habanalabs/gaudi: fix information printed on SM event

Print the SM name instead of index because it is more informational for
the user to know the SM name instead of id when a SM interrupt occurs.

In addition, the index that is printed is of the SOB group, not
a specific SOB.

Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit is contained in:
Oded Gabbay 2021-07-12 13:48:56 +03:00
parent 7148e647a5
commit ae2021d320

View File

@ -430,8 +430,14 @@ static s64 gaudi_state_dump_specs_props[] = {
[SP_NUM_CORES] = 1,
};
/* The order here is opposite to the order of the indexing in the h/w.
* i.e. SYNC_MGR_W_S is actually 0, SYNC_MGR_E_S is 1, etc.
*/
static const char * const gaudi_sync_manager_names[] = {
"SYNC_MGR_E_N", "SYNC_MGR_W_N", "SYNC_MGR_E_S", "SYNC_MGR_W_S",
"SYNC_MGR_E_N",
"SYNC_MGR_W_N",
"SYNC_MGR_E_S",
"SYNC_MGR_W_S",
NULL
};
@ -7414,24 +7420,30 @@ static void gaudi_print_sm_sei_info(struct hl_device *hdev, u16 event_type,
{
u32 index = event_type - GAUDI_EVENT_DMA_IF_SEI_0;
/* Flip the bits as the enum is ordered in the opposite way */
index = (index ^ 0x3) & 0x3;
switch (sei_data->sei_cause) {
case SM_SEI_SO_OVERFLOW:
dev_err(hdev->dev,
"SM %u SEI Error: SO %u overflow/underflow",
index, le32_to_cpu(sei_data->sei_log));
dev_err_ratelimited(hdev->dev,
"%s SEI Error: SOB Group %u overflow/underflow",
gaudi_sync_manager_names[index],
le32_to_cpu(sei_data->sei_log));
break;
case SM_SEI_LBW_4B_UNALIGNED:
dev_err(hdev->dev,
"SM %u SEI Error: Unaligned 4B LBW access, monitor agent address low - %#x",
index, le32_to_cpu(sei_data->sei_log));
dev_err_ratelimited(hdev->dev,
"%s SEI Error: Unaligned 4B LBW access, monitor agent address low - %#x",
gaudi_sync_manager_names[index],
le32_to_cpu(sei_data->sei_log));
break;
case SM_SEI_AXI_RESPONSE_ERR:
dev_err(hdev->dev,
"SM %u SEI Error: AXI ID %u response error",
index, le32_to_cpu(sei_data->sei_log));
dev_err_ratelimited(hdev->dev,
"%s SEI Error: AXI ID %u response error",
gaudi_sync_manager_names[index],
le32_to_cpu(sei_data->sei_log));
break;
default:
dev_err(hdev->dev, "Unknown SM SEI cause %u",
dev_err_ratelimited(hdev->dev, "Unknown SM SEI cause %u",
le32_to_cpu(sei_data->sei_log));
break;
}