#include <linux/wait.h>
#include <linux/sched.h>
+#include <drm/drm_drv.h>
+
#include "amdgpu.h"
#include "amdgpu_trace.h"
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));
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);
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,