| Message ID | 20220707213950.2.Ib07ecec3d5c17cb0e1efa6fcddaaa019ec2fb556@changeid |
|---|---|
| State | Superseded |
| Headers | show |
| Series | Improve GPU Recovery | expand |
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index eb8a666..f75ff4b 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -416,7 +416,6 @@ static void recover_worker(struct kthread_work *work) /* Record the crash state */ pm_runtime_get_sync(&gpu->pdev->dev); msm_gpu_crashstate_capture(gpu, submit, comm, cmd); - pm_runtime_put_sync(&gpu->pdev->dev); kfree(cmd); kfree(comm); @@ -464,6 +463,8 @@ static void recover_worker(struct kthread_work *work) } } + pm_runtime_put_sync(&gpu->pdev->dev); + mutex_unlock(&gpu->lock); msm_gpu_retire(gpu);
In the scenario where there is one a single submit which is hung, gpu is power collapsed when it is retired. Because of this, by the time we call reover(), gpu state would be already clear. Fix this by correctly managing the pm runtime votes. Signed-off-by: Akhil P Oommen <quic_akhilpo@quicinc.com> --- drivers/gpu/drm/msm/msm_gpu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)