Hi,
On 7/15/20 6:06 PM, Guenter Roeck wrote:
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/
Ack, fixed for v2.
Regards,
Hans
---
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);
