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]>
vieko · Sep 9, 2017 · f808c13 · f808c13
1 parent 09663c8
commit f808c13
Show file tree

Hide file tree

Showing 33 changed files with 145 additions and 105 deletions.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/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)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/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);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/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;

diff --git a/drivers/gpu/drm/drm_mm.c b/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;
 

diff --git a/drivers/gpu/drm/drm_vma_manager.c b/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)) {

diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/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);

diff --git a/drivers/gpu/drm/radeon/radeon.h b/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;

diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/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)

diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/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) {

diff --git a/drivers/infiniband/core/umem_rbtree.c b/drivers/infiniband/core/umem_rbtree.c
@@ -72,7 +72,7 @@ INTERVAL_TREE_DEFINE(struct umem_odp_node, rb, u64, __subtree_last,
 /* @last is not a part of the interval. See comment for function
  * node_last.
  */
-int rbt_ib_umem_for_each_in_range(struct rb_root *root,
+int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root,
 				  u64 start, u64 last,
 				  umem_call_back cb,
 				  void *cookie)
@@ -95,7 +95,7 @@ int rbt_ib_umem_for_each_in_range(struct rb_root *root,
 }
 EXPORT_SYMBOL(rbt_ib_umem_for_each_in_range);
 
-struct ib_umem_odp *rbt_ib_umem_lookup(struct rb_root *root,
+struct ib_umem_odp *rbt_ib_umem_lookup(struct rb_root_cached *root,
 				       u64 addr, u64 length)
 {
 	struct umem_odp_node *node;

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
@@ -118,7 +118,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	ucontext->closing = 0;
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	ucontext->umem_tree = RB_ROOT;
+	ucontext->umem_tree = RB_ROOT_CACHED;
 	init_rwsem(&ucontext->umem_rwsem);
 	ucontext->odp_mrs_count = 0;
 	INIT_LIST_HEAD(&ucontext->no_private_counters);

diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c
@@ -54,7 +54,7 @@
 
 struct mmu_rb_handler {
 	struct mmu_notifier mn;
-	struct rb_root root;
+	struct rb_root_cached root;
 	void *ops_arg;
 	spinlock_t lock;        /* protect the RB tree */
 	struct mmu_rb_ops *ops;
@@ -108,7 +108,7 @@ int hfi1_mmu_rb_register(void *ops_arg, struct mm_struct *mm,
 	if (!handlr)
 		return -ENOMEM;
 
-	handlr->root = RB_ROOT;
+	handlr->root = RB_ROOT_CACHED;
 	handlr->ops = ops;
 	handlr->ops_arg = ops_arg;
 	INIT_HLIST_NODE(&handlr->mn.hlist);
@@ -149,9 +149,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler)
 	INIT_LIST_HEAD(&del_list);
 
 	spin_lock_irqsave(&handler->lock, flags);
-	while ((node = rb_first(&handler->root))) {
+	while ((node = rb_first_cached(&handler->root))) {
 		rbnode = rb_entry(node, struct mmu_rb_node, node);
-		rb_erase(node, &handler->root);
+		rb_erase_cached(node, &handler->root);
 		/* move from LRU list to delete list */
 		list_move(&rbnode->list, &del_list);
 	}
@@ -300,7 +300,7 @@ static void mmu_notifier_mem_invalidate(struct mmu_notifier *mn,
 {
 	struct mmu_rb_handler *handler =
 		container_of(mn, struct mmu_rb_handler, mn);
-	struct rb_root *root = &handler->root;
+	struct rb_root_cached *root = &handler->root;
 	struct mmu_rb_node *node, *ptr = NULL;
 	unsigned long flags;
 	bool added = false;

diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -227,7 +227,7 @@ static void __usnic_uiom_reg_release(struct usnic_uiom_pd *pd,
 	vpn_last = vpn_start + npages - 1;
 
 	spin_lock(&pd->lock);
-	usnic_uiom_remove_interval(&pd->rb_root, vpn_start,
+	usnic_uiom_remove_interval(&pd->root, vpn_start,
 					vpn_last, &rm_intervals);
 	usnic_uiom_unmap_sorted_intervals(&rm_intervals, pd);
 
@@ -379,7 +379,7 @@ struct usnic_uiom_reg *usnic_uiom_reg_get(struct usnic_uiom_pd *pd,
 	err = usnic_uiom_get_intervals_diff(vpn_start, vpn_last,
 						(writable) ? IOMMU_WRITE : 0,
 						IOMMU_WRITE,
-						&pd->rb_root,
+						&pd->root,
 						&sorted_diff_intervals);
 	if (err) {
 		usnic_err("Failed disjoint interval vpn [0x%lx,0x%lx] err %d\n",
@@ -395,7 +395,7 @@ struct usnic_uiom_reg *usnic_uiom_reg_get(struct usnic_uiom_pd *pd,
 
 	}
 
-	err = usnic_uiom_insert_interval(&pd->rb_root, vpn_start, vpn_last,
+	err = usnic_uiom_insert_interval(&pd->root, vpn_start, vpn_last,
 					(writable) ? IOMMU_WRITE : 0);
 	if (err) {
 		usnic_err("Failed insert interval vpn [0x%lx,0x%lx] err %d\n",

diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.h b/drivers/infiniband/hw/usnic/usnic_uiom.h
@@ -55,7 +55,7 @@ struct usnic_uiom_dev {
 struct usnic_uiom_pd {
 	struct iommu_domain		*domain;
 	spinlock_t			lock;
-	struct rb_root			rb_root;
+	struct rb_root_cached		root;
 	struct list_head		devs;
 	int				dev_cnt;
 };

diff --git a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c
@@ -100,9 +100,9 @@ static int interval_cmp(void *priv, struct list_head *a, struct list_head *b)
 }
 
 static void
-find_intervals_intersection_sorted(struct rb_root *root, unsigned long start,
-					unsigned long last,
-					struct list_head *list)
+find_intervals_intersection_sorted(struct rb_root_cached *root,
+				   unsigned long start, unsigned long last,
+				   struct list_head *list)
 {
 	struct usnic_uiom_interval_node *node;
 
@@ -118,7 +118,7 @@ find_intervals_intersection_sorted(struct rb_root *root, unsigned long start,
 
 int usnic_uiom_get_intervals_diff(unsigned long start, unsigned long last,
 					int flags, int flag_mask,
-					struct rb_root *root,
+					struct rb_root_cached *root,
 					struct list_head *diff_set)
 {
 	struct usnic_uiom_interval_node *interval, *tmp;
@@ -175,7 +175,7 @@ void usnic_uiom_put_interval_set(struct list_head *intervals)
 		kfree(interval);
 }
 
-int usnic_uiom_insert_interval(struct rb_root *root, unsigned long start,
+int usnic_uiom_insert_interval(struct rb_root_cached *root, unsigned long start,
 				unsigned long last, int flags)
 {
 	struct usnic_uiom_interval_node *interval, *tmp;
@@ -246,8 +246,9 @@ int usnic_uiom_insert_interval(struct rb_root *root, unsigned long start,
 	return err;
 }
 
-void usnic_uiom_remove_interval(struct rb_root *root, unsigned long start,
-				unsigned long last, struct list_head *removed)
+void usnic_uiom_remove_interval(struct rb_root_cached *root,
+				unsigned long start, unsigned long last,
+				struct list_head *removed)
 {
 	struct usnic_uiom_interval_node *interval;