Re: [PATCH] drm/amdkfd: Copy HW exception data to user event

[Felix Kuehling <felix.kuehling@xxxxxxx>]

On 2023-11-17 00:20, David Yat Sin wrote:
> Fixes issue where user events of type KFD_EVENT_TYPE_HW_EXCEPTION do not
> have valid data
>
> Signed-off-by: David Yat Sin <David.YatSin@xxxxxxx>

Looks good to me. Do you need a KFD API version bump so ROCr can decide 
whether the information is valid?

Regards,
  Felix


> ---
>   drivers/gpu/drm/amd/amdkfd/kfd_events.c | 4 ++++
>   1 file changed, 4 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
> index 0f58be65132f..7d3db017f8d7 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
> @@ -880,6 +880,10 @@ static int copy_signaled_event_data(uint32_t num_events,
>   				dst = &data[i].memory_exception_data;
>   				src = &event->memory_exception_data;
>   				size = sizeof(struct kfd_hsa_memory_exception_data);
> +                        } else if (event->type == KFD_EVENT_TYPE_HW_EXCEPTION) {
> +                                dst = &data[i].hw_exception_data;
> +                                src = &event->hw_exception_data;
> +                                size = sizeof(struct kfd_hsa_hw_exception_data);
>   			} else if (event->type == KFD_EVENT_TYPE_SIGNAL &&
>   				waiter->event_age_enabled) {
>   				dst = &data[i].signal_event_data.last_event_age;