drm/amdgpu: Make use of drm_wedge_task_info

To notify userspace about which task (if any) made the device get in a
wedge state, make use of drm_wedge_task_info parameter, filling it with
the task PID and name.

Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20250617124949.2151549-7-andrealmeid@igalia.com
Signed-off-by: André Almeida <andrealmeid@igalia.com>
This commit is contained in:
André Almeida 2025-06-17 09:49:49 -03:00
parent 35dc4ce200
commit a72002cb18
2 changed files with 16 additions and 4 deletions

View File

@ -6363,8 +6363,17 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
atomic_set(&adev->reset_domain->reset_res, r);
if (!r)
drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL);
if (!r) {
struct amdgpu_task_info *ti = NULL;
if (job)
ti = amdgpu_vm_get_task_info_pasid(adev, job->pasid);
drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE,
ti ? &ti->task : NULL);
amdgpu_vm_put_task_info(ti);
}
return r;
}

View File

@ -89,6 +89,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
{
struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
struct amdgpu_job *job = to_amdgpu_job(s_job);
struct drm_wedge_task_info *info = NULL;
struct amdgpu_task_info *ti;
struct amdgpu_device *adev = ring->adev;
int idx;
@ -125,7 +126,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
ti = amdgpu_vm_get_task_info_pasid(ring->adev, job->pasid);
if (ti) {
amdgpu_vm_print_task_info(adev, ti);
amdgpu_vm_put_task_info(ti);
info = &ti->task;
}
/* attempt a per ring reset */
@ -164,13 +165,15 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
if (amdgpu_ring_sched_ready(ring))
drm_sched_start(&ring->sched, 0);
dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name);
drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL);
drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, info);
goto exit;
}
dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name);
}
dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
amdgpu_vm_put_task_info(ti);
if (amdgpu_device_should_recover_gpu(ring->adev)) {
struct amdgpu_reset_context reset_context;
memset(&reset_context, 0, sizeof(reset_context));