static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
+static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb);
static int rt_garbage_collect(struct dst_ops *ops);
static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old)
{
- struct rtable *rt = (struct rtable *) dst;
- struct inet_peer *peer;
- u32 *p = NULL;
-
- peer = rt_get_peer_create(rt, rt->rt_dst);
- if (peer) {
- u32 *old_p = __DST_METRICS_PTR(old);
- unsigned long prev, new;
-
- p = peer->metrics;
- if (inet_metrics_new(peer))
- memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
-
- new = (unsigned long) p;
- prev = cmpxchg(&dst->_metrics, old, new);
-
- if (prev != old) {
- p = __DST_METRICS_PTR(prev);
- if (prev & DST_METRICS_READ_ONLY)
- p = NULL;
- } else {
- if (rt->fi) {
- fib_info_put(rt->fi);
- rt->fi = NULL;
- }
- }
- }
- return p;
+ WARN_ON(1);
+ return NULL;
}
-static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr);
+static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
+ struct sk_buff *skb,
+ const void *daddr);
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
.update_pmtu = ip_rt_update_pmtu,
+ .redirect = ip_do_redirect,
.local_out = __ip_local_out,
.neigh_lookup = ipv4_neigh_lookup,
};
"HHUptod\tSpecDst");
else {
struct rtable *r = v;
- struct neighbour *n;
- int len, HHUptod;
-
- rcu_read_lock();
- n = dst_get_neighbour_noref(&r->dst);
- HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
- rcu_read_unlock();
+ int len;
seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
- "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
- r->dst.dev ? r->dst.dev->name : "*",
- (__force u32)r->rt_dst,
- (__force u32)r->rt_gateway,
- r->rt_flags, atomic_read(&r->dst.__refcnt),
- r->dst.__use, 0, (__force u32)r->rt_src,
- dst_metric_advmss(&r->dst) + 40,
- dst_metric(&r->dst, RTAX_WINDOW),
- (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
- dst_metric(&r->dst, RTAX_RTTVAR)),
- r->rt_key_tos,
- -1,
- HHUptod,
- r->rt_spec_dst, &len);
+ "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
+ r->dst.dev ? r->dst.dev->name : "*",
+ (__force u32)r->rt_dst,
+ (__force u32)r->rt_gateway,
+ r->rt_flags, atomic_read(&r->dst.__refcnt),
+ r->dst.__use, 0, (__force u32)r->rt_src,
+ dst_metric_advmss(&r->dst) + 40,
+ dst_metric(&r->dst, RTAX_WINDOW), 0,
+ r->rt_key_tos,
+ -1, 0, 0, &len);
seq_printf(seq, "%*s\n", 127 - len, "");
}
static inline int rt_valuable(struct rtable *rth)
{
return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
- (rt_has_peer(rth) && rt_peer_ptr(rth)->pmtu_expires);
+ rth->dst.expires;
}
static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
while ((rth = rcu_dereference_protected(*rthp,
lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) {
prefetch(rth->dst.rt_next);
- if (rt_is_expired(rth)) {
+ if (rt_is_expired(rth) ||
+ rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
*rthp = rth->dst.rt_next;
rt_free(rth);
continue;
}
- if (rth->dst.expires) {
- /* Entry is expired even if it is in use */
- if (time_before_eq(jiffies, rth->dst.expires)) {
-nofree:
- tmo >>= 1;
- rthp = &rth->dst.rt_next;
- /*
- * We only count entries on
- * a chain with equal hash inputs once
- * so that entries for different QOS
- * levels, and other non-hash input
- * attributes don't unfairly skew
- * the length computation
- */
- length += has_noalias(rt_hash_table[i].chain, rth);
- continue;
- }
- } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
- goto nofree;
- /* Cleanup aged off entries. */
- *rthp = rth->dst.rt_next;
- rt_free(rth);
+ /* We only count entries on a chain with equal
+ * hash inputs once so that entries for
+ * different QOS levels, and other non-hash
+ * input attributes don't unfairly skew the
+ * length computation
+ */
+ tmo >>= 1;
+ rthp = &rth->dst.rt_next;
+ length += has_noalias(rt_hash_table[i].chain, rth);
}
spin_unlock_bh(rt_hash_lock_addr(i));
sum += length;
get_random_bytes(&shuffle, sizeof(shuffle));
atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
- inetpeer_invalidate_family(AF_INET);
}
/*
return length >> FRACT_BITS;
}
-static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr)
+static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
+ struct sk_buff *skb,
+ const void *daddr)
{
- static const __be32 inaddr_any = 0;
struct net_device *dev = dst->dev;
const __be32 *pkey = daddr;
const struct rtable *rt;
struct neighbour *n;
rt = (const struct rtable *) dst;
-
- if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
- pkey = &inaddr_any;
- else if (rt->rt_gateway)
+ if (rt->rt_gateway)
pkey = (const __be32 *) &rt->rt_gateway;
+ else if (skb)
+ pkey = &ip_hdr(skb)->daddr;
n = __ipv4_neigh_lookup(dev, *(__force u32 *)pkey);
if (n)
return neigh_create(&arp_tbl, pkey, dev);
}
-static int rt_bind_neighbour(struct rtable *rt)
-{
- struct neighbour *n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
- if (IS_ERR(n))
- return PTR_ERR(n);
- dst_set_neighbour(&rt->dst, n);
-
- return 0;
-}
-
static struct rtable *rt_intern_hash(unsigned int hash, struct rtable *rt,
struct sk_buff *skb, int ifindex)
{
unsigned long now;
u32 min_score;
int chain_length;
- int attempts = !in_softirq();
restart:
chain_length = 0;
*/
rt->dst.flags |= DST_NOCACHE;
- if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
- int err = rt_bind_neighbour(rt);
- if (err) {
- net_warn_ratelimited("Neighbour table failure & not caching routes\n");
- ip_rt_put(rt);
- return ERR_PTR(err);
- }
- }
-
goto skip_hashing;
}
}
}
- /* Try to bind route to arp only if it is output
- route or unicast forwarding path.
