On Wed, Aug 1, 2018, 9:05 PM Andrey Grodzovsky <Andrey.Grodzovsky@amd.com> wrote:

Clarification question -=C2=A0 if the run = queues belong to different
schedulers they effectively point to different rings,

it means we allow to move (reschedule) a drm_sched_entity from one ring to another - i assume that the idea int the first place, that

you have a set of HW rings and you can utilize any of them for your jobs (like compute rings). Correct ?

Andrey

On 08/01/2018 04:20 AM, Nayan Deshmukh wrote:
> The function selects the run queue from the rq_list with the
> least load. The load is decided by the number of jobs in a
> scheduler.
>
> v2: avoid using atomic read twice consecutively, instead store
>=C2=A0 =C2=A0 =C2=A0 it locally
>
> Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com= >
> ---
>=C2=A0 =C2=A0drivers/gpu/drm/scheduler/gpu_scheduler.c | 25 +++++++++++= ++++++++++++++
>=C2=A0 =C2=A01 file changed, 25 insertions(+)
>
> diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/d= rm/scheduler/gpu_scheduler.c
> index 375f6f7f6a93..fb4e542660b0 100644
> --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
> +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
> @@ -255,6 +255,31 @@ static bool drm_sched_entity_is_ready(struct drm_= sched_entity *entity)
>=C2=A0 =C2=A0 =C2=A0 =C2=A0return true;
>=C2=A0 =C2=A0}
>=C2=A0 =C2=A0
> +/**
> + * drm_sched_entity_get_free_sched - Get the rq from rq_list with lea= st load
> + *
> + * @entity: scheduler entity
> + *
> + * Return the pointer to the rq with least load.
> + */
> +static struct drm_sched_rq *
> +drm_sched_entity_get_free_sched(struct drm_sched_entity *entity)
> +{
> +=C2=A0 =C2=A0 =C2=A0struct drm_sched_rq *rq =3D NULL;
> +=C2=A0 =C2=A0 =C2=A0unsigned int min_jobs =3D UINT_MAX, num_jobs;
> +=C2=A0 =C2=A0 =C2=A0int i;
> +
> +=C2=A0 =C2=A0 =C2=A0for (i =3D 0; i < entity->num_rq_list; ++i)= {
> +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0num_jobs =3D atomic_r= ead(&entity->rq_list[i]->sched->num_jobs);
> +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0if (num_jobs < min= _jobs) {
> +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= =C2=A0min_jobs =3D num_jobs;
> +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= =C2=A0rq =3D entity->rq_list[i];
> +=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0}
> +=C2=A0 =C2=A0 =C2=A0}
> +
> +=C2=A0 =C2=A0 =C2=A0return rq;
> +}
> +
>=C2=A0 =C2=A0static void drm_sched_entity_kill_jobs_cb(struct dma_fence= *f,
>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0struct dma_fence_cb = *cb)
>=C2=A0 =C2=A0{

--000000000000707621057261e2eb-- --===============1189009893== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVsCg== --===============1189009893==--