nvgpu: gpu: Support multiple tpc-pg masks.

- TPC powergating should be done before
  calling gk20a_enable_gr_hw.
  gk20a_enable_gr_hw() issues a GR engine reset.

  Without this fix, enabling 1 TPC from each PES
  causes ctxsw timeout error while running GFX Benchmark.

- Adds valid tpc-pg mask for 1/2/3/4 active TPC configs.
    TPC Config - TPC-MASK
  4 TPC configuration - 0x0
  3 TPC configuration - 0x1/0x2/0x4/0x8
  2 TPC configuration - 0x5/0x9/0x6/0xa

- We should not write to gr_fe_tpc_pesmask_r()
  as part of TPC-PG sequence. This register is for
  debug purpose only.

Bug 200442360

Change-Id: I6fbe1ad8fbc836ace8cbaf00ec3d21a12c73e0bd
Signed-off-by: Deepak Goyal <dgoyal@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1809772
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 3 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/include/nvgpu/gk20a.h b/drivers/gpu/nvgpu/include/nvgpu/gk20a.h
index 2ebe0011..8d7ccfa8 100644
--- a/drivers/gpu/nvgpu/include/nvgpu/gk20a.h
+++ b/drivers/gpu/nvgpu/include/nvgpu/gk20a.h
@@ -138,6 +138,8 @@ enum gk20a_cbc_op {
 
 #define nvgpu_get_litter_value(g, v) (g)->ops.get_litter_value((g), v)
 
+#define MAX_TPC_PG_CONFIGS      3
+
 enum nvgpu_unit;
 
 enum nvgpu_flush_op;
@@ -1592,7 +1594,7 @@ struct gk20a {
         u32 tpc_pg_mask;
         bool can_tpc_powergate;
 
-        u32 valid_tpc_mask;
+        u32 valid_tpc_mask[MAX_TPC_PG_CONFIGS];
 
         struct nvgpu_bios bios;
         bool bios_is_init;