radix-tree: use indirect bit

Rather than sign direct radix-tree pointers with a special bit, sign the
indirect one that hangs off the root.  This means that, given a lookup_slot
operation, the invalid result will be differentiated from the valid
(previously, valid results could have the bit either set or clear).

This does not affect slot lookups which occur under lock -- they can never
return an invalid result.  Is needed in future for lockless pagecache.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 21 insertions, 17 deletions

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 430e4a8c138..b6116b4445c 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -26,28 +26,31 @@
 #include <linux/rcupdate.h>
 
 /*
- * A direct pointer (root->rnode pointing directly to a data item,
- * rather than another radix_tree_node) is signalled by the low bit
- * set in the root->rnode pointer.
+ * An indirect pointer (root->rnode pointing to a radix_tree_node, rather
+ * than a data item) is signalled by the low bit set in the root->rnode
+ * pointer.
  *
- * In this case root->height is also NULL, but the direct pointer tests are
- * needed for RCU lookups when root->height is unreliable.
+ * In this case root->height is > 0, but the indirect pointer tests are
+ * needed for RCU lookups (because root->height is unreliable). The only
+ * time callers need worry about this is when doing a lookup_slot under
+ * RCU.
  */
-#define RADIX_TREE_DIRECT_PTR	1
+#define RADIX_TREE_INDIRECT_PTR	1
+#define RADIX_TREE_RETRY ((void *)-1UL)
 
-static inline void *radix_tree_ptr_to_direct(void *ptr)
+static inline void *radix_tree_ptr_to_indirect(void *ptr)
 {
-	return (void *)((unsigned long)ptr | RADIX_TREE_DIRECT_PTR);
+	return (void *)((unsigned long)ptr | RADIX_TREE_INDIRECT_PTR);
 }
 
-static inline void *radix_tree_direct_to_ptr(void *ptr)
+static inline void *radix_tree_indirect_to_ptr(void *ptr)
 {
-	return (void *)((unsigned long)ptr & ~RADIX_TREE_DIRECT_PTR);
+	return (void *)((unsigned long)ptr & ~RADIX_TREE_INDIRECT_PTR);
 }
 
-static inline int radix_tree_is_direct_ptr(void *ptr)
+static inline int radix_tree_is_indirect_ptr(void *ptr)
 {
-	return (int)((unsigned long)ptr & RADIX_TREE_DIRECT_PTR);
+	return (int)((unsigned long)ptr & RADIX_TREE_INDIRECT_PTR);
 }
 
 /*** radix-tree API starts here ***/
@@ -130,7 +133,10 @@ do {									\
  */
 static inline void *radix_tree_deref_slot(void **pslot)
 {
-	return radix_tree_direct_to_ptr(*pslot);
+	void *ret = *pslot;
+	if (unlikely(radix_tree_is_indirect_ptr(ret)))
+		ret = RADIX_TREE_RETRY;
+	return ret;
 }
 /**
  * radix_tree_replace_slot	- replace item in a slot
@@ -142,10 +148,8 @@ static inline void *radix_tree_deref_slot(void **pslot)
  */
 static inline void radix_tree_replace_slot(void **pslot, void *item)
 {
-	BUG_ON(radix_tree_is_direct_ptr(item));
-	rcu_assign_pointer(*pslot,
-		(void *)((unsigned long)item |
-			((unsigned long)*pslot & RADIX_TREE_DIRECT_PTR)));
+	BUG_ON(radix_tree_is_indirect_ptr(item));
+	rcu_assign_pointer(*pslot, item);
 }
 
 int radix_tree_insert(struct radix_tree_root *, unsigned long, void *);