habanalabs/gaudi: trigger state dump in case of SM errors

State dump is relevant to the user in case of Sync Manager error, so
we need to trigger it in that case as well.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit is contained in:
Ofir Bitton 2021-07-12 14:18:30 +03:00 committed by Oded Gabbay
parent a694615111
commit 7148e647a5

View File

@ -7894,8 +7894,9 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
u32 ctl = le32_to_cpu(eq_entry->hdr.ctl);
u16 event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK)
>> EQ_CTL_EVENT_TYPE_SHIFT);
u8 cause;
bool reset_required;
u8 cause;
int rc;
gaudi->events_stat[event_type]++;
gaudi->events_stat_aggregate[event_type]++;
@ -8081,6 +8082,10 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
gaudi_print_irq_info(hdev, event_type, false);
gaudi_print_sm_sei_info(hdev, event_type,
&eq_entry->sm_sei_data);
rc = hl_state_dump(hdev);
if (rc)
dev_err(hdev->dev,
"Error during system state dump %d\n", rc);
hl_fw_unmask_irq(hdev, event_type);
break;