drm/drm_ras: Add drm_ras netlink error event

Define a new netlink event 'error-event' and a new multicast group
'error-report' in drm_ras. Each event contains device name, node and
error information to identify the error triggering the event.

Add drm_ras_nl_error_event() to trigger an event from the driver.
Userspace must subscribe to 'error-report' to receive 'error-event'
notifications.

Usage:

$ sudo ynl --family drm_ras --subscribe error-report

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: Raag Jadav <raag.jadav@intel.com>
Link: https://patch.msgid.link/20260810112008.1858731-5-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

Documentation/gpu/drm-ras.rst

@@ -56,6 +56,7 @@ User space tools can:
   ``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.
+* Subscribe to the ``error-report`` multicast group to receive ``error-event``.
 
 YAML-based Interface
 --------------------
@@ -111,3 +112,23 @@ Example: Clear an error counter for a given node
 
     sudo ynl --family drm_ras --do clear-error-counter --json '{"node-id":0, "error-id":1}'
     None
+
+Example: Subscribe to ``error-report`` multicast group
+
+.. code-block:: bash
+
+    sudo ynl --family drm_ras --output-json --subscribe error-report
+
+.. code-block:: json
+
+    {
+        "name": "error-event",
+        "msg": {
+            "device-name": "0000:03:00.0",
+            "node-id": 1,
+            "node-name": "uncorrectable-errors",
+            "error-id": 1,
+            "error-name": "error_name1",
+            "error-value": 1
+        }
+    }

Documentation/netlink/specs/drm_ras.yaml

@@ -69,6 +69,33 @@ attribute-sets:
         name: error-value
         type: u32
         doc: Current value of the requested error counter.
+  -
+    name: error-event-attrs
+    attributes:
+      -
+        name: device-name
+        type: string
+        doc: Device (PCI BDF, UUID) that reported the error.
+      -
+        name: node-id
+        type: u32
+        doc: ID of the node that reported the error.
+      -
+        name: node-name
+        type: string
+        doc: Name of the node that reported the error.
+      -
+        name: error-id
+        type: u32
+        doc: ID of the error counter.
+      -
+        name: error-name
+        type: string
+        doc: Name of the error.
+      -
+        name: error-value
+        type: u32
+        doc: Current value of the error counter.
 
 operations:
   list:
@@ -124,3 +151,24 @@ operations:
       do:
         request:
           attributes: *id-attrs
+    -
+      name: error-event
+      doc: >-
+           Report an error event to userspace.
+           The event includes the device, node and error information
+           of the error that triggered the event.
+      attribute-set: error-event-attrs
+      mcgrp: error-report
+      event:
+        attributes:
+          - device-name
+          - node-id
+          - node-name
+          - error-id
+          - error-name
+          - error-value
+
+mcast-groups:
+  list:
+    -
+      name: error-report

drivers/gpu/drm/drm_ras.c

@@ -41,6 +41,11 @@
  *    Userspace must provide Node ID, Error ID.
  *    Clears specific error counter of a node if supported.
  *
+ * 4. ERROR_REPORT: Subscribe to this multicast group to receive error events
+ *
+ * 5. ERROR_EVENT: Report an error event to userspace. The event contains device, node
+ *    and error information that triggered the event.
+ *
  * Node registration:
  *
  * - drm_ras_node_register(): Registers a new node and assigns
@@ -186,6 +191,34 @@ static int msg_reply_value(struct sk_buff *msg, u32 error_id,
 			   value);
 }
 
+static int msg_put_error_event_attrs(struct sk_buff *msg, struct drm_ras_node *node,
+				     u32 error_id, const char *error_name, u32 value)
+{
+	int ret;
+
+	ret = nla_put_string(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_DEVICE_NAME, node->device_name);
+	if (ret)
+		return ret;
+
+	ret = nla_put_u32(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_ID, node->id);
+	if (ret)
+		return ret;
+
+	ret = nla_put_string(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_NAME, node->node_name);
+	if (ret)
+		return ret;
+
+	ret = nla_put_u32(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_ID, error_id);
+	if (ret)
+		return ret;
+
+	ret = nla_put_string(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_NAME, error_name);
+	if (ret)
+		return ret;
+
+	return nla_put_u32(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_VALUE, value);
+}
+
 static int doit_reply_value(struct genl_info *info, u32 node_id,
 			    u32 error_id)
 {
@@ -222,6 +255,74 @@ static int doit_reply_value(struct genl_info *info, u32 node_id,
 	return genlmsg_reply(msg, info);
 }
 
+/**
+ * drm_ras_nl_error_event() - Report an error event
+ * @node: Node structure
+ * @error_id: ID of the error
+ * @error_name: Name of the error
+ * @value: Value of the error counter
+ *
+ * Report an error-event to userspace using the error-report multicast group.
+ *
+ * Context: Process context only. Uses %GFP_KERNEL and multicasts to all
+ *          netns, which is unbounded work; callers in interrupt handlers
+ *          or other atomic context must defer event.
+ *
+ * Return: 0 on success, or negative errno on failure.
+ */
+int drm_ras_nl_error_event(struct drm_ras_node *node, u32 error_id, const char *error_name,
+			   u32 value)
+{
+	struct genl_info info;
+	struct sk_buff *msg;
+	struct nlattr *hdr;
+	int ret;
+
+	if (!node || !error_name)
+		return -EINVAL;
+
+	/* Check the node is currently registered */
+	if (xa_load(&drm_ras_xa, node->id) != node)
+		return -ENOENT;
+
+	/* Currently only Error Counter events are supported */
+	if (node->type != DRM_RAS_NODE_TYPE_ERROR_COUNTER)
+		return -EOPNOTSUPP;
+
+	/* Check the error ID is within the valid range */
+	if (error_id < node->error_counter_range.first ||
+	    error_id > node->error_counter_range.last)
+		return -EINVAL;
+
+	genl_info_init_ntf(&info, &drm_ras_nl_family, DRM_RAS_CMD_ERROR_EVENT);
+
+	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(msg, &info);
+	if (!hdr) {
+		ret = -EMSGSIZE;
+		goto free_msg;
+	}
+
+	ret = msg_put_error_event_attrs(msg, node, error_id, error_name, value);
+	if (ret)
+		goto cancel_msg;
+
+	genlmsg_end(msg, hdr);
+	genlmsg_multicast_allns(&drm_ras_nl_family, msg, 0, DRM_RAS_NLGRP_ERROR_REPORT);
+
+	return 0;
+
+cancel_msg:
+	genlmsg_cancel(msg, hdr);
+free_msg:
+	nlmsg_free(msg);
+	return ret;
+}
+EXPORT_SYMBOL(drm_ras_nl_error_event);
+
 /**
  * drm_ras_nl_get_error_counter_dumpit() - Dump all Error Counters
  * @skb: Netlink message buffer

drivers/gpu/drm/drm_ras_nl.c

@@ -58,6 +58,10 @@ static const struct genl_split_ops drm_ras_nl_ops[] = {
 	},
 };
 
+static const struct genl_multicast_group drm_ras_nl_mcgrps[] = {
+	[DRM_RAS_NLGRP_ERROR_REPORT] = { "error-report", },
+};
+
 struct genl_family drm_ras_nl_family __ro_after_init = {
 	.name		= DRM_RAS_FAMILY_NAME,
 	.version	= DRM_RAS_FAMILY_VERSION,
@@ -66,4 +70,6 @@ struct genl_family drm_ras_nl_family __ro_after_init = {
 	.module		= THIS_MODULE,
 	.split_ops	= drm_ras_nl_ops,
 	.n_split_ops	= ARRAY_SIZE(drm_ras_nl_ops),
+	.mcgrps		= drm_ras_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(drm_ras_nl_mcgrps),
 };

drivers/gpu/drm/drm_ras_nl.h

@@ -21,6 +21,10 @@ int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb,
 int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb,
 					struct genl_info *info);
 
+enum {
+	DRM_RAS_NLGRP_ERROR_REPORT,
+};
+
 extern struct genl_family drm_ras_nl_family;
 
 #endif /* _LINUX_DRM_RAS_GEN_H */

include/drm/drm_ras.h

@@ -80,9 +80,14 @@ struct drm_device;
 #if IS_ENABLED(CONFIG_DRM_RAS)
 int drm_ras_node_register(struct drm_ras_node *node);
 void drm_ras_node_unregister(struct drm_ras_node *node);
+int drm_ras_nl_error_event(struct drm_ras_node *node, u32 error_id, const char *error_name,
+			   u32 value);
 #else
 static inline int drm_ras_node_register(struct drm_ras_node *node) { return 0; }
 static inline void drm_ras_node_unregister(struct drm_ras_node *node) { }
+static inline int drm_ras_nl_error_event(struct drm_ras_node *node, u32 error_id,
+					 const char *error_name, u32 value)
+{ return 0; }
 #endif
 
 #endif

include/uapi/drm/drm_ras.h

@@ -38,13 +38,28 @@ enum {
 	DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1)
 };
 
+enum {
+	DRM_RAS_A_ERROR_EVENT_ATTRS_DEVICE_NAME = 1,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_ID,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_NAME,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_ID,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_NAME,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_VALUE,
+
+	__DRM_RAS_A_ERROR_EVENT_ATTRS_MAX,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_MAX = (__DRM_RAS_A_ERROR_EVENT_ATTRS_MAX - 1)
+};
+
 enum {
 	DRM_RAS_CMD_LIST_NODES = 1,
 	DRM_RAS_CMD_GET_ERROR_COUNTER,
 	DRM_RAS_CMD_CLEAR_ERROR_COUNTER,
+	DRM_RAS_CMD_ERROR_EVENT,
 
 	__DRM_RAS_CMD_MAX,
 	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)
 };
 
+#define DRM_RAS_MCGRP_ERROR_REPORT	"error-report"
+
 #endif /* _UAPI_LINUX_DRM_RAS_H */