net = dev_net(rt->dst.dev);
peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1);
if (!peer) {
- icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+ icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST,
+ rt_nexthop(rt, ip_hdr(skb)->daddr));
return;
}
time_after(jiffies,
(peer->rate_last +
(ip_rt_redirect_load << peer->rate_tokens)))) {
- icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+ __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);
+
+ icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
peer->rate_tokens == ip_rt_redirect_number)
net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
&ip_hdr(skb)->saddr, inet_iif(skb),
- &ip_hdr(skb)->daddr, &rt->rt_gateway);
+ &ip_hdr(skb)->daddr, &gw);
#endif
}
out_put_peer:
return 0;
}
-static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
+static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
+ struct dst_entry *dst = &rt->dst;
struct fib_result res;
+ if (dst->dev->mtu < mtu)
+ return;
+
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
+ if (!rt->rt_pmtu) {
+ dst->obsolete = DST_OBSOLETE_KILL;
+ } else {
+ rt->rt_pmtu = mtu;
+ dst->expires = max(1UL, jiffies + ip_rt_mtu_expires);
+ }
+
rcu_read_lock();
- if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) {
+ if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) {
struct fib_nh *nh = &FIB_RES_NH(res);
update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
jiffies + ip_rt_mtu_expires);
}
rcu_read_unlock();
- return mtu;
}
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct flowi4 fl4;
ip_rt_build_flow_key(&fl4, sk, skb);
- mtu = __ip_rt_update_pmtu(rt, &fl4, mtu);
-
- if (!rt->rt_pmtu) {
- dst->obsolete = DST_OBSOLETE_KILL;
- } else {
- rt->rt_pmtu = mtu;
- rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires);
- }
+ __ip_rt_update_pmtu(rt, &fl4, mtu);
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
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;
}
spin_lock_bh(&fnhe_lock);
if (daddr == fnhe->fnhe_daddr) {
- struct rtable *orig;
-
+ struct rtable *orig = rcu_dereference(fnhe->fnhe_rth);
+ if (orig && rt_is_expired(orig)) {
+ fnhe->fnhe_gw = 0;
+ fnhe->fnhe_pmtu = 0;
+ fnhe->fnhe_expires = 0;
+ }
if (fnhe->fnhe_pmtu) {
unsigned long expires = fnhe->fnhe_expires;
unsigned long diff = expires - jiffies;
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);
if (orig)
rt_free(orig);
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);
if (rt_is_input_route(rt)) {
p = (struct rtable **)&nh->nh_rth_input;
} else {
- if (!nh->nh_pcpu_rth_output)
- goto nocache;
p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
}
orig = *p;
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.
- */
-nocache:
- rt->dst.flags |= DST_NOCACHE;
+ } else
ret = false;
- }
return ret;
}
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;
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
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;
return -EINVAL;
}
-
err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
in_dev->dev, in_dev, &itag);
if (err < 0) {
goto cleanup;
}
- if (out_dev == in_dev && err &&
+ do_cache = res->fi && !itag;
+ if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
(IN_DEV_SHARED_MEDIA(out_dev) ||
- inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+ inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
flags |= RTCF_DOREDIRECT;
+ do_cache = false;
+ }
if (skb->protocol != htons(ETH_P_IP)) {
/* Not IP (i.e. ARP). Do not create route, if it is
}
}
- do_cache = false;
- if (res->fi) {
- if (!itag) {
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
- if (rt_cache_valid(rth)) {
- skb_dst_set_noref(skb, &rth->dst);
- goto out;
- }
- do_cache = true;
+ if (do_cache) {
+ rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+ if (rt_cache_valid(rth)) {
+ skb_dst_set_noref(skb, &rth->dst);
+ goto out;
}
}
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;
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;
struct in_device *in_dev;
u16 type = res->type;
struct rtable *rth;
+ bool do_cache;
in_dev = __in_dev_get_rcu(dev_out);
if (!in_dev)
}
fnhe = NULL;
+ do_cache = fi != NULL;
if (fi) {
struct rtable __rcu **prth;
+ struct fib_nh *nh = &FIB_RES_NH(*res);
- fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
+ fnhe = find_exception(nh, fl4->daddr);
if (fnhe)
prth = &fnhe->fnhe_rth;
- else
- prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output);
+ else {
+ if (unlikely(fl4->flowi4_flags &
+ FLOWI_FLAG_KNOWN_NH &&
+ !(nh->nh_gw &&
+ nh->nh_scope == RT_SCOPE_LINK))) {
+ do_cache = false;
+ goto add;
+ }
+ prth = __this_cpu_ptr(nh->nh_pcpu_rth_output);
+ }
rth = rcu_dereference(*prth);
if (rt_cache_valid(rth)) {
dst_hold(&rth->dst);
return rth;
}
}
+
+add:
rth = rt_dst_alloc(dev_out,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(in_dev, NOXFRM),
- fi);
+ do_cache);
if (!rth)
return ERR_PTR(-ENOBUFS);
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);
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);
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;
+ expires = rt->dst.expires;
+ if (expires) {
+ unsigned long now = jiffies;
+
+ if (time_before(now, expires))
+ expires -= now;
+ else
+ expires = 0;
+ }
+
memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
- if (rt->rt_pmtu)
+ if (rt->rt_pmtu && expires)
metrics[RTAX_MTU - 1] = rt->rt_pmtu;
if (rtnetlink_put_metrics(skb, metrics) < 0)
goto nla_put_failure;
if (fl4->flowi4_mark &&
- nla_put_be32(skb, RTA_MARK, fl4->flowi4_mark))
+ nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
error = rt->dst.error;
- expires = rt->dst.expires;
- if (expires) {
- if (time_before(jiffies, expires))
- expires -= jiffies;
- else
- expires = 0;
- }
if (rt_is_input_route(rt)) {
if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
projects / ~andy / linux / blobdiff