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>

diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
index dc80ca921d908d89da12460afaea11aaecb19417..ed0dee5aa9be66576fea0d6d5f72e94cf3248fca 100644 (file)
--- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
@@ -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;
        }

diff --git a/include/linux/habanalabs/cpucp_if.h b/include/linux/habanalabs/cpucp_if.h
index 7ed3fdd55dda531efa5d9607560e320b78eeaa34..29c50e7427d1b880121c2d1d11a339e537d51d70 100644 (file)
--- a/include/linux/habanalabs/cpucp_if.h
+++ b/include/linux/habanalabs/cpucp_if.h
@@ -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 */