[Intel-gfx] [PATCH 08/64] drm/i915: Retire oldest completed request before allocating next

[Tvrtko Ursulin]

On 07/07/16 09:41, Chris Wilson wrote:
> In order to keep the memory allocated for requests reasonably tight, try
> to reuse the oldest request (so long as it is completed and has no
> external references) for the next allocation.
>
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> ---
>   drivers/gpu/drm/i915/i915_gem_request.c | 7 +++++++
>   1 file changed, 7 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
> index 9e9aa6b725f7..ee1189c35509 100644
> --- a/drivers/gpu/drm/i915/i915_gem_request.c
> +++ b/drivers/gpu/drm/i915/i915_gem_request.c
> @@ -226,6 +226,13 @@ __i915_gem_request_alloc(struct intel_engine_cs *engine,
>   	if (ret)
>   		return ret;
>
> +	if (!list_empty(&engine->request_list)) {
> +		req = list_first_entry(&engine->request_list,
> +				       typeof(*req), list);
> +		if (i915_gem_request_completed(req))
> +			i915_gem_request_retire(req);
> +	}
> +
>   	req = kmem_cache_zalloc(dev_priv->requests, GFP_KERNEL);
>   	if (!req)
>   		return -ENOMEM;
>

I am thinking that this does not play well with the execlists which is 
holding references to requests for a little bit longer than they are on 
the engine->request_list.

In fact I don't see how you can just steal it without looking at the 
reference count.

Regards,

Tvrtko