gpu: nvgpu: fix setting gr_pd_ab_dist_cfg1_r()

gr_*__set_alpha_circular_buffer_size() left max_batches field of
  gr_pd_ab_dist_cfg1_r as 0 which results in too many alpha beta
  transitions and poor performance when tessellation or geometry
  shaders are used

Change-Id: If18feb1119e9672005455155dc56337cd444a1f1
Signed-off-by: David Li <davli@nvidia.com>
Reviewed-on: http://git-master/r/735476
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>

1 files changed, 2 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
index b709a980..d0c5da0e 100644
--- a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
@@ -4692,7 +4692,8 @@ static void gk20a_gr_set_alpha_circular_buffer_size(struct gk20a *g, u32 data)
                 gr_pd_ab_dist_cfg1_max_output_granularity_v();
 
         gk20a_writel(g, gr_pd_ab_dist_cfg1_r(),
-                gr_pd_ab_dist_cfg1_max_output_f(pd_ab_max_output));
+                gr_pd_ab_dist_cfg1_max_output_f(pd_ab_max_output) |
+                gr_pd_ab_dist_cfg1_max_batches_init_f());
 
         for (gpc_index = 0; gpc_index < gr->gpc_count; gpc_index++) {
                 stride = proj_gpc_stride_v() * gpc_index;