net: Use rcu lookups in inet_twsk_purge.

While we are looking up entries to free there is no reason to take
the lock in inet_twsk_purge.  We have to drop locks and restart
occassionally anyway so adding a few more in case we get on the
wrong list because of a timewait move is no big deal.  At the
same time not taking the lock for long periods of time is much
more polite to the rest of the users of the hash table.

In my test configuration of killing 4k network namespaces
this change causes 4k back to back runs of inet_twsk_purge on an
empty hash table to go from roughly 20.7s to 3.3s, and the total
time to destroy 4k network namespaces goes from roughly 44s to
3.3s.

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

diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 1f5d508bb18b80a4b8a3290ce0e3c0925b0e25f8..d38ca7c77b930f50cab109a3c9d46f68eea0f191 100644 (file)
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -427,31 +427,40 @@ void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo,
        struct inet_timewait_sock *tw;
        struct sock *sk;
        struct hlist_nulls_node *node;
-       int h;
+       unsigned int slot;
 
-       local_bh_disable();
-       for (h = 0; h <= hashinfo->ehash_mask; h++) {
-               struct inet_ehash_bucket *head =
-                       inet_ehash_bucket(hashinfo, h);
-               spinlock_t *lock = inet_ehash_lockp(hashinfo, h);
+       for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
+               struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
+restart_rcu:
+               rcu_read_lock();
 restart:
-               spin_lock(lock);
-               sk_nulls_for_each(sk, node, &head->twchain) {
-
+               sk_nulls_for_each_rcu(sk, node, &head->twchain) {
                        tw = inet_twsk(sk);
                        if (!net_eq(twsk_net(tw), net) ||
                            tw->tw_family != family)
                                continue;
 
-                       atomic_inc(&tw->tw_refcnt);
-                       spin_unlock(lock);
+                       if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt)))
+                               continue;
+
+                       if (unlikely(!net_eq(twsk_net(tw), net) ||
+                                    tw->tw_family != family)) {
+                               inet_twsk_put(tw);
+                               goto restart;
+                       }
+
+                       rcu_read_unlock();
                        inet_twsk_deschedule(tw, twdr);
                        inet_twsk_put(tw);
-
-                       goto restart;
+                       goto restart_rcu;
                }
-               spin_unlock(lock);
+               /* If the nulls value we got at the end of this lookup is
+                * not the expected one, we must restart lookup.
+                * We probably met an item that was moved to another chain.
+                */
+               if (get_nulls_value(node) != slot)
+                       goto restart;
+               rcu_read_unlock();
        }
-       local_bh_enable();
 }
 EXPORT_SYMBOL_GPL(inet_twsk_purge);