diff mbox

[3/6] drm/nouveau: hook up cache sync functions

Message ID 1377648050-6649-4-git-send-email-dev@lynxeye.de (mailing list archive)
State New, archived
Headers show

Commit Message

Lucas Stach Aug. 28, 2013, midnight UTC 
Signed-off-by: Lucas Stach <dev@lynxeye.de>
---
 drivers/gpu/drm/nouveau/nouveau_bo.c  | 4 ++++
 drivers/gpu/drm/nouveau/nouveau_gem.c | 5 +++++
 2 files changed, 9 insertions(+)

Comments

Konrad Rzeszutek Wilk Aug. 28, 2013, 4:43 p.m. UTC | #1 
On Wed, Aug 28, 2013 at 02:00:47AM +0200, Lucas Stach wrote:
> Signed-off-by: Lucas Stach <dev@lynxeye.de>
> ---
>  drivers/gpu/drm/nouveau/nouveau_bo.c  | 4 ++++
>  drivers/gpu/drm/nouveau/nouveau_gem.c | 5 +++++
>  2 files changed, 9 insertions(+)
> 
> diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
> index af20fba..f4a2eb9 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_bo.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
> @@ -411,6 +411,10 @@ nouveau_bo_validate(struct nouveau_bo *nvbo, bool interruptible,
>  {
>  	int ret;
>  
> +	if (nvbo->bo.ttm && nvbo->bo.ttm->caching_state == tt_cached)

You don't want to do it also for tt_wc ?

> +		ttm_dma_tt_cache_sync_for_device((struct ttm_dma_tt *)nvbo->bo.ttm,
> +			&nouveau_bdev(nvbo->bo.ttm->bdev)->dev->pdev->dev);
> +
>  	ret = ttm_bo_validate(&nvbo->bo, &nvbo->placement,
>  			      interruptible, no_wait_gpu);
>  	if (ret)
> diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
> index 830cb7b..f632b92 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_gem.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
> @@ -901,6 +901,11 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
>  	ret = ttm_bo_wait(&nvbo->bo, true, true, no_wait);
>  	spin_unlock(&nvbo->bo.bdev->fence_lock);
>  	drm_gem_object_unreference_unlocked(gem);
> +
> +	if (!ret && nvbo->bo.ttm && nvbo->bo.ttm->caching_state == tt_cached)

Ditto? 
> +		ttm_dma_tt_cache_sync_for_cpu((struct ttm_dma_tt *)nvbo->bo.ttm,
> +					      &dev->pdev->dev);
> +
>  	return ret;
>  }
>  
> -- 
> 1.8.3.1
> 
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/dri-devel
Lucas Stach Aug. 28, 2013, 4:58 p.m. UTC | #2 
Am Mittwoch, den 28.08.2013, 12:43 -0400 schrieb Konrad Rzeszutek Wilk:
> On Wed, Aug 28, 2013 at 02:00:47AM +0200, Lucas Stach wrote:
> > Signed-off-by: Lucas Stach <dev@lynxeye.de>
> > ---
> >  drivers/gpu/drm/nouveau/nouveau_bo.c  | 4 ++++
> >  drivers/gpu/drm/nouveau/nouveau_gem.c | 5 +++++
> >  2 files changed, 9 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
> > index af20fba..f4a2eb9 100644
> > --- a/drivers/gpu/drm/nouveau/nouveau_bo.c
> > +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
> > @@ -411,6 +411,10 @@ nouveau_bo_validate(struct nouveau_bo *nvbo, bool interruptible,
> >  {
> >  	int ret;
> >  
> > +	if (nvbo->bo.ttm && nvbo->bo.ttm->caching_state == tt_cached)
> 
> You don't want to do it also for tt_wc ?
> 
No the point of using writecombined memory for BOs is to explicitly
avoid the need for this cache sync. An uncached MMIO read from the
device should already flush out all writecombining buffers and this read
is always happening when submitting a pushbuf.

> > +		ttm_dma_tt_cache_sync_for_device((struct ttm_dma_tt *)nvbo->bo.ttm,
> > +			&nouveau_bdev(nvbo->bo.ttm->bdev)->dev->pdev->dev);
> > +
> >  	ret = ttm_bo_validate(&nvbo->bo, &nvbo->placement,
> >  			      interruptible, no_wait_gpu);
> >  	if (ret)
> > diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
> > index 830cb7b..f632b92 100644
> > --- a/drivers/gpu/drm/nouveau/nouveau_gem.c
> > +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
> > @@ -901,6 +901,11 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
> >  	ret = ttm_bo_wait(&nvbo->bo, true, true, no_wait);
> >  	spin_unlock(&nvbo->bo.bdev->fence_lock);
> >  	drm_gem_object_unreference_unlocked(gem);
> > +
> > +	if (!ret && nvbo->bo.ttm && nvbo->bo.ttm->caching_state == tt_cached)
> 
> Ditto?
cpu_prep is used to make the kernel aware of a following userspace read.
Writecombined mappings are essentially uncached from the read
perspective.

