Re: [PATCH 06/13] drm/amdgpu: use the new drm_exec object for CS v2

[Tatsuyuki Ishi <ishitatsuyuki@gmail.com>]

On 6/20/23 13:07, Tatsuyuki Ishi wrote:
>> @@ -1296,9 +1271,8 @@ static int amdgpu_cs_submit(struct 
>> amdgpu_cs_parser *p,
>>        */
>>       r = 0;
>>       amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
>> -        struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
>> -
>> -        r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range);
>> +        r |= !amdgpu_ttm_tt_get_user_pages_done(e->bo->tbo.ttm,
>> +                            e->range);
>>           e->range = NULL;
> 
> e->range = NULL; needs to be removed, or it's causing *massive* memory 
> leaks.

Actually, I quoted the wrong hunk, the correct one is below.

> @@ -928,18 +874,56 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
>  		e->user_invalidated = userpage_invalidated;
>  	}
>  
> -	r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true,
> -				   &duplicates);
> -	if (unlikely(r != 0)) {
> -		if (r != -ERESTARTSYS)
> -			DRM_ERROR("ttm_eu_reserve_buffers failed.\n");
> -		goto out_free_user_pages;
> +	drm_exec_while_not_all_locked(&p->exec) {
> +		r = amdgpu_vm_lock_pd(&fpriv->vm, &p->exec);
> +		drm_exec_continue_on_contention(&p->exec);
> +		if (unlikely(r))
> +			goto out_free_user_pages;
> +
> +		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
> +			r = drm_exec_prepare_obj(&p->exec, &e->bo->tbo.base, 2);
> +			drm_exec_break_on_contention(&p->exec);
> +			if (unlikely(r))
> +				goto out_free_user_pages;
> +
> +			e->bo_va = amdgpu_vm_bo_find(vm, e->bo);
> +			e->range = NULL;

This causes the leak.

> +		}
> +		drm_exec_continue_on_contention(&p->exec);
> +
> +		if (p->uf_bo) {
> +			r = drm_exec_prepare_obj(&p->exec, &p->uf_bo->tbo.base,
> +						 2);
> +			drm_exec_continue_on_contention(&p->exec);
> +			if (unlikely(r))
> +				goto out_free_user_pages;
> +		}
>  	}

Tatsuyuki