gpu: nvgpu: Add IOCTL for SM_EXCEPTION_TYPE_MASK

Add new ioctl to set the SM_EXCEPTION_TYPE_MASK is
added to dbg session.
Currently support SM_EXCEPTION_TYPE_MASK_FATAL type
If this type is set then the code will skip RC recovery,
instead trigger CILP preemption.

bug  200412641
JIRA NVGPU-702

Change-Id: I4b1f18379ee792cd324ccc555939e0f4f5c9e3b4
Signed-off-by: Vinod G <vinodg@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1729792
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 6 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gr_gk20a.h b/drivers/gpu/nvgpu/gk20a/gr_gk20a.h
index 0c6be57b..804e0e25 100644
--- a/drivers/gpu/nvgpu/gk20a/gr_gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/gr_gk20a.h
@@ -437,6 +437,12 @@ struct gr_gk20a {
         u32 no_of_sm;
         struct sm_info *sm_to_cluster;
         struct nvgpu_gr_sm_error_state *sm_error_states;
+
+#define NVGPU_SM_EXCEPTION_TYPE_MASK_NONE               (0x0U)
+#define NVGPU_SM_EXCEPTION_TYPE_MASK_FATAL              (0x1U << 0)
+        u32 sm_exception_mask_type;
+        u32 sm_exception_mask_refcount;
+
 #if defined(CONFIG_GK20A_CYCLE_STATS)
         struct nvgpu_mutex                      cs_lock;
         struct gk20a_cs_snapshot        *cs_data;