[PATCH 3/4] drm/i915: Implement end_cpu_access

[Chris Wilson]

On Wed, Aug 12, 2015 at 08:29:12PM -0300, Tiago Vignatti wrote:
> Signed-off-by: Tiago Vignatti <tiago.vignatti at intel.com>
> ---
>  drivers/gpu/drm/i915/i915_gem_dmabuf.c | 10 ++++++++++
>  1 file changed, 10 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
> index e9c2bfd..8447ba4 100644
> --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
> +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
> @@ -212,6 +212,15 @@ static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size
>  	return ret;
>  }
>  
> +static void i915_gem_end_cpu_access(struct dma_buf *dma_buf, size_t start, size_t length, enum dma_data_direction direction)
> +{
> +	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
> +	bool write = (direction == DMA_BIDIRECTIONAL || direction == DMA_TO_DEVICE);
> +
> +	if (i915_gem_object_set_to_gtt_domain(obj, write))
> +		DRM_ERROR("failed to set bo into the GTT\n");

Ok, the error here should indeed be rare (would require that the buffer
become active during the sync period and for the end_cpu_access to be
interrupted). To be completely sure that the error is worth reporting,
we should

mutex_lock(&dev->struct_mutex);
was_interruptible = dev_priv->mm.interruptible;
dev_priv->mm.interruptible = false;

ret = i915_gem_object_set_to_gtt_domain(obj, write);

dev_priv->mm.interruptible = was_interruptible;
mutex_unlock(&dev->struct_mutex);

if (unlikely(ret)) DRM_ERROR("unable to flush buffer following CPU access; rendering may be corrupt\n");
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre