Re: [PATCH v2 01/11] drm/xe/xe_ras: Add support to retrieve info queue data for CRI

[Michal Wajdeczko <michal.wajdeczko@intel.com>]

On 8/25/2026 7:59 PM, Badal Nilawar wrote:
> Add support to retrieve info queue data. While constructing CPER
> record info queue data will be retrieved when has_info_queue=1 is
> set in get_counter response.
> 
> Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
> Assisted-by: Copilot:claude-sonnet-4.6
> ---
> v2: Drop unused flags (Mallesh)
> ---
>  drivers/gpu/drm/xe/xe_ras.c                   |  34 ++++++
>  drivers/gpu/drm/xe/xe_ras_types.h             | 108 ++++++++++++++++++
>  drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |   2 +
>  3 files changed, 144 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
> index d25d25f77531..683087235482 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -661,6 +661,40 @@ int xe_ras_clear_counter(struct xe_device *xe, u8 severity, u8 component)
>  	return 0;
>  }
>  
> +static int get_info_queue_data(struct xe_device *xe,
> +			       const struct xe_ras_get_info_queue_data_request *req,
> +			       struct xe_ras_get_info_queue_data_response *out)
> +{
> +	struct xe_ras_get_info_queue_data_response response = {0};
> +	struct xe_sysctrl_mailbox_command command = {0};
> +	size_t rlen;
> +	int ret;
> +
> +	xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP,
> +				  XE_SYSCTRL_CMD_GET_INFO_QUEUE_DATA,
> +				  (void *)req, sizeof(*req), &response, sizeof(response));
> +
> +	ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
> +	if (ret) {
> +		xe_err(xe, "sysctrl: failed to get info queue data %d\n", ret);
> +		return ret;
> +	}
> +
> +	if (rlen != sizeof(response)) {
> +		xe_err(xe, "sysctrl: unexpected get info queue data response length %zu (expected %zu)\n",
> +		       rlen, sizeof(response));
> +		return -EIO;
> +	}
> +
> +	xe_dbg(xe, "[RAS]: info queue data: status=%u chunk_size=%u flags=0x%x\n",
> +	       response.operation_status,
> +	       response.queue_response.queue_header.chunk_size,
> +	       response.queue_response.queue_header.flags);
> +
> +	*out = response;
> +	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_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
> index 99b2466e2062..d87db9f5174a 100644
> --- a/drivers/gpu/drm/xe/xe_ras_types.h
> +++ b/drivers/gpu/drm/xe/xe_ras_types.h
> @@ -16,6 +16,10 @@
>  #define XE_RAS_MEMORY_DB_ECC			BIT(1)
>  #define XE_RAS_MEMORY_POISON			BIT(2)
>  #define XE_RAS_MEMORY_DATA_PARITY		BIT(5)
> +#define XE_RAS_INFO_QUEUE_MAX_CHUNK_SIZE	200
> +#define XE_RAS_INFO_QUEUE_MAX_TOTAL_SIZE	5120
> +#define XE_RAS_INFO_QUEUE_FLAG_AVAILABLE	0x01
> +#define XE_RAS_INFO_QUEUE_FLAG_MORE_DATA	0x02
>  
>  /**
>   * enum xe_ras_recovery_action - RAS recovery actions
> @@ -95,6 +99,109 @@ struct xe_ras_threshold_crossed {
>  	struct xe_ras_error_class counters[XE_RAS_NUM_COUNTERS];
>  } __packed;
>  
> +/**
> + * struct xe_ras_info_queue_header - Metadata for large info queue data transfers
> + *
> + * Provides chunk metadata for commands that support extended info queue
> + * functionality. Used when the total data exceeds a single mailbox response.
> + */
> +struct xe_ras_info_queue_header {
> +	/** @total_size: Total size of the complete info queue data in bytes */
> +	u32 total_size;
> +	/** @chunk_offset: Offset of this chunk within the total data in bytes */
> +	u32 chunk_offset;
> +	/** @chunk_size: Size of the data in this chunk in bytes */
> +	u32 chunk_size;
> +	/** @sequence_number: Sequence number for this chunk, starts at 0 */
> +	u32 sequence_number;
> +	/** @flags: Info queue control flags (RAS_INFO_QUEUE_FLAG_*) */
> +	u32 flags:8;
> +	/** @compression_type: Compression algorithm used; 0 = none */
> +	u32 compression_type:4;
> +	/** @num_headers: Number of detailed counter headers at start of queue_data */
> +	u32 num_headers:5;
> +	/** @reserved: Reserved for future use */
> +	u32 reserved:15;
> +	/** @checksum: CRC32 checksum of this chunk data */
> +	u32 checksum;
> +} __packed;

