rbtree: cache leftmost node internally

Patch series "rbtree: Cache leftmost node internally", v4.

A series to extending rbtrees to internally cache the leftmost node such
that we can have fast overlap check optimization for all interval tree
users[1].  The benefits of this series are that:

(i)   Unify users that do internal leftmost node caching.
(ii)  Optimize all interval tree users.
(iii) Convert at least two new users (epoll and procfs) to the new interface.

This patch (of 16):

Red-black tree semantics imply that nodes with smaller or greater (or
equal for duplicates) keys always be to the left and right,
respectively.  For the kernel this is extremely evident when considering
our rb_first() semantics.  Enabling lookups for the smallest node in the
tree in O(1) can save a good chunk of cycles in not having to walk down
the tree each time.  To this end there are a few core users that
explicitly do this, such as the scheduler and rtmutexes.  There is also
the desire for interval trees to have this optimization allowing faster
overlap checking.

This patch introduces a new 'struct rb_root_cached' which is just the
root with a cached pointer to the leftmost node.  The reason why the
regular rb_root was not extended instead of adding a new structure was
that this allows the user to have the choice between memory footprint
and actual tree performance.  The new wrappers on top of the regular
rb_root calls are:

 - rb_first_cached(cached_root) -- which is a fast replacement
     for rb_first.

 - rb_insert_color_cached(node, cached_root, new)

 - rb_erase_cached(node, cached_root)

In addition, augmented cached interfaces are also added for basic
insertion and deletion operations; which becomes important for the
interval tree changes.

With the exception of the inserts, which adds a bool for updating the
new leftmost, the interfaces are kept the same.  To this end, porting rb
users to the cached version becomes really trivial, and keeping current
rbtree semantics for users that don't care about the optimization
requires zero overhead.

Link: http://lkml.kernel.org/r/20170719014603.19029-2-dave@stgolabs.net
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 30 insertions, 3 deletions

diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index 9702b6e183bc..6bfd2b581f75 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -41,7 +41,9 @@ struct rb_augment_callbacks {
 	void (*rotate)(struct rb_node *old, struct rb_node *new);
 };
 
-extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+extern void __rb_insert_augmented(struct rb_node *node,
+				  struct rb_root *root,
+				  bool newleft, struct rb_node **leftmost,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
 /*
  * Fixup the rbtree and update the augmented information when rebalancing.
@@ -57,7 +59,16 @@ static inline void
 rb_insert_augmented(struct rb_node *node, struct rb_root *root,
 		    const struct rb_augment_callbacks *augment)
 {
-	__rb_insert_augmented(node, root, augment->rotate);
+	__rb_insert_augmented(node, root, false, NULL, augment->rotate);
+}
+
+static inline void
+rb_insert_augmented_cached(struct rb_node *node,
+			   struct rb_root_cached *root, bool newleft,
+			   const struct rb_augment_callbacks *augment)
+{
+	__rb_insert_augmented(node, &root->rb_root,
+			      newleft, &root->rb_leftmost, augment->rotate);
 }
 
 #define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield,	\
@@ -150,6 +161,7 @@ extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
 
 static __always_inline struct rb_node *
 __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		     struct rb_node **leftmost,
 		     const struct rb_augment_callbacks *augment)
 {
 	struct rb_node *child = node->rb_right;
@@ -157,6 +169,9 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 	struct rb_node *parent, *rebalance;
 	unsigned long pc;
 
+	if (leftmost && node == *leftmost)
+		*leftmost = rb_next(node);
+
 	if (!tmp) {
 		/*
 		 * Case 1: node to erase has no more than 1 child (easy!)
@@ -256,9 +271,21 @@ static __always_inline void
 rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 		   const struct rb_augment_callbacks *augment)
 {
-	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+	struct rb_node *rebalance = __rb_erase_augmented(node, root,
+							 NULL, augment);
 	if (rebalance)
 		__rb_erase_color(rebalance, root, augment->rotate);
 }
 
+static __always_inline void
+rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root,
+			  const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *rebalance = __rb_erase_augmented(node, &root->rb_root,
+							 &root->rb_leftmost,
+							 augment);
+	if (rebalance)
+		__rb_erase_color(rebalance, &root->rb_root, augment->rotate);
+}
+
 #endif	/* _LINUX_RBTREE_AUGMENTED_H */