On Thu, May 23, 2024 at 12:23:11PM +0200, Nirmoy Das wrote:
> On 5/22/2024 10:12 PM, José Roberto de Souza wrote:
>
> Process name help us track what application caused the gpug hang, this
> is crucial when running several applications at the same time.
>
> v2:
> - handle Xe KMD exec_queues without VM
>
> v3:
> - use get_pid_task() (suggested by Nirmoy)
>
> Cc: Rodrigo Vivi [1]<rodrigo.vivi at intel.com>
> Cc: Nirmoy Das [2]<nirmoy.das at intel.com>
> Signed-off-by: José Roberto de Souza [3]<jose.souza at intel.com>
>
> Reviewed-by : Nirmoy Das [4]<nirmoy.das at intel.com>
thank you both, pushed to drm-xe-next
>
> ---
> drivers/gpu/drm/xe/xe_devcoredump.c | 13 +++++++++++++
> drivers/gpu/drm/xe/xe_devcoredump_types.h | 2 ++
> 2 files changed, 15 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
> index e70aef7971930..1643d44f8bc42 100644
> --- a/drivers/gpu/drm/xe/xe_devcoredump.c
> +++ b/drivers/gpu/drm/xe/xe_devcoredump.c
> @@ -110,6 +110,7 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
> drm_printf(&p, "Snapshot time: %lld.%09ld\n", ts.tv_sec, ts.tv_nsec);
> ts = ktime_to_timespec64(ss->boot_time);
> drm_printf(&p, "Uptime: %lld.%09ld\n", ts.tv_sec, ts.tv_nsec);
> + drm_printf(&p, "Process: %s\n", ss->process_name);
> xe_device_snapshot_print(xe, &p);
>
> drm_printf(&p, "\n**** GuC CT ****\n");
> @@ -166,12 +167,24 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
> enum xe_hw_engine_id id;
> u32 adj_logical_mask = q->logical_mask;
> u32 width_mask = (0x1 << q->width) - 1;
> + const char *process_name = "no process";
> + struct task_struct *task = NULL;
> +
> int i;
> bool cookie;
>
> ss->snapshot_time = ktime_get_real();
> ss->boot_time = ktime_get_boottime();
>
> + if (q->vm) {
> + task = get_pid_task(q->vm->xef->drm->pid, PIDTYPE_PID);
> + if (task)
> + process_name = task->comm;
> + }
> + snprintf(ss->process_name, sizeof(ss->process_name), process_name);
> + if (task)
> + put_task_struct(task);
> +
> ss->gt = q->gt;
> INIT_WORK(&ss->work, xe_devcoredump_deferred_snap_work);
>
> diff --git a/drivers/gpu/drm/xe/xe_devcoredump_types.h b/drivers/gpu/drm/xe/xe_devcoredump_types.h
> index 6f654b63c7f1c..923cdf72a816a 100644
> --- a/drivers/gpu/drm/xe/xe_devcoredump_types.h
> +++ b/drivers/gpu/drm/xe/xe_devcoredump_types.h
> @@ -26,6 +26,8 @@ struct xe_devcoredump_snapshot {
> ktime_t snapshot_time;
> /** @boot_time: Relative boot time so the uptime can be calculated. */
> ktime_t boot_time;
> + /** @process_name: Name of process that triggered this gpu hang */
> + char process_name[TASK_COMM_LEN];
>
> /** @gt: Affected GT, used by forcewake for delayed capture */
> struct xe_gt *gt;
>
> References
>
> Visible links
> 1. mailto:rodrigo.vivi at intel.com
> 2. mailto:nirmoy.das at intel.com
> 3. mailto:jose.souza at intel.com
> 4. mailto:nirmoy.das at intel.com