diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 85b2ce54328c3e99da0f7cf4be06b039b70726f7..cdeb94d2a26b613014e239a1cbe8dce5b848e938 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -801,19 +801,38 @@ static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res,
 	return false;
 }
 
-bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags)
+static bool __io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res,
+			      u32 cflags)
 {
 	bool filled;
 
-	io_cq_lock(ctx);
 	filled = io_fill_cqe_aux(ctx, user_data, res, cflags);
 	if (!filled)
 		filled = io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
 
+	return filled;
+}
+
+bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags)
+{
+	bool filled;
+
+	io_cq_lock(ctx);
+	filled = __io_post_aux_cqe(ctx, user_data, res, cflags);
 	io_cq_unlock_post(ctx);
 	return filled;
 }
 
+/*
+ * Must be called from inline task_work so we now a flush will happen later,
+ * and obviously with ctx->uring_lock held (tw always has that).
+ */
+void io_add_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags)
+{
+	__io_post_aux_cqe(ctx, user_data, res, cflags);
+	ctx->submit_state.cq_flush = true;
+}
+
 /*
  * A helper for multishot requests posting additional CQEs.
  * Should only be used from a task_work including IO_URING_F_MULTISHOT.
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 7a8641214509ff2256e3d3ae1e2772eb0ec1eb60..e1ce908f067992f21db86c45753aaafccf7e6be0 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -65,6 +65,7 @@ bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow);
 int io_run_task_work_sig(struct io_ring_ctx *ctx);
 void io_req_defer_failed(struct io_kiocb *req, s32 res);
 bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
+void io_add_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
 bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags);
 void __io_commit_cqring_flush(struct io_ring_ctx *ctx);