sema/SemaCoroutine.cpp
@@ -1316,10 +1316,6 @@
   if (Res.isInvalid())
     return false;
 
-  if (GroType == FnRetType) {
-    GroDecl->setNRVOVariable(true);
-  }
-
   S.AddInitializerToDecl(GroDecl, Res.get(),
                          /*DirectInit=*/false);
 
@@ -1343,6 +1339,8 @@
     noteMemberDeclaredHere(S, ReturnValue, Fn);
     return false;
   }
+  if (cast<clang::ReturnStmt>(ReturnStmt.get())->getNRVOCandidate() == GroDecl)
+    GroDecl->setNRVOVariable(true);
 
   this->ReturnStmt = ReturnStmt.get();
   return true;
Index: test/CodeGenCoroutines/coro-alloc.cpp
===================================================================
--- test/CodeGenCoroutines/coro-alloc.cpp
+++ test/CodeGenCoroutines/coro-alloc.cpp
@@ -173,6 +173,7 @@
 // CHECK-LABEL: f4(
 extern "C" int f4(promise_on_alloc_failure_tag) {
   // CHECK: %[[RetVal:.+]] = alloca i32
+  // CHECK: %[[Gro:.+]] = alloca i32
   // CHECK: %[[ID:.+]] = call token @llvm.coro.id(i32 16
   // CHECK: %[[SIZE:.+]] = call i64 @llvm.coro.size.i64()
   // CHECK: %[[MEM:.+]] = call i8* @_ZnwmRKSt9nothrow_t(i64 %[[SIZE]], %"struct.std::nothrow_t"* dereferenceable(1) @_ZStL7nothrow)
@@ -186,7 +187,11 @@
 
   // CHECK: [[OKBB]]:
   // CHECK:   %[[OkRet:.+]] = call i32 @_ZNSt12experimental16coroutine_traitsIJi28promise_on_alloc_failure_tagEE12promise_type17get_return_objectEv(
-  // CHECK:   store i32 %[[OkRet]], i32* %[[RetVal]]
+  // CHECK:   store i32 %[[OkRet]], i32* %[[Gro]]
+
+  // CHECK: %[[Tmp1:.*]] = load i32, i32* %[[Gro]]
+  // CHECK-NEXT: store i32 %[[Tmp1]], i32* %[[RetVal]]
+  // CHECK-NEXT: br label %[[RetBB]]
 
   // CHECK: [[RetBB]]:
   // CHECK:   %[[LoadRet:.+]] = load i32, i32* %[[RetVal]], align 4
Index: test/CodeGenCoroutines/coro-gro-nrvo.cpp
===================================================================
--- /dev/null
+++ test/CodeGenCoroutines/coro-gro-nrvo.cpp
@@ -0,0 +1,87 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -fcoroutines-ts -std=c++14 -emit-llvm %s -o - -disable-llvm-passes | FileCheck %s
+
+#include "Inputs/coroutine.h"
+
+using namespace std::experimental;
+
+namespace std {
+
+struct nothrow_t {};
+constexpr nothrow_t nothrow = {};
+
+} // end namespace std
+
+// Required when get_return_object_on_allocation_failure() is defined by
+// the promise.
+void* operator new(__SIZE_TYPE__ __sz, const std::nothrow_t&) noexcept;
+void  operator delete(void* __p, const std::nothrow_t&) noexcept;
+
+
+template <class RetObject>
+struct promise_type {
+    RetObject get_return_object();
+    suspend_always initial_suspend();
+    suspend_never final_suspend();
+    void return_void();
+    static void unhandled_exception();
+};
+
+struct coro {
+  using promise_type = promise_type<coro>;
+  coro(coro const&);
+  struct Impl;
+  Impl *impl;
+};
+
+// Verify that the NRVO is applied to the Gro object.
+// CHECK-LABEL: define void @_Z1fi(%struct.coro* noalias sret %agg.result, i32)
+coro f(int) {
+// CHECK: %call = call i8* @_Znwm(
+// CHECK-NEXT: br label %[[CoroInit:.*]]
+
+// CHECK: {{.*}}[[CoroInit]]:
+// CHECK: store i1 false, i1* %gro.active
+// CHECK-NEXT: call void @{{.*get_return_objectEv}}(%struct.coro* sret %agg.result
+// CHECK-NEXT: store i1 true, i1* %gro.active
+  co_return;
+}
+
+
+template <class RetObject>
+struct promise_type_with_on_alloc_failure {
+    static RetObject get_return_object_on_allocation_failure();
+    RetObject get_return_object();
+    suspend_always initial_suspend();
+    suspend_never final_suspend();
+    void return_void();
+    static void unhandled_exception();
+};
+
+struct coro_two {
+  using promise_type = promise_type_with_on_alloc_failure<coro_two>;
+  coro_two(coro_two const&);
+  struct Impl;
+  Impl *impl;
+};
+
+// Verify that the NRVO is applied to the Gro object.
+// CHECK-LABEL: define void @_Z1hi(%struct.coro_two* noalias sret %agg.result, i32)
+ coro_two h(int) {
+
+// CHECK: %call = call i8* @_ZnwmRKSt9nothrow_t
+// CHECK-NEXT: %[[CheckNull:.*]] = icmp ne i8* %call, null
+// CHECK-NEXT: br i1 %[[CheckNull]], label %[[InitOnSuccess:.*]], label %[[InitOnFailure:.*]]
+
+// CHECK: {{.*}}[[InitOnFailure]]:
+// CHECK-NEXT: call void @{{.*get_return_object_on_allocation_failureEv}}(%struct.coro_two* sret %agg.result
+// CHECK-NEXT: br label %[[RetLabel:.*]]
+
+// CHECK: {{.*}}[[InitOnSuccess]]:
+// CHECK: store i1 false, i1* %gro.active
+// CHECK-NEXT: call void @{{.*get_return_objectEv}}(%struct.coro_two* sret %agg.result
+// CHECK-NEXT: store i1 true, i1* %gro.active
+
+// CHECK: [[RetLabel]]:
+// CHECK-NEXT: ret void
+  co_return;
+}