Commit 8bfc4963 authored by Zhanjun Dong's avatar Zhanjun Dong Committed by Matt Roper
Browse files

drm/xe/guc: Extract GuC error capture lists 



Upon the G2H Notify-Err-Capture event, parse through the
GuC Log Buffer (error-capture-subregion) and generate one or
more capture-nodes. A single node represents a single "engine-
instance-capture-dump" and contains at least 3 register lists:
global, engine-class and engine-instance. An internal link
list is maintained to store one or more nodes.

Because the link-list node generation happen before the call
to devcoredump, duplicate global and engine-class register
lists for each engine-instance register dump if we find
dependent-engine resets in a engine-capture-group.

To avoid dynamically allocate the output nodes during gt reset,
pre-allocate a fixed number of empty nodes up front (at the
time of ADS registration) that we can consume from or return to
an internal cached list of nodes.

Signed-off-by: default avatarZhanjun Dong <zhanjun.dong@intel.com>
Reviewed-by: default avatarAlan Previn <alan.previn.teres.alexis@intel.com>
Signed-off-by: default avatarMatt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241004193428.3311145-5-zhanjun.dong@intel.com
parent 84d15f42

drivers/gpu/drm/xe/abi/guc_actions_abi.h

+8 −0
Original line number Diff line number Diff line
@@ -176,6 +176,14 @@ enum xe_guc_sleep_state_status { 
#define GUC_LOG_CONTROL_VERBOSITY_MASK	(0xF << GUC_LOG_CONTROL_VERBOSITY_SHIFT)

#define GUC_LOG_CONTROL_DEFAULT_LOGGING	(1 << 8)



enum xe_guc_state_capture_event_status {

	XE_GUC_STATE_CAPTURE_EVENT_STATUS_SUCCESS = 0x0,

	XE_GUC_STATE_CAPTURE_EVENT_STATUS_NOSPACE = 0x1,

};



#define XE_GUC_STATE_CAPTURE_EVENT_STATUS_MASK      0x000000FF

#define XE_GUC_ACTION_STATE_CAPTURE_NOTIFICATION_DATA_LEN 1



#define XE_GUC_TLB_INVAL_TYPE_SHIFT 0

#define XE_GUC_TLB_INVAL_MODE_SHIFT 8

/* Flush PPC or SMRO caches along with TLB invalidation request */

drivers/gpu/drm/xe/abi/guc_log_abi.h

+55 −0
Original line number Diff line number Diff line
@@ -17,4 +17,59 @@ enum guc_log_buffer_type { 


#define GUC_LOG_BUFFER_TYPE_MAX		3



/**

 * struct guc_log_buffer_state - GuC log buffer state

 *

 * Below state structure is used for coordination of retrieval of GuC firmware

 * logs. Separate state is maintained for each log buffer type.

 * read_ptr points to the location where Xe read last in log buffer and

 * is read only for GuC firmware. write_ptr is incremented by GuC with number

 * of bytes written for each log entry and is read only for Xe.

 * When any type of log buffer becomes half full, GuC sends a flush interrupt.

 * GuC firmware expects that while it is writing to 2nd half of the buffer,

 * first half would get consumed by Host and then get a flush completed

 * acknowledgment from Host, so that it does not end up doing any overwrite

 * causing loss of logs. So when buffer gets half filled & Xe has requested

 * for interrupt, GuC will set flush_to_file field, set the sampled_write_ptr

 * to the value of write_ptr and raise the interrupt.

 * On receiving the interrupt Xe should read the buffer, clear flush_to_file

 * field and also update read_ptr with the value of sample_write_ptr, before

 * sending an acknowledgment to GuC. marker & version fields are for internal

 * usage of GuC and opaque to Xe. buffer_full_cnt field is incremented every

 * time GuC detects the log buffer overflow.

 */

struct guc_log_buffer_state {

	/** @marker: buffer state start marker */

	u32 marker[2];

	/** @read_ptr: the last byte offset that was read by KMD previously */

	u32 read_ptr;

	/**

	 * @write_ptr: the next byte offset location that will be written by

	 * GuC

	 */

	u32 write_ptr;

	/** @size: Log buffer size */

	u32 size;

	/**

	 * @sampled_write_ptr: Log buffer write pointer

	 * This is written by GuC to the byte offset of the next free entry in

	 * the buffer on log buffer half full or state capture notification

	 */

	u32 sampled_write_ptr;

	/**

	 * @wrap_offset: wraparound offset

	 * This is the byte offset of location 1 byte after last valid guc log

	 * event entry written by Guc firmware before there was a wraparound.

	 * This field is updated by guc firmware and should be used by Host

	 * when copying buffer contents to file.

	 */

	u32 wrap_offset;

	/** @flags: Flush to file flag and buffer full count */

	u32 flags;

#define	GUC_LOG_BUFFER_STATE_FLUSH_TO_FILE	GENMASK(0, 0)

#define	GUC_LOG_BUFFER_STATE_BUFFER_FULL_CNT	GENMASK(4, 1)

	/** @version: The Guc-Log-Entry format version */

	u32 version;

} __packed;



#endif

drivers/gpu/drm/xe/xe_guc_capture.c

+722 −3

File changed.

Preview size limit exceeded, changes collapsed.

drivers/gpu/drm/xe/xe_guc_capture.h

+1 −0
Original line number Diff line number Diff line
@@ -37,6 +37,7 @@ xe_engine_class_to_guc_capture_class(enum xe_engine_class class) 
	return xe_guc_class_to_capture_class(xe_engine_class_to_guc_class(class));

}



void xe_guc_capture_process(struct xe_guc *guc);

int xe_guc_capture_getlist(struct xe_guc *guc, u32 owner, u32 type,

			   enum guc_capture_list_class_type capture_class, void **outptr);

int xe_guc_capture_getlistsize(struct xe_guc *guc, u32 owner, u32 type,

drivers/gpu/drm/xe/xe_guc_ct.c

+2 −0
Original line number Diff line number Diff line
@@ -1254,6 +1254,8 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len) 
		/* Selftest only at the moment */

		break;

	case XE_GUC_ACTION_STATE_CAPTURE_NOTIFICATION:

		ret = xe_guc_error_capture_handler(guc, payload, adj_len);

		break;

	case XE_GUC_ACTION_NOTIFY_FLUSH_LOG_BUFFER_TO_FILE:

		/* FIXME: Handle this */

		break;