accel/habanalabs: add generic message type to get error counters

Add a new CPUCP generic message type to retrieve HBM, SRAM and critical
error counters from the device.

Signed-off-by: Vitaly Margolin <vitaly.margolin@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Signed-off-by: Koby Elbaz <koby.elbaz@intel.com>
This commit is contained in:
Vitaly Margolin
2025-09-25 09:09:25 +03:00
committed by Koby Elbaz
parent b4fd8e56c9
commit 5295be6c4e
2 changed files with 5 additions and 0 deletions
@@ -961,6 +961,9 @@ static int send_fw_generic_request(struct hl_device *hdev, struct hl_info_args *
case HL_PASSTHROUGH_VERSIONS:
need_input_buff = false;
break;
case HL_GET_ERR_COUNTERS_CMD:
need_input_buff = true;
break;
default:
return -EINVAL;
}
+2
View File
@@ -1425,9 +1425,11 @@ struct cpucp_monitor_dump {
* from "pkt_subidx" field in struct cpucp_packet.
*
* HL_PASSTHROUGHT_VERSIONS - Fetch all firmware versions.
* HL_GET_ERR_COUNTERS_CMD - Command to get error counters
*/
enum hl_passthrough_type {
HL_PASSTHROUGH_VERSIONS,
HL_GET_ERR_COUNTERS_CMD,
};
#endif /* CPUCP_IF_H */