From mboxrd@z Thu Jan 1 00:00:00 1970 From: ebiederm@xmission.com (Eric W. Biederman) Subject: [PATCH] net: Move rcu_barrier from rollback_registered_many to netdev_run_todo. Date: Fri, 14 Oct 2011 01:25:23 -0700 Message-ID: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Eric Dumazet , To: David Miller Return-path: Received: from out02.mta.xmission.com ([166.70.13.232]:59381 "EHLO out02.mta.xmission.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751646Ab1JNIZA (ORCPT ); Fri, 14 Oct 2011 04:25:00 -0400 Sender: netdev-owner@vger.kernel.org List-ID: This patch moves the rcu_barrier from rollback_registered_many (inside the rtnl_lock) into netdev_run_todo (just outside the rtnl_lock). This allows us to gain the full benefit of sychronize_net calling synchronize_rcu_expedited when the rtnl_lock is held. The rcu_barrier in rollback_registered_many was originally a synchronize_net but was promoted to be a rcu_barrier() when it was found that people were unnecessarily hitting the 250ms wait in netdev_wait_allrefs(). Changing the rcu_barrier back to a synchronize_net is therefore safe. Since we only care about waiting for the rcu callbacks before we get to netdev_wait_allrefs() it is also safe to move the wait into netdev_run_todo. This was tested by creating and destroying 1000 tap devices and observing /proc/lock_stat. /proc/lock_stat reports this change reduces the hold times of the rtnl_lock by a factor of 10. There was no observable difference in the amount of time it takes to destroy a network device. Signed-off-by: Eric W. Biederman --- net/core/dev.c | 8 +++++++- 1 files changed, 7 insertions(+), 1 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 70ecb86..44dcacf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5235,7 +5235,7 @@ static void rollback_registered_many(struct list_head *head) dev = list_first_entry(head, struct net_device, unreg_list); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - rcu_barrier(); + synchronize_net(); list_for_each_entry(dev, head, unreg_list) dev_put(dev); @@ -5748,6 +5748,12 @@ void netdev_run_todo(void) __rtnl_unlock(); + /* Wait for rcu callbacks to finish before attempting to drain + * the device list. This usually avoids a 250ms wait. + */ + if (!list_empty(&list)) + rcu_barrier(); + while (!list_empty(&list)) { struct net_device *dev = list_first_entry(&list, struct net_device, todo_list); -- 1.7.2.5