drm/i915: Create a kmem_cache to allocate struct i915_priolist from

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@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170517121007.27224-9-chris@chris-wilson.co.uk

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;
 

drivers/gpu/drm/i915/i915_gem.c

@@ -4866,12 +4866,16 @@ 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);
@@ -4895,6 +4899,8 @@ 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:
@@ -4918,6 +4924,7 @@ 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);

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;

drivers/gpu/drm/i915/intel_lrc.c

@@ -499,7 +499,7 @@ 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;
@@ -661,7 +661,7 @@ find_priolist:
 	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 */

drivers/gpu/drm/i915/selftests/mock_gem_device.c

@@ -74,6 +74,7 @@ static void mock_device_release(struct drm_device *dev)
 
 	destroy_workqueue(i915->wq);
 
+	kmem_cache_destroy(i915->priorities);
 	kmem_cache_destroy(i915->dependencies);
 	kmem_cache_destroy(i915->requests);
 	kmem_cache_destroy(i915->vmas);
@@ -186,12 +187,16 @@ struct drm_i915_private *mock_gem_device(void)
 	if (!i915->dependencies)
 		goto err_requests;
 
+	i915->priorities = KMEM_CACHE(i915_priolist, SLAB_HWCACHE_ALIGN);
+	if (!i915->priorities)
+		goto err_dependencies;
+
 	mutex_lock(&i915->drm.struct_mutex);
 	INIT_LIST_HEAD(&i915->gt.timelines);
 	err = i915_gem_timeline_init__global(i915);
 	if (err) {
 		mutex_unlock(&i915->drm.struct_mutex);
-		goto err_dependencies;
+		goto err_priorities;
 	}
 
 	mock_init_ggtt(i915);
@@ -211,6 +216,8 @@ struct drm_i915_private *mock_gem_device(void)
 err_engine:
 	for_each_engine(engine, i915, id)
 		mock_engine_free(engine);
+err_priorities:
+	kmem_cache_destroy(i915->priorities);
 err_dependencies:
 	kmem_cache_destroy(i915->dependencies);
 err_requests: