xe_devcoredump.c | Explore in Territory

// SPDX-License-Identifier: MIT
/*
 * Copyright © 2023 Intel Corporation
 */

#include "xe_devcoredump.h"
#include "xe_devcoredump_types.h"

#include <linux/devcoredump.h>
#include <generated/utsrelease.h>

#include <drm/drm_managed.h>

#include "xe_device.h"
#include "xe_exec_queue.h"
#include "xe_force_wake.h"
#include "xe_gt.h"
#include "xe_gt_printk.h"
#include "xe_guc_ct.h"
#include "xe_guc_submit.h"
#include "xe_hw_engine.h"
#include "xe_sched_job.h"
#include "xe_vm.h"

/**
 * DOC: Xe device coredump
 *
 * Devices overview:
 * Xe uses dev_coredump infrastructure for exposing the crash errors in a
 * standardized way.
 * devcoredump exposes a temporary device under /sys/class/devcoredump/
 * which is linked with our card device directly.
 * The core dump can be accessed either from
 * /sys/class/drm/card<n>/device/devcoredump/ or from
 * /sys/class/devcoredump/devcd<m> where
 * /sys/class/devcoredump/devcd<m>/failing_device is a link to
 * /sys/class/drm/card<n>/device/.
 *
 * Snapshot at hang:
 * The 'data' file is printed with a drm_printer pointer at devcoredump read
 * time. For this reason, we need to take snapshots from when the hang has
 * happened, and not only when the user is reading the file. Otherwise the
 * information is outdated since the resets might have happened in between.
 *
 * 'First' failure snapshot:
 * In general, the first hang is the most critical one since the following hangs
 * can be a consequence of the initial hang. For this reason we only take the
 * snapshot of the 'first' failure and ignore subsequent calls of this function,
 * at least while the coredump device is alive. Dev_coredump has a delayed work
 * queue that will eventually delete the device and free all the dump
 * information.
 */

#ifdef CONFIG_DEV_COREDUMP

/* 1 hour timeout */
#define XE_COREDUMP_TIMEOUT_JIFFIES …

static struct xe_device *coredump_to_xe(const struct xe_devcoredump *coredump)
{ … }

static struct xe_guc *exec_queue_to_guc(struct xe_exec_queue *q)
{ … }

static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
{ … }

static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
				   size_t count, void *data, size_t datalen)
{ … }

static void xe_devcoredump_free(void *data)
{ … }

static void devcoredump_snapshot(struct xe_devcoredump *coredump,
				 struct xe_sched_job *job)
{ … }

/**
 * xe_devcoredump - Take the required snapshots and initialize coredump device.
 * @job: The faulty xe_sched_job, where the issue was detected.
 *
 * This function should be called at the crash time within the serialized
 * gt_reset. It is skipped if we still have the core dump device available
 * with the information of the 'first' snapshot.
 */
void xe_devcoredump(struct xe_sched_job *job)
{ … }

static void xe_driver_devcoredump_fini(void *arg)
{ … }

int xe_devcoredump_init(struct xe_device *xe)
{ … }
#endif
linux/drivers/gpu/drm/xe/xe_devcoredump.c
