On Fri, Mar 3, 2023 at 2:10 AM Dmitry Baryshkov
<dmitry.baryshkov@xxxxxxxxxx> wrote:
>
> On 03/03/2023 01:53, Rob Clark wrote:
> > From: Rob Clark <robdclark@xxxxxxxxxxxx>
> >
> > Track the nearest deadline on a fence timeline and set a timer to expire
> > shortly before to trigger boost if the fence has not yet been signaled.
> >
> > v2: rebase
> >
> > Signed-off-by: Rob Clark <robdclark@xxxxxxxxxxxx>
> > ---
> > drivers/gpu/drm/msm/msm_fence.c | 74 +++++++++++++++++++++++++++++++++
> > drivers/gpu/drm/msm/msm_fence.h | 20 +++++++++
> > 2 files changed, 94 insertions(+)
>
> Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@xxxxxxxxxx>
>
> A small question: do we boost to fit into the deadline or to miss the
> deadline for as little as possible? If the former is the case, we might
> need to adjust 3ms depending on the workload.
The goal is as much to run with higher clock on the next frame as it
is to not miss a deadline. Ie. we don't want devfreq to come to the
conclusion that running at <50% clks is best due to the amount of
utilization caused by missing ever other vblank.
But 3ms is mostly just "seems like a good compromise" value. It might change.
BR,
-R
> >
> > diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
> > index 56641408ea74..51b461f32103 100644
> > --- a/drivers/gpu/drm/msm/msm_fence.c
> > +++ b/drivers/gpu/drm/msm/msm_fence.c
> > @@ -8,6 +8,35 @@
> >
> > #include "msm_drv.h"
> > #include "msm_fence.h"
> > +#include "msm_gpu.h"
> > +
> > +static struct msm_gpu *fctx2gpu(struct msm_fence_context *fctx)
> > +{
> > + struct msm_drm_private *priv = fctx->dev->dev_private;
> > + return priv->gpu;
> > +}
> > +
> > +static enum hrtimer_restart deadline_timer(struct hrtimer *t)
> > +{
> > + struct msm_fence_context *fctx = container_of(t,
> > + struct msm_fence_context, deadline_timer);
> > +
> > + kthread_queue_work(fctx2gpu(fctx)->worker, &fctx->deadline_work);
> > +
> > + return HRTIMER_NORESTART;
> > +}
> > +
> > +static void deadline_work(struct kthread_work *work)
> > +{
> > + struct msm_fence_context *fctx = container_of(work,
> > + struct msm_fence_context, deadline_work);
> > +
> > + /* If deadline fence has already passed, nothing to do: */
> > + if (msm_fence_completed(fctx, fctx->next_deadline_fence))
> > + return;
> > +
> > + msm_devfreq_boost(fctx2gpu(fctx), 2);
> > +}
> >
> >
> > struct msm_fence_context *
> > @@ -36,6 +65,13 @@ msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr,
> > fctx->completed_fence = fctx->last_fence;
> > *fctx->fenceptr = fctx->last_fence;
> >
> > + hrtimer_init(&fctx->deadline_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
> > + fctx->deadline_timer.function = deadline_timer;
> > +
> > + kthread_init_work(&fctx->deadline_work, deadline_work);
> > +
> > + fctx->next_deadline = ktime_get();
> > +
> > return fctx;
> > }
> >
> > @@ -62,6 +98,8 @@ void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence)
> > spin_lock_irqsave(&fctx->spinlock, flags);
> > if (fence_after(fence, fctx->completed_fence))
> > fctx->completed_fence = fence;
> > + if (msm_fence_completed(fctx, fctx->next_deadline_fence))
> > + hrtimer_cancel(&fctx->deadline_timer);
> > spin_unlock_irqrestore(&fctx->spinlock, flags);
> > }
> >
> > @@ -92,10 +130,46 @@ static bool msm_fence_signaled(struct dma_fence *fence)
> > return msm_fence_completed(f->fctx, f->base.seqno);
> > }
> >
> > +static void msm_fence_set_deadline(struct dma_fence *fence, ktime_t deadline)
> > +{
> > + struct msm_fence *f = to_msm_fence(fence);
> > + struct msm_fence_context *fctx = f->fctx;
> > + unsigned long flags;
> > + ktime_t now;
> > +
> > + spin_lock_irqsave(&fctx->spinlock, flags);
> > + now = ktime_get();
> > +
> > + if (ktime_after(now, fctx->next_deadline) ||
> > + ktime_before(deadline, fctx->next_deadline)) {
> > + fctx->next_deadline = deadline;
> > + fctx->next_deadline_fence =
> > + max(fctx->next_deadline_fence, (uint32_t)fence->seqno);
> > +
> > + /*
> > + * Set timer to trigger boost 3ms before deadline, or
> > + * if we are already less than 3ms before the deadline
> > + * schedule boost work immediately.
> > + */
> > + deadline = ktime_sub(deadline, ms_to_ktime(3));
> > +
> > + if (ktime_after(now, deadline)) {
> > + kthread_queue_work(fctx2gpu(fctx)->worker,
> > + &fctx->deadline_work);
> > + } else {
> > + hrtimer_start(&fctx->deadline_timer, deadline,
> > + HRTIMER_MODE_ABS);
> > + }
> > + }
> > +
> > + spin_unlock_irqrestore(&fctx->spinlock, flags);
> > +}
> > +
> > static const struct dma_fence_ops msm_fence_ops = {
> > .get_driver_name = msm_fence_get_driver_name,
> > .get_timeline_name = msm_fence_get_timeline_name,
> > .signaled = msm_fence_signaled,
> > + .set_deadline = msm_fence_set_deadline,
> > };
> >
> > struct dma_fence *
> > diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h
> > index 7f1798c54cd1..cdaebfb94f5c 100644
> > --- a/drivers/gpu/drm/msm/msm_fence.h
> > +++ b/drivers/gpu/drm/msm/msm_fence.h
> > @@ -52,6 +52,26 @@ struct msm_fence_context {
> > volatile uint32_t *fenceptr;
> >
> > spinlock_t spinlock;
> > +
> > + /*
> > + * TODO this doesn't really deal with multiple deadlines, like
> > + * if userspace got multiple frames ahead.. OTOH atomic updates
> > + * don't queue, so maybe that is ok
> > + */
> > +
> > + /** next_deadline: Time of next deadline */
> > + ktime_t next_deadline;
> > +
> > + /**
> > + * next_deadline_fence:
> > + *
> > + * Fence value for next pending deadline. The deadline timer is
> > + * canceled when this fence is signaled.
> > + */
> > + uint32_t next_deadline_fence;
> > +
> > + struct hrtimer deadline_timer;
> > + struct kthread_work deadline_work;
> > };
> >
> > struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev,
>
> --
> With best wishes
> Dmitry
>
