[Mesa-dev] [PATCH v2 5/5] i965/gen9: Allocate YF/YS tiled buffer objects

[Ben Widawsky]

On Tue, Jun 23, 2015 at 01:23:05PM -0700, Anuj Phogat wrote:
> In case of I915_TILING_{X,Y} we need to pass tiling format to libdrm
> using drm_intel_bo_alloc_tiled(). But, In case of YF/YS tiled buffers
> libdrm need not know about the tiling format because these buffers
> don't have hardware support to be tiled or detiled through a fenced
> region. libdrm still need to know buffer alignment value for its use
> in kernel when resolving the relocation.
> 
> Using drm_intel_bo_alloc_for_render() for YF/YS tiled buffers
> satisfy both the above conditions.
> 
> V2: Delete min/max buffer size restrictions not valid for i965+.
>     Remove redundant align to tile size statements.
>     Remove some redundant code now when there are no min/max buffer size.
> 
> Signed-off-by: Anuj Phogat <anuj.phogat at gmail.com>
> Cc: Ben Widawsky <ben at bwidawsk.net>
> ---
>  src/mesa/drivers/dri/i965/intel_mipmap_tree.c | 62 +++++++++++++++++++++++++--
>  1 file changed, 58 insertions(+), 4 deletions(-)
> 
> diff --git a/src/mesa/drivers/dri/i965/intel_mipmap_tree.c b/src/mesa/drivers/dri/i965/intel_mipmap_tree.c
> index 80c52f2..5bcb094 100644
> --- a/src/mesa/drivers/dri/i965/intel_mipmap_tree.c
> +++ b/src/mesa/drivers/dri/i965/intel_mipmap_tree.c
> @@ -558,6 +558,48 @@ intel_lower_compressed_format(struct brw_context *brw, mesa_format format)
>     }
>  }
>  
> +/* This function computes Yf/Ys tiled bo size, alignment and pitch. */
> +static uint64_t
> +intel_get_yf_ys_bo_size(struct intel_mipmap_tree *mt, unsigned *alignment,
> +                        uint64_t *pitch)
> +{
> +   const uint32_t bpp = mt->cpp * 8;
> +   const uint32_t aspect_ratio = (bpp == 16 || bpp == 64) ? 2 : 1;
> +   uint32_t tile_width, tile_height;
> +   uint64_t stride, size, aligned_y;
> +
> +   assert(mt->tr_mode != INTEL_MIPTREE_TRMODE_NONE);
> +
> +   *alignment = mt->tr_mode == INTEL_MIPTREE_TRMODE_YF ? 4096 : 64 * 1024;
> +
> +   switch (bpp) {
> +   case 8:
> +      tile_height = 64;
> +      break;
> +   case 16:
> +   case 32:
> +      tile_height = 32;
> +      break;
> +   case 64:
> +   case 128:
> +      tile_height = 16;
> +      break;
> +   default:
> +      unreachable("not reached");
> +   }
> +
> +   if (mt->tr_mode == INTEL_MIPTREE_TRMODE_YS)
> +      tile_height *= 4;
> +
> +   aligned_y = ALIGN(mt->total_height, tile_height);
> +   stride = mt->total_width * mt->cpp;
> +   tile_width = tile_height * mt->cpp * aspect_ratio;
> +   stride = ALIGN(stride, tile_width);
> +   size = stride * aligned_y;
> +
> +   *pitch = stride;
> +   return size;
> +}
>  
>  struct intel_mipmap_tree *
>  intel_miptree_create(struct brw_context *brw,
> @@ -616,11 +658,23 @@ intel_miptree_create(struct brw_context *brw,
>        alloc_flags |= BO_ALLOC_FOR_RENDER;
>  
>     unsigned long pitch;
> -   mt->bo = drm_intel_bo_alloc_tiled(brw->bufmgr, "miptree", total_width,
> -                                     total_height, mt->cpp, &mt->tiling,
> -                                     &pitch, alloc_flags);
>     mt->etc_format = etc_format;
> -   mt->pitch = pitch;
> +
> +   if (mt->tr_mode != INTEL_MIPTREE_TRMODE_NONE) {
> +      unsigned alignment = 0;
> +      unsigned long size;
> +      size = intel_get_yf_ys_bo_size(mt, &alignment, &pitch);
> +      assert(size);
> +      mt->bo = drm_intel_bo_alloc_for_render(brw->bufmgr, "miptree",
> +                                             size, alignment);
> +      mt->pitch = pitch;
> +   } else {
> +      mt->bo = drm_intel_bo_alloc_tiled(brw->bufmgr, "miptree",
> +                                        total_width, total_height, mt->cpp,
> +                                        &mt->tiling, &pitch,
> +                                        alloc_flags);
> +      mt->pitch = pitch;
> +   }
>  
>     /* If the BO is too large to fit in the aperture, we need to use the
>      * BLT engine to support it.  Prior to Sandybridge, the BLT paths can't
> 

You could move mt->pitch = pitch outside of the if/else (or get rid of the local
variable entirely):
Reviewed-by: Ben Widawsky <ben at bwidawsk.net>