Commit f808c13f authored by Davidlohr Bueso's avatar Davidlohr Bueso Committed by Linus Torvalds

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().

[jglisse@redhat.com: fix deadlock from typo vm_lock_anon_vma()]
  Link: http://lkml.kernel.org/r/20170808225719.20723-1-jglisse@redhat.com
Link: http://lkml.kernel.org/r/20170719014603.19029-12-dave@stgolabs.netSigned-off-by: default avatarDavidlohr Bueso <dbueso@suse.de>
Signed-off-by: default avatarJérôme Glisse <jglisse@redhat.com>
Acked-by: default avatarChristian König <christian.koenig@amd.com>
Acked-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: default avatarDoug Ledford <dledford@redhat.com>
Acked-by: default avatarMichael S. Tsirkin <mst@redhat.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Christian Benvenuti <benve@cisco.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 09663c86
......@@ -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)
......
......@@ -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);
......
......@@ -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;
......
......@@ -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;
......
......@@ -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)) {
......
......@@ -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);
......
......@@ -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;
......
......@@ -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)
......
......@@ -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) {
......
......@@ -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;
......
......@@ -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);
......
......@@ -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;
......
......@@ -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",
......
......@@ -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;
};
......
......@@ -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;
......
......@@ -48,12 +48,12 @@ struct usnic_uiom_interval_node {
extern void
usnic_uiom_interval_tree_insert(struct usnic_uiom_interval_node *node,
struct rb_root *root);
struct rb_root_cached *root);
extern void
usnic_uiom_interval_tree_remove(struct usnic_uiom_interval_node *node,
struct rb_root *root);
struct rb_root_cached *root);
extern struct usnic_uiom_interval_node *
usnic_uiom_interval_tree_iter_first(struct rb_root *root,
usnic_uiom_interval_tree_iter_first(struct rb_root_cached *root,
unsigned long start,
unsigned long last);
extern struct usnic_uiom_interval_node *
......@@ -63,7 +63,7 @@ usnic_uiom_interval_tree_iter_next(struct usnic_uiom_interval_node *node,
* Inserts {start...last} into {root}. If there are overlaps,
* nodes will be broken up and merged
*/
int usnic_uiom_insert_interval(struct rb_root *root,
int usnic_uiom_insert_interval(struct rb_root_cached *root,
unsigned long start, unsigned long last,
int flags);
/*
......@@ -71,7 +71,7 @@ int usnic_uiom_insert_interval(struct rb_root *root,
* 'removed.' The caller is responsibile for freeing memory of nodes in
* 'removed.'
*/
void usnic_uiom_remove_interval(struct rb_root *root,
void usnic_uiom_remove_interval(struct rb_root_cached *root,
unsigned long start, unsigned long last,
struct list_head *removed);
/*
......@@ -81,7 +81,7 @@ void usnic_uiom_remove_interval(struct rb_root *root,
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);
/* Call this to free diff_set returned by usnic_uiom_get_intervals_diff */
void usnic_uiom_put_interval_set(struct list_head *intervals);
......
......@@ -1271,7 +1271,7 @@ static struct vhost_umem *vhost_umem_alloc(void)
if (!umem)
return NULL;
umem->umem_tree = RB_ROOT;
umem->umem_tree = RB_ROOT_CACHED;
umem->numem = 0;
INIT_LIST_HEAD(&umem->umem_list);
......
......@@ -71,7 +71,7 @@ struct vhost_umem_node {
};
struct vhost_umem {
struct rb_root umem_tree;
struct rb_root_cached umem_tree;
struct list_head umem_list;
int numem;
};
......
......@@ -334,7 +334,7 @@ static void remove_huge_page(struct page *page)
}
static void
hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end)
hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
{
struct vm_area_struct *vma;
......@@ -498,7 +498,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
i_size_write(inode, offset);
i_mmap_lock_write(mapping);
if (!RB_EMPTY_ROOT(&mapping->i_mmap))
if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
i_mmap_unlock_write(mapping);
remove_inode_hugepages(inode, offset, LLONG_MAX);
......@@ -523,7 +523,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
inode_lock(inode);
i_mmap_lock_write(mapping);
if (!RB_EMPTY_ROOT(&mapping->i_mmap))
if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
hugetlb_vmdelete_list(&mapping->i_mmap,
hole_start >> PAGE_SHIFT,
hole_end >> PAGE_SHIFT);
......
