[PATCH 0/2] Add drm_ras netlink error event support

[PATCH 0/2] Add drm_ras netlink error event support

[Riana Tauro]

Define a new netlink event 'error-event' and a new multicast group
'error-notify' 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.
Wire this support to xe drm_ras to notify userspace whenever a GT or
SoC error occurs in PVC.

$ sudo ./tools/net/ynl/pyynl/cli.py --family drm_ras --output-json \
--subscribe error-notify

{
    "name": "error-event",
     "msg": {
         "device-name": "0000:03:00.0",
         "node-id": 1,
         "node-name": "uncorrectable-errors",
         "error-id": 1,
         "error-name": "core-compute",
         "error-value": 1
     }
}

Riana Tauro (2):
  drm/drm_ras: Add drm_ras netlink error event
  drm/xe/xe_drm_ras: Add error-event support in XE drm_ras

 Documentation/gpu/drm-ras.rst            | 21 ++++++
 Documentation/netlink/specs/drm_ras.yaml | 50 ++++++++++++++
 drivers/gpu/drm/drm_ras.c                | 86 ++++++++++++++++++++++++
 drivers/gpu/drm/drm_ras_nl.c             |  6 ++
 drivers/gpu/drm/drm_ras_nl.h             |  4 ++
 drivers/gpu/drm/xe/xe_drm_ras.c          | 29 ++++++++
 drivers/gpu/drm/xe/xe_drm_ras.h          |  6 ++
 drivers/gpu/drm/xe/xe_hw_error.c         |  7 +-
 include/drm/drm_ras.h                    |  5 ++
 include/uapi/drm/drm_ras.h               | 15 +++++
 10 files changed, 228 insertions(+), 1 deletion(-)

-- 
2.47.1

[PATCH 1/2] drm/drm_ras: Add drm_ras netlink error event

[Riana Tauro]

Define a new netlink event 'error-event' and a new multicast group
'error-notify' 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-notify' to receive 'error-event'
notifications.

Usage:

    $ sudo ./tools/net/ynl/pyynl/cli.py --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            | 21 ++++++
 Documentation/netlink/specs/drm_ras.yaml | 50 ++++++++++++++
 drivers/gpu/drm/drm_ras.c                | 86 ++++++++++++++++++++++++
 drivers/gpu/drm/drm_ras_nl.c             |  6 ++
 drivers/gpu/drm/drm_ras_nl.h             |  4 ++
 include/drm/drm_ras.h                    |  5 ++
 include/uapi/drm/drm_ras.h               | 15 +++++
 7 files changed, 187 insertions(+)

diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst
index 83c21853b74b..5a96dde75539 100644
--- a/Documentation/gpu/drm-ras.rst
+++ b/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-notify`` multicast group to receive ``error-event`` notifications.
 
 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-notify`` multicast group
+
+.. code-block:: bash
+
+    sudo ./tools/net/ynl/pyynl/cli.py --family drm_ras --output-json --subscribe error-notify
+
+.. 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
+        }
+    }
diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
index e113056f8c01..d94c73a61aea 100644
--- a/Documentation/netlink/specs/drm_ras.yaml
+++ b/Documentation/netlink/specs/drm_ras.yaml
@@ -69,6 +69,35 @@ 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 name chosen by the driver at registration.
+             Can be a PCI BDF, UUID, or module name if unique.
+      -
+        name: node-id
+        type: u32
+        doc: Node ID of the node that triggered the event.
+      -
+        name: node-name
+        type: string
+        doc: Node name of the node that triggered the event.
+      -
+        name: error-id
+        type: u32
+        doc: Error ID of the counter that triggered the event.
+      -
+        name: error-name
+        type: string
+        doc: Name of the error that triggered the event.
+      -
+        name: error-value
+        type: u32
+        doc: Current value of the error counter.
 
 operations:
   list:
@@ -124,3 +153,24 @@ operations:
       do:
         request:
           attributes: *id-attrs
+    -
+      name: error-event
+      doc: >-
+           Notify userspace of an error event.
+           The event includes the device, node and error information
+           of the error that triggered the event.
+      attribute-set: error-event-attrs
+      mcgrp: error-notify
+      event:
+        attributes:
+          - device-name
+          - node-id
+          - node-name
+          - error-id
+          - error-name
+          - error-value
+
+mcast-groups:
+  list:
+    -
+      name: error-notify
diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
index d6eab29a1394..6696ec21782e 100644
--- a/drivers/gpu/drm/drm_ras.c
+++ b/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_NOTIFY: Subscribe to this multicast group to receive error events
+ *
+ * 5. ERROR_EVENT: Notify userspace of an error event. 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 +255,59 @@ static int doit_reply_value(struct genl_info *info, u32 node_id,
 	return genlmsg_reply(msg, info);
 }
 
