lib/interval_tree: fast overlap detection

Allow interval trees to quickly check for overlaps to avoid unnecesary
tree lookups in interval_tree_iter_first().

As of this patch, all interval tree flavors will require using a
'rb_root_cached' such that we can have the leftmost node easily
available.  While most users will make use of this feature, those with
special functions (in addition to the generic insert, delete, search
calls) will avoid using the cached option as they can do funky things
with insertions -- for example, vma_interval_tree_insert_after().

[[email protected]: fix deadlock from typo vm_lock_anon_vma()]
  Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Davidlohr Bueso <[email protected]>
Signed-off-by: Jérôme Glisse <[email protected]>
Acked-by: Christian König <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Doug Ledford <[email protected]>
Acked-by: Michael S. Tsirkin <[email protected]>
Cc: David Airlie <[email protected]>
Cc: Jason Wang <[email protected]>
Cc: Christian Benvenuti <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c

@@ -51,7 +51,7 @@ struct amdgpu_mn {
 
 	/* objects protected by lock */
 	struct mutex		lock;
-	struct rb_root		objects;
+	struct rb_root_cached	objects;
 };
 
 struct amdgpu_mn_node {
@@ -76,8 +76,8 @@ static void amdgpu_mn_destroy(struct work_struct *work)
 	mutex_lock(&adev->mn_lock);
 	mutex_lock(&rmn->lock);
 	hash_del(&rmn->node);
-	rbtree_postorder_for_each_entry_safe(node, next_node, &rmn->objects,
-					     it.rb) {
+	rbtree_postorder_for_each_entry_safe(node, next_node,
+					     &rmn->objects.rb_root, it.rb) {
 		list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) {
 			bo->mn = NULL;
 			list_del_init(&bo->mn_list);
@@ -221,7 +221,7 @@ static struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
 	rmn->mm = mm;
 	rmn->mn.ops = &amdgpu_mn_ops;
 	mutex_init(&rmn->lock);
-	rmn->objects = RB_ROOT;
+	rmn->objects = RB_ROOT_CACHED;
 
 	r = __mmu_notifier_register(&rmn->mn, mm);
 	if (r)

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

@@ -2475,7 +2475,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	u64 flags;
 	uint64_t init_pde_value = 0;
 
-	vm->va = RB_ROOT;
+	vm->va = RB_ROOT_CACHED;
 	vm->client_id = atomic64_inc_return(&adev->vm_manager.client_counter);
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
 		vm->reserved_vmid[i] = NULL;
@@ -2596,10 +2596,11 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	amd_sched_entity_fini(vm->entity.sched, &vm->entity);
 
-	if (!RB_EMPTY_ROOT(&vm->va)) {
+	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
 		dev_err(adev->dev, "still active bo inside vm\n");
 	}
-	rbtree_postorder_for_each_entry_safe(mapping, tmp, &vm->va, rb) {
+	rbtree_postorder_for_each_entry_safe(mapping, tmp,
+					     &vm->va.rb_root, rb) {
 		list_del(&mapping->list);
 		amdgpu_vm_it_remove(mapping, &vm->va);
 		kfree(mapping);

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h

@@ -118,7 +118,7 @@ struct amdgpu_vm_pt {
 
 struct amdgpu_vm {
 	/* tree of virtual addresses mapped */
-	struct rb_root		va;
+	struct rb_root_cached	va;
 
 	/* protecting invalidated */
 	spinlock_t		status_lock;

drivers/gpu/drm/drm_mm.c

@@ -169,7 +169,7 @@ INTERVAL_TREE_DEFINE(struct drm_mm_node, rb,
 struct drm_mm_node *
 __drm_mm_interval_first(const struct drm_mm *mm, u64 start, u64 last)
 {
-	return drm_mm_interval_tree_iter_first((struct rb_root *)&mm->interval_tree,
+	return drm_mm_interval_tree_iter_first((struct rb_root_cached *)&mm->interval_tree,
 					       start, last) ?: (struct drm_mm_node *)&mm->head_node;
 }
 EXPORT_SYMBOL(__drm_mm_interval_first);
@@ -180,6 +180,7 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node,
 	struct drm_mm *mm = hole_node->mm;
 	struct rb_node **link, *rb;
 	struct drm_mm_node *parent;
+	bool leftmost = true;
 
 	node->__subtree_last = LAST(node);
 
@@ -196,9 +197,10 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node,
 
 		rb = &hole_node->rb;
 		link = &hole_node->rb.rb_right;
+		leftmost = false;
 	} else {
 		rb = NULL;
-		link = &mm->interval_tree.rb_node;
+		link = &mm->interval_tree.rb_root.rb_node;
 	}
 
 	while (*link) {
@@ -208,14 +210,15 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node,
 			parent->__subtree_last = node->__subtree_last;
 		if (node->start < parent->start)
 			link = &parent->rb.rb_left;
-		else
+		else {
 			link = &parent->rb.rb_right;
+			leftmost = true;
+		}
 	}
 
 	rb_link_node(&node->rb, rb, link);
-	rb_insert_augmented(&node->rb,
-			    &mm->interval_tree,
-			    &drm_mm_interval_tree_augment);
+	rb_insert_augmented_cached(&node->rb, &mm->interval_tree, leftmost,
+				   &drm_mm_interval_tree_augment);
 }
 
