Merge tag 'amd-drm-next-6.14-2024-12-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.14-2024-12-18:

amdgpu:
- RAS updates
- ISP updates
- SDMA queue reset support
- Rework DPM powergating interfaces
- Documentation updates and cleanups
- Panel replay fixes
- DCN 3.5 updates
- DP tunneling fixes
- Use a pm notifier to more gracefully handle VRAM eviction on suspend or hibernate
- Add debugfs interfaces for forcing scheduling to specific engine instances
- GG 9.5 updates
- IH 4.4 updates
- Make missing optional firmware less noisy
- PSP 13.x updates
- SMU 13.x updates
- VCN 5.x updates
- JPEG 5.x updates
- Misc cleanups
- GC 12.x updates
- DRM panic support
- DC FAMS updates
- DSC fixes
- job handling fixes

amdkfd:
- GG 9.5 updates
- Logging improvements
- Misc cleanups
- Various Optimizations

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241218201758.2580723-1-alexander.deucher@amd.com

1 files changed, 8 insertions, 10 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index b9d08bc96581..100f04475943 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -102,8 +102,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 		return DRM_GPU_SCHED_STAT_ENODEV;
 	}
 
-	adev->job_hang = true;
-
 	/*
 	 * Do the coredump immediately after a job timeout to get a very
 	 * close dump/snapshot/representation of GPU's current error status
@@ -181,7 +179,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	}
 
 exit:
-	adev->job_hang = false;
 	drm_dev_exit(idx);
 	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
@@ -197,11 +194,6 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (!*job)
 		return -ENOMEM;
 
-	/*
-	 * Initialize the scheduler to at least some ring so that we always
-	 * have a pointer to adev.
-	 */
-	(*job)->base.sched = &adev->rings[0]->sched;
 	(*job)->vm = vm;
 
 	amdgpu_sync_create(&(*job)->explicit_sync);
@@ -255,7 +247,6 @@ void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds,
 
 void amdgpu_job_free_resources(struct amdgpu_job *job)
 {
-	struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched);
 	struct dma_fence *f;
 	unsigned i;
 
@@ -268,7 +259,7 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 		f = NULL;
 
 	for (i = 0; i < job->num_ibs; ++i)
-		amdgpu_ib_free(ring->adev, &job->ibs[i], f);
+		amdgpu_ib_free(&job->ibs[i], f);
 }
 
 static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
@@ -367,6 +358,13 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job,
 			dev_err(ring->adev->dev, "Error getting VM ID (%d)\n", r);
 			goto error;
 		}
+		/*
+		 * The VM structure might be released after the VMID is
+		 * assigned, we had multiple problems with people trying to use
+		 * the VM pointer so better set it to NULL.
+		 */
+		if (!fence)
+			job->vm = NULL;
 	}
 
 	return fence;