[PATCH] drm/amdkfd: Checkpoint and restore queues on GFX11

[Alex Deucher]

Acked-by: Alex Deucher <alexander.deucher at amd.com>

On Fri, Aug 25, 2023 at 4:10 PM David Francis <David.Francis at amd.com> wrote:
>
> The code in kfd_mqd_manager_v11.c to support criu dump and
> restore of queue state was missing.
>
> Added it; should be equivalent to kfd_mqd_manager_v10.c.
>
> CC: Felix Kuehling <felix.kuehling at amd.com>
> Signed-off-by: David Francis <David.Francis at amd.com>
> ---
>  .../gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c  | 41 +++++++++++++++++++
>  1 file changed, 41 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
> index 2319467d2d95..2a79d37da95d 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
> @@ -321,6 +321,43 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
>         return 0;
>  }
>
> +static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst)
> +{
> +       struct v11_compute_mqd *m;
> +
> +       m = get_mqd(mqd);
> +
> +       memcpy(mqd_dst, m, sizeof(struct v11_compute_mqd));
> +}
> +
> +static void restore_mqd(struct mqd_manager *mm, void **mqd,
> +                       struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
> +                       struct queue_properties *qp,
> +                       const void *mqd_src,
> +                       const void *ctl_stack_src, const u32 ctl_stack_size)
> +{
> +       uint64_t addr;
> +       struct v11_compute_mqd *m;
> +
> +       m = (struct v11_compute_mqd *) mqd_mem_obj->cpu_ptr;
> +       addr = mqd_mem_obj->gpu_addr;
> +
> +       memcpy(m, mqd_src, sizeof(*m));
> +
> +       *mqd = m;
> +       if (gart_addr)
> +               *gart_addr = addr;
> +
> +       m->cp_hqd_pq_doorbell_control =
> +               qp->doorbell_off <<
> +                       CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
> +       pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
> +                       m->cp_hqd_pq_doorbell_control);
> +
> +       qp->is_active = 0;
> +}
> +
> +
>  static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
>                         struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
>                         struct queue_properties *q)
> @@ -457,6 +494,8 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
>                 mqd->is_occupied = kfd_is_occupied_cp;
>                 mqd->mqd_size = sizeof(struct v11_compute_mqd);
>                 mqd->get_wave_state = get_wave_state;
> +               mqd->checkpoint_mqd = checkpoint_mqd;
> +               mqd->restore_mqd = restore_mqd;
>  #if defined(CONFIG_DEBUG_FS)
>                 mqd->debugfs_show_mqd = debugfs_show_mqd;
>  #endif
> @@ -500,6 +539,8 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
>                 mqd->update_mqd = update_mqd_sdma;
>                 mqd->destroy_mqd = kfd_destroy_mqd_sdma;
>                 mqd->is_occupied = kfd_is_occupied_sdma;
> +               mqd->checkpoint_mqd = checkpoint_mqd;
> +               mqd->restore_mqd = restore_mqd;
>                 mqd->mqd_size = sizeof(struct v11_sdma_mqd);
>  #if defined(CONFIG_DEBUG_FS)
>                 mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
> --
> 2.34.1
>