From 0115e8e30d6fcdd4b8faa30d3ffd90859a591f51 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Aug 2012 17:19:46 +0000 Subject: net: remove delay at device dismantle I noticed extra one second delay in device dismantle, tracked down to a call to dst_dev_event() while some call_rcu() are still in RCU queues. These call_rcu() were posted by rt_free(struct rtable *rt) calls. We then wait a little (but one second) in netdev_wait_allrefs() before kicking again NETDEV_UNREGISTER. As the call_rcu() are now completed, dst_dev_event() can do the needed device swap on busy dst. To solve this problem, add a new NETDEV_UNREGISTER_FINAL, called after a rcu_barrier(), but outside of RTNL lock. Use NETDEV_UNREGISTER_FINAL with care ! Change dst_dev_event() handler to react to NETDEV_UNREGISTER_FINAL Also remove NETDEV_UNREGISTER_BATCH, as its not used anymore after IP cache removal. With help from Gao feng Signed-off-by: Eric Dumazet Cc: Tom Herbert Cc: Mahesh Bandewar Cc: "Eric W. Biederman" Cc: Gao feng Signed-off-by: David S. Miller --- net/core/fib_rules.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/core/fib_rules.c') diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index ab7db83236c9..585093755c23 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -711,15 +711,16 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, struct net *net = dev_net(dev); struct fib_rules_ops *ops; - ASSERT_RTNL(); switch (event) { case NETDEV_REGISTER: + ASSERT_RTNL(); list_for_each_entry(ops, &net->rules_ops, list) attach_rules(&ops->rules_list, dev); break; case NETDEV_UNREGISTER: + ASSERT_RTNL(); list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); break; -- cgit v1.2.3