drm/amdgpu: don't call drm_sched_stop/start() in asic reset

We only want to stop the work queues, not mess with the
fences, etc.

v2: add the job back to the pending list.
v3: return the proper job status so scheduler adds the
    job back to the pending list

Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 9a051c84f50d86720480da02ec6aa8f2c3baedde..820a0d7a1fdeb314c1688f23b86b654dd9109b34 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6304,7 +6304,7 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *adev,
                        if (!amdgpu_ring_sched_ready(ring))
                                continue;
 
-                       drm_sched_stop(&ring->sched, job ? &job->base : NULL);
+                       drm_sched_wqueue_stop(&ring->sched);
 
                        if (need_emergency_restart)
                                amdgpu_job_stop_all_jobs_on_sched(&ring->sched);
@@ -6388,7 +6388,7 @@ static int amdgpu_device_sched_resume(struct list_head *device_list,
                        if (!amdgpu_ring_sched_ready(ring))
                                continue;
 
-                       drm_sched_start(&ring->sched, 0);
+                       drm_sched_wqueue_start(&ring->sched);
                }
 
                if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index d7c1ffbf7626c886caf1c63214de4ca9522ef633..cf0419f682049dda4a450ad63fba8e42ad87cdb5 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -92,7 +92,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
        struct drm_wedge_task_info *info = NULL;
        struct amdgpu_task_info *ti = NULL;
        struct amdgpu_device *adev = ring->adev;
-       enum drm_gpu_sched_stat status = DRM_GPU_SCHED_STAT_RESET;
        int idx, r;
 
        if (!drm_dev_enter(adev_to_drm(adev), &idx)) {
@@ -147,8 +146,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
                                ring->sched.name);
                        drm_dev_wedged_event(adev_to_drm(adev),
                                             DRM_WEDGE_RECOVERY_NONE, info);
-                       /* This is needed to add the job back to the pending list */
-                       status = DRM_GPU_SCHED_STAT_NO_HANG;
                        goto exit;
                }
                dev_err(adev->dev, "Ring %s reset failed\n", ring->sched.name);
@@ -184,7 +181,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 exit:
        amdgpu_vm_put_task_info(ti);
        drm_dev_exit(idx);
-       return status;
+       /* This is needed to add the job back to the pending list */
+       return DRM_GPU_SCHED_STAT_NO_HANG;
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,