Re: [PATCH] drm/amdgpu/job: Replace DRM_INFO/ERROR logging

[Christian König]

Am 08.07.24 um 21:04 schrieb Alex Deucher:

Use the dev_info/err variants so we get per device logging
in multi-GPU cases.

Signed-off-by: Alex Deucher <alexander.deuc...@amd.com>

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

---
  drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 21 +++++++++++----------
  1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index cf0c4470ab9c..e238f2832f65 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -41,7 +41,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct 
drm_sched_job *s_job)
        int r;

if (!drm_dev_enter(adev_to_drm(adev), &idx)) {

-               DRM_INFO("%s - device unplugged skipping recovery on 
scheduler:%s",
+               dev_info(adev->dev, "%s - device unplugged skipping recovery on 
scheduler:%s",
                         __func__, s_job->sched->name);

/* Effectively the job is aborted as the device is gone */

@@ -53,19 +53,20 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct 
drm_sched_job *s_job)

if (amdgpu_gpu_recovery &&

            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);
+               dev_err(adev->dev, "ring %s timeout, but soft recovered\n",
+                       s_job->sched->name);
                goto exit;
        }

- DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n",

-                  job->base.sched->name, 
atomic_read(&ring->fence_drv.last_seq),
-                  ring->fence_drv.sync_seq);
+       dev_err(adev->dev, "ring %s timeout, signaled seq=%u, emitted seq=%u\n",
+               job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
+               ring->fence_drv.sync_seq);

ti = amdgpu_vm_get_task_info_pasid(ring->adev, job->pasid);

        if (ti) {
-               DRM_ERROR("Process information: process %s pid %d thread %s pid 
%d\n",
-                         ti->process_name, ti->tgid, ti->task_name, ti->pid);
+               dev_err(adev->dev,
+                       "Process information: process %s pid %d thread %s pid 
%d\n",
+                       ti->process_name, ti->tgid, ti->task_name, ti->pid);
                amdgpu_vm_put_task_info(ti);
        }

@@ -82,7 +83,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) r = amdgpu_device_gpu_recover(ring->adev, job, &reset_context);

                if (r)
-                       DRM_ERROR("GPU Recovery Failed: %d\n", r);
+                       dev_err(adev->dev, "GPU Recovery Failed: %d\n", r);
        } else {
                drm_sched_suspend_timeout(&ring->sched);
                if (amdgpu_sriov_vf(adev))
@@ -274,7 +275,7 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job,
        while (!fence && job->vm && !job->vmid) {
                r = amdgpu_vmid_grab(job->vm, ring, job, &fence);
                if (r) {
-                       DRM_ERROR("Error getting VM ID (%d)\n", r);
+                       dev_err(ring->adev->dev, "Error getting VM ID (%d)\n", 
r);
                        goto error;
                }
        }