Documentation/netlink/specs/drm_ras.yaml

# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
---
name: drm-ras
protocol: genetlink
uapi-header: drm/drm_ras.h

doc: >-
  DRM RAS (Reliability, Availability, Serviceability) over Generic Netlink.
  Provides a standardized mechanism for DRM drivers to register "nodes"
  representing hardware/software components capable of reporting error counters.
  Userspace tools can query the list of nodes or individual error counters
  via the Generic Netlink interface.

definitions:
  -
    type: enum
    name: node-type
    value-start: 1
    entries: [error-counter]
    doc: >-
         Type of the node. Currently, only error-counter nodes are
         supported, which expose reliability counters for a hardware/software
         component.

attribute-sets:
  -
    name: node-attrs
    attributes:
      -
        name: node-id
        type: u32
        doc: >-
             Unique identifier for the node.
             Assigned dynamically by the DRM RAS core upon registration.
      -
        name: device-name
        type: string
        doc: >-
             Device name chosen by the driver at registration.
             Can be a PCI BDF, UUID, or module name if unique.
      -
        name: node-name
        type: string
        doc: >-
             Node name chosen by the driver at registration.
             Can be an IP block name, or any name that identifies the
             RAS node inside the device.
      -
        name: node-type
        type: u32
        doc: Type of this node, identifying its function.
        enum: node-type
  -
    name: error-counter-attrs
    attributes:
      -
        name: node-id
        type: u32
        doc: Node ID targeted by this error counter operation.
      -
        name: error-id
        type: u32
        doc: Unique identifier for a specific error counter within an node.
      -
        name: error-name
        type: string
        doc: Name of the error.
      -
        name: error-value
        type: u32
        doc: Current value of the requested error counter.

operations:
  list:
    -
      name: list-nodes
      doc: >-
           Retrieve the full list of currently registered DRM RAS nodes.
           Each node includes its dynamically assigned ID, name, and type.
           **Important:** User space must call this operation first to obtain
           the node IDs. These IDs are required for all subsequent
           operations on nodes, such as querying error counters.
      attribute-set: node-attrs
      flags: [admin-perm]
      dump:
        reply:
          attributes:
            - node-id
            - device-name
            - node-name
            - node-type
    -
      name: get-error-counter
      doc: >-
           Retrieve error counter for a given node.
           The response includes the id, the name, and even the current
           value of each counter.
      attribute-set: error-counter-attrs
      flags: [admin-perm]
      do:
        request:
          attributes: &id-attrs
            - node-id
            - error-id
        reply:
          attributes: &errorinfo
            - error-id
            - error-name
            - error-value
      dump:
        request:
          attributes:
            - node-id
        reply:
          attributes: *errorinfo
    -
      name: clear-error-counter
      doc: >-
           Clear error counter for a given node.
           The request includes the error-id and node-id of the
           counter to be cleared.
      attribute-set: error-counter-attrs
      flags: [admin-perm]
      do:
        request:
          attributes: *id-attrs