On 7/15/20 6:23 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.
>
> Signed-off-by: Hans de Goede <hdegoede@xxxxxxxxxx>
subject: s/tryong/trying/
> ---
> 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 ea14240423d1..5adc30666566 100644
> --- a/drivers/usb/typec/tcpm/tcpm.c
> +++ b/drivers/usb/typec/tcpm/tcpm.c
> @@ -971,6 +971,9 @@ static void tcpm_queue_vdm_unlocked(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);
>
