ipvs: avoid expiring many connections from timer

Add new functions ip_vs_conn_del() and ip_vs_conn_del_put()
to release many IPVS connections in process context.
They are suitable for connections found in table
when we do not want to overload the timers.

Currently, the change is useful for the dropentry delayed
work but it will be used also in following patch
when flushing connections to failed destinations.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Reviewed-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 02f2f636798d11bdce848b0d46f6990db765c627..b3921ae927407f221466a71dd2c138a921280a6a 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -807,6 +807,31 @@ static void ip_vs_conn_rcu_free(struct rcu_head *head)
        kmem_cache_free(ip_vs_conn_cachep, cp);
 }
 
+/* Try to delete connection while not holding reference */
+static void ip_vs_conn_del(struct ip_vs_conn *cp)
+{
+       if (del_timer(&cp->timer)) {
+               /* Drop cp->control chain too */
+               if (cp->control)
+                       cp->timeout = 0;
+               ip_vs_conn_expire(&cp->timer);
+       }
+}
+
+/* Try to delete connection while holding reference */
+static void ip_vs_conn_del_put(struct ip_vs_conn *cp)
+{
+       if (del_timer(&cp->timer)) {
+               /* Drop cp->control chain too */
+               if (cp->control)
+                       cp->timeout = 0;
+               __ip_vs_conn_put(cp);
+               ip_vs_conn_expire(&cp->timer);
+       } else {
+               __ip_vs_conn_put(cp);
+       }
+}
+
 static void ip_vs_conn_expire(struct timer_list *t)
 {
        struct ip_vs_conn *cp = from_timer(cp, t, timer);
@@ -827,14 +852,17 @@ static void ip_vs_conn_expire(struct timer_list *t)
 
                /* does anybody control me? */
                if (ct) {
+                       bool has_ref = !cp->timeout && __ip_vs_conn_get(ct);
+
                        ip_vs_control_del(cp);
                        /* Drop CTL or non-assured TPL if not used anymore */
-                       if (!cp->timeout && !atomic_read(&ct->n_control) &&
+                       if (has_ref && !atomic_read(&ct->n_control) &&
                            (!(ct->flags & IP_VS_CONN_F_TEMPLATE) ||
                             !(ct->state & IP_VS_CTPL_S_ASSURED))) {
                                IP_VS_DBG(4, "drop controlling connection\n");
-                               ct->timeout = 0;
-                               ip_vs_conn_expire_now(ct);
+                               ip_vs_conn_del_put(ct);
+                       } else if (has_ref) {
+                               __ip_vs_conn_put(ct);
                        }
                }
 
@@ -1317,8 +1345,7 @@ try_drop:
 
 drop:
                        IP_VS_DBG(4, "drop connection\n");
-                       cp->timeout = 0;
-                       ip_vs_conn_expire_now(cp);
+                       ip_vs_conn_del(cp);
                }
                cond_resched_rcu();
        }
@@ -1341,19 +1368,15 @@ flush_again:
                hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) {
                        if (cp->ipvs != ipvs)
                                continue;
-                       /* As timers are expired in LIFO order, restart
-                        * the timer of controlling connection first, so
-                        * that it is expired after us.
-                        */
+                       if (atomic_read(&cp->n_control))
+                               continue;
                        cp_c = cp->control;
-                       /* cp->control is valid only with reference to cp */
-                       if (cp_c && __ip_vs_conn_get(cp)) {
+                       IP_VS_DBG(4, "del connection\n");
+                       ip_vs_conn_del(cp);
+                       if (cp_c && !atomic_read(&cp_c->n_control)) {
                                IP_VS_DBG(4, "del controlling connection\n");
-                               ip_vs_conn_expire_now(cp_c);
-                               __ip_vs_conn_put(cp);
+                               ip_vs_conn_del(cp_c);
                        }
-                       IP_VS_DBG(4, "del connection\n");
-                       ip_vs_conn_expire_now(cp);
                }
                cond_resched_rcu();
        }

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 0eed388c960bde0afa157412cfb8ede13b8a2c96..4af83f466dfc2cd0d0720d7b445bff87a2bcda72 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -224,7 +224,8 @@ static void defense_work_handler(struct work_struct *work)
        update_defense_level(ipvs);
        if (atomic_read(&ipvs->dropentry))
                ip_vs_random_dropentry(ipvs);
-       schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
+       queue_delayed_work(system_long_wq, &ipvs->defense_work,
+                          DEFENSE_TIMER_PERIOD);
 }
 #endif
 
@@ -4082,7 +4083,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
        ipvs->sysctl_tbl = tbl;
        /* Schedule defense work */
        INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
-       schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
+       queue_delayed_work(system_long_wq, &ipvs->defense_work,
+                          DEFENSE_TIMER_PERIOD);
 
        return 0;
 }