io_uring: avoid unnecessary io_wq_work copy for fast poll feature

Basically IORING_OP_POLL_ADD command and async armed poll handlers
for regular commands don't touch io_wq_work, so only REQ_F_WORK_INITIALIZED
is set, can we do io_wq_work copy and restore.
Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -4262,7 +4262,8 @@ static void io_async_task_func(struct callback_head *cb)
 	spin_unlock_irq(&ctx->completion_lock);
 
 	/* restore ->work in case we need to retry again */
-	memcpy(&req->work, &apoll->work, sizeof(req->work));
+	if (req->flags & REQ_F_WORK_INITIALIZED)
+		memcpy(&req->work, &apoll->work, sizeof(req->work));
 	kfree(apoll);
 
 	if (!canceled) {
@@ -4359,7 +4360,8 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 		return false;
 
 	req->flags |= REQ_F_POLLED;
-	memcpy(&apoll->work, &req->work, sizeof(req->work));
+	if (req->flags & REQ_F_WORK_INITIALIZED)
+		memcpy(&apoll->work, &req->work, sizeof(req->work));
 	had_io = req->io != NULL;
 
 	get_task_struct(current);
@@ -4384,7 +4386,8 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 		if (!had_io)
 			io_poll_remove_double(req);
 		spin_unlock_irq(&ctx->completion_lock);
-		memcpy(&req->work, &apoll->work, sizeof(req->work));
+		if (req->flags & REQ_F_WORK_INITIALIZED)
+			memcpy(&req->work, &apoll->work, sizeof(req->work));
 		kfree(apoll);
 		return false;
 	}
@@ -4429,7 +4432,9 @@ static bool io_poll_remove_one(struct io_kiocb *req)
 			 * io_req_work_drop_env below when dropping the
 			 * final reference.
 			 */
-			memcpy(&req->work, &apoll->work, sizeof(req->work));
+			if (req->flags & REQ_F_WORK_INITIALIZED)
+				memcpy(&req->work, &apoll->work,
+				       sizeof(req->work));
 			kfree(apoll);
 		}
 	}