Databook doesn't say we should stall if we
get XferNotReady(STATUS) while we're expecting
something else.
Instead of stalling and restarting, tests have
proven that ignoring the event is far more
effective.
This problem has been caught while rewriting
ep0 handling in order we pass Link Layer TD7.6.
Signed-off-by: Felipe Balbi <balbi@ti.com>
break;
case DEPEVT_STATUS_CONTROL_STATUS:
+ if (dwc->ep0_next_event != DWC3_EP0_NRDY_STATUS)
+ return;
+
dev_vdbg(dwc->dev, "Control Status\n");
dwc->ep0state = EP0_STATUS_PHASE;
- if (dwc->ep0_next_event != DWC3_EP0_NRDY_STATUS) {
- dev_vdbg(dwc->dev, "Expected %d got %d\n",
- dwc->ep0_next_event,
- DWC3_EP0_NRDY_STATUS);
-
- dwc3_ep0_stall_and_restart(dwc);
- return;
- }
-
if (dwc->delayed_status) {
WARN_ON_ONCE(event->endpoint_number != 1);
dev_vdbg(dwc->dev, "Mass Storage delayed status\n");