+/**
+ * drm_ras_nl_error_event() - Notify listeners of an error event
+ * @node: Node structure
+ * @error_id: ID of the error
+ * @error_name: Name of the error
+ * @value: Value associated with the error
+ * @flags: GFP flags for memory allocation
+ *
+ * Sends a notification to all listeners about an error event on a specific
+ * RAS node.
+ *
+ * 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, gfp_t flags)
+{
+	struct genl_info info;
+	struct sk_buff *msg;
+	struct nlattr *hdr;
+	int err = -EMSGSIZE;
+
+	if (!error_name)
+		return -EINVAL;
+
+	if (!genl_has_listeners(&drm_ras_nl_family, &init_net, DRM_RAS_NLGRP_ERROR_NOTIFY))
+		return 0;
+
+	genl_info_init_ntf(&info, &drm_ras_nl_family, DRM_RAS_CMD_ERROR_EVENT);
+
+	msg = genlmsg_new(NLMSG_GOODSIZE, flags);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(msg, &info);
+	if (!hdr)
+		goto err_free_msg;
+
+	err = msg_put_error_event_attrs(msg, node, error_id, error_name, value);
+	if (err)
+		goto err_cancel;
+
+	genlmsg_end(msg, hdr);
+	genlmsg_multicast(&drm_ras_nl_family, msg, 0, DRM_RAS_NLGRP_ERROR_NOTIFY, flags);
+	return 0;
+
+err_cancel:
+	genlmsg_cancel(msg, hdr);
+err_free_msg:
+	nlmsg_free(msg);
+	return err;
+}
+EXPORT_SYMBOL(drm_ras_nl_error_event);
+
 /**
  * drm_ras_nl_get_error_counter_dumpit() - Dump all Error Counters
  * @skb: Netlink message buffer
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..d4a275efdbb0 100644
--- a/include/drm/drm_ras.h
+++ b/include/drm/drm_ras.h
@@ -78,9 +78,14 @@ 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, 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 int drm_ras_nl_error_event(struct drm_ras_node *node, u32 error_id,
+					 const char *error_name, u32 value, gfp_t flags)
+{ return 0; }
 #endif
 
 #endif
diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
index 218a3ee86805..bb2a8a872a44 100644
--- a/include/uapi/drm/drm_ras.h
+++ b/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_NOTIFY	"error-notify"
+
 #endif /* _UAPI_LINUX_DRM_RAS_H */
-- 
2.47.1

Re: [PATCH 1/2] drm/drm_ras: Add drm_ras netlink error event

[Raag Jadav]

On Mon, May 18, 2026 at 04:50:50PM +0530, Riana Tauro wrote:
> Define a new netlink event 'error-event' and a new multicast group
> 'error-notify' 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-notify' to receive 'error-event'
> notifications.
> 
> Usage:
> 
>     $ sudo ./tools/net/ynl/pyynl/cli.py --family drm_ras \

Nit: Make the leading space consistent with other patches.

>       --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            | 21 ++++++
>  Documentation/netlink/specs/drm_ras.yaml | 50 ++++++++++++++
>  drivers/gpu/drm/drm_ras.c                | 86 ++++++++++++++++++++++++
>  drivers/gpu/drm/drm_ras_nl.c             |  6 ++
>  drivers/gpu/drm/drm_ras_nl.h             |  4 ++
>  include/drm/drm_ras.h                    |  5 ++
>  include/uapi/drm/drm_ras.h               | 15 +++++
>  7 files changed, 187 insertions(+)
> 
> diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst
> index 83c21853b74b..5a96dde75539 100644
> --- a/Documentation/gpu/drm-ras.rst
> +++ b/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-notify`` multicast group to receive ``error-event`` notifications.
>  
>  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-notify`` multicast group
> +
> +.. code-block:: bash
> +
> +    sudo ./tools/net/ynl/pyynl/cli.py --family drm_ras --output-json --subscribe error-notify

So ynl can't do this? If yes, make it consistent with other commands
(and also in commit message). If no, please document it.

> +
> +.. 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
> +        }
> +    }
> diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
> index e113056f8c01..d94c73a61aea 100644
> --- a/Documentation/netlink/specs/drm_ras.yaml
> +++ b/Documentation/netlink/specs/drm_ras.yaml
> @@ -69,6 +69,35 @@ 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 name chosen by the driver at registration.
> +             Can be a PCI BDF, UUID, or module name if unique.
> +      -
> +        name: node-id

Curious, can we reuse existing partial attr-set?

