gpu: nvgpu: ramin_big_page_size default val is set to 64kb

-MMU_CTRL_USE_PDB_BIG_PAGE_SIZE is set to TRUE and hence
 RAMIN_BIG_PAGE_SIZE should be set to 64KB i.e. val 1.
 By default this is set to 128KB i.e. val 0.
-This change will also fix an issue where perfbuffer_enable and
 nvgpu_init_hwpm function pass 0 as big page size while initializing
 inst_block and due to which ramin_big_page_size does not get updated
 to 64KB and remains set to unsupported 128KB value.
-Volta supports 64KB for big pages. Selecting 128KB for
 big pages results in an UNBOUND_INSTANCE fault.

Bug 200327596

Change-Id: Ie304e4e5ff7bedaead27e9380d64c59013dd64ca
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1639540
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 2 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gp10b/mm_gp10b.c b/drivers/gpu/nvgpu/gp10b/mm_gp10b.c
index 8cefbd3e..33591edc 100644
--- a/drivers/gpu/nvgpu/gp10b/mm_gp10b.c
+++ b/drivers/gpu/nvgpu/gp10b/mm_gp10b.c
@@ -431,8 +431,9 @@ void gp10b_mm_init_pdb(struct gk20a *g, struct nvgpu_mem *inst_block,
                   ram_in_page_dir_base_target_sys_mem_ncoh_f(),
                   ram_in_page_dir_base_target_vid_mem_f()) |
                 ram_in_page_dir_base_vol_true_f() |
+                ram_in_big_page_size_64kb_f() |
                 ram_in_page_dir_base_lo_f(pdb_addr_lo) |
-                1 << 10);
+                ram_in_use_ver2_pt_format_true_f());
 
         nvgpu_mem_wr32(g, inst_block, ram_in_page_dir_base_hi_w(),
                 ram_in_page_dir_base_hi_f(pdb_addr_hi));