On 7/24/20 10:47 AM, Hans de Goede wrote: > The tcpm.c code for sending VDMs assumes that there will only be one VDM > in flight at the time. The "queue" used by tcpm_queue_vdm is only 1 entry > deep. > > This assumes that the higher layers (tcpm state-machine and alt-mode > drivers) ensure that queuing a new VDM before the old one has been > completely send (or it timed out) add a WARN_ON to check for this. Just in case you resend ... "has been sent" is grammatically correct. The feedback on https://www.quora.com/What-is-the-difference-between-send-and-sent explains it in detail. > > Signed-off-by: Hans de Goede <hdegoede@xxxxxxxxxx> Reviewed-by: Guenter Roeck <linux@xxxxxxxxxxxx> Thanks, Guenter > --- > Changes in v2: > - Fix typo in commit-msg subject > --- > drivers/usb/typec/tcpm/tcpm.c | 3 +++ > 1 file changed, 3 insertions(+) > > diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c > index 9b26b57a0172..cc786d558f14 100644 > --- a/drivers/usb/typec/tcpm/tcpm.c > +++ b/drivers/usb/typec/tcpm/tcpm.c > @@ -971,6 +971,9 @@ static void tcpm_queue_vdm(struct tcpm_port *port, const u32 header, > { > WARN_ON(!mutex_is_locked(&port->lock)); > > + /* Make sure we are not still processing a previous VDM packet */ > + WARN_ON(port->vdm_state > VDM_STATE_DONE); > + > port->vdo_count = cnt + 1; > port->vdo_data[0] = header; > memcpy(&port->vdo_data[1], data, sizeof(u32) * cnt); >
