radix-tree: fix race in gang lookup

commit 46437f9a upstream.

If the indirect_ptr bit is set on a slot, that indicates we need to redo
the lookup.  Introduce a new function radix_tree_iter_retry() which
forces the loop to retry the lookup by setting 'slot' to NULL and
turning the iterator back to point at the problematic entry.

This is a pretty rare problem to hit at the moment; the lookup has to
race with a grow of the radix tree from a height of 0.  The consequences
of hitting this race are that gang lookup could return a pointer to a
radix_tree_node instead of a pointer to whatever the user had inserted
in the tree.

Fixes: cebbd29e ("radix-tree: rewrite gang lookup using iterator")
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ohad Ben-Cohen <ohad@wizery.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

include/linux/radix-tree.h

@@ -369,6 +369,22 @@ radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start)
 void **radix_tree_next_chunk(struct radix_tree_root *root,
 			     struct radix_tree_iter *iter, unsigned flags);
 
+/**
+ * radix_tree_iter_retry - retry this chunk of the iteration
+ * @iter:	iterator state
+ *
+ * If we iterate over a tree protected only by the RCU lock, a race
+ * against deletion or creation may result in seeing a slot for which
+ * radix_tree_deref_retry() returns true.  If so, call this function
+ * and continue the iteration.
+ */
+static inline __must_check
+void **radix_tree_iter_retry(struct radix_tree_iter *iter)
+{
+	iter->next_index = iter->index;
+	return NULL;
+}
+
 /**
  * radix_tree_chunk_size - get current chunk size
  *

lib/radix-tree.c

@@ -1019,9 +1019,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 		return 0;
 
 	radix_tree_for_each_slot(slot, root, &iter, first_index) {
-		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		results[ret] = rcu_dereference_raw(*slot);
 		if (!results[ret])
 			continue;
+		if (radix_tree_is_indirect_ptr(results[ret])) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
 		if (++ret == max_items)
 			break;
 	}
@@ -1098,9 +1102,13 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
 		return 0;
 
 	radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
-		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		results[ret] = rcu_dereference_raw(*slot);
 		if (!results[ret])
 			continue;
+		if (radix_tree_is_indirect_ptr(results[ret])) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
 		if (++ret == max_items)
 			break;
 	}