From 8c1960d506bea78b693c2be8fb55f755d6e56f5d Mon Sep 17 00:00:00 2001
From: Mike Karels <karels@FreeBSD.org>
Date: Sat, 25 Mar 2017 15:06:28 +0000
Subject: [PATCH] Fix reference count leak with L2 caching.

ip_forward, TCP/IPv6, and probably SCTP leaked references to L2 cache
entry because they used their own routes on the stack, not in_pcb routes.
The original model for route caching was callers that provided a route
structure to ip{,6}input() would keep the route, and this model was used
for L2 caching as well. Instead, change L2 caching to be done by default
only when using a route structure in the in_pcb; the pcb deallocation
code frees L2 as well as L3 cacches. A separate change will add route
caching to TCP/IPv6.

Another suggestion was to have the transport protocols indicate willingness
to use L2 caching, but this approach keeps the changes in the network
level

Reviewed by:    ae gnn
MFC after:      2 weeks
Differential Revision:  https://reviews.freebsd.org/D10059
---
 sys/netinet/in_pcb.c      | 6 ++++++
 sys/netinet/ip_output.c   | 3 +--
 sys/netinet6/ip6_output.c | 3 +--
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/sys/netinet/in_pcb.c b/sys/netinet/in_pcb.c
index 59ff8e66f87..3c88d1cf5f2 100644
--- a/sys/netinet/in_pcb.c
+++ b/sys/netinet/in_pcb.c
@@ -328,6 +328,12 @@ in_pcballoc(struct socket *so, struct inpcbinfo *pcbinfo)
 #endif
 	inp->inp_gencnt = ++pcbinfo->ipi_gencnt;
 	refcount_init(&inp->inp_refcount, 1);	/* Reference from inpcbinfo */
+
+	/*
+	 * Routes in inpcb's can cache L2 as well; they are guaranteed
+	 * to be cleaned up.
+	 */
+	inp->inp_route.ro_flags = RT_LLE_CACHE;
 	INP_LIST_WUNLOCK(pcbinfo);
 #if defined(IPSEC) || defined(IPSEC_SUPPORT) || defined(MAC)
 out:
diff --git a/sys/netinet/ip_output.c b/sys/netinet/ip_output.c
index f958285d56a..3f8178045db 100644
--- a/sys/netinet/ip_output.c
+++ b/sys/netinet/ip_output.c
@@ -242,8 +242,7 @@ ip_output(struct mbuf *m, struct mbuf *opt, struct route *ro, int flags,
 	if (ro == NULL) {
 		ro = &iproute;
 		bzero(ro, sizeof (*ro));
-	} else
-		ro->ro_flags |= RT_LLE_CACHE;
+	}
 
 #ifdef FLOWTABLE
 	if (ro->ro_rt == NULL)
diff --git a/sys/netinet6/ip6_output.c b/sys/netinet6/ip6_output.c
index debc02955ea..c851038c12d 100644
--- a/sys/netinet6/ip6_output.c
+++ b/sys/netinet6/ip6_output.c
@@ -494,8 +494,7 @@ ip6_output(struct mbuf *m0, struct ip6_pktopts *opt,
 	if (ro == NULL) {
 		ro = &ip6route;
 		bzero((caddr_t)ro, sizeof(*ro));
-	} else
-		ro->ro_flags |= RT_LLE_CACHE;
+	}
 	ro_pmtu = ro;
 	if (opt && opt->ip6po_rthdr)
 		ro = &opt->ip6po_route;