diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
--- a/clang/lib/CodeGen/BackendUtil.cpp
+++ b/clang/lib/CodeGen/BackendUtil.cpp
@@ -579,8 +579,9 @@
   // At O0 and O1 we only run the always inliner which is more efficient. At
   // higher optimization levels we run the normal inliner.
   if (CodeGenOpts.OptimizationLevel <= 1) {
-    bool InsertLifetimeIntrinsics = (CodeGenOpts.OptimizationLevel != 0 &&
-                                     !CodeGenOpts.DisableLifetimeMarkers);
+    bool InsertLifetimeIntrinsics = ((CodeGenOpts.OptimizationLevel != 0 &&
+                                      !CodeGenOpts.DisableLifetimeMarkers) ||
+                                     LangOpts.Coroutines);
     PMBuilder.Inliner = createAlwaysInlinerLegacyPass(InsertLifetimeIntrinsics);
   } else {
     // We do not want to inline hot callsites for SamplePGO module-summary build
@@ -1176,7 +1177,10 @@
       // which is just that always inlining occurs. Further, disable generating
       // lifetime intrinsics to avoid enabling further optimizations during
       // code generation.
-      MPM.addPass(AlwaysInlinerPass(/*InsertLifetimeIntrinsics=*/false));
+      // However, we need to insert lifetime intrinsics to avoid invalid access
+      // caused by multithreaded coroutines.
+      MPM.addPass(
+          AlwaysInlinerPass(/*InsertLifetimeIntrinsics=*/LangOpts.Coroutines));
 
       // At -O0, we can still do PGO. Add all the requested passes for
       // instrumentation PGO, if requested.
diff --git a/clang/test/CodeGenCoroutines/coro-always-inline.cpp b/clang/test/CodeGenCoroutines/coro-always-inline.cpp
new file mode 100644
--- /dev/null
+++ b/clang/test/CodeGenCoroutines/coro-always-inline.cpp
@@ -0,0 +1,54 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm -fcoroutines-ts \
+// RUN:   -fexperimental-new-pass-manager -O0 %s -o - | FileCheck %s
+// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm -fcoroutines-ts \
+// RUN:   -fexperimental-new-pass-manager -fno-inline -O0 %s -o - | FileCheck %s
+
+// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm -fcoroutines-ts \
+// RUN:   -O0 %s -o - | FileCheck %s
+// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm -fcoroutines-ts \
+// RUN:   -fno-inline -O0 %s -o - | FileCheck %s
+
+namespace std {
+namespace experimental {
+
+struct handle {};
+
+struct awaitable {
+  bool await_ready() { return true; }
+  // CHECK-NOT: await_suspend
+  inline void __attribute__((__always_inline__)) await_suspend(handle) {}
+  bool await_resume() { return true; }
+};
+
+template <typename T>
+struct coroutine_handle {
+  static handle from_address(void *address) { return {}; }
+};
+
+template <typename T = void>
+struct coroutine_traits {
+  struct promise_type {
+    awaitable initial_suspend() { return {}; }
+    awaitable final_suspend() { return {}; }
+    void return_void() {}
+    T get_return_object() { return T(); }
+    void unhandled_exception() {}
+  };
+};
+} // namespace experimental
+} // namespace std
+
+// CHECK-LABEL: @_Z3foov
+// CHECK-LABEL: entry:
+// CHECK-NEXT: %this.addr.i{{[0-9]*}} = alloca %"struct.std::experimental::awaitable"*, align 8
+// CHECK-NEXT: %this.addr.i{{[0-9]*}} = alloca %"struct.std::experimental::awaitable"*, align 8
+// CHECK: [[CAST0:%[0-9]+]] = bitcast %"struct.std::experimental::awaitable"** %this.addr.i{{[0-9]*}} to i8*
+// CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 8, i8* [[CAST0]])
+// CHECK: [[CAST1:%[0-9]+]] = bitcast %"struct.std::experimental::awaitable"** %this.addr.i{{[0-9]*}} to i8*
+// CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 8, i8* [[CAST1]])
+
+// CHECK: [[CAST2:%[0-9]+]] = bitcast %"struct.std::experimental::awaitable"** %this.addr.i{{[0-9]*}} to i8*
+// CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 8, i8* [[CAST2]])
+// CHECK: [[CAST3:%[0-9]+]] = bitcast %"struct.std::experimental::awaitable"** %this.addr.i{{[0-9]*}} to i8*
+// CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 8, i8* [[CAST3]])
+void foo() { co_return; }