SUNRPC: Prevent an rpc_task wakeup race

The lockless RPC_IS_QUEUED() test in __rpc_execute means that we need to
be careful about ordering the calls to rpc_test_and_set_running(task) and
rpc_clear_queued(task). If we get the order wrong, then we may end up
testing the RPC_TASK_RUNNING flag after __rpc_execute() has looped
and changed the state of the rpc_task.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index f8529fc8e54275c5b7b9809f0219f20608ffb472..5356b120dbf8e2fe61ba88081d1fab1941f135a9 100644 (file)
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -324,11 +324,17 @@ EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task);
  * Note: If the task is ASYNC, and is being made runnable after sitting on an
  * rpc_wait_queue, this must be called with the queue spinlock held to protect
  * the wait queue operation.
+ * Note the ordering of rpc_test_and_set_running() and rpc_clear_queued(),
+ * which is needed to ensure that __rpc_execute() doesn't loop (due to the
+ * lockless RPC_IS_QUEUED() test) before we've had a chance to test
+ * the RPC_TASK_RUNNING flag.
  */
 static void rpc_make_runnable(struct rpc_task *task)
 {
+       bool need_wakeup = !rpc_test_and_set_running(task);
+
        rpc_clear_queued(task);
-       if (rpc_test_and_set_running(task))
+       if (!need_wakeup)
                return;
        if (RPC_IS_ASYNC(task)) {
                INIT_WORK(&task->u.tk_work, rpc_async_schedule);