gpu: nvgpu: hal for syncpt_incr_per_release

Create hal to indicate syncpt increments per release.
Legacy chip uses 2 syncpt increments per release and gv1xx
onwards uses 1 syncpt increment per release.

Bug 2066025

Change-Id: I5d6d0a5368ef561f8150fbb7120181f49f6e338b
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1669817
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This commit is contained in:
seshendra Gadagottu
2018-03-06 13:25:11 -08:00
committed by mobile promotions
parent 7a5a2fb75a
commit 3df619f68a
13 changed files with 30 additions and 2 deletions

View File

@@ -406,6 +406,7 @@ void gk20a_fifo_add_syncpt_wait_cmd(struct gk20a *g,
struct priv_cmd_entry *cmd, u32 off,
u32 id, u32 thresh, u64 gpu_va);
u32 gk20a_fifo_get_syncpt_wait_cmd_size(void);
u32 gk20a_fifo_get_syncpt_incr_per_release(void);
void gk20a_fifo_add_syncpt_incr_cmd(struct gk20a *g,
bool wfi_cmd, struct priv_cmd_entry *cmd,
u32 id, u64 gpu_va);