gpu: nvgpu: nvlink: Add HAL for pll setup

Before nvlink 2.2, driver was responsible for setting the NVLink clocks
during NVLink initialization. For the purpose of security, NVLink PLL
handling is moved to Minion in nvlink 2.2 and driver should stop writing
to these registers.

JIRA NVLINK-167

Change-Id: I18392a29c322da55053037bfde62c8f74ee75288
Signed-off-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1730597
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 1 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/gv100/nvlink_gv100.h b/drivers/gpu/nvgpu/gv100/nvlink_gv100.h
index a583c576..0c58438c 100644
--- a/drivers/gpu/nvgpu/gv100/nvlink_gv100.h
+++ b/drivers/gpu/nvgpu/gv100/nvlink_gv100.h
@@ -31,6 +31,7 @@ int gv100_nvlink_init(struct gk20a *g);
 int gv100_nvlink_isr(struct gk20a *g);
 int gv100_nvlink_minion_send_command(struct gk20a *g, u32 link_id, u32 command,
                                                 u32 scratch_0, bool sync);
+int gv100_nvlink_setup_pll(struct gk20a *g, unsigned long link_mask);
 /* API */
 int gv100_nvlink_link_early_init(struct gk20a *g, unsigned long mask);
 u32 gv100_nvlink_link_get_mode(struct gk20a *g, u32 link_id);