[Why]
Running into bugchecks during stress test where rptr is 0xFFFFFFFF.
Typically this is caused by a hard hang, and can come from HW outside
of DCN.
[How]
To prevent bugchecks when writing the DMUB rptr, fist check that the
rptr is valid.
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Solomon Chiu <solomon.chiu@amd.com>
Signed-off-by: Wyatt Wood <wyatt.wood@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
DMUB_STATUS_QUEUE_FULL,
DMUB_STATUS_TIMEOUT,
DMUB_STATUS_INVALID,
+ DMUB_STATUS_HW_FAILURE,
};
/* enum dmub_asic - dmub asic identifier */
enum dmub_status dmub_srv_wait_for_idle(struct dmub_srv *dmub,
uint32_t timeout_us)
{
- uint32_t i;
+ uint32_t i, rptr;
if (!dmub->hw_init)
return DMUB_STATUS_INVALID;
for (i = 0; i <= timeout_us; ++i) {
- dmub->inbox1_rb.rptr = dmub->hw_funcs.get_inbox1_rptr(dmub);
+ rptr = dmub->hw_funcs.get_inbox1_rptr(dmub);
+
+ if (rptr > dmub->inbox1_rb.capacity)
+ return DMUB_STATUS_HW_FAILURE;
+
+ dmub->inbox1_rb.rptr = rptr;
+
if (dmub_rb_empty(&dmub->inbox1_rb))
return DMUB_STATUS_OK;