Re: [RFC PATCH 2/7] drm/xe/xe_ras: Add support to retrieve info queue data for CRI

["Mallesh, Koujalagi" <mallesh.koujalagi@intel.com>]

[-- Attachment #1: Type: text/plain, Size: 8580 bytes --]


On 02-07-2026 04:44 pm, Badal Nilawar wrote:
> Add support to retrieve info queue data. It can be retrieved when
> has_info_queue=1 and RAS_INFO_QUEUE_FLAG_MORE_DATA is set in
> response of XE_SYSCTRL_CMD_GET_COUNTER.
>
nit: Please change commit message, we haven't checked has_info_queue=1
>   
> Signed-off-by: Badal Nilawar<badal.nilawar@intel.com>
> Assisted-by: Copilot:claude-sonnet-4.6
> ---
>   drivers/gpu/drm/xe/xe_ras.c                   |  34 ++++++
>   drivers/gpu/drm/xe/xe_ras_types.h             | 112 +++++++++++++++++-
>   drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |   2 +
>   3 files changed, 147 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
> index 44f4e1a3455b..85b0202467f6 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -270,6 +270,40 @@ 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)
> +{
Why we need info queue data? When we are going to use info queue data?
> +	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);
> +
What happen when system control send corrupt data?
> +	*out = response;
> +	return 0;
> +}
> +
>   /**
>    * xe_ras_init - Initialize Xe RAS
>    * @xe: xe device instance
> diff --git a/drivers/gpu/drm/xe/xe_ras_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
> index 6688e11f57a8..fc496888b3f8 100644
> --- a/drivers/gpu/drm/xe/xe_ras_types.h
> +++ b/drivers/gpu/drm/xe/xe_ras_types.h
> @@ -9,6 +9,12 @@
>   #include <linux/types.h>
>   
>   #define XE_RAS_NUM_COUNTERS			16
> +#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
> +#define XE_RAS_INFO_QUEUE_FLAG_OVERFLOW         0x04
> +#define XE_RAS_INFO_QUEUE_FLAG_COMPRESSED       0x08
>   

What is use of XE_RAS_INFO_QUEUE_FLAG_COMPRESSED? When we are using it?

Thanks,

-/Mallesh

>   /**
>    * struct xe_ras_error_common - Error fields that are common across all products
> @@ -71,7 +77,64 @@ struct xe_ras_threshold_crossed {
>   } __packed;
>   
>   /**
> - * struct xe_ras_get_counter_request - Request structure for get counter
> + * 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;
> +
> +/**
> + * 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_get_counter_request - Request for get error counter
>    */
>   struct xe_ras_get_counter_request {
>   	/** @counter: Error counter to be queried */
> @@ -121,4 +184,51 @@ struct xe_ras_clear_counter_response {
>   	/** @reserved1: Reserved for future use */
>   	u32 reserved1[3];
>   } __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;
> +
>   #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..538d93352655 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> +++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> @@ -25,11 +25,13 @@ 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_PENDING_EVENT: Retrieve pending event
> + * @XE_SYSCTRL_CMD_GET_INFO_QUEUE_DATA: Retrieve a chunk of info queue data
>    */
>   enum xe_sysctrl_gfsp_cmd {
>   	XE_SYSCTRL_CMD_GET_COUNTER		= 0x03,
>   	XE_SYSCTRL_CMD_CLEAR_COUNTER		= 0x04,
>   	XE_SYSCTRL_CMD_GET_PENDING_EVENT	= 0x07,
> +	XE_SYSCTRL_CMD_GET_INFO_QUEUE_DATA	= 0x0D,
>   };
>   
>   /**

[-- Attachment #2: Type: text/html, Size: 9404 bytes --]