On 07/10/2014 08:28 AM, Tony Lindgren wrote:

quoted

--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c

@@ -571,7 +573,17 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep)
 			serial_out(p, UART_EFR, 0);
 			serial_out(p, UART_LCR, 0);
 		}
+
+		if (!device_may_wakeup(p->port.dev)) {
+			if (sleep)
+				pm_runtime_forbid(p->port.dev);
+			else
+				pm_runtime_allow(p->port.dev);
+		}
 	}
+out:
+	pm_runtime_mark_last_busy(p->port.dev);
+	pm_runtime_put_autosuspend(p->port.dev);
 }

The device_may_wakeup logic here is wrong as I described in the
earlier thread. For runtime PM, the wake-up events should be
always enabled. So the device_may_wakeup checks should be only
done for suspend and resume.

Okay. I dropped it from here.

Regards,

Tony

Sebastian