> +        type: u32
> +        doc: Node ID of the node that triggered the event.
> +      -
> +        name: node-name
> +        type: string
> +        doc: Node name of the node that triggered the event.
> +      -
> +        name: error-id
> +        type: u32
> +        doc: Error ID of the counter that triggered the event.
> +      -
> +        name: error-name
> +        type: string
> +        doc: Name of the error that triggered the event.
> +      -
> +        name: error-value
> +        type: u32
> +        doc: Current value of the error counter.
>  
>  operations:
>    list:
> @@ -124,3 +153,24 @@ operations:
>        do:
>          request:
>            attributes: *id-attrs
> +    -
> +      name: error-event
> +      doc: >-
> +           Notify userspace of an error event.
> +           The event includes the device, node and error information
> +           of the error that triggered the event.
> +      attribute-set: error-event-attrs
> +      mcgrp: error-notify
> +      event:
> +        attributes:
> +          - device-name
> +          - node-id
> +          - node-name
> +          - error-id
> +          - error-name
> +          - error-value
> +
> +mcast-groups:
> +  list:
> +    -
> +      name: error-notify
> diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
> index d6eab29a1394..6696ec21782e 100644
> --- a/drivers/gpu/drm/drm_ras.c
> +++ b/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_NOTIFY: Subscribe to this multicast group to receive error events
> + *
> + * 5. ERROR_EVENT: Notify userspace of an error event. 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 +255,59 @@ static int doit_reply_value(struct genl_info *info, u32 node_id,
>  	return genlmsg_reply(msg, info);
>  }
>  
> +/**
> + * drm_ras_nl_error_event() - Notify listeners of an error event
> + * @node: Node structure
> + * @error_id: ID of the error
> + * @error_name: Name of the error
> + * @value: Value associated with the error
> + * @flags: GFP flags for memory allocation
> + *
> + * Sends a notification to all listeners about an error event on a specific
> + * RAS node.
> + *
> + * 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, gfp_t flags)
> +{
> +	struct genl_info info;
> +	struct sk_buff *msg;
> +	struct nlattr *hdr;
> +	int err = -EMSGSIZE;

Redundant initialization, see below.

> +	if (!error_name)
> +		return -EINVAL;
> +
> +	if (!genl_has_listeners(&drm_ras_nl_family, &init_net, DRM_RAS_NLGRP_ERROR_NOTIFY))
> +		return 0;
> +
> +	genl_info_init_ntf(&info, &drm_ras_nl_family, DRM_RAS_CMD_ERROR_EVENT);
> +	msg = genlmsg_new(NLMSG_GOODSIZE, flags);
> +	if (!msg)
> +		return -ENOMEM;
> +
> +	hdr = genlmsg_iput(msg, &info);

Make this part of below and return err directly.

> +	if (!hdr)
> +		goto err_free_msg;
> +
> +	err = msg_put_error_event_attrs(msg, node, error_id, error_name, value);
> +	if (err)
> +		goto err_cancel;
> +
> +	genlmsg_end(msg, hdr);
> +	genlmsg_multicast(&drm_ras_nl_family, msg, 0, DRM_RAS_NLGRP_ERROR_NOTIFY, flags);
> +	return 0;
> +
> +err_cancel:
> +	genlmsg_cancel(msg, hdr);
> +err_free_msg:
> +	nlmsg_free(msg);
> +	return err;
> +}
> +EXPORT_SYMBOL(drm_ras_nl_error_event);
> +
>  /**
>   * drm_ras_nl_get_error_counter_dumpit() - Dump all Error Counters
>   * @skb: Netlink message buffer
> 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..d4a275efdbb0 100644
> --- a/include/drm/drm_ras.h
> +++ b/include/drm/drm_ras.h
> @@ -78,9 +78,14 @@ 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, 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 int drm_ras_nl_error_event(struct drm_ras_node *node, u32 error_id,
> +					 const char *error_name, u32 value, gfp_t flags)
> +{ return 0; }
>  #endif
>  
>  #endif
> diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
> index 218a3ee86805..bb2a8a872a44 100644
> --- a/include/uapi/drm/drm_ras.h
> +++ b/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_NOTIFY	"error-notify"

Where is this used?

Raag

>  #endif /* _UAPI_LINUX_DRM_RAS_H */
> -- 
> 2.47.1
> 

[PATCH 2/2] drm/xe/xe_drm_ras: Add error-event support in XE drm_ras

[Riana Tauro]

Add error-event support in XE drm_ras to notify userspace
whenever a GT or SoC error occurs.