......@@ -353,7 +353,7 @@ void address_space_init_once(struct address_space *mapping)
init_rwsem(&mapping->i_mmap_rwsem);
INIT_LIST_HEAD(&mapping->private_list);
spin_lock_init(&mapping->private_lock);
mapping->i_mmap = RB_ROOT;
mapping->i_mmap = RB_ROOT_CACHED;
}
EXPORT_SYMBOL(address_space_init_once);
......
......@@ -172,7 +172,7 @@ struct drm_mm {
* according to the (increasing) start address of the memory node. */
struct drm_mm_node head_node;
/* Keep an interval_tree for fast lookup of drm_mm_nodes by address. */
struct rb_root interval_tree;
struct rb_root_cached interval_tree;
struct rb_root holes_size;
struct rb_root holes_addr;
......
......@@ -392,7 +392,7 @@ struct address_space {
struct radix_tree_root page_tree; /* radix tree of all pages */
spinlock_t tree_lock; /* and lock protecting it */
atomic_t i_mmap_writable;/* count VM_SHARED mappings */
struct rb_root i_mmap; /* tree of private and shared mappings */
struct rb_root_cached i_mmap; /* tree of private and shared mappings */
struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */
/* Protected by tree_lock together with the radix tree */
unsigned long nrpages; /* number of total pages */
......@@ -487,7 +487,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping)
*/
static inline int mapping_mapped(struct address_space *mapping)
{
return !RB_EMPTY_ROOT(&mapping->i_mmap);
return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root);
}
/*
......
......@@ -11,13 +11,15 @@ struct interval_tree_node {
};
extern void
interval_tree_insert(struct interval_tree_node *node, struct rb_root *root);
interval_tree_insert(struct interval_tree_node *node,
struct rb_root_cached *root);
extern void
interval_tree_remove(struct interval_tree_node *node, struct rb_root *root);
interval_tree_remove(struct interval_tree_node *node,
struct rb_root_cached *root);
extern struct interval_tree_node *
interval_tree_iter_first(struct rb_root *root,
interval_tree_iter_first(struct rb_root_cached *root,
unsigned long start, unsigned long last);
extern struct interval_tree_node *
......
......@@ -65,11 +65,13 @@ RB_DECLARE_CALLBACKS(static, ITPREFIX ## _augment, ITSTRUCT, ITRB, \
\
/* Insert / remove interval nodes from the tree */ \
\
ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, struct rb_root *root) \
ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, \
struct rb_root_cached *root) \
{ \
struct rb_node **link = &root->rb_node, *rb_parent = NULL; \
struct rb_node **link = &root->rb_root.rb_node, *rb_parent = NULL; \
ITTYPE start = ITSTART(node), last = ITLAST(node); \
ITSTRUCT *parent; \
bool leftmost = true; \
\
while (*link) { \
rb_parent = *link; \
......@@ -78,18 +80,22 @@ ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, struct rb_root *root) \
parent->ITSUBTREE = last; \
if (start < ITSTART(parent)) \
link = &parent->ITRB.rb_left; \
else \
else { \
link = &parent->ITRB.rb_right; \
leftmost = false; \
} \
} \
\
node->ITSUBTREE = last; \
rb_link_node(&node->ITRB, rb_parent, link); \
rb_insert_augmented(&node->ITRB, root, &ITPREFIX ## _augment); \
rb_insert_augmented_cached(&node->ITRB, root, \
leftmost, &ITPREFIX ## _augment); \
} \
\
ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, struct rb_root *root) \
ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, \
struct rb_root_cached *root) \
{ \
rb_erase_augmented(&node->ITRB, root, &ITPREFIX ## _augment); \
rb_erase_augmented_cached(&node->ITRB, root, &ITPREFIX ## _augment); \
} \
\
/* \
......@@ -140,15 +146,35 @@ ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last) \
} \
\
ITSTATIC ITSTRUCT * \
ITPREFIX ## _iter_first(struct rb_root *root, ITTYPE start, ITTYPE last) \
ITPREFIX ## _iter_first(struct rb_root_cached *root, \
ITTYPE start, ITTYPE last) \
{ \
ITSTRUCT *node; \
ITSTRUCT *node, *leftmost; \
\
if (!root->rb_node) \
if (!root->rb_root.rb_node) \
return NULL; \
node = rb_entry(root->rb_node, ITSTRUCT, ITRB); \
\
/* \
* Fastpath range intersection/overlap between A: [a0, a1] and \
* B: [b0, b1] is given by: \
* \
* a0 <= b1 && b0 <= a1 \
* \
* ... where A holds the lock range and B holds the smallest \
* 'start' and largest 'last' in the tree. For the later, we \
* rely on the root node, which by augmented interval tree \
* property, holds the largest value in its last-in-subtree. \
* This allows mitigating some of the tree walk overhead for \
* for non-intersecting ranges, maintained and consulted in O(1). \
*/ \
node = rb_entry(root->rb_root.rb_node, ITSTRUCT, ITRB); \
if (node->ITSUBTREE < start) \
return NULL; \
\
leftmost = rb_entry(root->rb_leftmost, ITSTRUCT, ITRB); \
if (ITSTART(leftmost) > last) \
return NULL; \
\
return ITPREFIX ## _subtree_search(node, start, last); \
} \
\
......
