When ip_output()/ip6_output() is supplied a struct route *ro argument,

it skips FLOWTABLE lookup. However, the non-NULL ro has dual meaning
here: it may be supplied to provide route, and it may be supplied to
store and return to caller the route that ip_output()/ip6_output()
finds. In the latter case skipping FLOWTABLE lookup is pessimisation.

The difference between struct route filled by FLOWTABLE and filled
by rtalloc() family is that the former doesn't hold a reference on
its rtentry. Reference is hold by flow entry, and it is about to
be released in future. Thus, route filled by FLOWTABLE shouldn't
be passed to RTFREE() macro.

- Introduce new flag for struct route/route_in6, that marks route
  not holding a reference on rtentry.
- Introduce new macro RO_RTFREE() that cleans up a struct route
  depending on its kind.
- All callers to ip_output()/ip6_output() that do supply non-NULL
  but empty route should use RO_RTFREE() to free results of
  lookup.
- ip_output()/ip6_output() now do FLOWTABLE lookup always when
  ro->ro_rt == NULL.

Tested by:	tuexen (SCTP part)

1 files changed, 22 insertions, 22 deletions

diff --git a/sys/netinet/ip_output.c b/sys/netinet/ip_output.c
index d13c397..cc38dcf 100644
--- a/sys/netinet/ip_output.c
+++ b/sys/netinet/ip_output.c
@@ -105,6 +105,10 @@ extern	struct protosw inetsw[];
  * ip_len and ip_off are in host format.
  * The mbuf chain containing the packet will be freed.
  * The mbuf opt, if present, will not be freed.
+ * If route ro is present and has ro_rt initialized, route lookup would be
+ * skipped and ro->ro_rt would be used. If ro is present but ro->ro_rt is NULL,
+ * then result of route lookup is stored in ro->ro_rt.
+ *
  * In the IP forwarding case, the packet will arrive with options already
  * inserted, so must have a NULL opt pointer.
  */
@@ -119,7 +123,6 @@ ip_output(struct mbuf *m, struct mbuf *opt, struct route *ro, int flags,
 	int mtu;
 	int n;	/* scratchpad */
 	int error = 0;
-	int nortfree = 0;
 	struct sockaddr_in *dst;
 	struct in_ifaddr *ia = NULL;
 	int isbroadcast, sw_csum;
@@ -146,24 +149,23 @@ ip_output(struct mbuf *m, struct mbuf *opt, struct route *ro, int flags,
 	if (ro == NULL) {
 		ro = &iproute;
 		bzero(ro, sizeof (*ro));
+	}
 
 #ifdef FLOWTABLE
-		{
-			struct flentry *fle;
+	if (ro->ro_rt == NULL) {
+		struct flentry *fle;
 			
-			/*
-			 * The flow table returns route entries valid for up to 30
-			 * seconds; we rely on the remainder of ip_output() taking no
-			 * longer than that long for the stability of ro_rt.  The
-			 * flow ID assignment must have happened before this point.
-			 */
-			if ((fle = flowtable_lookup_mbuf(V_ip_ft, m, AF_INET)) != NULL) {
-				flow_to_route(fle, ro);
-				nortfree = 1;
-			}
-		}
-#endif
+		/*
+		 * The flow table returns route entries valid for up to 30
+		 * seconds; we rely on the remainder of ip_output() taking no
+		 * longer than that long for the stability of ro_rt. The
+		 * flow ID assignment must have happened before this point.
+		 */
+		fle = flowtable_lookup_mbuf(V_ip_ft, m, AF_INET);
+		if (fle != NULL)
+			flow_to_route(fle, ro);
 	}
+#endif
 
 	if (opt) {
 		int len = 0;
@@ -209,10 +211,9 @@ again:
 		    !RT_LINK_IS_UP(rte->rt_ifp) ||
 			  dst->sin_family != AF_INET ||
 			  dst->sin_addr.s_addr != ip->ip_dst.s_addr)) {
-		if (!nortfree)
-			RTFREE(rte);
-		rte = ro->ro_rt = (struct rtentry *)NULL;
-		ro->ro_lle = (struct llentry *)NULL;
+		RO_RTFREE(ro);
+		ro->ro_lle = NULL;
+		rte = NULL;
 	}
 #ifdef IPFIREWALL_FORWARD
 	if (rte == NULL && fwd_tag == NULL) {
@@ -672,9 +673,8 @@ passout:
 		IPSTAT_INC(ips_fragmented);
 
 done:
-	if (ro == &iproute && ro->ro_rt && !nortfree) {
-		RTFREE(ro->ro_rt);
-	}
+	if (ro == &iproute)
+		RO_RTFREE(ro);
 	if (ia != NULL)
 		ifa_free(&ia->ia_ifa);
 	return (error);