gpu: nvgpu: Add pd_max_batches sysfs node for gp10b

Add a new sysfs node pd_max_batches for setting max batches value in
NV_PGRAPH_PRI_PD_AB_DIST_CONFIG_1_MAX_BATCHES register which controls
max number of batches per alpha-beta transition stored in PD.

Bug 1927124

Change-Id: I2817f2d70dab348d8b0b8ba19bf1e9b9d23ca907
Signed-off-by: Sandeep Shinde <sashinde@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1544104
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
(cherry picked from commit aa4daddda23aa44a84464200f497eac802a8e6ce)
Reviewed-on: https://git-master.nvidia.com/r/1543355
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
GVS: Gerrit_Virtual_Submit

1 files changed, 18 insertions, 6 deletions

diff --git a/drivers/gpu/nvgpu/gp10b/gr_gp10b.c b/drivers/gpu/nvgpu/gp10b/gr_gp10b.c
index 74af9817..ee7118e7 100644
--- a/drivers/gpu/nvgpu/gp10b/gr_gp10b.c
+++ b/drivers/gpu/nvgpu/gp10b/gr_gp10b.c
@@ -420,9 +420,15 @@ int gr_gp10b_commit_global_cb_manager(struct gk20a *g,
                 gr_gpc0_ppc0_cbm_beta_cb_size_v_granularity_v()) /
                 gr_pd_ab_dist_cfg1_max_output_granularity_v();
 
-        gr_gk20a_ctx_patch_write(g, ch_ctx, gr_pd_ab_dist_cfg1_r(),
-                gr_pd_ab_dist_cfg1_max_output_f(pd_ab_max_output) |
-                gr_pd_ab_dist_cfg1_max_batches_init_f(), patch);
+        if (g->gr.pd_max_batches) {
+                gr_gk20a_ctx_patch_write(g, ch_ctx, gr_pd_ab_dist_cfg1_r(),
+                        gr_pd_ab_dist_cfg1_max_output_f(pd_ab_max_output) |
+                        gr_pd_ab_dist_cfg1_max_batches_f(g->gr.pd_max_batches), patch);
+        } else {
+                gr_gk20a_ctx_patch_write(g, ch_ctx, gr_pd_ab_dist_cfg1_r(),
+                        gr_pd_ab_dist_cfg1_max_output_f(pd_ab_max_output) |
+                        gr_pd_ab_dist_cfg1_max_batches_init_f(), patch);
+        }
 
         attrib_offset_in_chunk = alpha_offset_in_chunk +
                 gr->tpc_count * gr->alpha_cb_size;
@@ -751,9 +757,15 @@ void gr_gp10b_set_alpha_circular_buffer_size(struct gk20a *g, u32 data)
                 gr_gpc0_ppc0_cbm_alpha_cb_size_v_granularity_v() /
                 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_batches_init_f());
+        if (g->gr.pd_max_batches) {
+                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_batches_f(g->gr.pd_max_batches));
+        } else {
+                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_batches_init_f());
+        }
 
         for (gpc_index = 0; gpc_index < gr->gpc_count; gpc_index++) {
                 stride = gpc_stride * gpc_index;