diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_job.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 36 |
1 files changed, 23 insertions, 13 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 0a0dcbf0798d..07771721af9d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -135,8 +135,12 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) ring->funcs->reset) { dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name); + /* Stop the scheduler to prevent anybody else from touching the ring buffer. */ + drm_sched_wqueue_stop(&ring->sched); r = amdgpu_ring_reset(ring, job->vmid, job->hw_fence); if (!r) { + /* Start the scheduler again */ + drm_sched_wqueue_start(&ring->sched); atomic_inc(&ring->adev->gpu_reset_counter); dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name); @@ -147,7 +151,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) dev_err(adev->dev, "Ring %s reset failed\n", ring->sched.name); } - dma_fence_set_error(&s_job->s_fence->finished, -ETIME); + if (dma_fence_get_status(&s_job->s_fence->finished) == 0) + dma_fence_set_error(&s_job->s_fence->finished, -ETIME); if (amdgpu_device_should_recover_gpu(ring->adev)) { struct amdgpu_reset_context reset_context; @@ -176,7 +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 DRM_GPU_SCHED_STAT_RESET; + /* 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, @@ -190,18 +196,18 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (num_ibs == 0) return -EINVAL; - *job = kzalloc(struct_size(*job, ibs, num_ibs), GFP_KERNEL); + *job = kzalloc_flex(**job, ibs, num_ibs); if (!*job) return -ENOMEM; - af = kzalloc(sizeof(struct amdgpu_fence), GFP_KERNEL); + af = kzalloc_obj(struct amdgpu_fence); if (!af) { r = -ENOMEM; goto err_job; } (*job)->hw_fence = af; - af = kzalloc(sizeof(struct amdgpu_fence), GFP_KERNEL); + af = kzalloc_obj(struct amdgpu_fence); if (!af) { r = -ENOMEM; goto err_fence; @@ -217,8 +223,11 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (!entity) return 0; - return drm_sched_job_init(&(*job)->base, entity, 1, owner, - drm_client_id); + r = drm_sched_job_init(&(*job)->base, entity, 1, owner, drm_client_id); + if (!r) + return 0; + + kfree((*job)->hw_vm_fence); err_fence: kfree((*job)->hw_fence); @@ -278,9 +287,10 @@ void amdgpu_job_free_resources(struct amdgpu_job *job) unsigned i; /* Check if any fences were initialized */ - if (job->base.s_fence && job->base.s_fence->finished.ops) + if (job->base.s_fence && + dma_fence_was_initialized(&job->base.s_fence->finished)) f = &job->base.s_fence->finished; - else if (job->hw_fence && job->hw_fence->base.ops) + else if (dma_fence_was_initialized(&job->hw_fence->base)) f = &job->hw_fence->base; else f = NULL; @@ -297,11 +307,11 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job) amdgpu_sync_free(&job->explicit_sync); - if (job->hw_fence->base.ops) + if (dma_fence_was_initialized(&job->hw_fence->base)) dma_fence_put(&job->hw_fence->base); else kfree(job->hw_fence); - if (job->hw_vm_fence->base.ops) + if (dma_fence_was_initialized(&job->hw_vm_fence->base)) dma_fence_put(&job->hw_vm_fence->base); else kfree(job->hw_vm_fence); @@ -335,11 +345,11 @@ void amdgpu_job_free(struct amdgpu_job *job) if (job->gang_submit != &job->base.s_fence->scheduled) dma_fence_put(job->gang_submit); - if (job->hw_fence->base.ops) + if (dma_fence_was_initialized(&job->hw_fence->base)) dma_fence_put(&job->hw_fence->base); else kfree(job->hw_fence); - if (job->hw_vm_fence->base.ops) + if (dma_fence_was_initialized(&job->hw_vm_fence->base)) dma_fence_put(&job->hw_vm_fence->base); else kfree(job->hw_vm_fence); |