From ce82653d6cfcc95ba88c25908664878459fb1b8d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 6 Apr 2010 22:36:20 +0100 Subject: radix_tree_tag_get() is not as safe as the docs make out [ver #2] radix_tree_tag_get() is not safe to use concurrently with radix_tree_tag_set() or radix_tree_tag_clear(). The problem is that the double tag_get() in radix_tree_tag_get(): if (!tag_get(node, tag, offset)) saw_unset_tag = 1; if (height == 1) { int ret = tag_get(node, tag, offset); may see the value change due to the action of set/clear. RCU is no protection against this as no pointers are being changed, no nodes are being replaced according to a COW protocol - set/clear alter the node directly. The documentation in linux/radix-tree.h, however, says that radix_tree_tag_get() is an exception to the rule that "any function modifying the tree or tags (...) must exclude other modifications, and exclude any functions reading the tree". The problem is that the next statement in radix_tree_tag_get() checks that the tag doesn't vary over time: BUG_ON(ret && saw_unset_tag); This has been seen happening in FS-Cache: https://www.redhat.com/archives/linux-cachefs/2010-April/msg00013.html To this end, remove the BUG_ON() from radix_tree_tag_get() and note in various comments that the value of the tag may change whilst the RCU read lock is held, and thus that the return value of radix_tree_tag_get() may not be relied upon unless radix_tree_tag_set/clear() and radix_tree_delete() are excluded from running concurrently with it. Reported-by: Romain DEGEZ Signed-off-by: David Howells Acked-by: Nick Piggin Signed-off-by: Linus Torvalds --- lib/radix-tree.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'lib/radix-tree.c') diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 0871582aa29d..2a087e0f9863 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -555,6 +555,10 @@ EXPORT_SYMBOL(radix_tree_tag_clear); * * 0: tag not present or not set * 1: tag set + * + * Note that the return value of this function may not be relied on, even if + * the RCU lock is held, unless tag modification and node deletion are excluded + * from concurrency. */ int radix_tree_tag_get(struct radix_tree_root *root, unsigned long index, unsigned int tag) @@ -595,12 +599,8 @@ int radix_tree_tag_get(struct radix_tree_root *root, */ if (!tag_get(node, tag, offset)) saw_unset_tag = 1; - if (height == 1) { - int ret = tag_get(node, tag, offset); - - BUG_ON(ret && saw_unset_tag); - return !!ret; - } + if (height == 1) + return !!tag_get(node, tag, offset); node = rcu_dereference_raw(node->slots[offset]); shift -= RADIX_TREE_MAP_SHIFT; height--; -- cgit v1.2.3-58-ga151