[PATCH v4 0/5] Introduce error threshold to drm_ras

[PATCH v4 0/5] Introduce error threshold to drm_ras

[Raag Jadav]

This series introduces error threshold to drm_ras infrastructure. This
allows user to get and set the error threshold of a specific counter.

Detailed description in commit message and documentation.

v2: Document threshold definition (Riana)
    Return -EOPNOTSUPP on threshold callbacks absence (Riana)
    Cancel and free genlmsg on failure (Riana)
    Document threshold bounds checking responsibility (Riana)
    Add RAS operation status codes (Riana)
    Use goto (Riana)

v3: Move documentation from yaml to rst file (Riana)
    s/value/threshold (Riana)
    Use goto for error handling (Riana)
    Reuse status codes and uapi mapping from counter series (Riana)
    Access request/response counter using local pointer (Riana)
    Mark unused field as reserved (Riana)
    Return -ENOENT on info absence (Riana)

v4: Clarify 0 threshold expectations (Riana)
    Drop redundant wrapping (Riana)
    Make debug logs consistent (Riana)
    Update kdoc (Riana)

Raag Jadav (5):
  drm/ras: Cancel and free message on get counter failure
  drm/ras: Introduce error threshold
  drm/xe/ras: Add support for error threshold
  drm/xe/drm_ras: Wire up error threshold callbacks
  drm/xe/sysctrl: Reuse xe_sysctrl_create_command()

 Documentation/gpu/drm-ras.rst                 |  18 ++
 Documentation/netlink/specs/drm_ras.yaml      |  32 ++++
 drivers/gpu/drm/drm_ras.c                     | 178 +++++++++++++++++-
 drivers/gpu/drm/drm_ras_nl.c                  |  27 +++
 drivers/gpu/drm/drm_ras_nl.h                  |   4 +
 drivers/gpu/drm/xe/xe_drm_ras.c               |  34 ++++
 drivers/gpu/drm/xe/xe_ras.c                   | 105 +++++++++++
 drivers/gpu/drm/xe/xe_ras.h                   |   2 +
 drivers/gpu/drm/xe/xe_ras_types.h             |  51 +++++
 drivers/gpu/drm/xe/xe_sysctrl_event.c         |  28 +--
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |   4 +
 include/drm/drm_ras.h                         |  28 +++
 include/uapi/drm/drm_ras.h                    |   3 +
 13 files changed, 487 insertions(+), 27 deletions(-)

-- 
2.43.0

[PATCH v4 1/5] drm/ras: Cancel and free message on get counter failure

[Raag Jadav]

doit_reply_value() directly returns on get counter failure, which results
in stale sk_buff and genetlink header that aren't cleaned up. Fix it and
while at it, consolidate error handling using goto.

Fixes: c36218dc49f5 ("drm/ras: Introduce the DRM RAS infrastructure over generic netlink")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
---
v2: Use goto (Riana)
---
 drivers/gpu/drm/drm_ras.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
index d6eab29a1394..467a169026fc 100644
--- a/drivers/gpu/drm/drm_ras.c
+++ b/drivers/gpu/drm/drm_ras.c
@@ -201,25 +201,28 @@ static int doit_reply_value(struct genl_info *info, u32 node_id,
 
 	hdr = genlmsg_iput(msg, info);
 	if (!hdr) {
-		nlmsg_free(msg);
-		return -EMSGSIZE;
+		ret = -EMSGSIZE;
+		goto free_msg;
 	}
 
 	ret = get_node_error_counter(node_id, error_id,
 				     &error_name, &value);
 	if (ret)
-		return ret;
+		goto cancel_msg;
 
 	ret = msg_reply_value(msg, error_id, error_name, value);
-	if (ret) {
-		genlmsg_cancel(msg, hdr);
-		nlmsg_free(msg);
-		return ret;
-	}
+	if (ret)
+		goto cancel_msg;
 
 	genlmsg_end(msg, hdr);
 
 	return genlmsg_reply(msg, info);
+
+cancel_msg:
+	genlmsg_cancel(msg, hdr);
+free_msg:
+	nlmsg_free(msg);
+	return ret;
 }
 
 /**
-- 
2.43.0

[PATCH v4 2/5] drm/ras: Introduce error threshold

[Raag Jadav]

