gpu: nvgpu: handle pm_prepare_poweroff failure

As part of gk20a_pm_prepare_poweroff, gpu hw state
is destroyed even in case of any errors. So try to recover
from that situation by calling gk20a_pm_finalize_poweron.

Bug 200380708

Change-Id: Ibff656cda67241ad111fd22701e05871f20d6f70
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1653750
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 6 insertions, 4 deletions

diff --git a/drivers/gpu/nvgpu/common/linux/module.c b/drivers/gpu/nvgpu/common/linux/module.c
index 814f2fc9..67dfeff3 100644
--- a/drivers/gpu/nvgpu/common/linux/module.c
+++ b/drivers/gpu/nvgpu/common/linux/module.c
@@ -928,23 +928,25 @@ fail:
 static int gk20a_pm_runtime_suspend(struct device *dev)
 {
         int err = 0;
+        struct gk20a *g = get_gk20a(dev);
 
         if (gk20a_gpu_is_virtual(dev))
                 err = vgpu_pm_prepare_poweroff(dev);
         else
                 err = gk20a_pm_prepare_poweroff(dev);
-        if (err)
+        if (err) {
+                nvgpu_err(g, "failed to power off, err=%d", err);
                 goto fail;
+        }
 
         err = gk20a_pm_railgate(dev);
         if (err)
-                goto fail_railgate;
+                goto fail;
 
         return 0;
 
-fail_railgate:
-        gk20a_pm_finalize_poweron(dev);
 fail:
+        gk20a_pm_finalize_poweron(dev);
         pm_runtime_mark_last_busy(dev);
         return err;
 }