- Allocate a small flowtable in ip_input.c (changeable by tuneable)

- Use for accelerating ip_output

3 files changed, 19 insertions, 2 deletions

diff --git a/sys/netinet/ip_input.c b/sys/netinet/ip_input.c
index 920d741..2db3afb 100644
--- a/sys/netinet/ip_input.c
+++ b/sys/netinet/ip_input.c
@@ -64,6 +64,7 @@ __FBSDID("$FreeBSD$");
 #include <net/route.h>
 #include <net/netisr.h>
 #include <net/vnet.h>
+#include <net/flowtable.h>
 
 #include <netinet/in.h>
 #include <netinet/in_systm.h>
@@ -211,6 +212,11 @@ SYSCTL_INT(_net_inet_ip, IPCTL_DEFMTU, mtu, CTLFLAG_RW,
 SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_ip, OID_AUTO, stealth, CTLFLAG_RW,
     ipstealth, 0, "IP stealth mode, no TTL decrementation on forwarding");
 #endif
+static int ip_output_flowtable_size = 2048;
+TUNABLE_INT("net.inet.ip.output_flowtable_size", &ip_output_flowtable_size);
+SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_ip, OID_AUTO, output_flowtable_size,
+    CTLFLAG_RDTUN, ip_output_flowtable_size, 2048,
+    "number of entries in the per-cpu output flow caches");
 
 /*
  * ipfw_ether and ipfw_bridge hooks.
@@ -221,6 +227,7 @@ ip_dn_io_t *ip_dn_io_ptr = NULL;
 #ifdef VIMAGE_GLOBALS
 int fw_one_pass;
 #endif
+struct flowtable *ip_ft;
 
 static void	ip_freef(struct ipqhead *, struct ipq *);
 
@@ -342,6 +349,8 @@ ip_init(void)
 	ipintrq.ifq_maxlen = ipqmaxlen;
 	mtx_init(&ipintrq.ifq_mtx, "ip_inq", NULL, MTX_DEF);
 	netisr_register(NETISR_IP, ip_input, &ipintrq, 0);
+
+	ip_ft = flowtable_alloc(ip_output_flowtable_size, FL_PCPU);
 }
 
 void
diff --git a/sys/netinet/ip_output.c b/sys/netinet/ip_output.c
index 76d8f2a..20acb921 100644
--- a/sys/netinet/ip_output.c
+++ b/sys/netinet/ip_output.c
@@ -59,6 +59,7 @@ __FBSDID("$FreeBSD$");
 #include <net/netisr.h>
 #include <net/pfil.h>
 #include <net/route.h>
+#include <net/flowtable.h>
 #ifdef RADIX_MPATH
 #include <net/radix_mpath.h>
 #endif
@@ -135,6 +136,7 @@ ip_output(struct mbuf *m, struct mbuf *opt, struct route *ro, int flags,
 	int hlen = sizeof (struct ip);
 	int mtu;
 	int len, error = 0;
+	int nortfree = 0;
 	struct sockaddr_in *dst = NULL;	/* keep compiler happy */
 	struct in_ifaddr *ia = NULL;
 	int isbroadcast, sw_csum;
@@ -158,6 +160,10 @@ ip_output(struct mbuf *m, struct mbuf *opt, struct route *ro, int flags,
 			m->m_flags |= M_FLOWID;
 		}
 	}
+	if ((ro == &iproute) && (ro->ro_rt == NULL) && (ro->ro_lle == NULL)) {
+		if (flowtable_lookup(ip_ft, m, ro) == 0)
+			nortfree = 1;
+	}
 
 	if (opt) {
 		len = 0;
@@ -199,7 +205,8 @@ again:
 	if (ro->ro_rt && ((ro->ro_rt->rt_flags & RTF_UP) == 0 ||
 			  dst->sin_family != AF_INET ||
 			  dst->sin_addr.s_addr != ip->ip_dst.s_addr)) {
-		RTFREE(ro->ro_rt);
+		if (!nortfree)
+			RTFREE(ro->ro_rt);
 		ro->ro_rt = (struct rtentry *)NULL;
 	}
 #ifdef IPFIREWALL_FORWARD
@@ -638,7 +645,7 @@ passout:
 		IPSTAT_INC(ips_fragmented);
 
 done:
-	if (ro == &iproute && ro->ro_rt) {
+	if (ro == &iproute && ro->ro_rt && !nortfree) {
 		RTFREE(ro->ro_rt);
 	}
 	return (error);
diff --git a/sys/netinet/vinet.h b/sys/netinet/vinet.h
index b65acc1..20a36c5 100644
--- a/sys/netinet/vinet.h
+++ b/sys/netinet/vinet.h
@@ -72,6 +72,7 @@ struct vnet_inet {
 	int	_ip_sendsourcequench;
 	int	_ip_do_randomid;
 	int	_ip_checkinterface;
+	int	_ip_output_flowtable_size;
 	u_short	_ip_id;
 
 	uma_zone_t _ipq_zone;