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>

2 files changed, 2 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/common/linux/driver_common.c b/drivers/gpu/nvgpu/common/linux/driver_common.c
index 9029366f..695bb307 100644
--- a/drivers/gpu/nvgpu/common/linux/driver_common.c
+++ b/drivers/gpu/nvgpu/common/linux/driver_common.c
@@ -62,6 +62,7 @@ static void nvgpu_init_vars(struct gk20a *g)
         nvgpu_mutex_init(&g->client_lock);
         nvgpu_mutex_init(&g->poweron_lock);
         nvgpu_mutex_init(&g->poweroff_lock);
+        nvgpu_mutex_init(&g->ctxsw_disable_lock);
 
         l->regs_saved = l->regs;
         l->bar1_saved = l->bar1;
diff --git a/drivers/gpu/nvgpu/common/linux/vgpu/vgpu_linux.c b/drivers/gpu/nvgpu/common/linux/vgpu/vgpu_linux.c
index 1e5efa38..6f040603 100644
--- a/drivers/gpu/nvgpu/common/linux/vgpu/vgpu_linux.c
+++ b/drivers/gpu/nvgpu/common/linux/vgpu/vgpu_linux.c
@@ -76,6 +76,7 @@ static void vgpu_init_vars(struct gk20a *g, struct gk20a_platform *platform)
 
         nvgpu_mutex_init(&g->poweron_lock);
         nvgpu_mutex_init(&g->poweroff_lock);
+        nvgpu_mutex_init(&g->ctxsw_disable_lock);
         l->regs_saved = l->regs;
         l->bar1_saved = l->bar1;