Files
linux/drivers/gpu/drm/xe/xe_guc_submit.h
Matthew Brost c9474b726b drm/xe: Wedge the entire device
Wedge the entire device, not just GT which may have triggered the wedge.
To implement this, cleanup the layering so xe_device_declare_wedged()
calls into the lower layers (GT) to ensure entire device is wedged.

While we are here, also signal any pending GT TLB invalidations upon
wedging device.

Lastly, short circuit reset wait if device is wedged.

v2:
 - Short circuit reset wait if device is wedged (Local testing)

Fixes: 8ed9aaae39 ("drm/xe: Force wedged state and block GT reset upon any GPU hang")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240716063902.1390130-1-matthew.brost@intel.com
(cherry picked from commit 7dbe8af13c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2024-07-18 10:25:33 -04:00

42 lines
1.4 KiB
C

/* SPDX-License-Identifier: MIT */
/*
* Copyright © 2022 Intel Corporation
*/
#ifndef _XE_GUC_SUBMIT_H_
#define _XE_GUC_SUBMIT_H_
#include <linux/types.h>
struct drm_printer;
struct xe_exec_queue;
struct xe_guc;
int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids);
int xe_guc_submit_reset_prepare(struct xe_guc *guc);
void xe_guc_submit_reset_wait(struct xe_guc *guc);
void xe_guc_submit_stop(struct xe_guc *guc);
int xe_guc_submit_start(struct xe_guc *guc);
void xe_guc_submit_wedge(struct xe_guc *guc);
int xe_guc_sched_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
int xe_guc_deregister_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
int xe_guc_exec_queue_reset_handler(struct xe_guc *guc, u32 *msg, u32 len);
int xe_guc_exec_queue_memory_cat_error_handler(struct xe_guc *guc, u32 *msg,
u32 len);
int xe_guc_exec_queue_reset_failure_handler(struct xe_guc *guc, u32 *msg, u32 len);
struct xe_guc_submit_exec_queue_snapshot *
xe_guc_exec_queue_snapshot_capture(struct xe_exec_queue *q);
void
xe_guc_exec_queue_snapshot_capture_delayed(struct xe_guc_submit_exec_queue_snapshot *snapshot);
void
xe_guc_exec_queue_snapshot_print(struct xe_guc_submit_exec_queue_snapshot *snapshot,
struct drm_printer *p);
void
xe_guc_exec_queue_snapshot_free(struct xe_guc_submit_exec_queue_snapshot *snapshot);
void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p);
#endif