radix-tree: fix RCU bug

Salman Qazi describes the following radix-tree bug:

In the following case, we get can get a deadlock:

0.  The radix tree contains two items, one has the index 0.
1.  The reader (in this case find_get_pages) takes the rcu_read_lock.
2.  The reader acquires slot(s) for item(s) including the index 0 item.
3.  The non-zero index item is deleted, and as a consequence the other item is
    moved to the root of the tree. The place where it used to be is queued for
    deletion after the readers finish.
3b. The zero item is deleted, removing it from the direct slot, it remains in
    the rcu-delayed indirect node.
4.  The reader looks at the index 0 slot, and finds that the page has 0 ref
    count
5.  The reader looks at it again, hoping that the item will either be freed or
    the ref count will increase. This never happens, as the slot it is looking
    at will never be updated. Also, this slot can never be reclaimed because
    the reader is holding rcu_read_lock and is in an infinite loop.

The fix is to re-use the same "indirect" pointer case that requires a slot
lookup retry into a general "retry the lookup" bit.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Reported-by: Salman Qazi <sqazi@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 23 insertions, 16 deletions

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index a39cbed9ee17..ab2baa5c4884 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -34,19 +34,13 @@
  * 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.
+ *
+ * Indirect pointer in fact is also used to tag the last pointer of a node
+ * when it is shrunk, before we rcu free the node. See shrink code for
+ * details.
  */
 #define RADIX_TREE_INDIRECT_PTR	1
-#define RADIX_TREE_RETRY ((void *)-1UL)
-
-static inline void *radix_tree_ptr_to_indirect(void *ptr)
-{
-	return (void *)((unsigned long)ptr | RADIX_TREE_INDIRECT_PTR);
-}
 
-static inline void *radix_tree_indirect_to_ptr(void *ptr)
-{
-	return (void *)((unsigned long)ptr & ~RADIX_TREE_INDIRECT_PTR);
-}
 #define radix_tree_indirect_to_ptr(ptr) \
 	radix_tree_indirect_to_ptr((void __force *)(ptr))
 
@@ -140,16 +134,29 @@ do {									\
  *		removed.
  *
  * For use with radix_tree_lookup_slot().  Caller must hold tree at least read
- * locked across slot lookup and dereference.  More likely, will be used with
- * radix_tree_replace_slot(), as well, so caller will hold tree write locked.
+ * locked across slot lookup and dereference. Not required if write lock is
+ * held (ie. items cannot be concurrently inserted).
+ *
+ * radix_tree_deref_retry must be used to confirm validity of the pointer if
+ * only the read lock is held.
  */
 static inline void *radix_tree_deref_slot(void **pslot)
 {
-	void *ret = rcu_dereference(*pslot);
-	if (unlikely(radix_tree_is_indirect_ptr(ret)))
-		ret = RADIX_TREE_RETRY;
-	return ret;
+	return rcu_dereference(*pslot);
 }
+
+/**
+ * radix_tree_deref_retry	- check radix_tree_deref_slot
+ * @arg:	pointer returned by radix_tree_deref_slot
+ * Returns:	0 if retry is not required, otherwise retry is required
+ *
+ * radix_tree_deref_retry must be used with radix_tree_deref_slot.
+ */
+static inline int radix_tree_deref_retry(void *arg)
+{
+	return unlikely((unsigned long)arg & RADIX_TREE_INDIRECT_PTR);
+}
+
 /**
  * radix_tree_replace_slot	- replace item in a slot
  * @pslot:	pointer to slot, returned by radix_tree_lookup_slot