From c1384c9c4c184543375b52a0997d06cd98145164 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 14 Jun 2007 18:00:42 -0400 Subject: [PATCH] SUNRPC: fix hang due to eventd deadlock... Brian Behlendorf writes: The root cause of the NFS hang we were observing appears to be a rare deadlock between the kernel provided usermodehelper API and the linux NFS client. The deadlock can arise because both of these services use the generic linux work queues. The usermodehelper API run the specified user application in the context of the work queue. And NFS submits both cleanup and reconnect work to the generic work queue for handling. Normally this is fine but a deadlock can result in the following situation. - NFS client is in a disconnected state - [events/0] runs a usermodehelper app with an NFS dependent operation, this triggers an NFS reconnect. - NFS reconnect happens to be submitted to [events/0] work queue. - Deadlock, the [events/0] work queue will never process the reconnect because it is blocked on the previous NFS dependent operation which will not complete.` The solution is simply to run reconnect requests on rpciod. Signed-off-by: Trond Myklebust --- net/sunrpc/xprt.c | 4 ++-- net/sunrpc/xprtsock.c | 17 +++++++---------- 2 files changed, 9 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 5b05b73e4c1d..518acb74a5bb 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -127,7 +127,7 @@ static void xprt_clear_locked(struct rpc_xprt *xprt) clear_bit(XPRT_LOCKED, &xprt->state); smp_mb__after_clear_bit(); } else - schedule_work(&xprt->task_cleanup); + queue_work(rpciod_workqueue, &xprt->task_cleanup); } /* @@ -515,7 +515,7 @@ xprt_init_autodisconnect(unsigned long data) if (xprt_connecting(xprt)) xprt_release_write(xprt, NULL); else - schedule_work(&xprt->task_cleanup); + queue_work(rpciod_workqueue, &xprt->task_cleanup); return; out_abort: spin_unlock(&xprt->transport_lock); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index cc33c5880abb..ee6ad3baf680 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -653,8 +653,7 @@ static void xs_destroy(struct rpc_xprt *xprt) dprintk("RPC: xs_destroy xprt %p\n", xprt); - cancel_delayed_work(&transport->connect_worker); - flush_scheduled_work(); + cancel_rearming_delayed_work(&transport->connect_worker); xprt_disconnect(xprt); xs_close(xprt); @@ -1001,7 +1000,7 @@ static void xs_tcp_state_change(struct sock *sk) /* Try to schedule an autoclose RPC calls */ set_bit(XPRT_CLOSE_WAIT, &xprt->state); if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) - schedule_work(&xprt->task_cleanup); + queue_work(rpciod_workqueue, &xprt->task_cleanup); default: xprt_disconnect(xprt); } @@ -1410,18 +1409,16 @@ static void xs_connect(struct rpc_task *task) dprintk("RPC: xs_connect delayed xprt %p for %lu " "seconds\n", xprt, xprt->reestablish_timeout / HZ); - schedule_delayed_work(&transport->connect_worker, - xprt->reestablish_timeout); + queue_delayed_work(rpciod_workqueue, + &transport->connect_worker, + xprt->reestablish_timeout); xprt->reestablish_timeout <<= 1; if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO) xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO; } else { dprintk("RPC: xs_connect scheduled xprt %p\n", xprt); - schedule_delayed_work(&transport->connect_worker, 0); - - /* flush_scheduled_work can sleep... */ - if (!RPC_IS_ASYNC(task)) - flush_scheduled_work(); + queue_delayed_work(rpciod_workqueue, + &transport->connect_worker, 0); } } -- GitLab