Am 28.08.2014 um 08:56 schrieb Michel D?nzer:
> From: Michel D?nzer <michel.daenzer at amd.com>
>
> This flag is a hint that userspace expects the BO to be accessed by the
> CPU. We can use that hint to prevent such BOs from ever being stored in
> the CPU inaccessible part of VRAM.
>
> Signed-off-by: Michel D?nzer <michel.daenzer at amd.com>

This patch is Reviewed-by: Christian K?nig <christian.koenig at amd.com>

I think we need a similar negative flags as well, e.g. 
RADEON_GEM_NO_CPU_ACCESS.

This way we can stop forcing buffers into the visible VRAM while pinning 
them for scanout.

Regards,
Christian.

> ---
>   drivers/gpu/drm/radeon/radeon_object.c | 11 +++++++++--
>   include/uapi/drm/radeon_drm.h          |  2 ++
>   2 files changed, 11 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/radeon/radeon_object.c 
> b/drivers/gpu/drm/radeon/radeon_object.c
> index dc74cc5..908ea541 100644
> --- a/drivers/gpu/drm/radeon/radeon_object.c
> +++ b/drivers/gpu/drm/radeon/radeon_object.c
> @@ -143,7 +143,12 @@ void radeon_ttm_placement_from_domain(struct radeon_bo 
> *rbo, u32 domain)
>   
>       for (i = 0; i < c; ++i) {
>               rbo->placements[i].fpfn = 0;
> -             rbo->placements[i].lpfn = 0;
> +             if ((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
> +                 (rbo->placements[i].flags & TTM_PL_FLAG_VRAM))
> +                     rbo->placements[i].lpfn =
> +                             rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
> +             else
> +                     rbo->placements[i].lpfn = 0;
>       }
>   
>       /*
> @@ -151,7 +156,9 @@ void radeon_ttm_placement_from_domain(struct radeon_bo 
> *rbo, u32 domain)
>        * improve fragmentation quality.
>        * 512kb was measured as the most optimal number.
>        */
> -     if (rbo->tbo.mem.size > 512 * 1024) {
> +     if (!((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
> +           (rbo->placements[i].flags & TTM_PL_FLAG_VRAM)) &&
> +         rbo->tbo.mem.size > 512 * 1024) {
>               for (i = 0; i < c; i++) {
>                       rbo->placements[i].flags |= TTM_PL_FLAG_TOPDOWN;
>               }
> diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
> index 509b2d7..bf0067b 100644
> --- a/include/uapi/drm/radeon_drm.h
> +++ b/include/uapi/drm/radeon_drm.h
> @@ -799,6 +799,8 @@ struct drm_radeon_gem_info {
>   #define RADEON_GEM_NO_BACKING_STORE (1 << 0)
>   #define RADEON_GEM_GTT_UC           (1 << 1)
>   #define RADEON_GEM_GTT_WC           (1 << 2)
> +/* BO is expected to be accessed by the CPU */
> +#define RADEON_GEM_CPU_ACCESS                (1 << 3)
>   
>   struct drm_radeon_gem_create {
>       uint64_t        size;

Reply via email to