Add get-error-threshold and set-error-threshold command support which
allows querying/setting error threshold of the counter. Threshold in RAS
context means the number of errors the hardware is expected to accumulate
before it raises them to software. This is to have a fine grained control
over error notifications that are raised by the hardware.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
v2: Document threshold definition (Riana)
    Return -EOPNOTSUPP on threshold callbacks absence (Riana)
    Cancel and free genlmsg on failure (Riana)
    Document threshold bounds checking responsibility (Riana)
v3: Move documentation from yaml to rst file (Riana)
    s/value/threshold (Riana)
    Use goto for error handling (Riana)
v4: Clarify 0 threshold expectations (Riana)
    Drop redundant wrapping (Riana)
---
 Documentation/gpu/drm-ras.rst            |  18 +++
 Documentation/netlink/specs/drm_ras.yaml |  32 +++++
 drivers/gpu/drm/drm_ras.c                | 161 +++++++++++++++++++++++
 drivers/gpu/drm/drm_ras_nl.c             |  27 ++++
 drivers/gpu/drm/drm_ras_nl.h             |   4 +
 include/drm/drm_ras.h                    |  28 ++++
 include/uapi/drm/drm_ras.h               |   3 +
 7 files changed, 273 insertions(+)

diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst
index 83c21853b74b..2718f8aee09d 100644
--- a/Documentation/gpu/drm-ras.rst
+++ b/Documentation/gpu/drm-ras.rst
@@ -56,6 +56,10 @@ 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.
+* Query specific error counter threshold with the ``get-error-threshold`` command, using both
+  ``node-id`` and ``error-id`` as parameters.
+* Set specific error counter threshold with the ``set-error-threshold`` command, using
+  ``node-id``, ``error-id`` and ``error-threshold`` as parameters.
 
 YAML-based Interface
 --------------------
@@ -111,3 +115,17 @@ 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: Query error threshold of a given counter
+
+.. code-block:: bash
+
+    sudo ynl --family drm_ras --do get-error-threshold --json '{"node-id":0, "error-id":1}'
+    {'error-id': 1, 'error-name': 'error_name1', 'error-threshold': 16}
+
+Example: Set error threshold of a given counter
+
+.. code-block:: bash
+
+    sudo ynl --family drm_ras --do set-error-threshold --json '{"node-id":0, "error-id":1, "error-threshold":8}'
+    None
diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
index e113056f8c01..9cf7f9cde242 100644
--- a/Documentation/netlink/specs/drm_ras.yaml
+++ b/Documentation/netlink/specs/drm_ras.yaml
@@ -69,6 +69,10 @@ attribute-sets:
         name: error-value
         type: u32
         doc: Current value of the requested error counter.
+      -
+        name: error-threshold
+        type: u32
+        doc: Error threshold of the counter.
 
 operations:
   list:
@@ -124,3 +128,31 @@ operations:
       do:
         request:
           attributes: *id-attrs
+    -
+      name: get-error-threshold
+      doc: >-
+           Retrieve error threshold of a given counter.
+           The response includes the id, the name, and current threshold
+           of the counter.
+      attribute-set: error-counter-attrs
+      flags: [admin-perm]
+      do:
+        request:
+          attributes: *id-attrs
+        reply:
+          attributes:
+            - error-id
+            - error-name
+            - error-threshold
+    -
+      name: set-error-threshold
+      doc: >-
+           Set error threshold of a given counter.
+      attribute-set: error-counter-attrs
+      flags: [admin-perm]
+      do:
+        request:
+          attributes:
+            - node-id
+            - error-id
+            - error-threshold
diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
index 467a169026fc..d60c40ac5427 100644
--- a/drivers/gpu/drm/drm_ras.c
+++ b/drivers/gpu/drm/drm_ras.c
@@ -41,6 +41,13 @@
  *    Userspace must provide Node ID, Error ID.
  *    Clears specific error counter of a node if supported.
  *
+ * 4. GET_ERROR_THRESHOLD: Query error threshold of a given counter.
+ *    Userspace must provide Node ID and Error ID.
+ *    Returns the error threshold of a specific counter.
+ *
+ * 5. SET_ERROR_THRESHOLD: Set error threshold of a given counter.
+ *    Userspace must provide Node ID, Error ID and threshold to be set.
+ *
  * Node registration:
  *
  * - drm_ras_node_register(): Registers a new node and assigns
@@ -61,6 +68,16 @@
  *     + The error counters in the driver doesn't need to be contiguous, but the
  *       driver must return -ENOENT to the query_error_counter as an indication
  *       that the ID should be skipped and not listed in the netlink API.
+ *     + The driver can optionally implement query_error_threshold() and
+ *       set_error_threshold() callbacks to facilitate getting/setting error
+ *       threshold of the counter. Threshold in RAS context means the number of
+ *       errors the hardware is expected to accumulate before it raises them to
+ *       software. This is to have a fine grained control over error notifications
+ *       that are raised by the hardware.
+ *     + The driver is responsible for error threshold bounds checking.
+ *     + Threshold of 0 can mean invalid threshold or act as a disable notifications
+ *       toggle for that counter depending on usecase and the driver is responsible
+ *       for handling it as needed.
  *
  * Netlink handlers:
  *
@@ -72,6 +89,10 @@
  *   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.
+ * - drm_ras_nl_get_error_threshold_doit(): Implements the GET_ERROR_THRESHOLD doit
+ *   operation, fetching the error threshold of a specific counter.
+ * - drm_ras_nl_set_error_threshold_doit(): Implements the SET_ERROR_THRESHOLD doit
+ *   operation, setting the error threshold of a specific counter.
  */
 
 static DEFINE_XARRAY_ALLOC(drm_ras_xa);
@@ -168,6 +189,40 @@ static int get_node_error_counter(u32 node_id, u32 error_id,
 	return node->query_error_counter(node, error_id, name, value);
 }
 
+static int get_node_error_threshold(u32 node_id, u32 error_id, const char **name, u32 *threshold)
+{
+	struct drm_ras_node *node;
+
+	node = xa_load(&drm_ras_xa, node_id);
+	if (!node)
+		return -ENOENT;
+
+	if (!node->query_error_threshold)
+		return -EOPNOTSUPP;
+
+	if (error_id < node->error_counter_range.first || error_id > node->error_counter_range.last)
+		return -EINVAL;
+
+	return node->query_error_threshold(node, error_id, name, threshold);
+}
+
+static int set_node_error_threshold(u32 node_id, u32 error_id, u32 threshold)
+{
+	struct drm_ras_node *node;
+
+	node = xa_load(&drm_ras_xa, node_id);
+	if (!node)
+		return -ENOENT;
+
+	if (!node->set_error_threshold)
+		return -EOPNOTSUPP;
+
+	if (error_id < node->error_counter_range.first || error_id > node->error_counter_range.last)
+		return -EINVAL;
+
+	return node->set_error_threshold(node, error_id, threshold);
+}
+
 static int msg_reply_value(struct sk_buff *msg, u32 error_id,
 			   const char *error_name, u32 value)
 {
@@ -186,6 +241,22 @@ static int msg_reply_value(struct sk_buff *msg, u32 error_id,
 			   value);
 }
 
+static int msg_reply_threshold(struct sk_buff *msg, u32 error_id, const char *error_name,
+			       u32 threshold)
+{
+	int ret;
+
+	ret = nla_put_u32(msg, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID, error_id);
+	if (ret)
+		return ret;
+
+	ret = nla_put_string(msg, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_NAME, error_name);
+	if (ret)
+		return ret;
+
+	return nla_put_u32(msg, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD, threshold);
+}
+
 static int doit_reply_value(struct genl_info *info, u32 node_id,
 			    u32 error_id)
 {
@@ -225,6 +296,43 @@ static int doit_reply_value(struct genl_info *info, u32 node_id,
 	return ret;
 }
 