- */
- if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
- int err = rt_bind_neighbour(rt);
- if (err) {
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- if (err != -ENOBUFS) {
- rt_drop(rt);
- return ERR_PTR(err);
- }
-
- /* Neighbour tables are full and nothing
- can be released. Try to shrink route cache,
- it is most likely it holds some neighbour records.
- */
- if (attempts-- > 0) {
- int saved_elasticity = ip_rt_gc_elasticity;
- int saved_int = ip_rt_gc_min_interval;
- ip_rt_gc_elasticity = 1;
- ip_rt_gc_min_interval = 0;
- rt_garbage_collect(&ipv4_dst_ops);
- ip_rt_gc_min_interval = saved_int;
- ip_rt_gc_elasticity = saved_elasticity;
- goto restart;
- }
-
- net_warn_ratelimited("Neighbour table overflow\n");
- rt_drop(rt);
- return ERR_PTR(-ENOBUFS);
- }
- }
-
rt->dst.rt_next = rt_hash_table[hash].chain;
/*
return rt;
}
-static atomic_t __rt_peer_genid = ATOMIC_INIT(0);
-
-static u32 rt_peer_genid(void)
-{
- return atomic_read(&__rt_peer_genid);
-}
-
-void rt_bind_peer(struct rtable *rt, __be32 daddr, int create)
-{
- struct inet_peer_base *base;
- struct inet_peer *peer;
-
- base = inetpeer_base_ptr(rt->_peer);
- if (!base)
- return;
-
- peer = inet_getpeer_v4(base, daddr, create);
- if (peer) {
- if (!rt_set_peer(rt, peer))
- inet_putpeer(peer);
- else
- rt->rt_peer_genid = rt_peer_genid();
- }
-}
-
/*
* Peer allocation may fail only in serious out-of-memory conditions. However
* we still can generate some output.
void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
{
- struct rtable *rt = (struct rtable *) dst;
-
- if (rt && !(rt->dst.flags & DST_NOPEER)) {
- struct inet_peer *peer = rt_get_peer_create(rt, rt->rt_dst);
+ struct net *net = dev_net(dst->dev);
+ struct inet_peer *peer;
- /* If peer is attached to destination, it is never detached,
- so that we need not to grab a lock to dereference it.
