gpu: nvgpu: add refcounting for ctxsw disable/enable

ctxsw disable could be called recursively for RM server. Suspend
contexts disables ctxsw at the beginning, then call tsg disable and
preempt. If preempt timeout happens, it goes to recovery path, which
will try to disable ctxsw again. More details on Bug 200331110.

Jira VQRM-2982

Change-Id: I4659c842ae73ed59be51ae65b25366f24abcaf22
Signed-off-by: Shashank Singh <shashsingh@nvidia.com>
Signed-off-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1671716
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Sourab Gupta <sourabg@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 3 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gk20a.h b/drivers/gpu/nvgpu/gk20a/gk20a.h
index 3442861c..4ebdb6a4 100644
--- a/drivers/gpu/nvgpu/gk20a/gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/gk20a.h
@@ -1191,6 +1191,9 @@ struct gk20a {
 
         nvgpu_atomic_t usage_count;
 
+        struct nvgpu_mutex ctxsw_disable_lock;
+        int ctxsw_disable_count;
+
         struct nvgpu_ref refcount;
 
         const char *name;