From c36218dc49f5e9ef9e3074670fdae7ac3a7e794f Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi Date: Wed, 4 Mar 2026 13:14:08 +0530 Subject: drm/ras: Introduce the DRM RAS infrastructure over generic netlink Introduces the DRM RAS infrastructure over generic netlink. The new interface allows drivers to expose RAS nodes and their associated error counters to userspace in a structured and extensible way. Each drm_ras node can register its own set of error counters, which are then discoverable and queryable through netlink operations. This lays the groundwork for reporting and managing hardware error states in a unified manner across different DRM drivers. Currently it only supports error-counter nodes. But it can be extended later. The registration is also not tied to any drm node, so it can be used by accel devices as well. It uses the new and mandatory YAML description format stored in Documentation/netlink/specs/. This forces a single generic netlink family namespace for the entire drm: "drm-ras". But multiple-endpoints are supported within the single family. Any modification to this API needs to be applied to Documentation/netlink/specs/drm_ras.yaml before regenerating the code: $ tools/net/ynl/pyynl/ynl_gen_c.py --spec \ Documentation/netlink/specs/drm_ras.yaml --mode uapi --header \ -o include/uapi/drm/drm_ras.h $ tools/net/ynl/pyynl/ynl_gen_c.py --spec \ Documentation/netlink/specs/drm_ras.yaml --mode kernel \ --header -o drivers/gpu/drm/drm_ras_nl.h $ tools/net/ynl/pyynl/ynl_gen_c.py --spec \ Documentation/netlink/specs/drm_ras.yaml \ --mode kernel --source -o drivers/gpu/drm/drm_ras_nl.c Cc: Zack McKevitt Cc: Lijo Lazar Cc: Hawking Zhang Cc: Jakub Kicinski Cc: David S. Miller Cc: Paolo Abeni Cc: Eric Dumazet Cc: netdev@vger.kernel.org Co-developed-by: Aravind Iddamsetty Signed-off-by: Aravind Iddamsetty Signed-off-by: Riana Tauro Reviewed-by: Zack McKevitt Acked-by: Jakub Kicinski Acked-by: Maarten Lankhorst Link: https://patch.msgid.link/20260304074412.464435-8-riana.tauro@intel.com Signed-off-by: Rodrigo Vivi --- include/uapi/drm/drm_ras.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 include/uapi/drm/drm_ras.h (limited to 'include/uapi') diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h new file mode 100644 index 000000000000..5f40fa5b869d --- /dev/null +++ b/include/uapi/drm/drm_ras.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/drm_ras.yaml */ +/* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _UAPI_LINUX_DRM_RAS_H +#define _UAPI_LINUX_DRM_RAS_H + +#define DRM_RAS_FAMILY_NAME "drm-ras" +#define DRM_RAS_FAMILY_VERSION 1 + +/* + * Type of the node. Currently, only error-counter nodes are supported, which + * expose reliability counters for a hardware/software component. + */ +enum drm_ras_node_type { + DRM_RAS_NODE_TYPE_ERROR_COUNTER = 1, +}; + +enum { + DRM_RAS_A_NODE_ATTRS_NODE_ID = 1, + DRM_RAS_A_NODE_ATTRS_DEVICE_NAME, + DRM_RAS_A_NODE_ATTRS_NODE_NAME, + DRM_RAS_A_NODE_ATTRS_NODE_TYPE, + + __DRM_RAS_A_NODE_ATTRS_MAX, + DRM_RAS_A_NODE_ATTRS_MAX = (__DRM_RAS_A_NODE_ATTRS_MAX - 1) +}; + +enum { + DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID = 1, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_NAME, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_VALUE, + + __DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX, + DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1) +}; + +enum { + DRM_RAS_CMD_LIST_NODES = 1, + DRM_RAS_CMD_GET_ERROR_COUNTER, + + __DRM_RAS_CMD_MAX, + DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1) +}; + +#endif /* _UAPI_LINUX_DRM_RAS_H */ -- cgit v1.2.3