$ sudo ./tools/net/ynl/pyynl/cli.py --family drm_ras --output-json \
--subscribe error-notify

{
    "name": "error-event",
     "msg": {
         "device-name": "0000:03:00.0",
         "node-id": 1,
         "node-name": "uncorrectable-errors",
         "error-id": 1,
         "error-name": "core-compute",
         "error-value": 1
     }
}

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
---
 drivers/gpu/drm/xe/xe_drm_ras.c  | 29 +++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_drm_ras.h  |  6 ++++++
 drivers/gpu/drm/xe/xe_hw_error.c |  7 ++++++-
 3 files changed, 41 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
index c21c8b428de6..68d9f561d61d 100644
--- a/drivers/gpu/drm/xe/xe_drm_ras.c
+++ b/drivers/gpu/drm/xe/xe_drm_ras.c
@@ -181,6 +181,35 @@ static void xe_drm_ras_unregister_nodes(struct drm_device *device, void *arg)
 	}
 }
 
+/**
+ * xe_drm_ras_event() - Notify userspace of an error event
+ * @xe: xe device structure
+ * @error_id: error id
+ * @severity: error severity
+ * @flags: flags for allocation
+ *
+ * Notifies userspace of an error.
+ */
+void xe_drm_ras_event(struct xe_device *xe, u32 error_id,
+		      enum drm_xe_ras_error_severity severity, gfp_t flags)
+{
+	struct xe_drm_ras *ras = &xe->ras;
+	struct drm_ras_node *node = &ras->node[severity];
+	struct xe_drm_ras_counter *info = ras->info[severity];
+	u32 value;
+	int ret;
+
+	if (!info || !info[error_id].name)
+		return;
+
+	value = atomic_read(&info[error_id].counter);
+
+	ret = drm_ras_nl_error_event(node, error_id, info[error_id].name, value, flags);
+	if (ret)
+		drm_err(&xe->drm, "Failed to send RAS error event for error %s: %d\n",
+			info[error_id].name, ret);
+}
+
 /**
  * xe_drm_ras_init() - Initialize DRM RAS
  * @xe: xe device instance
diff --git a/drivers/gpu/drm/xe/xe_drm_ras.h b/drivers/gpu/drm/xe/xe_drm_ras.h
index 365c70e93e82..b9b8b541d591 100644
--- a/drivers/gpu/drm/xe/xe_drm_ras.h
+++ b/drivers/gpu/drm/xe/xe_drm_ras.h
@@ -5,11 +5,17 @@
 #ifndef _XE_DRM_RAS_H_
 #define _XE_DRM_RAS_H_
 
+#include <linux/types.h>
+
+#include <drm/xe_drm.h>
+
 struct xe_device;
 
 #define for_each_error_severity(i)	\
 	for (i = 0; i < DRM_XE_RAS_ERR_SEV_MAX; i++)
 
 int xe_drm_ras_init(struct xe_device *xe);
+void xe_drm_ras_event(struct xe_device *xe, u32 error_id,
+		      enum drm_xe_ras_error_severity severity, gfp_t flags);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 5135e8e4093f..c0fda18601cd 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -279,7 +279,7 @@ static void gt_hw_error_handler(struct xe_tile *tile, const enum hardware_error
 	if (hw_err == HARDWARE_ERROR_NONFATAL) {
 		atomic_inc(&info[error_id].counter);
 		log_hw_error(tile, info[error_id].name, severity);
-		return;
+		goto notify;
 	}
 
 	for (i = 0; i < PVC_GT_VECTOR_LEN(hw_err); i++) {
@@ -336,6 +336,9 @@ static void gt_hw_error_handler(struct xe_tile *tile, const enum hardware_error
 
 		xe_mmio_write32(mmio, ERR_STAT_GT_VECTOR_REG(hw_err, i), vector);
 	}
+
+notify:
+	xe_drm_ras_event(xe, error_id, severity, GFP_ATOMIC);
 }
 
 static void soc_slave_ieh_handler(struct xe_tile *tile, const enum hardware_error hw_err, u32 error_id)
@@ -418,6 +421,8 @@ static void soc_hw_error_handler(struct xe_tile *tile, const enum hardware_error
 
 	xe_mmio_write32(mmio, SOC_GLOBAL_ERR_STAT_REG(master, hw_err), master_global_errstat);
 
+	xe_drm_ras_event(xe, error_id, severity, GFP_ATOMIC);
+
 unmask_gsysevtctl:
 	for (i = 0; i < XE_SOC_NUM_IEH; i++)
 		xe_mmio_write32(mmio, SOC_GSYSEVTCTL_REG(master, slave, i),
-- 
2.47.1