[Intel-gfx] [PATCH v2] drm/i915: Track the last-active inside the i915_vma

[Chris Wilson]

Using a VMA on more than one timeline concurrently is the exception
rather than the rule (using it concurrently on multiple engines). As we
expect to only use one active tracker, store the most recently used
tracker inside the i915_vma itself and only fallback to the radixtree if
we need a second or more concurrent active trackers.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_vma.c | 36 +++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_vma.h |  1 +
 2 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 2faad2a1d00e..9b69d24c5cf1 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -119,6 +119,12 @@ i915_vma_retire(struct i915_gem_active *base, struct i915_request *rq)
 	__i915_vma_retire(active->vma, rq);
 }
 
+static void
+i915_vma_last_retire(struct i915_gem_active *base, struct i915_request *rq)
+{
+	__i915_vma_retire(container_of(base, struct i915_vma, last_active), rq);
+}
+
 static struct i915_vma *
 vma_create(struct drm_i915_gem_object *obj,
 	   struct i915_address_space *vm,
@@ -136,6 +142,7 @@ vma_create(struct drm_i915_gem_object *obj,
 
 	vma->active = RB_ROOT;
 
+	init_request_active(&vma->last_active, i915_vma_last_retire);
 	init_request_active(&vma->last_fence, NULL);
 	vma->vm = vm;
 	vma->ops = &vm->vma_ops;
@@ -895,6 +902,15 @@ static struct i915_gem_active *lookup_active(struct i915_vma *vma, u64 idx)
 {
 	struct i915_vma_active *active;
 	struct rb_node **p, *parent;
+	struct i915_request *old;
+
+	old = i915_gem_active_raw(&vma->last_active,
+				  &vma->vm->i915->drm.struct_mutex);
+	if (!old || old->fence.context == idx)
+		goto out;
+
+	/* Move the currently active fence into the rbtree */
+	idx = old->fence.context;
 
 	parent = NULL;
 	p = &vma->active.rb_node;
@@ -903,7 +919,7 @@ static struct i915_gem_active *lookup_active(struct i915_vma *vma, u64 idx)
 
 		active = rb_entry(parent, struct i915_vma_active, node);
 		if (active->timeline == idx)
-			return &active->base;
+			goto replace;
 
 		if (active->timeline < idx)
 			p = &parent->rb_right;
@@ -922,7 +938,18 @@ static struct i915_gem_active *lookup_active(struct i915_vma *vma, u64 idx)
 	rb_link_node(&active->node, parent, p);
 	rb_insert_color(&active->node, &vma->active);
 
-	return &active->base;
+replace:
+	if (i915_gem_active_isset(&active->base)) {
+		__list_del_entry(&active->base.link);
+		vma->active_count--;
+		GEM_BUG_ON(!vma->active_count);
+	}
+	GEM_BUG_ON(list_empty(&vma->last_active.link));
+	list_replace_init(&vma->last_active.link, &active->base.link);
+	active->base.request = fetch_and_zero(&vma->last_active.request);
+
+out:
+	return &vma->last_active;
 }
 
 int i915_vma_move_to_active(struct i915_vma *vma,
@@ -1002,6 +1029,11 @@ int i915_vma_unbind(struct i915_vma *vma)
 		 */
 		__i915_vma_pin(vma);
 
+		ret = i915_gem_active_retire(&vma->last_active,
+					     &vma->vm->i915->drm.struct_mutex);
+		if (ret)
+			goto unpin;
+
 		rbtree_postorder_for_each_entry_safe(active, n,
 						     &vma->active, node) {
 			ret = i915_gem_active_retire(&active->base,
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index c297b0a0dc47..f06d66377107 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -97,6 +97,7 @@ struct i915_vma {
 
 	unsigned int active_count;
 	struct rb_root active;
+	struct i915_gem_active last_active;
 	struct i915_gem_active last_fence;
 
 	/**
-- 
2.18.0