[PATCH 3/4] drm/drm_ras: Add DRM RAS netlink error event notification

[Riana Tauro <riana.tauro@intel.com>]

Add support for asynchronous error notifications in drm_ras.

Define a new `error-event` netlink event and a new multicast
group `error-notify` in drm_ras spec. Each event contains
a node-id and error-id to identify the type and source
of error.

Add drm_ras_error_notify() to trigger this event from drivers.
Userspace can receive this event by subscribing to the
multicast group error-notify.

Example: Using ynl tool

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

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>
---
 Documentation/gpu/drm-ras.rst            |  9 +++++
 Documentation/netlink/specs/drm_ras.yaml | 14 +++++++
 drivers/gpu/drm/drm_ras.c                | 48 ++++++++++++++++++++++++
 drivers/gpu/drm/drm_ras_nl.c             |  6 +++
 drivers/gpu/drm/drm_ras_nl.h             |  4 ++
 include/drm/drm_ras.h                    |  2 +
 include/uapi/drm/drm_ras.h               |  3 ++
 7 files changed, 86 insertions(+)

diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst
index 4636e68f5678..09b2918f67bd 100644
--- a/Documentation/gpu/drm-ras.rst
+++ b/Documentation/gpu/drm-ras.rst
@@ -54,6 +54,8 @@ 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.
+* Listen to ``error-event`` notifications for error events by subscribing to the
+  ``error-notify`` multicast group.
 
 YAML-based Interface
 --------------------
@@ -109,3 +111,10 @@ 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: Listen to error events
+
+.. code-block:: bash
+
+    sudo ynl --family drm_ras --subscribe error-notify
+    {'msg': {'error-id': 1, 'node-id': 1}, 'name': 'error-event'}
diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
index e113056f8c01..4dc047be59e9 100644
--- a/Documentation/netlink/specs/drm_ras.yaml
+++ b/Documentation/netlink/specs/drm_ras.yaml
@@ -124,3 +124,17 @@ operations:
       do:
         request:
           attributes: *id-attrs
+    -
+      name: error-event
+      doc: >-
+           Notify userspace of an error event.
+           The event includes the error-id and node-id of the error
+           that triggered the event.
+      attribute-set: error-counter-attrs
+      event:
+        attributes: *id-attrs
+
+mcast-groups:
+  list:
+    -
+      name: error-notify
diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
index d6eab29a1394..36a3a79cbbea 100644
--- a/drivers/gpu/drm/drm_ras.c
+++ b/drivers/gpu/drm/drm_ras.c
@@ -41,6 +41,10 @@
  *    Userspace must provide Node ID, Error ID.
  *    Clears specific error counter of a node if supported.
  *
+ * 4. ERROR_EVENT: Notify userspace of an error event.
+ *    The event includes the error-id and node-id of the error
+ *    that triggered the event.
+ *
  * Node registration:
  *
  * - drm_ras_node_register(): Registers a new node and assigns
@@ -355,6 +359,50 @@ int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb,
 	return node->clear_error_counter(node, error_id);
 }
 
+/**
+ * drm_ras_error_notify() - Notify userspace of an error event
+ * @node: Node structure
+ * @error_id: ID of the error counter that triggered the event
+ * @flags: GFP flags for memory allocation
+ *
+ * Notifies userspace of an error event related to a specific RAS node and error counter.
+ */
+void drm_ras_error_notify(struct drm_ras_node *node, u32 error_id, gfp_t flags)
+{
+	struct genl_info info;
+	struct sk_buff *msg;
+	struct nlattr *hdr;
+	int ret;
+
+	genl_info_init_ntf(&info, &drm_ras_nl_family, DRM_RAS_CMD_ERROR_EVENT);
+
+	msg = genlmsg_new(NLMSG_GOODSIZE, flags);
+	if (!msg)
+		return;
+
+	hdr = genlmsg_iput(msg, &info);
+	if (!hdr)
+		goto err_free;
+
+	ret = nla_put_u32(msg, DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID, node->id);
+	if (ret)
+		goto err_cancel;
+
+	ret = nla_put_u32(msg, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID, error_id);
+	if (ret)
+		goto err_cancel;
+
+	genlmsg_end(msg, hdr);
+	genlmsg_multicast(&drm_ras_nl_family, msg, 0, DRM_RAS_NLGRP_ERROR_NOTIFY, flags);
+	return;
+
+err_cancel:
+	genlmsg_cancel(msg, hdr);
+err_free:
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(drm_ras_error_notify);
+
 /**
  * drm_ras_node_register() - Register a new RAS node
  * @node: Node structure to register
diff --git a/drivers/gpu/drm/drm_ras_nl.c b/drivers/gpu/drm/drm_ras_nl.c
index dea1c1b2494e..ac724bb87a3b 100644
--- a/drivers/gpu/drm/drm_ras_nl.c
+++ b/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_NOTIFY] = { "error-notify", },
+};
+
 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),
 };
diff --git a/drivers/gpu/drm/drm_ras_nl.h b/drivers/gpu/drm/drm_ras_nl.h
index a398643572a5..17e1af8cc3b3 100644
--- a/drivers/gpu/drm/drm_ras_nl.h
+++ b/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_NOTIFY,
+};
+
 extern struct genl_family drm_ras_nl_family;
 
 #endif /* _LINUX_DRM_RAS_GEN_H */
diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
index f2a787bc4f64..a2d4f257c9c2 100644
--- a/include/drm/drm_ras.h
+++ b/include/drm/drm_ras.h
@@ -78,9 +78,11 @@ 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);
+void drm_ras_error_notify(struct drm_ras_node *node, u32 error_id, gfp_t flags);
 #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 void drm_ras_error_notify(struct drm_ras_node *node, u32 error_id, gfp_t flags) { }
 #endif
 
 #endif
diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
index 218a3ee86805..47fafeff93e7 100644
--- a/include/uapi/drm/drm_ras.h
+++ b/include/uapi/drm/drm_ras.h
@@ -42,9 +42,12 @@ 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_NOTIFY	"error-notify"
+
 #endif /* _UAPI_LINUX_DRM_RAS_H */
-- 
2.47.1