| Message ID | 20220817204224.v4.3.Ib07ecec3d5c17cb0e1efa6fcddaaa019ec2fb556@changeid |
|---|---|
| State | Accepted |
| Commit | 06097e372accb843db7174b337367c5a3f97af52 |
| 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 e1dd3cc..1945efb 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -398,7 +398,6 @@ 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); @@ -446,6 +445,8 @@ 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> --- (no changes since v1) drivers/gpu/drm/msm/msm_gpu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)