drm/amdgpu: skip all jobs of guilty vm

If the vm is guilty of a GPU reset, skips all its jobs.

Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index ec2dd2b644a7e3d29a9d0fbeaa25ceef1d7332a6..53998615d3f1b97f7f9ac9340f23516e1abe6cda 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -171,6 +171,7 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 {
        struct dma_fence *fence = NULL;
        struct amdgpu_job *job;
+       struct amdgpu_fpriv *fpriv = NULL;
        int r;
 
        if (!sched_job) {
@@ -182,10 +183,16 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
        BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
        trace_amdgpu_sched_run_job(job);
-       r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job, &fence);
-       if (r)
-               DRM_ERROR("Error scheduling IBs (%d)\n", r);
-
+       if (job->vm)
+               fpriv = container_of(job->vm, struct amdgpu_fpriv, vm);
+       /* skip ib schedule when vram is lost */
+       if (fpriv && amdgpu_kms_vram_lost(job->adev, fpriv))
+               DRM_ERROR("Skip scheduling IBs!\n");
+       else {
+               r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job, &fence);
+               if (r)
+                       DRM_ERROR("Error scheduling IBs (%d)\n", r);
+       }
        /* if gpu reset, hw fence will be replaced here */
        dma_fence_put(job->fence);
        job->fence = dma_fence_get(fence);