......@@ -2034,13 +2034,13 @@ extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
/* interval_tree.c */
void vma_interval_tree_insert(struct vm_area_struct *node,
struct rb_root *root);
struct rb_root_cached *root);
void vma_interval_tree_insert_after(struct vm_area_struct *node,
struct vm_area_struct *prev,
struct rb_root *root);
struct rb_root_cached *root);
void vma_interval_tree_remove(struct vm_area_struct *node,
struct rb_root *root);
struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root *root,
struct rb_root_cached *root);
struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root,
unsigned long start, unsigned long last);
struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node,
unsigned long start, unsigned long last);
......@@ -2050,11 +2050,12 @@ struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node,
vma; vma = vma_interval_tree_iter_next(vma, start, last))
void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
struct rb_root *root);
struct rb_root_cached *root);
void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
struct rb_root *root);
struct anon_vma_chain *anon_vma_interval_tree_iter_first(
struct rb_root *root, unsigned long start, unsigned long last);
struct rb_root_cached *root);
struct anon_vma_chain *
anon_vma_interval_tree_iter_first(struct rb_root_cached *root,
unsigned long start, unsigned long last);
struct anon_vma_chain *anon_vma_interval_tree_iter_next(
struct anon_vma_chain *node, unsigned long start, unsigned long last);
#ifdef CONFIG_DEBUG_VM_RB
......
......@@ -55,7 +55,9 @@ struct anon_vma {
* is serialized by a system wide lock only visible to
* mm_take_all_locks() (mm_all_locks_mutex).
*/
struct rb_root rb_root; /* Interval tree of private "related" vmas */
/* Interval tree of private "related" vmas */
struct rb_root_cached rb_root;
};
/*
......
......@@ -111,22 +111,25 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 start_offset, u64 bcnt,
void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 start_offset,
u64 bound);
void rbt_ib_umem_insert(struct umem_odp_node *node, struct rb_root *root);
void rbt_ib_umem_remove(struct umem_odp_node *node, struct rb_root *root);
void rbt_ib_umem_insert(struct umem_odp_node *node,
struct rb_root_cached *root);
void rbt_ib_umem_remove(struct umem_odp_node *node,
struct rb_root_cached *root);
typedef int (*umem_call_back)(struct ib_umem *item, u64 start, u64 end,
void *cookie);
/*
* Call the callback on each ib_umem in the range. Returns the logical or of
* the return values of the functions called.
*/
int rbt_ib_umem_for_each_in_range(struct rb_root *root, u64 start, u64 end,
int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root,
u64 start, u64 end,
umem_call_back cb, void *cookie);
/*
* Find first region intersecting with address range.
* Return NULL if not found
*/
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);
static inline int ib_umem_mmu_notifier_retry(struct ib_umem *item,
......
......@@ -1457,7 +1457,7 @@ struct ib_ucontext {
struct pid *tgid;
#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
struct rb_root umem_tree;
struct rb_root_cached umem_tree;
/*
* Protects .umem_rbroot and tree, as well as odp_mrs_count and
* mmu notifiers registration.
......
......@@ -19,14 +19,14 @@ __param(bool, search_all, false, "Searches will iterate all nodes in the tree");
__param(uint, max_endpoint, ~0, "Largest value for the interval's endpoint");
static struct rb_root root = RB_ROOT;
static struct rb_root_cached root = RB_ROOT_CACHED;
static struct interval_tree_node *nodes = NULL;
static u32 *queries = NULL;
static struct rnd_state rnd;
static inline unsigned long
search(struct rb_root *root, unsigned long start, unsigned long last)
search(struct rb_root_cached *root, unsigned long start, unsigned long last)
{
struct interval_tree_node *node;
unsigned long results = 0;
......
......@@ -28,7 +28,7 @@ INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb,
/* Insert node immediately after prev in the interval tree */
void vma_interval_tree_insert_after(struct vm_area_struct *node,
struct vm_area_struct *prev,
struct rb_root *root)
struct rb_root_cached *root)
{
struct rb_node **link;