[PATCH 4/5] drm/amdgpu: implement grab dedicated vmid

[Christian König]

Am 21.04.2017 um 12:05 schrieb Chunming Zhou:
> Change-Id: I64da2701c9fdcf986afb90ba1492a78d5bef1b6c
> Signed-off-by: Chunming Zhou <David1.Zhou at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 60 ++++++++++++++++++++++++++++++++++
>   1 file changed, 60 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index 21cca99..5764a14 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -408,6 +408,62 @@ bool amdgpu_vm_dedicated_vmid_ready(struct amdgpu_vm *vm)
>   	return true;
>   }
>   
> +int amdgpu_vm_grab_dedicated_vmid(struct amdgpu_vm *vm,
> +				  struct amdgpu_ring *ring,
> +				  struct amdgpu_sync *sync,
> +				  struct fence *fence,
> +				  struct amdgpu_job *job)
> +{
> +	struct amdgpu_device *adev = ring->adev;
> +	unsigned vmhub = ring->funcs->vmhub;
> +	struct amdgpu_vm_id *id = vm->dedicated_vmid[vmhub];
> +	struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
> +	struct fence *updates = sync->last_vm_update;
> +	int r = 0;
> +	struct fence *flushed, *tmp;
> +	bool needs_flush = false;
> +
> +	mutex_lock(&id_mgr->lock);
> +	tmp = amdgpu_sync_get_fence(&id->active);
> +	if (tmp) {
> +		r = amdgpu_sync_fence(adev, sync, tmp);
> +		fence_put(tmp);
> +		mutex_unlock(&id_mgr->lock);
> +		return r;
> +	}

This only needs to be done when we flush the VMID, otherwise it is 
unnecessary and really kills performance.

Christian.

> +
> +	if (amdgpu_vm_had_gpu_reset(adev, id))
> +		needs_flush = true;
> +
> +	flushed  = id->flushed_updates;
> +	if (updates && (!flushed || updates->context != flushed->context ||
> +			fence_is_later(updates, flushed)))
> +		needs_flush = true;
> +
> +	/* Good we can use this VMID. Remember this submission as
> +	* user of the VMID.
> +	*/
> +	r = amdgpu_sync_fence(ring->adev, &id->active, fence);
> +	if (r)
> +		goto out;
> +
> +	if (updates && (!flushed || updates->context != flushed->context ||
> +			fence_is_later(updates, flushed))) {
> +		fence_put(id->flushed_updates);
> +		id->flushed_updates = fence_get(updates);
> +	}
> +	id->pd_gpu_addr = job->vm_pd_addr;
> +	id->current_gpu_reset_count = atomic_read(&adev->gpu_reset_counter);
> +	atomic64_set(&id->owner, vm->client_id);
> +	job->vm_needs_flush = needs_flush;
> +
> +	job->vm_id = id - id_mgr->ids;
> +	trace_amdgpu_vm_grab_id(vm, ring, job);
> +out:
> +	mutex_unlock(&id_mgr->lock);
> +	return r;
> +}
> +
>   /**
>    * amdgpu_vm_grab_id - allocate the next free VMID
>    *
> @@ -432,6 +488,10 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
>   	unsigned i;
>   	int r = 0;
>   
> +	if (amdgpu_vm_dedicated_vmid_ready(vm))
> +		return amdgpu_vm_grab_dedicated_vmid(vm, ring, sync,
> +						     fence, job);
> +
>   	fences = kmalloc_array(sizeof(void *), id_mgr->num_ids, GFP_KERNEL);
>   	if (!fences)
>   		return -ENOMEM;