diff mbox series

[3/7] drm/msm: Fix cx collapse issue during recovery

Message ID 20220707213950.3.I4ac27a0b34ea796ce0f938bb509e257516bc6f57@changeid
State Superseded
Headers show
Series Improve GPU Recovery | expand

Commit Message

Akhil P Oommen July 7, 2022, 4:10 p.m. UTC
There are some hardware logic under CX domain. For a successful
recovery, we should ensure cx headswitch collapses to ensure all the
stale states are cleard out. This is especially true to for a6xx family
where we can GMU co-processor.

Currently, cx doesn't collapse due to a devlink between gpu and its
smmu. So the *struct gpu device* needs to be runtime suspended to ensure
that the iommu driver removes its vote on cx gdsc.

Signed-off-by: Akhil P Oommen <quic_akhilpo@quicinc.com>
---

 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 16 ++++++++++++++--
 drivers/gpu/drm/msm/msm_gpu.c         |  2 --
 2 files changed, 14 insertions(+), 4 deletions(-)

Comments

Rob Clark July 7, 2022, 5:10 p.m. UTC | #1
On Thu, Jul 7, 2022 at 9:11 AM Akhil P Oommen <quic_akhilpo@quicinc.com> wrote:
>
> There are some hardware logic under CX domain. For a successful
> recovery, we should ensure cx headswitch collapses to ensure all the
> stale states are cleard out. This is especially true to for a6xx family
> where we can GMU co-processor.
>
> Currently, cx doesn't collapse due to a devlink between gpu and its
> smmu. So the *struct gpu device* needs to be runtime suspended to ensure
> that the iommu driver removes its vote on cx gdsc.
>
> Signed-off-by: Akhil P Oommen <quic_akhilpo@quicinc.com>
> ---
>
>  drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 16 ++++++++++++++--
>  drivers/gpu/drm/msm/msm_gpu.c         |  2 --
>  2 files changed, 14 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> index 42ed9a3..57a7ad5 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> @@ -1210,8 +1210,20 @@ static void a6xx_recover(struct msm_gpu *gpu)
>          */
>         gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 0);
>
> -       gpu->funcs->pm_suspend(gpu);
> -       gpu->funcs->pm_resume(gpu);
> +       /*
> +        * Now drop all the pm_runtime usage count to allow cx gdsc to collapse.
> +        * First drop the usage count from all active submits
> +        */
> +       for (i = gpu->active_submits; i > 0; i--)
> +               pm_runtime_put(&gpu->pdev->dev);

Would pm_runtime_force_suspend/resume() work instead?

BR,
-R

> +
> +       /* And the final one from recover worker */
> +       pm_runtime_put_sync(&gpu->pdev->dev);
> +
> +       for (i = gpu->active_submits; i > 0; i--)
> +               pm_runtime_get(&gpu->pdev->dev);
> +
> +       pm_runtime_get_sync(&gpu->pdev->dev);
>
>         msm_gpu_hw_init(gpu);
>  }
> diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
> index f75ff4b..48171b6 100644
> --- a/drivers/gpu/drm/msm/msm_gpu.c
> +++ b/drivers/gpu/drm/msm/msm_gpu.c
> @@ -444,9 +444,7 @@ static void recover_worker(struct kthread_work *work)
>                 /* retire completed submits, plus the one that hung: */
>                 retire_submits(gpu);
>
> -               pm_runtime_get_sync(&gpu->pdev->dev);
>                 gpu->funcs->recover(gpu);
> -               pm_runtime_put_sync(&gpu->pdev->dev);
>
>                 /*
>                  * Replay all remaining submits starting with highest priority
> --
> 2.7.4
>
diff mbox series

Patch

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 42ed9a3..57a7ad5 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1210,8 +1210,20 @@  static void a6xx_recover(struct msm_gpu *gpu)
 	 */
 	gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 0);
 
-	gpu->funcs->pm_suspend(gpu);
-	gpu->funcs->pm_resume(gpu);
+	/*
+	 * Now drop all the pm_runtime usage count to allow cx gdsc to collapse.
+	 * First drop the usage count from all active submits
+	 */
+	for (i = gpu->active_submits; i > 0; i--)
+		pm_runtime_put(&gpu->pdev->dev);
+
+	/* And the final one from recover worker */
+	pm_runtime_put_sync(&gpu->pdev->dev);
+
+	for (i = gpu->active_submits; i > 0; i--)
+		pm_runtime_get(&gpu->pdev->dev);
+
+	pm_runtime_get_sync(&gpu->pdev->dev);
 
 	msm_gpu_hw_init(gpu);
 }
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index f75ff4b..48171b6 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -444,9 +444,7 @@  static void recover_worker(struct kthread_work *work)
 		/* retire completed submits, plus the one that hung: */
 		retire_submits(gpu);
 
-		pm_runtime_get_sync(&gpu->pdev->dev);
 		gpu->funcs->recover(gpu);
-		pm_runtime_put_sync(&gpu->pdev->dev);
 
 		/*
 		 * Replay all remaining submits starting with highest priority