+static int doit_reply_threshold(struct genl_info *info, u32 node_id, u32 error_id)
+{
+	const char *error_name;
+	struct sk_buff *msg;
+	struct nlattr *hdr;
+	u32 threshold;
+	int ret;
+
+	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(msg, info);
+	if (!hdr) {
+		ret = -EMSGSIZE;
+		goto free_msg;
+	}
+
+	ret = get_node_error_threshold(node_id, error_id, &error_name, &threshold);
+	if (ret)
+		goto cancel_msg;
+
+	ret = msg_reply_threshold(msg, error_id, error_name, threshold);
+	if (ret)
+		goto cancel_msg;
+
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_reply(msg, info);
+
+cancel_msg:
+	genlmsg_cancel(msg, hdr);
+free_msg:
+	nlmsg_free(msg);
+	return ret;
+}
+
 /**
  * drm_ras_nl_get_error_counter_dumpit() - Dump all Error Counters
  * @skb: Netlink message buffer
@@ -358,6 +466,59 @@ int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb,
 	return node->clear_error_counter(node, error_id);
 }
 
+/**
+ * drm_ras_nl_get_error_threshold_doit() - Query error threshold of a counter
+ * @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 retrieves
+ * the error threshold of the corresponding counter. Sends the result back to
+ * the requesting user via the standard Genl reply.
+ *
+ * Return: 0 on success, or negative errno on failure.
+ */
+int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	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]);
+
+	return doit_reply_threshold(info, node_id, error_id);
+}
+
+/**
+ * drm_ras_nl_set_error_threshold_doit() - Set error threshold of a counter
+ * @skb: Netlink message buffer
+ * @info: Generic Netlink info containing attributes of the request
+ *
+ * Extracts the Node ID, Error ID and threshold from the netlink attributes and
+ * sets the error threshold of the corresponding counter.
+ *
+ * Return: 0 on success, or negative errno on failure.
+ */
+int drm_ras_nl_set_error_threshold_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	u32 node_id, error_id, threshold;
+
+	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) ||
+	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD))
+		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]);
+	threshold = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD]);
+
+	return set_node_error_threshold(node_id, error_id, threshold);
+}
+
 /**
  * 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..02e8e5054d05 100644
--- a/drivers/gpu/drm/drm_ras_nl.c
+++ b/drivers/gpu/drm/drm_ras_nl.c
@@ -28,6 +28,19 @@ static const struct nla_policy drm_ras_clear_error_counter_nl_policy[DRM_RAS_A_E
 	[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID] = { .type = NLA_U32, },
 };
 
+/* DRM_RAS_CMD_GET_ERROR_THRESHOLD - do */
+static const struct nla_policy drm_ras_get_error_threshold_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, },
+};
+
+/* DRM_RAS_CMD_SET_ERROR_THRESHOLD - do */
+static const struct nla_policy drm_ras_set_error_threshold_nl_policy[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD + 1] = {
+	[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID] = { .type = NLA_U32, },
+	[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID] = { .type = NLA_U32, },
+	[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD] = { .type = NLA_U32, },
+};
+
 /* Ops table for drm_ras */
 static const struct genl_split_ops drm_ras_nl_ops[] = {
 	{
@@ -56,6 +69,20 @@ static const struct genl_split_ops drm_ras_nl_ops[] = {
 		.maxattr	= DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
+	{
+		.cmd		= DRM_RAS_CMD_GET_ERROR_THRESHOLD,
+		.doit		= drm_ras_nl_get_error_threshold_doit,
+		.policy		= drm_ras_get_error_threshold_nl_policy,
+		.maxattr	= DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= DRM_RAS_CMD_SET_ERROR_THRESHOLD,
+		.doit		= drm_ras_nl_set_error_threshold_doit,
+		.policy		= drm_ras_set_error_threshold_nl_policy,
+		.maxattr	= DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
 
 struct genl_family drm_ras_nl_family __ro_after_init = {
diff --git a/drivers/gpu/drm/drm_ras_nl.h b/drivers/gpu/drm/drm_ras_nl.h
index a398643572a5..57b1e647d833 100644
--- a/drivers/gpu/drm/drm_ras_nl.h
+++ b/drivers/gpu/drm/drm_ras_nl.h
@@ -20,6 +20,10 @@ 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);
+int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int drm_ras_nl_set_error_threshold_doit(struct sk_buff *skb,
+					struct genl_info *info);
 
 extern struct genl_family drm_ras_nl_family;
 
diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
index f2a787bc4f64..683a3844f84f 100644
--- a/include/drm/drm_ras.h
+++ b/include/drm/drm_ras.h
@@ -69,6 +69,34 @@ struct drm_ras_node {
 	 */
 	int (*clear_error_counter)(struct drm_ras_node *node, u32 error_id);
 
