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>

1 files changed, 20 insertions, 27 deletions

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)