summaryrefslogtreecommitdiff
path: root/net/netfilter
diff options
context:
space:
mode:
authorAndrew Sy Kim <kim.andrewsy@gmail.com>2020-07-08 12:16:38 -0400
committerPablo Neira Ayuso <pablo@netfilter.org>2020-07-22 01:17:59 +0200
commit35dfb013149f74c2be1ff9c78f14e6a3cd1539d1 (patch)
treec667d506f5c295992d6381398a5f4c4c0fbd6a51 /net/netfilter
parent336f531ab17c3f480f8289d26c35bd48302ed085 (diff)
ipvs: queue delayed work to expire no destination connections if expire_nodest_conn=1
When expire_nodest_conn=1 and a destination is deleted, IPVS does not expire the existing connections until the next matching incoming packet. If there are many connection entries from a single client to a single destination, many packets may get dropped before all the connections are expired (more likely with lots of UDP traffic). An optimization can be made where upon deletion of a destination, IPVS queues up delayed work to immediately expire any connections with a deleted destination. This ensures any reused source ports from a client (within the IPVS timeouts) are scheduled to new real servers instead of silently dropped. Signed-off-by: Andrew Sy Kim <kim.andrewsy@gmail.com> Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c39
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c47
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c22
3 files changed, 81 insertions, 27 deletions
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index b3921ae92740..a90b8eac16ac 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1389,6 +1389,45 @@ flush_again:
goto flush_again;
}
}
+
+#ifdef CONFIG_SYSCTL
+void ip_vs_expire_nodest_conn_flush(struct netns_ipvs *ipvs)
+{
+ int idx;
+ struct ip_vs_conn *cp, *cp_c;
+ struct ip_vs_dest *dest;
+
+ rcu_read_lock();
+ for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
+ hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) {
+ if (cp->ipvs != ipvs)
+ continue;
+
+ dest = cp->dest;
+ if (!dest || (dest->flags & IP_VS_DEST_F_AVAILABLE))
+ continue;
+
+ if (atomic_read(&cp->n_control))
+ continue;
+
+ cp_c = cp->control;
+ 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_del(cp_c);
+ }
+ }
+ cond_resched_rcu();
+
+ /* netns clean up started, abort delayed work */
+ if (!ipvs->enable)
+ break;
+ }
+ rcu_read_unlock();
+}
+#endif
+
/*
* per netns init and exit
*/
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b4a6b7662f3f..e3668a6e54e4 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -694,16 +694,10 @@ static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs)
return ipvs->sysctl_nat_icmp_send;
}
-static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
-{
- return ipvs->sysctl_expire_nodest_conn;
-}
-
#else
static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; }
static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; }
-static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) { return 0; }
#endif
@@ -2097,36 +2091,35 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
}
}
- if (unlikely(!cp)) {
- int v;
-
- if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph))
- return v;
- }
-
- IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet");
-
/* Check the server status */
- if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
+ if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
/* the destination server is not available */
+ if (sysctl_expire_nodest_conn(ipvs)) {
+ bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
- __u32 flags = cp->flags;
-
- /* when timer already started, silently drop the packet.*/
- if (timer_pending(&cp->timer))
- __ip_vs_conn_put(cp);
- else
- ip_vs_conn_put(cp);
+ if (!old_ct)
+ cp->flags &= ~IP_VS_CONN_F_NFCT;
- if (sysctl_expire_nodest_conn(ipvs) &&
- !(flags & IP_VS_CONN_F_ONE_PACKET)) {
- /* try to expire the connection immediately */
ip_vs_conn_expire_now(cp);
+ __ip_vs_conn_put(cp);
+ if (old_ct)
+ return NF_DROP;
+ cp = NULL;
+ } else {
+ __ip_vs_conn_put(cp);
+ return NF_DROP;
}
+ }
- return NF_DROP;
+ if (unlikely(!cp)) {
+ int v;
+
+ if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph))
+ return v;
}
+ IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet");
+
ip_vs_in_stats(cp, skb);
ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
if (cp->packet_xmit)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 4af83f466dfc..f984d2c881ff 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -210,6 +210,17 @@ static void update_defense_level(struct netns_ipvs *ipvs)
local_bh_enable();
}
+/* Handler for delayed work for expiring no
+ * destination connections
+ */
+static void expire_nodest_conn_handler(struct work_struct *work)
+{
+ struct netns_ipvs *ipvs;
+
+ ipvs = container_of(work, struct netns_ipvs,
+ expire_nodest_conn_work.work);
+ ip_vs_expire_nodest_conn_flush(ipvs);
+}
/*
* Timer for checking the defense
@@ -1164,6 +1175,12 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest,
list_add(&dest->t_list, &ipvs->dest_trash);
dest->idle_start = 0;
spin_unlock_bh(&ipvs->dest_trash_lock);
+
+ /* Queue up delayed work to expire all no destination connections.
+ * No-op when CONFIG_SYSCTL is disabled.
+ */
+ if (!cleanup)
+ ip_vs_enqueue_expire_nodest_conns(ipvs);
}
@@ -4086,6 +4103,10 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
queue_delayed_work(system_long_wq, &ipvs->defense_work,
DEFENSE_TIMER_PERIOD);
+ /* Init delayed work for expiring no dest conn */
+ INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work,
+ expire_nodest_conn_handler);
+
return 0;
}
@@ -4093,6 +4114,7 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs)
{
struct net *net = ipvs->net;
+ cancel_delayed_work_sync(&ipvs->expire_nodest_conn_work);
cancel_delayed_work_sync(&ipvs->defense_work);
cancel_work_sync(&ipvs->defense_work.work);
unregister_net_sysctl_table(ipvs->sysctl_hdr);