+	/**
+	 * @query_error_threshold:
+	 *
+	 * This callback is used by drm-ras to query error threshold of a
+	 * specific counter.
+	 *
+	 * Driver should expect query_error_threshold() to be called with
+	 * error_id from `error_counter_range.first` to
+	 * `error_counter_range.last`.
+	 *
+	 * Returns: 0 on success, negative error code on failure.
+	 */
+	int (*query_error_threshold)(struct drm_ras_node *node, u32 error_id, const char **name,
+				     u32 *threshold);
+	/**
+	 * @set_error_threshold:
+	 *
+	 * This callback is used by drm-ras to set error threshold of a specific
+	 * counter.
+	 *
+	 * Driver should expect set_error_threshold() to be called with error_id
+	 * from `error_counter_range.first` to `error_counter_range.last`.
+	 * Driver is responsible for error threshold bounds checking.
+	 *
+	 * Returns: 0 on success, negative error code on failure.
+	 */
+	int (*set_error_threshold)(struct drm_ras_node *node, u32 error_id, u32 threshold);
+
 	/** @priv: Driver private data */
 	void *priv;
 };
diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
index 218a3ee86805..27c68956495f 100644
--- a/include/uapi/drm/drm_ras.h
+++ b/include/uapi/drm/drm_ras.h
@@ -33,6 +33,7 @@ enum {
 	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_ERROR_THRESHOLD,
 
 	__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX,
 	DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1)
@@ -42,6 +43,8 @@ enum {
 	DRM_RAS_CMD_LIST_NODES = 1,
 	DRM_RAS_CMD_GET_ERROR_COUNTER,
 	DRM_RAS_CMD_CLEAR_ERROR_COUNTER,
+	DRM_RAS_CMD_GET_ERROR_THRESHOLD,
+	DRM_RAS_CMD_SET_ERROR_THRESHOLD,
 
 	__DRM_RAS_CMD_MAX,
 	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)
-- 
2.43.0

[PATCH v4 3/5] drm/xe/ras: Add support for error threshold

[Raag Jadav]

System controller allows getting/setting per counter threshold for
correctable errors, which it uses to raise error events to the driver.
Get/set it using the respective mailbox command.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
v2: Add RAS operation status codes (Riana)
v3: Reuse status codes and uapi mapping from counter series (Riana)
    Access request/response counter using local pointer (Riana)
    Mark unused field as reserved (Riana)
v4: Make debug logs consistent (Riana)
    Update kdoc (Riana)
---
 drivers/gpu/drm/xe/xe_ras.c                   | 105 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_ras.h                   |   2 +
 drivers/gpu/drm/xe/xe_ras_types.h             |  51 +++++++++
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |   4 +
 4 files changed, 162 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 44f4e1a3455b..afee8202d24e 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -270,6 +270,111 @@ int xe_ras_clear_counter(struct xe_device *xe, u8 severity, u8 component)
 	return 0;
 }
 
