[Intel-gfx] [PATCH 09/12] drm/i915: Create a kmem_cache to allocate struct i915_priolist from

[Tvrtko Ursulin]

On 11/05/2017 20:59, Chris Wilson wrote:
> The i915_priolist are allocated within an atomic context on a path where
> we wish to minimise latency. If we use a dedicated kmem_cache, we have
> the advantage of a local freelist from which to service new requests
> that should keep the latency impact of an allocation small. Though
> currently we expect the majority of requests to be at default priority
> (and so hit the preallocate priolist), once userspace starts using
> priorities they are likely to use many fine grained policies improving
> the utilisation of a private slab.
>
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
> ---
>  drivers/gpu/drm/i915/i915_drv.h            | 1 +
>  drivers/gpu/drm/i915/i915_gem.c            | 9 ++++++++-
>  drivers/gpu/drm/i915/i915_guc_submission.c | 2 +-
>  drivers/gpu/drm/i915/intel_lrc.c           | 4 ++--
>  4 files changed, 12 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index ff3574a56812..7f192efbe088 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2027,6 +2027,7 @@ struct drm_i915_private {
>  	struct kmem_cache *vmas;
>  	struct kmem_cache *requests;
>  	struct kmem_cache *dependencies;
> +	struct kmem_cache *priorities;
>
>  	const struct intel_device_info info;
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 75d7575b81f4..f52d72b1a5b4 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4871,12 +4871,16 @@ i915_gem_load_init(struct drm_i915_private *dev_priv)
>  	if (!dev_priv->dependencies)
>  		goto err_requests;
>
> +	dev_priv->priorities = KMEM_CACHE(i915_priolist, SLAB_HWCACHE_ALIGN);
> +	if (!dev_priv->priorities)
> +		goto err_dependencies;
> +
>  	mutex_lock(&dev_priv->drm.struct_mutex);
>  	INIT_LIST_HEAD(&dev_priv->gt.timelines);
>  	err = i915_gem_timeline_init__global(dev_priv);
>  	mutex_unlock(&dev_priv->drm.struct_mutex);
>  	if (err)
> -		goto err_dependencies;
> +		goto err_priorities;
>
>  	INIT_LIST_HEAD(&dev_priv->context_list);
>  	INIT_WORK(&dev_priv->mm.free_work, __i915_gem_free_work);
> @@ -4900,6 +4904,8 @@ i915_gem_load_init(struct drm_i915_private *dev_priv)
>
>  	return 0;
>
> +err_priorities:
> +	kmem_cache_destroy(dev_priv->priorities);
>  err_dependencies:
>  	kmem_cache_destroy(dev_priv->dependencies);
>  err_requests:
> @@ -4923,6 +4929,7 @@ void i915_gem_load_cleanup(struct drm_i915_private *dev_priv)
>  	WARN_ON(!list_empty(&dev_priv->gt.timelines));
>  	mutex_unlock(&dev_priv->drm.struct_mutex);
>
> +	kmem_cache_destroy(dev_priv->priorities);
>  	kmem_cache_destroy(dev_priv->dependencies);
>  	kmem_cache_destroy(dev_priv->requests);
>  	kmem_cache_destroy(dev_priv->vmas);
> diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
> index 440bab856cc2..53c022c47687 100644
> --- a/drivers/gpu/drm/i915/i915_guc_submission.c
> +++ b/drivers/gpu/drm/i915/i915_guc_submission.c
> @@ -704,7 +704,7 @@ static bool i915_guc_dequeue(struct intel_engine_cs *engine)
>  		rb_erase(&p->node, &engine->execlist_queue);
>  		INIT_LIST_HEAD(&p->requests);
>  		if (p->priority != I915_PRIORITY_NORMAL)
> -			kfree(p);
> +			kmem_cache_free(engine->i915->priorities, p);
>  	}
>  done:
>  	engine->execlist_first = rb;
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 849b35796de7..7e41529bd074 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -500,7 +500,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
>  		rb_erase(&p->node, &engine->execlist_queue);
>  		INIT_LIST_HEAD(&p->requests);
>  		if (p->priority != I915_PRIORITY_NORMAL)
> -			kfree(p);
> +			kmem_cache_free(engine->i915->priorities, p);
>  	}
>  done:
>  	engine->execlist_first = rb;
> @@ -659,7 +659,7 @@ insert_request(struct intel_engine_cs *engine,
>  	if (prio == I915_PRIORITY_NORMAL) {
>  		p = &engine->default_priolist;
>  	} else {
> -		p = kmalloc(sizeof(*p), GFP_ATOMIC);
> +		p = kmem_cache_alloc(engine->i915->priorities, GFP_ATOMIC);
>  		/* Convert an allocation failure to a priority bump */
>  		if (unlikely(!p)) {
>  			prio = I915_PRIORITY_NORMAL; /* recurses just once */
>

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Regards,

Tvrtko