From 298073181112a6ab6c30fe7971b99de968daf81e Mon Sep 17 00:00:00 2001 From: Neil Brown Date: Mon, 15 Jun 2015 15:55:30 +1000 Subject: [PATCH] SUNRPC: never enqueue a ->rq_cong request on ->sending If the sending queue has a task without ->rq_cong set at the front, and then a number of tasks with ->rq_cong set such that they use the entire congestion window, then the queue deadlocks. The first entry cannot be processed until later entries complete. This scenario has been seen with a client using UDP to access a server, and the network connection breaking for a period of time - it doesn't recover. It never really makes sense for an ->rq_cong request to be on the ->sending queue, but it can happen when a request is being retried, and finds the transport if locked (XPRT_LOCKED). In this case we simple call __xprt_put_cong() and the deadlock goes away. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- net/sunrpc/xprt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e1fb538..3ca31f2 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -68,6 +68,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net); static void xprt_request_init(struct rpc_task *, struct rpc_xprt *); static void xprt_connect_status(struct rpc_task *task); static int __xprt_get_cong(struct rpc_xprt *, struct rpc_task *); +static void __xprt_put_cong(struct rpc_xprt *, struct rpc_rqst *); static void xprt_destroy(struct rpc_xprt *xprt); static DEFINE_SPINLOCK(xprt_list_lock); @@ -250,6 +251,8 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) } xprt_clear_locked(xprt); out_sleep: + if (req) + __xprt_put_cong(xprt, req); dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt); task->tk_timeout = 0; task->tk_status = -EAGAIN; -- 2.7.4