+/**
+ * xe_ras_get_threshold() - Get error counter threshold
+ * @xe: Xe device instance
+ * @severity: Error severity to be queried (&enum drm_xe_ras_error_severity)
+ * @component: Error component to be queried (&enum drm_xe_ras_error_component)
+ * @threshold: Counter threshold
+ *
+ * This function retrieves the error threshold of a specific counter based on
+ * severity and component.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int xe_ras_get_threshold(struct xe_device *xe, u8 severity, u8 component, u32 *threshold)
+{
+	struct xe_ras_get_threshold_response response = {};
+	struct xe_ras_get_threshold_request request = {};
+	struct xe_sysctrl_mailbox_command command = {};
+	struct xe_ras_error_class *counter;
+	size_t len;
+	int ret;
+
+	counter = &request.counter;
+	counter->common.severity = drm_to_xe_ras_severity(severity);
+	counter->common.component = drm_to_xe_ras_component(component);
+
+	xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_GET_THRESHOLD,
+				  &request, sizeof(request), &response, sizeof(response));
+
+	guard(xe_pm_runtime)(xe);
+	ret = xe_sysctrl_send_command(&xe->sc, &command, &len);
+	if (ret) {
+		xe_err(xe, "sysctrl: failed to get threshold %d\n", ret);
+		return ret;
+	}
+
+	if (len != sizeof(response)) {
+		xe_err(xe, "sysctrl: unexpected get threshold response length %zu (expected %zu)\n",
+		       len, sizeof(response));
+		return -EIO;
+	}
+
+	counter = &response.counter;
+	*threshold = response.threshold;
+
+	xe_dbg(xe, "[RAS]: get threshold %u for %s %s\n", *threshold,
+	       comp_to_str(counter->common.component), sev_to_str(counter->common.severity));
+	return 0;
+}
+
+/**
+ * xe_ras_set_threshold() - Set error counter threshold
+ * @xe: Xe device instance
+ * @severity: Error severity to be set (&enum drm_xe_ras_error_severity)
+ * @component: Error component to be set (&enum drm_xe_ras_error_component)
+ * @threshold: Counter threshold
+ *
+ * This function sets the error threshold of a specific counter based on
+ * severity and component.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 threshold)
+{
+	struct xe_ras_set_threshold_response response = {};
+	struct xe_ras_set_threshold_request request = {};
+	struct xe_sysctrl_mailbox_command command = {};
+	struct xe_ras_error_class *counter;
+	size_t len;
+	int ret;
+
+	counter = &request.counter;
+	counter->common.severity = drm_to_xe_ras_severity(severity);
+	counter->common.component = drm_to_xe_ras_component(component);
+	request.threshold = threshold;
+
+	xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_SET_THRESHOLD,
+				  &request, sizeof(request), &response, sizeof(response));
+
+	guard(xe_pm_runtime)(xe);
+	ret = xe_sysctrl_send_command(&xe->sc, &command, &len);
+	if (ret) {
+		xe_err(xe, "sysctrl: failed to set threshold %d\n", ret);
+		return ret;
+	}
+
+	if (len != sizeof(response)) {
+		xe_err(xe, "sysctrl: unexpected set threshold response length %zu (expected %zu)\n",
+		       len, sizeof(response));
+		return -EIO;
+	}
+
+	ret = ras_status_to_errno(response.status);
+	if (ret) {
+		xe_err(xe, "sysctrl: set threshold command failed with status %#x\n",
+		       response.status);
+		return ret;
+	}
+
+	counter = &response.counter;
+
+	xe_dbg(xe, "[RAS]: set threshold %u for %s %s\n", response.threshold,
