gpu: nvgpu: Call handle_replayable_fault via HAL

gr_gv11b.c had a direct dependency to fb_gv11b.c because it calls FB
to process replayable faults while waiting for SM lockdown. Redirect
that call via HAL to remove the dependency.

JIRA NVGPU-714

Change-Id: Ie6df3658f06b1f867893bc98fe581c95813f0431
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1772884
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/gv11b/hal_gv11b.c b/drivers/gpu/nvgpu/gv11b/hal_gv11b.c
index 9e9387d0..5bfa85da 100644
--- a/drivers/gpu/nvgpu/gv11b/hal_gv11b.c
+++ b/drivers/gpu/nvgpu/gv11b/hal_gv11b.c
@@ -439,6 +439,7 @@ static const struct gpu_ops gv11b_ops = {
                 .set_debug_mode = gm20b_fb_set_debug_mode,
                 .tlb_invalidate = gk20a_fb_tlb_invalidate,
                 .hub_isr = gv11b_fb_hub_isr,
+                .handle_replayable_fault = gv11b_fb_handle_replayable_mmu_fault,
                 .mem_unlock = NULL,
                 .enable_hub_intr = gv11b_fb_enable_hub_intr,
                 .disable_hub_intr = gv11b_fb_disable_hub_intr,