On Wed, 2015-12-09 at 13:57 +0000, Chris Wilson wrote:
> On Wed, Dec 09, 2015 at 06:16:17PM +0530, ankitprasad.r.sharma@xxxxxxxxx wrote:
> > From: Ankitprasad Sharma <ankitprasad.r.sharma@xxxxxxxxx>
> >
> > This patch adds support for clearing buffer objects via CPU/GTT. This
> > is particularly useful for clearing out the non shmem backed objects.
> > Currently intend to use this only for buffers allocated from stolen
> > region.
> >
> > v2: Added kernel doc for i915_gem_clear_object(), corrected/removed
> > variable assignments (Tvrtko)
> >
> > v3: Map object page by page to the gtt if the pinning of the whole object
> > to the ggtt fails, Corrected function name (Chris)
> >
> > Testcase: igt/gem_stolen
> >
> > Signed-off-by: Ankitprasad Sharma <ankitprasad.r.sharma@xxxxxxxxx>
> > Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
> > ---
> > drivers/gpu/drm/i915/i915_drv.h | 1 +
> > drivers/gpu/drm/i915/i915_gem.c | 79 +++++++++++++++++++++++++++++++++++++++++
> > 2 files changed, 80 insertions(+)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> > index 548a0eb..8e554d3 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.h
> > +++ b/drivers/gpu/drm/i915/i915_drv.h
> > @@ -2856,6 +2856,7 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
> > int *needs_clflush);
> >
> > int __must_check i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
> > +int i915_gem_object_clear(struct drm_i915_gem_object *obj);
> >
> > static inline int __sg_page_count(struct scatterlist *sg)
> > {
> > diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> > index 9d2e6e3..d57e850 100644
> > --- a/drivers/gpu/drm/i915/i915_gem.c
> > +++ b/drivers/gpu/drm/i915/i915_gem.c
> > @@ -5244,3 +5244,82 @@ fail:
> > drm_gem_object_unreference(&obj->base);
> > return ERR_PTR(ret);
> > }
> > +
> > +/**
> > + * i915_gem_clear_object() - Clear buffer object via CPU/GTT
> > + * @obj: Buffer object to be cleared
> > + *
> > + * Return: 0 - success, non-zero - failure
> > + */
> > +int i915_gem_object_clear(struct drm_i915_gem_object *obj)
> > +{
> > + int ret, i;
> > + char __iomem *base;
> > + size_t size = obj->base.size;
> > + struct drm_i915_private *i915 = to_i915(obj->base.dev);
> > + struct drm_mm_node node;
> > +
> > + WARN_ON(!mutex_is_locked(&obj->base.dev->struct_mutex));
>
> Just lockdep_assert_held.
>
> > + ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE | PIN_NONBLOCK);
>
> Would be nice to get the PIN_NOFAULT patches in to give preference to
> userspace mappings....
>
Wouldn't it be better, not to use 2 approaches and just do the clearing
using the insert_page function. (not to even try mapping the whole
object) ?
Thanks,
Ankit
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
