diff mbox series

[v6,12/16] drm/amdgpu: Prevent any job recoveries after device is unplugged.

Message ID 20210510163625.407105-13-andrey.grodzovsky@amd.com (mailing list archive)
State New, archived
Headers show
Series RFC Support hot device unplug in amdgpu | expand

Commit Message

Andrey Grodzovsky May 10, 2021, 4:36 p.m. UTC
Return DRM_TASK_STATUS_ENODEV back to the scheduler when device
is not present so they timeout timer will not be rearmed.

v5: Update to match updated return values in enum drm_gpu_sched_stat

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

Comments

Christian König May 11, 2021, 6:53 a.m. UTC | #1
Am 10.05.21 um 18:36 schrieb Andrey Grodzovsky:
> Return DRM_TASK_STATUS_ENODEV back to the scheduler when device
> is not present so they timeout timer will not be rearmed.
>
> v5: Update to match updated return values in enum drm_gpu_sched_stat
>
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>

Reviewed-by: Christian König <christian.koenig@amd.com>

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 19 ++++++++++++++++---
>   1 file changed, 16 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index 759b34799221..d33e6d97cc89 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -25,6 +25,8 @@
>   #include <linux/wait.h>
>   #include <linux/sched.h>
>   
> +#include <drm/drm_drv.h>
> +
>   #include "amdgpu.h"
>   #include "amdgpu_trace.h"
>   
> @@ -34,6 +36,15 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>   	struct amdgpu_job *job = to_amdgpu_job(s_job);
>   	struct amdgpu_task_info ti;
>   	struct amdgpu_device *adev = ring->adev;
> +	int idx;
> +
> +	if (!drm_dev_enter(&adev->ddev, &idx)) {
> +		DRM_INFO("%s - device unplugged skipping recovery on scheduler:%s",
> +			 __func__, s_job->sched->name);
> +
> +		/* Effectively the job is aborted as the device is gone */
> +		return DRM_GPU_SCHED_STAT_ENODEV;
> +	}
>   
>   	memset(&ti, 0, sizeof(struct amdgpu_task_info));
>   
> @@ -41,7 +52,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>   	    amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
>   		DRM_ERROR("ring %s timeout, but soft recovered\n",
>   			  s_job->sched->name);
> -		return DRM_GPU_SCHED_STAT_NOMINAL;
> +		goto exit;
>   	}
>   
>   	amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti);
> @@ -53,13 +64,15 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>   
>   	if (amdgpu_device_should_recover_gpu(ring->adev)) {
>   		amdgpu_device_gpu_recover(ring->adev, job);
> -		return DRM_GPU_SCHED_STAT_NOMINAL;
>   	} else {
>   		drm_sched_suspend_timeout(&ring->sched);
>   		if (amdgpu_sriov_vf(adev))
>   			adev->virt.tdr_debug = true;
> -		return DRM_GPU_SCHED_STAT_NOMINAL;
>   	}
> +
> +exit:
> +	drm_dev_exit(idx);
> +	return DRM_GPU_SCHED_STAT_NOMINAL;
>   }
>   
>   int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
diff mbox series

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 759b34799221..d33e6d97cc89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -25,6 +25,8 @@ 
 #include <linux/wait.h>
 #include <linux/sched.h>
 
+#include <drm/drm_drv.h>
+
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 
@@ -34,6 +36,15 @@  static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	struct amdgpu_job *job = to_amdgpu_job(s_job);
 	struct amdgpu_task_info ti;
 	struct amdgpu_device *adev = ring->adev;
+	int idx;
+
+	if (!drm_dev_enter(&adev->ddev, &idx)) {
+		DRM_INFO("%s - device unplugged skipping recovery on scheduler:%s",
+			 __func__, s_job->sched->name);
+
+		/* Effectively the job is aborted as the device is gone */
+		return DRM_GPU_SCHED_STAT_ENODEV;
+	}
 
 	memset(&ti, 0, sizeof(struct amdgpu_task_info));
 
@@ -41,7 +52,7 @@  static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	    amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
 		DRM_ERROR("ring %s timeout, but soft recovered\n",
 			  s_job->sched->name);
-		return DRM_GPU_SCHED_STAT_NOMINAL;
+		goto exit;
 	}
 
 	amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti);
@@ -53,13 +64,15 @@  static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 
 	if (amdgpu_device_should_recover_gpu(ring->adev)) {
 		amdgpu_device_gpu_recover(ring->adev, job);
-		return DRM_GPU_SCHED_STAT_NOMINAL;
 	} else {
 		drm_sched_suspend_timeout(&ring->sched);
 		if (amdgpu_sriov_vf(adev))
 			adev->virt.tdr_debug = true;
-		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
+
+exit:
+	drm_dev_exit(idx);
+	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,