Commit 7148e647 authored by Ofir Bitton's avatar Ofir Bitton Committed by Oded Gabbay

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: default avatarOfir Bitton <obitton@habana.ai>
Reviewed-by: default avatarOded Gabbay <ogabbay@kernel.org>
Signed-off-by: default avatarOded Gabbay <ogabbay@kernel.org>
parent a6946151
...@@ -7894,8 +7894,9 @@ static void gaudi_handle_eqe(struct hl_device *hdev, ...@@ -7894,8 +7894,9 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
u32 ctl = le32_to_cpu(eq_entry->hdr.ctl); u32 ctl = le32_to_cpu(eq_entry->hdr.ctl);
u16 event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK) u16 event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK)
>> EQ_CTL_EVENT_TYPE_SHIFT); >> EQ_CTL_EVENT_TYPE_SHIFT);
u8 cause;
bool reset_required; bool reset_required;
u8 cause;
int rc;
gaudi->events_stat[event_type]++; gaudi->events_stat[event_type]++;
gaudi->events_stat_aggregate[event_type]++; gaudi->events_stat_aggregate[event_type]++;
...@@ -8081,6 +8082,10 @@ static void gaudi_handle_eqe(struct hl_device *hdev, ...@@ -8081,6 +8082,10 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
gaudi_print_irq_info(hdev, event_type, false); gaudi_print_irq_info(hdev, event_type, false);
gaudi_print_sm_sei_info(hdev, event_type, gaudi_print_sm_sei_info(hdev, event_type,
&eq_entry->sm_sei_data); &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); hl_fw_unmask_irq(hdev, event_type);
break; break;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment