lib/rbtree.c has ensured that there is not possible to
inadvertently cause (temporary) loops in the tree structure
as seen in program order of the modifier. But loop is still
possible to be seen in searcher due to CPU's reordering.
for example:
modifier searcher
left rotate at parent
parent->rb_right is node
search to parent
parent->rb_right is node
+->see node->rb_left changed
WRITE_ONCE(parent->rb_right, tmp);-+ | node->rb_left is parennt
no smp_wmb(), some ARCHs can | |
reorder these two writes | | loop long between
WRITE_ONCE(node->rb_left, parent);-+-+ parent and node
|
+--->finally see
parent->rb_right
The long loop won't stop until the modifer's CPU flushes
its writes. Too avoid it, we should limit the searching depth.
There are no more than (1<<BITS_PER_LONG)-1 nodes in the tree.
And the max_depth of a tree is no more than 2*lg(node_count+1),
which is no mare than 2*BITS_PER_LONG.
So the searching should stop when diving down up to
2*BITS_PER_LONG depth.
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Paul E. McKenney <paul...@kernel.org>
Cc: Oleg Nesterov <o...@redhat.com>
Cc: Michel Lespinasse <wal...@google.com>
Cc: Andrea Arcangeli <aarca...@redhat.com>
Cc: Rik van Riel <r...@redhat.com>
Cc: Mathieu Desnoyers <mathieu.desnoy...@efficios.com>
Signed-off-by: Lai Jiangshan <la...@linux.alibaba.com>
---
include/linux/rbtree_latch.h | 39 ++++++++++++++++++++++++++++++++++++
1 file changed, 39 insertions(+)
diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h
index 7d012faa509a..638942f53c0a 100644
--- a/include/linux/rbtree_latch.h
+++ b/include/linux/rbtree_latch.h
@@ -102,11 +102,47 @@ __lt_erase(struct latch_tree_node *ltn, struct
latch_tree_root *ltr, int idx)
rb_erase(<n->node[idx], <r->tree[idx]);
}
+/*
+ * Beware when rbtree is being searched in RCU read sites.
+ *
+ * lib/rbtree.c has ensured that there is not possible to
+ * inadvertently cause (temporary) loops in the tree structure
+ * as seen in program order of the modifier. But loop is still
+ * possible to be seen in searcher due to CPU's reordering.
+ *
+ * for example:
+ * modifier searcher
+ *
+ * left rotate at parent search to parent
+ * parent->rb_right is node parent->rb_right is node
+ * +->see node->rb_left changed
+ * WRITE_ONCE(parent->rb_right, tmp);-+ | node->rb_left is parennt
+ * no smp_wmb(), some ARCHs can | |
+ * reorder these two writes | | loop long between
+ * WRITE_ONCE(node->rb_left, parent);-+-+ parent and node
+ * |
+ * +--->finally see
+ * parent->rb_right
+ *
+ * The long loop won't stop until the searcher finally see the changes
+ * from the modifier. Too avoid it, we should limit the searching depth.
+ *
+ * Limited by the address space of the kernel, there are no more than
+ * (1<<BITS_PER_LONG)-1 nodes in the tree. And the max_depth of a tree is
+ * no more than 2*lg(node_count+1), which is no mare than 2*BITS_PER_LONG.
+ *
+ * So the searching should stop when diving down up to
+ * 2*BITS_PER_LONG depth.
+ *
+ * Note: the above problem is not subject to the TSO memory model, such as
+ * x86, which can dispense with the depth check.
+ */
static __always_inline struct latch_tree_node *
__lt_find(void *key, struct latch_tree_root *ltr, int idx,
int (*comp)(void *key, struct latch_tree_node *node))
{
struct rb_node *node = rcu_dereference_raw(ltr->tree[idx].rb_node);
+ int depth = 2 * BITS_PER_LONG;
struct latch_tree_node *ltn;
int c;
@@ -120,6 +156,9 @@ __lt_find(void *key, struct latch_tree_root *ltr, int idx,
node = rcu_dereference_raw(node->rb_right);
else
return ltn;
+
+ if (!IS_ENABLED(CONFIG_X86) && (--depth < 0))
+ break;
}
return NULL;
--
2.20.1