+	       comp_to_str(counter->common.component), sev_to_str(counter->common.severity));
+	return 0;
+}
+
 /**
  * xe_ras_init - Initialize Xe RAS
  * @xe: xe device instance
diff --git a/drivers/gpu/drm/xe/xe_ras.h b/drivers/gpu/drm/xe/xe_ras.h
index ba0b0224df23..1aa43c54b710 100644
--- a/drivers/gpu/drm/xe/xe_ras.h
+++ b/drivers/gpu/drm/xe/xe_ras.h
@@ -15,6 +15,8 @@ void xe_ras_counter_threshold_crossed(struct xe_device *xe,
 				      struct xe_sysctrl_event_response *response);
 int xe_ras_get_counter(struct xe_device *xe, u8 severity, u8 component, u32 *value);
 int xe_ras_clear_counter(struct xe_device *xe, u8 severity, u8 component);
+int xe_ras_get_threshold(struct xe_device *xe, u8 severity, u8 component, u32 *threshold);
+int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 threshold);
 void xe_ras_init(struct xe_device *xe);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_ras_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
index 6688e11f57a8..747b651880cd 100644
--- a/drivers/gpu/drm/xe/xe_ras_types.h
+++ b/drivers/gpu/drm/xe/xe_ras_types.h
@@ -121,4 +121,55 @@ struct xe_ras_clear_counter_response {
 	/** @reserved1: Reserved for future use */
 	u32 reserved1[3];
 } __packed;
+
+/**
+ * struct xe_ras_get_threshold_request - Request structure for get threshold
+ */
+struct xe_ras_get_threshold_request {
+	/** @counter: Counter to get threshold for */
+	struct xe_ras_error_class counter;
+	/** @reserved: Reserved for future use */
+	u32 reserved;
+} __packed;
+
+/**
+ * struct xe_ras_get_threshold_response - Response structure for get threshold
+ */
+struct xe_ras_get_threshold_response {
+	/** @counter: Counter ID */
+	struct xe_ras_error_class counter;
+	/** @threshold: Current threshold of the counter */
+	u32 threshold;
+	/** @reserved: Reserved for future use */
+	u32 reserved[4];
+} __packed;
+
+/**
+ * struct xe_ras_set_threshold_request - Request structure for set threshold
+ */
+struct xe_ras_set_threshold_request {
+	/** @counter: Counter to set threshold for */
+	struct xe_ras_error_class counter;
+	/** @threshold: Threshold to be set */
+	u32 threshold;
+	/** @reserved: Reserved for future use */
+	u32 reserved;
+} __packed;
+
+/**
+ * struct xe_ras_set_threshold_response - Response structure for set threshold
+ */
+struct xe_ras_set_threshold_response {
+	/** @counter: Counter ID */
+	struct xe_ras_error_class counter;
+	/** @reserved: Reserved */
+	u32 reserved;
+	/** @threshold: Updated threshold */
+	u32 threshold;
+	/** @status: Operation status */
+	u32 status;
+	/** @reserved1: Reserved for future use */
+	u32 reserved1[2];
+} __packed;
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
index 6e3753554510..10f06aa5c4b5 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
@@ -24,11 +24,15 @@ enum xe_sysctrl_group {
  *
  * @XE_SYSCTRL_CMD_GET_COUNTER: Get error counter value
  * @XE_SYSCTRL_CMD_CLEAR_COUNTER: Clear error counter value
+ * @XE_SYSCTRL_CMD_GET_THRESHOLD: Retrieve error threshold
+ * @XE_SYSCTRL_CMD_SET_THRESHOLD: Set error threshold
  * @XE_SYSCTRL_CMD_GET_PENDING_EVENT: Retrieve pending event
  */
 enum xe_sysctrl_gfsp_cmd {
 	XE_SYSCTRL_CMD_GET_COUNTER		= 0x03,
 	XE_SYSCTRL_CMD_CLEAR_COUNTER		= 0x04,
+	XE_SYSCTRL_CMD_GET_THRESHOLD		= 0x05,
+	XE_SYSCTRL_CMD_SET_THRESHOLD		= 0x06,
 	XE_SYSCTRL_CMD_GET_PENDING_EVENT	= 0x07,
 };
 
