ipvs: queue delayed work to expire no destination connections if expire_nodest_conn=1

[upstream commit 35dfb01314]

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>

include/net/ip_vs.h

@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>             /* for struct rwlock_t */
 #include <linux/atomic.h>               /* for struct atomic_t */
 #include <linux/refcount.h>             /* for struct refcount_t */
+#include <linux/workqueue.h>
 
 #include <linux/compiler.h>
 #include <linux/timer.h>
@@ -887,6 +888,8 @@ struct netns_ipvs {
 	atomic_t		conn_out_counter;
 
 #ifdef CONFIG_SYSCTL
+	/* delayed work for expiring no dest connections */
+	struct delayed_work	expire_nodest_conn_work;
 	/* 1/rate drop and drop-entry variables */
 	struct delayed_work	defense_work;   /* Work handler */
 	int			drop_rate;
@@ -1054,6 +1057,11 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs)
 	return ipvs->sysctl_conn_reuse_mode;
 }
 
+static inline int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_expire_nodest_conn;
+}
+
 static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs)
 {
 	return ipvs->sysctl_schedule_icmp;
@@ -1146,6 +1154,11 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs)
 	return 1;
 }
 
+static inline int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
+{
+	return 0;
+}
+
 static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs)
 {
 	return 0;
@@ -1515,6 +1528,22 @@ static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; }
 #endif
 
+#ifdef CONFIG_SYSCTL
+/* Enqueue delayed work for expiring no dest connections
+ * Only run when sysctl_expire_nodest=1
+ */
+static inline void ip_vs_enqueue_expire_nodest_conns(struct netns_ipvs *ipvs)
+{
+	if (sysctl_expire_nodest_conn(ipvs))
+		queue_delayed_work(system_long_wq,
+				   &ipvs->expire_nodest_conn_work, 1);
+}
+
+void ip_vs_expire_nodest_conn_flush(struct netns_ipvs *ipvs);
+#else
+static inline void ip_vs_enqueue_expire_nodest_conns(struct netns_ipvs *ipvs) {}
+#endif
+
 #define IP_VS_DFWD_METHOD(dest) (atomic_read(&(dest)->conn_flags) & \
 				 IP_VS_CONN_F_FWD_MASK)
 

net/netfilter/ipvs/ip_vs_conn.c

@@ -823,6 +823,17 @@ 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);
+	}
+}
+
 static void ip_vs_conn_expire(struct timer_list *t)
 {
 	struct ip_vs_conn *cp = from_timer(cp, t, timer);
@@ -1382,6 +1393,45 @@ 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
  */

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
 
@@ -2126,6 +2120,26 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 		}
 	}
 
+	/* Check the server status */
+	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);
+
+			if (!old_ct)
+				cp->flags &= ~IP_VS_CONN_F_NFCT;
+
+			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;
+		}
+	}
+
 	if (unlikely(!cp)) {
 		int v;
 
@@ -2135,27 +2149,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 
 	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)) {
-		/* the destination server is not available */
-
-		__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 (sysctl_expire_nodest_conn(ipvs) &&
-		    !(flags & IP_VS_CONN_F_ONE_PACKET)) {
-			/* try to expire the connection immediately */
-			ip_vs_conn_expire_now(cp);
-		}
-
-		return NF_DROP;
-	}
-
 	ip_vs_in_stats(cp, skb);
 	ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 	if (cp->packet_xmit)

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
@@ -1163,6 +1174,12 @@ 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);
 }
 
 
@@ -4081,6 +4098,10 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
 	schedule_delayed_work(&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;
 }
 
@@ -4088,6 +4109,7 @@ 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);