[PATCH v6 3/5] drm/xe/ras: Add support for error threshold

[Raag Jadav <raag.jadav@intel.com>]

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>
Reviewed-by: Riana Tauro <riana.tauro@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)
v6: Check for valid counter
---
 drivers/gpu/drm/xe/xe_ras.c                   | 111 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_ras.h                   |   2 +
 drivers/gpu/drm/xe/xe_ras_types.h             |  50 ++++++++
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |   4 +
 4 files changed, 167 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index d25d25f77531..de4cb9ef7355 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -661,6 +661,117 @@ 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;
+	}
+
+	if (!ras_counter_is_valid(xe, &response.counter))
+		return -EBADMSG;
+
+	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;
+
+	if (!ras_counter_is_valid(xe, counter))
+		return -EBADMSG;
+
+	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;
+}
+
 static ssize_t gpu_health_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct xe_ras_get_health_response response = {0};
diff --git a/drivers/gpu/drm/xe/xe_ras.h b/drivers/gpu/drm/xe/xe_ras.h
index 618364734043..0b8669f28d56 100644
--- a/drivers/gpu/drm/xe/xe_ras.h
+++ b/drivers/gpu/drm/xe/xe_ras.h
@@ -16,6 +16,8 @@ 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);
 enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe);
 
diff --git a/drivers/gpu/drm/xe/xe_ras_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
index 99b2466e2062..fe6f3658a2a4 100644
--- a/drivers/gpu/drm/xe/xe_ras_types.h
+++ b/drivers/gpu/drm/xe/xe_ras_types.h
@@ -147,6 +147,56 @@ struct xe_ras_clear_counter_response {
 	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;
+
 /**
  * struct xe_ras_error_array - Details of the error types
  */
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
index d0341538ad05..66e7cbcc3f91 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
@@ -25,6 +25,8 @@ enum xe_sysctrl_group {
  * @XE_SYSCTRL_CMD_GET_SOC_ERROR: Retrieve basic error information
  * @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
  * @XE_SYSCTRL_CMD_GET_HEALTH: Retrieve gpu health
  * @XE_SYSCTRL_CMD_SET_HEALTH: Set gpu health
@@ -33,6 +35,8 @@ enum xe_sysctrl_gfsp_cmd {
 	XE_SYSCTRL_CMD_GET_SOC_ERROR		= 0x01,
 	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,
 	XE_SYSCTRL_CMD_GET_HEALTH		= 0x0B,
 	XE_SYSCTRL_CMD_SET_HEALTH		= 0x0C,
-- 
2.43.0