all those __packed structs look like part of the firmware ABI
shouldn't we keep them in a separate file in abi/ folder
> +
> +/**
> + * struct xe_ras_info_queue_request - Request for a specific chunk of info queue data
> + *
> + * Allows the driver to request continuation of large info queue transfers
> + * by specifying an offset and size within the full data set.
> + */
> +struct xe_ras_info_queue_request {
> +	/** @requested_offset: Byte offset of the requested data chunk */
> +	u32 requested_offset;
> +	/** @requested_size: Maximum size of the requested chunk in bytes */
> +	u32 requested_size;
> +	/** @session_id: Session ID to correlate multi-chunk transfers */
> +	struct xe_ras_error_class session_id;
> +	/** @reserved: Reserved for future use */
> +	u32 reserved;
> +} __packed;
> +
> +/**
> + * struct xe_ras_info_queue_response - Generic response for commands with info queues
> + *
> + * Standard response format for any command that returns an info queue
> + * payload. May be embedded in a command-specific response structure.
> + */
> +struct xe_ras_info_queue_response {
> +	/** @queue_header: Info queue metadata for this chunk */
> +	struct xe_ras_info_queue_header queue_header;
> +	/** @queue_data: Info queue data for this chunk */
> +	u8 queue_data[XE_RAS_INFO_QUEUE_MAX_CHUNK_SIZE];
> +} __packed;
> +
> +/**
> + * struct xe_ras_info_queue_dynamic_counter_hdr - Aggregate counter header entry
> + *
> + * When a session requests aggregate counter data, one header per matching
> + * dynamic counter class is prepended to the queue data. The @counter field
> + * indicates how many subsequent error log entries belong to this class.
> + */
> +struct xe_ras_info_queue_dynamic_counter_hdr {
> +	/** @error_class: Error class associated with this counter group */
> +	struct xe_ras_error_class error_class;
> +	/** @counter: Number of error log entries that follow for this class */
> +	u32 counter;
> +} __packed;
> +
> +/**
> + * struct xe_ras_error_log - Single error log entry following dynamic counter headers
> + */
> +struct xe_ras_error_log {
> +	/** @timestamp: Timestamp when the error was recorded */
> +	u64 timestamp;
> +	/** @error_details: Error-specific details */
> +	u32 error_details[16];
> +} __packed;
> +
> +/**
> + * struct xe_ras_get_info_queue_data_request - Request for RAS_CMD_GET_INFO_QUEUE_DATA
> + */
> +struct xe_ras_get_info_queue_data_request {
> +	/** @queue_request: Info queue request parameters */
> +	struct xe_ras_info_queue_request queue_request;
> +	/** @source_command: Original command that generated the info queue */
> +	u32 source_command;
> +	/** @source_context: Context from original command, if applicable */
> +	struct xe_ras_error_class source_context;
> +} __packed;
> +
> +/**
> + * struct xe_ras_get_info_queue_data_response - Response for RAS_CMD_GET_INFO_QUEUE_DATA
> + */
> +struct xe_ras_get_info_queue_data_response {
> +	/** @operation_status: Status of the retrieval operation */
> +	u32 operation_status;
> +	/** @queue_response: Info queue data chunk */
> +	struct xe_ras_info_queue_response queue_response;
> +} __packed;
> +
>  /**
>   * struct xe_ras_get_counter_request - Request structure for get counter
>   */
> @@ -286,4 +393,5 @@ struct xe_ras_set_health_response {
>  	/** @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 d0341538ad05..17f53cb78dc4 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> +++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> @@ -28,6 +28,7 @@ enum xe_sysctrl_group {
>   * @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
> + * @XE_SYSCTRL_CMD_GET_INFO_QUEUE_DATA: Retrieve a chunk of info queue data
>   */
>  enum xe_sysctrl_gfsp_cmd {
>  	XE_SYSCTRL_CMD_GET_SOC_ERROR		= 0x01,
> @@ -36,6 +37,7 @@ enum xe_sysctrl_gfsp_cmd {
>  	XE_SYSCTRL_CMD_GET_PENDING_EVENT	= 0x07,
>  	XE_SYSCTRL_CMD_GET_HEALTH		= 0x0B,
>  	XE_SYSCTRL_CMD_SET_HEALTH		= 0x0C,
> +	XE_SYSCTRL_CMD_GET_INFO_QUEUE_DATA	= 0x0D,
>  };
>  
>  /**