net: Batch inet_twsk_purge

This function walks the whole hashtable so there is no point in
passing it a network namespace.  Instead I purge all timewait
sockets from dead network namespaces that I find.  If the namespace
is one of the once I am trying to purge I am guaranteed no new timewait
sockets can be formed so this will get them all.  If the namespace
is one I am not acting for it might form a few more but I will
call inet_twsk_purge again and  shortly to get rid of them.  In
any even if the network namespace is dead timewait sockets are
useless.

Move the calls of inet_twsk_purge into batch_exit routines so
that if I am killing a bunch of namespaces at once I will just
call inet_twsk_purge once and save a lot of redundant unnecessary
work.

My simple 4k network namespace exit test the cleanup time dropped from
roughly 8.2s to 1.6s.  While the time spent running inet_twsk_purge fell
to about 2ms.  1ms for ipv4 and 1ms for ipv6.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 21 insertions, 11 deletions

diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index d38ca7c..31f931e 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -421,7 +421,7 @@ out:
 
 EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick);
 
-void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo,
+void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 		     struct inet_timewait_death_row *twdr, int family)
 {
 	struct inet_timewait_sock *tw;
@@ -436,15 +436,15 @@ restart_rcu:
 restart:
 		sk_nulls_for_each_rcu(sk, node, &head->twchain) {
 			tw = inet_twsk(sk);
-			if (!net_eq(twsk_net(tw), net) ||
-			    tw->tw_family != family)
+			if ((tw->tw_family != family) ||
+				atomic_read(&twsk_net(tw)->count))
 				continue;
 
 			if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt)))
 				continue;
 
-			if (unlikely(!net_eq(twsk_net(tw), net) ||
-				     tw->tw_family != family)) {
+			if (unlikely((tw->tw_family != family) ||
+				     atomic_read(&twsk_net(tw)->count))) {
 				inet_twsk_put(tw);
 				goto restart;
 			}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 59c911f..fee9aab 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2529,12 +2529,17 @@ static int __net_init tcp_sk_init(struct net *net)
 static void __net_exit tcp_sk_exit(struct net *net)
 {
 	inet_ctl_sock_destroy(net->ipv4.tcp_sock);
-	inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET);
+}
+
+static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
+{
+	inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET);
 }
 
 static struct pernet_operations __net_initdata tcp_sk_ops = {
-       .init = tcp_sk_init,
-       .exit = tcp_sk_exit,
+       .init	   = tcp_sk_init,
+       .exit	   = tcp_sk_exit,
+       .exit_batch = tcp_sk_exit_batch,
 };
 
 void __init tcp_v4_init(void)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fc0a4e5..aadd7ce 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2184,12 +2184,17 @@ static int tcpv6_net_init(struct net *net)
 static void tcpv6_net_exit(struct net *net)
 {
 	inet_ctl_sock_destroy(net->ipv6.tcp_sk);
-	inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET6);
+}
+
+static void tcpv6_net_exit_batch(struct list_head *net_exit_list)
+{
+	inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6);
 }
 
 static struct pernet_operations tcpv6_net_ops = {
-	.init = tcpv6_net_init,
-	.exit = tcpv6_net_exit,
+	.init	    = tcpv6_net_init,
+	.exit	    = tcpv6_net_exit,
+	.exit_batch = tcpv6_net_exit_batch,
 };
 
 int __init tcpv6_init(void)