IPVS: one-packet scheduling

Allow one-packet scheduling for UDP connections. When the fwmark-based or
normal virtual service is marked with '-o' or '--ops' options all
connections are created only to schedule one packet. Useful to schedule UDP
packets from same client port to different real servers. Recommended with
RR or WRR schedulers (the connections are not visible with ipvsadm -L).

Signed-off-by: Nick Chalk <nick@loadbalancer.org>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Patrick McHardy <kaber@trash.net>

3 files changed, 29 insertions, 11 deletions

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index d8f7e8ef67b4..717e6233d50f 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -158,6 +158,9 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
 	unsigned hash;
 	int ret;
 
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		return 0;
+
 	/* Hash by protocol, client address and port */
 	hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport);
 
@@ -355,8 +358,9 @@ struct ip_vs_conn *ip_vs_conn_out_get
  */
 void ip_vs_conn_put(struct ip_vs_conn *cp)
 {
-	/* reset it expire in its timeout */
-	mod_timer(&cp->timer, jiffies+cp->timeout);
+	unsigned long t = (cp->flags & IP_VS_CONN_F_ONE_PACKET) ?
+		0 : cp->timeout;
+	mod_timer(&cp->timer, jiffies+t);
 
 	__ip_vs_conn_put(cp);
 }
@@ -649,7 +653,7 @@ static void ip_vs_conn_expire(unsigned long data)
 	/*
 	 *	unhash it if it is hashed in the conn table
 	 */
-	if (!ip_vs_conn_unhash(cp))
+	if (!ip_vs_conn_unhash(cp) && !(cp->flags & IP_VS_CONN_F_ONE_PACKET))
 		goto expire_later;
 
 	/*
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 1cd6e3fd058b..50907d8472a3 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -194,6 +194,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	struct ip_vs_dest *dest;
 	struct ip_vs_conn *ct;
 	__be16  dport;			/* destination port to forward */
+	__be16  flags;
 	union nf_inet_addr snet;	/* source network of the client,
 					   after masking */
 
@@ -340,6 +341,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		dport = ports[1];
 	}
 
+	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
+		 && iph.protocol == IPPROTO_UDP)?
+		IP_VS_CONN_F_ONE_PACKET : 0;
+
 	/*
 	 *    Create a new connection according to the template
 	 */
@@ -347,7 +352,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 			    &iph.saddr, ports[0],
 			    &iph.daddr, ports[1],
 			    &dest->addr, dport,
-			    0,
+			    flags,
 			    dest);
 	if (cp == NULL) {
 		ip_vs_conn_put(ct);
@@ -377,7 +382,7 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	struct ip_vs_conn *cp = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
-	__be16 _ports[2], *pptr;
+	__be16 _ports[2], *pptr, flags;
 
 	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
 	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
@@ -407,6 +412,10 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		return NULL;
 	}
 
+	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
+		 && iph.protocol == IPPROTO_UDP)?
+		IP_VS_CONN_F_ONE_PACKET : 0;
+
 	/*
 	 *    Create a connection entry.
 	 */
@@ -414,7 +423,7 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 			    &iph.saddr, pptr[0],
 			    &iph.daddr, pptr[1],
 			    &dest->addr, dest->port ? dest->port : pptr[1],
-			    0,
+			    flags,
 			    dest);
 	if (cp == NULL)
 		return NULL;
@@ -464,6 +473,9 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 	if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) {
 		int ret, cs;
 		struct ip_vs_conn *cp;
+		__u16 flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
+				iph.protocol == IPPROTO_UDP)?
+				IP_VS_CONN_F_ONE_PACKET : 0;
 		union nf_inet_addr daddr =  { .all = { 0, 0, 0, 0 } };
 
 		ip_vs_service_put(svc);
@@ -474,7 +486,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 				    &iph.saddr, pptr[0],
 				    &iph.daddr, pptr[1],
 				    &daddr, 0,
-				    IP_VS_CONN_F_BYPASS,
+				    IP_VS_CONN_F_BYPASS | flags,
 				    NULL);
 		if (cp == NULL)
 			return NF_DROP;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 36dc1d88c2fa..0f0c079c422a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1864,14 +1864,16 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
 					   svc->scheduler->name);
 			else
 #endif
-				seq_printf(seq, "%s  %08X:%04X %s ",
+				seq_printf(seq, "%s  %08X:%04X %s %s ",
 					   ip_vs_proto_name(svc->protocol),
 					   ntohl(svc->addr.ip),
 					   ntohs(svc->port),
-					   svc->scheduler->name);
+					   svc->scheduler->name,
+					   (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
 		} else {
-			seq_printf(seq, "FWM  %08X %s ",
-				   svc->fwmark, svc->scheduler->name);
+			seq_printf(seq, "FWM  %08X %s %s",
+				   svc->fwmark, svc->scheduler->name,
+				   (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
 		}
 
 		if (svc->flags & IP_VS_SVC_F_PERSISTENT)