drm/drm_ras: Add clear-error-counter netlink command to drm_ras

Introduce a new 'clear-error-counter' drm_ras command to reset the counter
value for a specific error counter of a given node.

The command is a 'do' netlink request with 'node-id' and 'error-id'
as parameters with no response payload.

Usage:

$ sudo ynl --family drm_ras  --do clear-error-counter --json \
'{"node-id":1, "error-id":1}'
None

Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Zack McKevitt <zachary.mckevitt@oss.qualcomm.com>
Cc: Lijo Lazar <lijo.lazar@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://patch.msgid.link/20260409073318.2909379-5-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Maxime Ripard <mripard@redhat.com>

Documentation/gpu/drm-ras.rst

@@ -52,6 +52,8 @@ User space tools can:
   as a parameter.
 * Query specific error counter values with the ``get-error-counter`` command, using both
   ``node-id`` and ``error-id`` as parameters.
+* Clear specific error counters with the ``clear-error-counter`` command, using both
+  ``node-id`` and ``error-id`` as parameters.
 
 YAML-based Interface
 --------------------
@@ -101,3 +103,9 @@ Example: Query an error counter for a given node
     sudo ynl --family drm_ras --do get-error-counter --json '{"node-id":0, "error-id":1}'
     {'error-id': 1, 'error-name': 'error_name1', 'error-value': 0}
 
+Example: Clear an error counter for a given node
+
+.. code-block:: bash
+
+    sudo ynl --family drm_ras --do clear-error-counter --json '{"node-id":0, "error-id":1}'
+    None

Documentation/netlink/specs/drm_ras.yaml

@@ -99,7 +99,7 @@ operations:
       flags: [admin-perm]
       do:
         request:
-          attributes:
+          attributes: &id-attrs
             - node-id
             - error-id
         reply:
@@ -113,3 +113,14 @@ operations:
             - 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

drivers/gpu/drm/drm_ras.c

@@ -26,7 +26,7 @@
  * efficient lookup by ID. Nodes can be registered or unregistered
  * dynamically at runtime.
  *
- * A Generic Netlink family `drm_ras` exposes two main operations to
+ * A Generic Netlink family `drm_ras` exposes the below operations to
  * userspace:
  *
  * 1. LIST_NODES: Dump all currently registered RAS nodes.
@@ -37,6 +37,10 @@
  *    Returns all counters of a node if only Node ID is provided or specific
  *    error counters.
  *
+ * 3. CLEAR_ERROR_COUNTER: Clear error counter of a given node.
+ *    Userspace must provide Node ID, Error ID.
+ *    Clears specific error counter of a node if supported.
+ *
  * Node registration:
  *
  * - drm_ras_node_register(): Registers a new node and assigns
@@ -66,6 +70,8 @@
  *   operation, fetching all counters from a specific node.
  * - drm_ras_nl_get_error_counter_doit(): Implements the GET_ERROR_COUNTER doit
  *   operation, fetching a counter value from a specific node.
+ * - drm_ras_nl_clear_error_counter_doit(): Implements the CLEAR_ERROR_COUNTER doit
+ *   operation, clearing a counter value from a specific node.
  */
 
 static DEFINE_XARRAY_ALLOC(drm_ras_xa);
@@ -314,6 +320,41 @@ int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb,
 	return doit_reply_value(info, node_id, error_id);
 }
 
+/**
+ * drm_ras_nl_clear_error_counter_doit() - Clear an error counter of a node
+ * @skb: Netlink message buffer
+ * @info: Generic Netlink info containing attributes of the request
+ *
+ * Extracts the node ID and error ID from the netlink attributes and
+ * clears the current value.
+ *
+ * Return: 0 on success, or negative errno on failure.
+ */
+int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct drm_ras_node *node;
+	u32 node_id, error_id;
+
+	if (!info->attrs ||
+	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID) ||
+	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID))
+		return -EINVAL;
+
+	node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID]);
+	error_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID]);
+
+	node = xa_load(&drm_ras_xa, node_id);
+	if (!node || !node->clear_error_counter)
+		return -ENOENT;
+
+	if (error_id < node->error_counter_range.first ||
+	    error_id > node->error_counter_range.last)
+		return -EINVAL;
+
+	return node->clear_error_counter(node, error_id);
+}
+
 /**
  * drm_ras_node_register() - Register a new RAS node
  * @node: Node structure to register

drivers/gpu/drm/drm_ras_nl.c

@@ -22,6 +22,12 @@ static const struct nla_policy drm_ras_get_error_counter_dump_nl_policy[DRM_RAS_
 	[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID] = { .type = NLA_U32, },
 };
 
+/* DRM_RAS_CMD_CLEAR_ERROR_COUNTER - do */
+static const struct nla_policy drm_ras_clear_error_counter_nl_policy[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID + 1] = {
+	[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID] = { .type = NLA_U32, },
+	[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID] = { .type = NLA_U32, },
+};
+
 /* Ops table for drm_ras */
 static const struct genl_split_ops drm_ras_nl_ops[] = {
 	{
@@ -43,6 +49,13 @@ static const struct genl_split_ops drm_ras_nl_ops[] = {
 		.maxattr	= DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DRM_RAS_CMD_CLEAR_ERROR_COUNTER,
+		.doit		= drm_ras_nl_clear_error_counter_doit,
+		.policy		= drm_ras_clear_error_counter_nl_policy,
+		.maxattr	= DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
 
 struct genl_family drm_ras_nl_family __ro_after_init = {

drivers/gpu/drm/drm_ras_nl.h

@@ -18,6 +18,8 @@ int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb,
 				      struct genl_info *info);
 int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb,
 					struct netlink_callback *cb);
+int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb,
+					struct genl_info *info);
 
 extern struct genl_family drm_ras_nl_family;
 

include/drm/drm_ras.h

@@ -58,6 +58,17 @@ struct drm_ras_node {
 	int (*query_error_counter)(struct drm_ras_node *node, u32 error_id,
 				   const char **name, u32 *val);
 
+	/**
+	 * @clear_error_counter:
+	 *
+	 * This callback is used by drm_ras to clear a specific error counter.
+	 * Driver should implement this callback to support clearing error counters
+	 * of a node.
+	 *
+	 * Returns: 0 on success, negative error code on failure.
+	 */
+	int (*clear_error_counter)(struct drm_ras_node *node, u32 error_id);
+
 	/** @priv: Driver private data */
 	void *priv;
 };

include/uapi/drm/drm_ras.h

@@ -41,6 +41,7 @@ enum {
 enum {
 	DRM_RAS_CMD_LIST_NODES = 1,
 	DRM_RAS_CMD_GET_ERROR_COUNTER,
+	DRM_RAS_CMD_CLEAR_ERROR_COUNTER,
 
 	__DRM_RAS_CMD_MAX,
 	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)