>  
> > +		ttm_dma_tt_cache_sync_for_cpu((struct ttm_dma_tt *)nvbo->bo.ttm,
> > +					      &dev->pdev->dev);
> > +
> >  	return ret;
> >  }
> >  
> > -- 
> > 1.8.3.1
> > 
> > _______________________________________________
> > dri-devel mailing list
> > dri-devel@lists.freedesktop.org
> > http://lists.freedesktop.org/mailman/listinfo/dri-devel
Konrad Rzeszutek Wilk Aug. 28, 2013, 6:21 p.m. UTC | #3 
On Wed, Aug 28, 2013 at 06:58:37PM +0200, Lucas Stach wrote:
> Am Mittwoch, den 28.08.2013, 12:43 -0400 schrieb Konrad Rzeszutek Wilk:
> > On Wed, Aug 28, 2013 at 02:00:47AM +0200, Lucas Stach wrote:
> > > Signed-off-by: Lucas Stach <dev@lynxeye.de>
> > > ---
> > >  drivers/gpu/drm/nouveau/nouveau_bo.c  | 4 ++++
> > >  drivers/gpu/drm/nouveau/nouveau_gem.c | 5 +++++
> > >  2 files changed, 9 insertions(+)
> > > 
> > > diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
> > > index af20fba..f4a2eb9 100644
> > > --- a/drivers/gpu/drm/nouveau/nouveau_bo.c
> > > +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
> > > @@ -411,6 +411,10 @@ nouveau_bo_validate(struct nouveau_bo *nvbo, bool interruptible,
> > >  {
> > >  	int ret;
> > >  
> > > +	if (nvbo->bo.ttm && nvbo->bo.ttm->caching_state == tt_cached)
> > 
> > You don't want to do it also for tt_wc ?
> > 
> No the point of using writecombined memory for BOs is to explicitly
> avoid the need for this cache sync. An uncached MMIO read from the
> device should already flush out all writecombining buffers and this read
> is always happening when submitting a pushbuf.


Could you include this explanation in the git commit description please?

> 
> > > +		ttm_dma_tt_cache_sync_for_device((struct ttm_dma_tt *)nvbo->bo.ttm,
> > > +			&nouveau_bdev(nvbo->bo.ttm->bdev)->dev->pdev->dev);
> > > +
> > >  	ret = ttm_bo_validate(&nvbo->bo, &nvbo->placement,
> > >  			      interruptible, no_wait_gpu);
> > >  	if (ret)
> > > diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
> > > index 830cb7b..f632b92 100644
> > > --- a/drivers/gpu/drm/nouveau/nouveau_gem.c
> > > +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
> > > @@ -901,6 +901,11 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
> > >  	ret = ttm_bo_wait(&nvbo->bo, true, true, no_wait);
> > >  	spin_unlock(&nvbo->bo.bdev->fence_lock);
> > >  	drm_gem_object_unreference_unlocked(gem);
> > > +
> > > +	if (!ret && nvbo->bo.ttm && nvbo->bo.ttm->caching_state == tt_cached)
> > 
> > Ditto?
> cpu_prep is used to make the kernel aware of a following userspace read.
> Writecombined mappings are essentially uncached from the read
> perspective.
> 
> >  
> > > +		ttm_dma_tt_cache_sync_for_cpu((struct ttm_dma_tt *)nvbo->bo.ttm,
> > > +					      &dev->pdev->dev);
> > > +
> > >  	return ret;
> > >  }
> > >  
> > > -- 
> > > 1.8.3.1
> > > 
> > > _______________________________________________
> > > dri-devel mailing list
> > > dri-devel@lists.freedesktop.org
> > > http://lists.freedesktop.org/mailman/listinfo/dri-devel
> 
>
diff mbox

Patch

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index af20fba..f4a2eb9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -411,6 +411,10 @@  nouveau_bo_validate(struct nouveau_bo *nvbo, bool interruptible,
 {
 	int ret;
 
+	if (nvbo->bo.ttm && nvbo->bo.ttm->caching_state == tt_cached)
+		ttm_dma_tt_cache_sync_for_device((struct ttm_dma_tt *)nvbo->bo.ttm,
+			&nouveau_bdev(nvbo->bo.ttm->bdev)->dev->pdev->dev);
+
 	ret = ttm_bo_validate(&nvbo->bo, &nvbo->placement,
 			      interruptible, no_wait_gpu);
 	if (ret)
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 830cb7b..f632b92 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -901,6 +901,11 @@  nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
 	ret = ttm_bo_wait(&nvbo->bo, true, true, no_wait);
 	spin_unlock(&nvbo->bo.bdev->fence_lock);
 	drm_gem_object_unreference_unlocked(gem);
+
+	if (!ret && nvbo->bo.ttm && nvbo->bo.ttm->caching_state == tt_cached)
+		ttm_dma_tt_cache_sync_for_cpu((struct ttm_dma_tt *)nvbo->bo.ttm,
+					      &dev->pdev->dev);
+
 	return ret;
 }