ipv4: introduce rt_uses_gateway
Add new flag to remember when route is via gateway.
We will use it to allow rt_gateway to contain address of
directly connected host for the cases when DST_NOCACHE is
used or when the NH exception caches per-destination route
without DST_NOCACHE flag, i.e. when routes are not used for
other destinations. By this way we force the neighbour
resolving to work with the routed destination but we
can use different address in the packet, feature needed
for IPVS-DR where original packet for virtual IP is routed
via route to real IP.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f0c5b9c..d34ce29 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -406,7 +406,7 @@
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
return &rt->dst;
@@ -442,7 +442,7 @@
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
rcu_read_unlock();
return &rt->dst;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 7f35ac2..694de3b 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -85,7 +85,7 @@
rt = skb_rtable(skb);
- if (opt->is_strictroute && rt->rt_gateway)
+ if (opt->is_strictroute && rt->rt_uses_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 24a29a3..6537a40 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -193,7 +193,7 @@
}
rcu_read_lock_bh();
- nexthop = rt->rt_gateway ? rt->rt_gateway : ip_hdr(skb)->daddr;
+ nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
@@ -371,7 +371,7 @@
skb_dst_set_noref(skb, &rt->dst);
packet_routed:
- if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway)
+ if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
goto no_route;
/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5b0180f..3a116cb 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1126,7 +1126,7 @@
mtu = dst->dev->mtu;
if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
- if (rt->rt_gateway && mtu > 576)
+ if (rt->rt_uses_gateway && mtu > 576)
mtu = 576;
}
@@ -1177,7 +1177,9 @@
if (fnhe->fnhe_gw) {
rt->rt_flags |= RTCF_REDIRECTED;
rt->rt_gateway = fnhe->fnhe_gw;
- }
+ rt->rt_uses_gateway = 1;
+ } else if (!rt->rt_gateway)
+ rt->rt_gateway = daddr;
orig = rcu_dereference(fnhe->fnhe_rth);
rcu_assign_pointer(fnhe->fnhe_rth, rt);
@@ -1186,13 +1188,6 @@
fnhe->fnhe_stamp = jiffies;
ret = true;
- } else {
- /* Routes we intend to cache in nexthop exception have
- * the DST_NOCACHE bit clear. However, if we are
- * unsuccessful at storing this route into the cache
- * we really need to set it.
- */
- rt->dst.flags |= DST_NOCACHE;
}
spin_unlock_bh(&fnhe_lock);
@@ -1215,15 +1210,8 @@
if (prev == orig) {
if (orig)
rt_free(orig);
- } else {
- /* Routes we intend to cache in the FIB nexthop have
- * the DST_NOCACHE bit clear. However, if we are
- * unsuccessful at storing this route into the cache
- * we really need to set it.
- */
- rt->dst.flags |= DST_NOCACHE;
+ } else
ret = false;
- }
return ret;
}
@@ -1284,8 +1272,10 @@
if (fi) {
struct fib_nh *nh = &FIB_RES_NH(*res);
- if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
+ if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) {
rt->rt_gateway = nh->nh_gw;
+ rt->rt_uses_gateway = 1;
+ }
dst_init_metrics(&rt->dst, fi->fib_metrics, true);
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
@@ -1294,8 +1284,18 @@
cached = rt_bind_exception(rt, fnhe, daddr);
else if (!(rt->dst.flags & DST_NOCACHE))
cached = rt_cache_route(nh, rt);
- }
- if (unlikely(!cached))
+ if (unlikely(!cached)) {
+ /* Routes we intend to cache in nexthop exception or
+ * FIB nexthop have the DST_NOCACHE bit clear.
+ * However, if we are unsuccessful at storing this
+ * route into the cache we really need to set it.
+ */
+ rt->dst.flags |= DST_NOCACHE;
+ if (!rt->rt_gateway)
+ rt->rt_gateway = daddr;
+ rt_add_uncached_list(rt);
+ }
+ } else
rt_add_uncached_list(rt);
#ifdef CONFIG_IP_ROUTE_CLASSID
@@ -1363,6 +1363,7 @@
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
if (our) {
rth->dst.input= ip_local_deliver;
@@ -1432,7 +1433,6 @@
return -EINVAL;
}
-
err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
in_dev->dev, in_dev, &itag);
if (err < 0) {
@@ -1488,6 +1488,7 @@
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
rth->dst.input = ip_forward;
@@ -1658,6 +1659,7 @@
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
@@ -1826,6 +1828,7 @@
rth->rt_iif = orig_oif ? : 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
RT_CACHE_STAT_INC(out_slow_tot);
@@ -2104,6 +2107,7 @@
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_gateway = ort->rt_gateway;
+ rt->rt_uses_gateway = ort->rt_uses_gateway;
INIT_LIST_HEAD(&rt->rt_uncached);
@@ -2182,7 +2186,7 @@
if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
goto nla_put_failure;
}
- if (rt->rt_gateway &&
+ if (rt->rt_uses_gateway &&
nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
goto nla_put_failure;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 681ea2f..05c5ab8 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -91,6 +91,7 @@
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
xdst->u.rt.rt_gateway = rt->rt_gateway;
+ xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
