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.net
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Doug Ledford <dledford@redhat.com>
Acked-by: Michael 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: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 509434a..6111976 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -392,7 +392,7 @@
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 int mapping_mapped(struct address_space *mapping)
{
- return !RB_EMPTY_ROOT(&mapping->i_mmap);
+ return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root);
}
/*
diff --git a/include/linux/interval_tree.h b/include/linux/interval_tree.h
index 724556a..202ee12 100644
--- a/include/linux/interval_tree.h
+++ b/include/linux/interval_tree.h
@@ -11,13 +11,15 @@
};
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 *
diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h
index 58370e1..f096423 100644
--- a/include/linux/interval_tree_generic.h
+++ b/include/linux/interval_tree_generic.h
@@ -65,11 +65,13 @@
\
/* 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 @@
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 @@
} \
\
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); \
} \
\
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5195e27..f8c10d3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2034,13 +2034,13 @@
/* 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 @@
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
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index f8ca2e7..733d3d8 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -55,7 +55,9 @@
* 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;
};
/*