-- 
2.43.0

[PATCH v4 4/5] drm/xe/drm_ras: Wire up error threshold callbacks

[Raag Jadav]

Now that we have get/set error threshold support in xe driver, wire them
up to drm_ras so that userspace can make use of the functionality.

$ sudo ynl --family drm_ras --do get-error-threshold \
--json '{"node-id":0, "error-id":2}'
{'error-id': 2, 'error-name': 'soc-internal', 'error-threshold': 16}

$ sudo ynl --family drm_ras --do set-error-threshold \
--json '{"node-id":0, "error-id":2, "error-threshold":8}'
None

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
---
v3: Return -ENOENT on info absence (Riana)
---
 drivers/gpu/drm/xe/xe_drm_ras.c | 34 +++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
index 7937d8ba0ed9..4afa2ad98300 100644
--- a/drivers/gpu/drm/xe/xe_drm_ras.c
+++ b/drivers/gpu/drm/xe/xe_drm_ras.c
@@ -86,6 +86,38 @@ static int clear_correctable_error_counter(struct drm_ras_node *node, u32 error_
 	return clear_error_counter(xe, DRM_XE_RAS_ERR_SEV_CORRECTABLE, error_id);
 }
 
+static int query_correctable_error_threshold(struct drm_ras_node *ep, u32 error_id,
+					     const char **name, u32 *threshold)
+{
+	struct xe_device *xe = ep->priv;
+	struct xe_drm_ras *ras = &xe->ras;
+	struct xe_drm_ras_counter *info = ras->info[DRM_XE_RAS_ERR_SEV_CORRECTABLE];
+
+	if (!info || !info[error_id].name)
+		return -ENOENT;
+
+	if (!xe->info.has_sysctrl)
+		return -EOPNOTSUPP;
+
+	*name = info[error_id].name;
+	return xe_ras_get_threshold(xe, DRM_XE_RAS_ERR_SEV_CORRECTABLE, error_id, threshold);
+}
+
+static int set_correctable_error_threshold(struct drm_ras_node *ep, u32 error_id, u32 threshold)
+{
+	struct xe_device *xe = ep->priv;
+	struct xe_drm_ras *ras = &xe->ras;
+	struct xe_drm_ras_counter *info = ras->info[DRM_XE_RAS_ERR_SEV_CORRECTABLE];
+
+	if (!info || !info[error_id].name)
+		return -ENOENT;
+
+	if (!xe->info.has_sysctrl)
+		return -EOPNOTSUPP;
+
+	return xe_ras_set_threshold(xe, DRM_XE_RAS_ERR_SEV_CORRECTABLE, error_id, threshold);
+}
+
 static struct xe_drm_ras_counter *allocate_and_copy_counters(struct xe_device *xe)
 {
 	struct xe_drm_ras_counter *counter;
@@ -134,6 +166,8 @@ static int assign_node_params(struct xe_device *xe, struct drm_ras_node *node,
 	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE) {
 		node->query_error_counter = query_correctable_error_counter;
 		node->clear_error_counter = clear_correctable_error_counter;
+		node->query_error_threshold = query_correctable_error_threshold;
+		node->set_error_threshold = set_correctable_error_threshold;
 	} else {
 		node->query_error_counter = query_uncorrectable_error_counter;
 		node->clear_error_counter = clear_uncorrectable_error_counter;
-- 
2.43.0

[PATCH v4 5/5] drm/xe/sysctrl: Reuse xe_sysctrl_create_command()

[Raag Jadav]

Now that we have a helper to create sysctrl command, reuse it for
threshold crossed events.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
 drivers/gpu/drm/xe/xe_sysctrl_event.c | 28 ++++++++-------------------
 1 file changed, 8 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_sysctrl_event.c b/drivers/gpu/drm/xe/xe_sysctrl_event.c
index b4d17329af6c..0547b7b39726 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_event.c
+++ b/drivers/gpu/drm/xe/xe_sysctrl_event.c
@@ -49,18 +49,6 @@ static void get_pending_event(struct xe_sysctrl *sc, struct xe_sysctrl_mailbox_c
 	} while (response->count);
 }
 
-static void event_request_prepare(struct xe_device *xe, struct xe_sysctrl_app_msg_hdr *header,
-				  struct xe_sysctrl_event_request *request)
-{
-	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
-
-	header->data = REG_FIELD_PREP(APP_HDR_GROUP_ID_MASK, XE_SYSCTRL_GROUP_GFSP) |
-		       REG_FIELD_PREP(APP_HDR_COMMAND_MASK, XE_SYSCTRL_CMD_GET_PENDING_EVENT);
-
-	request->vector = xe_device_has_msix(xe) ? XE_IRQ_DEFAULT_MSIX : 0;
-	request->fn = PCI_FUNC(pdev->devfn);
-}
-
 /**
  * xe_sysctrl_event() - Handler for System Controller events
  * @sc: System Controller instance
@@ -72,16 +60,16 @@ void xe_sysctrl_event(struct xe_sysctrl *sc)
 	struct xe_sysctrl_mailbox_command command = {};
 	struct xe_sysctrl_event_response response = {};
 	struct xe_sysctrl_event_request request = {};
-	struct xe_sysctrl_app_msg_hdr header = {};
+	struct xe_device *xe = sc_to_xe(sc);
+	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 
-	xe_device_assert_mem_access(sc_to_xe(sc));
-	event_request_prepare(sc_to_xe(sc), &header, &request);
+	xe_device_assert_mem_access(xe);
 
-	command.header = header;
-	command.data_in = &request;
-	command.data_in_len = sizeof(request);
-	command.data_out = &response;
-	command.data_out_len = sizeof(response);
+	request.vector = xe_device_has_msix(xe) ? XE_IRQ_DEFAULT_MSIX : 0;
+	request.fn = PCI_FUNC(pdev->devfn);
+
+	xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_GET_PENDING_EVENT,
+				  &request, sizeof(request), &response, sizeof(response));
 
 	guard(mutex)(&sc->event_lock);
 	get_pending_event(sc, &command);
-- 
2.43.0