gpu: nvgpu: support to parse VF table

JIRA DNVGPU-123

function was added to retrieve V for F or
F for V for a given clock domain.
Clock domain can be master or slave.
F or V can be intermediate point between two
successive V or F values in VF table.
VF table should be cached before calling this function.
A F value below Fmin will return Vmin.
F > Fmax will return error
A V value above Vmax wil return F max.
A V value below Vmin will return error.

Change-Id: I28b4e8647510c6933e9e1204cfff31d74616e11a
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/1211234
(cherry-picked from commit 5b83b03f2454fbec8d49a064ed09b09c92d3e9fa)
Reviewed-on: http://git-master/r/1235054
Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>

1 files changed, 4 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/pstate/pstate.c b/drivers/gpu/nvgpu/pstate/pstate.c
index 83f17937..94ff5010 100644
--- a/drivers/gpu/nvgpu/pstate/pstate.c
+++ b/drivers/gpu/nvgpu/pstate/pstate.c
@@ -96,6 +96,10 @@ int gk20a_init_pstate_pmu_support(struct gk20a *g)
                 return err;
 
         err = clk_pmu_vf_inject(g);
+        if (err)
+                return err;
+
+        err = clk_vf_point_cache(g);
         return err;
 }