 #define RB_INSERT(root, member, expr) do { \
@@ -577,7 +580,7 @@ void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new)
 	*new = *old;
 
 	list_replace(&old->node_list, &new->node_list);
-	rb_replace_node(&old->rb, &new->rb, &old->mm->interval_tree);
+	rb_replace_node(&old->rb, &new->rb, &old->mm->interval_tree.rb_root);
 
 	if (drm_mm_hole_follows(old)) {
 		list_replace(&old->hole_stack, &new->hole_stack);
@@ -863,7 +866,7 @@ void drm_mm_init(struct drm_mm *mm, u64 start, u64 size)
 	mm->color_adjust = NULL;
 
 	INIT_LIST_HEAD(&mm->hole_stack);
-	mm->interval_tree = RB_ROOT;
+	mm->interval_tree = RB_ROOT_CACHED;
 	mm->holes_size = RB_ROOT;
 	mm->holes_addr = RB_ROOT;
 

drivers/gpu/drm/drm_vma_manager.c

@@ -147,7 +147,7 @@ struct drm_vma_offset_node *drm_vma_offset_lookup_locked(struct drm_vma_offset_m
 	struct rb_node *iter;
 	unsigned long offset;
 
-	iter = mgr->vm_addr_space_mm.interval_tree.rb_node;
+	iter = mgr->vm_addr_space_mm.interval_tree.rb_root.rb_node;
 	best = NULL;
 
 	while (likely(iter)) {

drivers/gpu/drm/i915/i915_gem_userptr.c

@@ -49,7 +49,7 @@ struct i915_mmu_notifier {
 	spinlock_t lock;
 	struct hlist_node node;
 	struct mmu_notifier mn;
-	struct rb_root objects;
+	struct rb_root_cached objects;
 	struct workqueue_struct *wq;
 };
 
@@ -123,7 +123,7 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 	struct interval_tree_node *it;
 	LIST_HEAD(cancelled);
 
-	if (RB_EMPTY_ROOT(&mn->objects))
+	if (RB_EMPTY_ROOT(&mn->objects.rb_root))
 		return;
 
 	/* interval ranges are inclusive, but invalidate range is exclusive */
@@ -172,7 +172,7 @@ i915_mmu_notifier_create(struct mm_struct *mm)
 
 	spin_lock_init(&mn->lock);
 	mn->mn.ops = &i915_gem_userptr_notifier;
-	mn->objects = RB_ROOT;
+	mn->objects = RB_ROOT_CACHED;
 	mn->wq = alloc_workqueue("i915-userptr-release", WQ_UNBOUND, 0);
 	if (mn->wq == NULL) {
 		kfree(mn);

drivers/gpu/drm/radeon/radeon.h

@@ -924,7 +924,7 @@ struct radeon_vm_id {
 struct radeon_vm {
 	struct mutex		mutex;
 
-	struct rb_root		va;
+	struct rb_root_cached	va;
 
 	/* protecting invalidated and freed */
 	spinlock_t		status_lock;

drivers/gpu/drm/radeon/radeon_mn.c

@@ -50,7 +50,7 @@ struct radeon_mn {
 
 	/* objects protected by lock */
 	struct mutex		lock;
-	struct rb_root		objects;
+	struct rb_root_cached	objects;
 };
 
 struct radeon_mn_node {
@@ -75,8 +75,8 @@ static void radeon_mn_destroy(struct work_struct *work)
 	mutex_lock(&rdev->mn_lock);
 	mutex_lock(&rmn->lock);
 	hash_del(&rmn->node);
-	rbtree_postorder_for_each_entry_safe(node, next_node, &rmn->objects,
-					     it.rb) {
+	rbtree_postorder_for_each_entry_safe(node, next_node,
+					     &rmn->objects.rb_root, it.rb) {
 
 		interval_tree_remove(&node->it, &rmn->objects);
 		list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) {
@@ -205,7 +205,7 @@ static struct radeon_mn *radeon_mn_get(struct radeon_device *rdev)
 	rmn->mm = mm;
 	rmn->mn.ops = &radeon_mn_ops;
 	mutex_init(&rmn->lock);
-	rmn->objects = RB_ROOT;
+	rmn->objects = RB_ROOT_CACHED;
 	
 	r = __mmu_notifier_register(&rmn->mn, mm);
 	if (r)

drivers/gpu/drm/radeon/radeon_vm.c

@@ -1185,7 +1185,7 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 		vm->ids[i].last_id_use = NULL;
 	}
 	mutex_init(&vm->mutex);
-	vm->va = RB_ROOT;
+	vm->va = RB_ROOT_CACHED;
 	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->invalidated);
 	INIT_LIST_HEAD(&vm->freed);
@@ -1232,10 +1232,11 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 	struct radeon_bo_va *bo_va, *tmp;
 	int i, r;
 
-	if (!RB_EMPTY_ROOT(&vm->va)) {
+	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
 		dev_err(rdev->dev, "still active bo inside vm\n");
 	}
-	rbtree_postorder_for_each_entry_safe(bo_va, tmp, &vm->va, it.rb) {
+	rbtree_postorder_for_each_entry_safe(bo_va, tmp,
+					     &vm->va.rb_root, it.rb) {
 		interval_tree_remove(&bo_va->it, &vm->va);
 		r = radeon_bo_reserve(bo_va->bo, false);
 		if (!r) {