Re: [PATCH v10 07/11] drm/etnaviv: Add support for the dma coherent device

[Sui Jingfeng]

Hi,

On 2023/6/22 01:53, Lucas Stach wrote:
> Am Donnerstag, dem 22.06.2023 um 01:31 +0800 schrieb Sui Jingfeng:
> > Hi,
> >
> > On 2023/6/22 00:07, Lucas Stach wrote:
> > > And as the HW guarantees it on your platform, your platform
> > > implementation makes this function effectively a no-op. Skipping the
> > > call to this function is breaking the DMA API abstraction, as now the
> > > driver is second guessing the DMA API implementation. I really see no
> > > reason to do this.
> > It is the same reason you chose the word 'effectively', not 'difinitely'.
> >
> > We don't want waste the CPU's time,
> >
> >
> >    to running the dma_sync_sg_for_cpu funcion() function
> >
> >
> > ```
> >
> > void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
> >               int nelems, enum dma_data_direction dir)
> > {
> >       const struct dma_map_ops *ops = get_dma_ops(dev);
> >
> >       BUG_ON(!valid_dma_direction(dir));
> >       if (dma_map_direct(dev, ops))
> >           dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
> >       else if (ops->sync_sg_for_cpu)
> >           ops->sync_sg_for_cpu(dev, sg, nelems, dir);
> >       debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
> > }
> >
> > ```
> >
> >
> >    to running the this:
> >
> >
> > ```
> >
> > int etnaviv_gem_cpu_fini(struct drm_gem_object *obj)
> > {
> >       struct drm_device *dev = obj->dev;
> >       struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
> >       struct etnaviv_drm_private *priv = dev->dev_private;
> >
> >       if (!priv->dma_coherent && etnaviv_obj->flags & ETNA_BO_CACHED) {
> >           /* fini without a prep is almost certainly a userspace error */
> >           WARN_ON(etnaviv_obj->last_cpu_prep_op == 0);
> >           dma_sync_sgtable_for_device(dev->dev, etnaviv_obj->sgt,
> > etnaviv_op_to_dma_dir(etnaviv_obj->last_cpu_prep_op));
> >           etnaviv_obj->last_cpu_prep_op = 0;
> >       }
> >
> >       return 0;
> > }
> >
> > ```
> My judgment as the maintainer of this driver is that the small CPU
> overhead of calling this function is very well worth it, if the
> alternative is breaking the DMA API abstractions.
>
> > But, this is acceptable, because we can kill the GEM_CPU_PREP and
> > GEM_CPU_FINI ioctl entirely
> >
> > at userspace for cached buffer, as this is totally not needed for cached
> > mapping on our platform.
> And that statement isn't true either.

Yes, you are right here. I admit.


Because I have suffered such problem in the past when developing 
xf86-video-loongson.

The root cause, I think,  is the CPU don't know when the GPU have 
finished the rendering.

Or there still some data reside in the GPU's cache.


We have to call etna_bo_cpu_prep(etna_bo, DRM_ETNA_PREP_READ) function

to make sure the  data fetch by CPU is the latest.


I realized this knowledge(issue) five month ago in this year, see [1] 
for reference.

I  just forget this thing when doing the debate with you.


[1] 
https://gitlab.freedesktop.org/longxin2019/xf86-video-loongson/-/commit/95f9596eb19223c3109ea1f32c3e086fd1d43bd8

||


>   The CPU_PREP/FINI ioctls also
> provide fence synchronization between CPU and GPU.

You are correct here.

> There are a few very
> specific cases where skipping those ioctls is acceptable (mostly when
> the userspace driver explicitly wants unsynchronized access), but in
> most cases they are required for correctness.

OK, you are extremely correct.

> Regards,
> Lucas

--
Jingfeng