- */
- if (peer) {
- iph->id = htons(inet_getid(peer, more));
- return;
- }
- } else if (!rt)
- pr_debug("rt_bind_peer(0) @%p\n", __builtin_return_address(0));
+ peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1);
+ if (peer) {
+ iph->id = htons(inet_getid(peer, more));
+ inet_putpeer(peer);
+ return;
+ }
ip_select_fb_ident(iph);
}
spin_unlock_bh(rt_hash_lock_addr(hash));
}
-static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb)
{
- struct rtable *rt = (struct rtable *) dst;
- __be32 orig_gw = rt->rt_gateway;
- struct neighbour *n, *old_n;
-
- dst_confirm(&rt->dst);
+ const struct iphdr *iph = (const struct iphdr *) skb->data;
+ __be32 new_gw = icmp_hdr(skb)->un.gateway;
+ __be32 old_gw = ip_hdr(skb)->saddr;
+ struct net_device *dev = skb->dev;
+ __be32 daddr = iph->daddr;
+ __be32 saddr = iph->saddr;
+ struct in_device *in_dev;
+ struct neighbour *n;
+ struct rtable *rt;
+ struct net *net;
- rt->rt_gateway = peer->redirect_learned.a4;
+ switch (icmp_hdr(skb)->code & 7) {
+ case ICMP_REDIR_NET:
+ case ICMP_REDIR_NETTOS:
+ case ICMP_REDIR_HOST:
+ case ICMP_REDIR_HOSTTOS:
+ break;
- n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
- if (IS_ERR(n)) {
- rt->rt_gateway = orig_gw;
+ default:
return;
}
- old_n = xchg(&rt->dst._neighbour, n);
- if (old_n)
- neigh_release(old_n);
- if (!(n->nud_state & NUD_VALID)) {
- neigh_event_send(n, NULL);
- } else {
- rt->rt_flags |= RTCF_REDIRECTED;
- call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
- }
-}
-/* called in rcu_read_lock() section */
-void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
- __be32 saddr, struct net_device *dev)
-{
- int s, i;
- struct in_device *in_dev = __in_dev_get_rcu(dev);
- __be32 skeys[2] = { saddr, 0 };
- int ikeys[2] = { dev->ifindex, 0 };
- struct inet_peer *peer;
- struct net *net;
+ rt = (struct rtable *) dst;
+ if (rt->rt_gateway != old_gw)
+ return;
+ in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
return;
goto reject_redirect;
}
- for (s = 0; s < 2; s++) {
- for (i = 0; i < 2; i++) {
- unsigned int hash;
- struct rtable __rcu **rthp;
- struct rtable *rt;
-
- hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
-
- rthp = &rt_hash_table[hash].chain;
-
- while ((rt = rcu_dereference(*rthp)) != NULL) {
- rthp = &rt->dst.rt_next;
-
- if (rt->rt_key_dst != daddr ||
- rt->rt_key_src != skeys[s] ||
- rt->rt_oif != ikeys[i] ||
- rt_is_input_route(rt) ||
- rt_is_expired(rt) ||
- !net_eq(dev_net(rt->dst.dev), net) ||
- rt->dst.error ||
- rt->dst.dev != dev ||
- rt->rt_gateway != old_gw)
- continue;
-
- peer = rt_get_peer_create(rt, rt->rt_dst);
- if (peer) {
- if (peer->redirect_learned.a4 != new_gw) {
- peer->redirect_learned.a4 = new_gw;
- atomic_inc(&__rt_peer_genid);
- }
- check_peer_redir(&rt->dst, peer);
- }
- }
+ n = ipv4_neigh_lookup(dst, NULL, &new_gw);
+ if (n) {
+ if (!(n->nud_state & NUD_VALID)) {
+ neigh_event_send(n, NULL);
+ } else {
+ rt->rt_gateway = new_gw;
+ rt->rt_flags |= RTCF_REDIRECTED;
+ call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
}
+ neigh_release(n);
}
return;
;
}
-static bool peer_pmtu_expired(struct inet_peer *peer)
-{
- unsigned long orig = ACCESS_ONCE(peer->pmtu_expires);
-
- return orig &&
- time_after_eq(jiffies, orig) &&
- cmpxchg(&peer->pmtu_expires, orig, 0) == orig;
-}
-
-static bool peer_pmtu_cleaned(struct inet_peer *peer)
-{
- unsigned long orig = ACCESS_ONCE(peer->pmtu_expires);
-
- return orig &&
- cmpxchg(&peer->pmtu_expires, orig, 0) == orig;
-}
-
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
{
struct rtable *rt = (struct rtable *)dst;
if (dst->obsolete > 0) {
ip_rt_put(rt);
ret = NULL;
- } else if (rt->rt_flags & RTCF_REDIRECTED) {
+ } else if ((rt->rt_flags & RTCF_REDIRECTED) ||
+ rt->dst.expires) {
unsigned int hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
rt->rt_oif,
rt_genid(dev_net(dst->dev)));
rt_del(hash, rt);
ret = NULL;
- } else if (rt_has_peer(rt)) {
- struct inet_peer *peer = rt_peer_ptr(rt);
- if (peer_pmtu_expired(peer))
- dst_metric_set(dst, RTAX_MTU, peer->pmtu_orig);
}
}
return ret;
struct rtable *rt = skb_rtable(skb);
struct in_device *in_dev;
struct inet_peer *peer;
+ struct net *net;
int log_martians;
rcu_read_lock();
log_martians = IN_DEV_LOG_MARTIANS(in_dev);
rcu_read_unlock();
- peer = rt_get_peer_create(rt, rt->rt_dst);
+ 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);
return;
*/
if (peer->rate_tokens >= ip_rt_redirect_number) {
peer->rate_last = jiffies;
- return;
+ goto out_put_peer;
}
/* Check for load limit; set rate_last to the latest sent
&rt->rt_dst, &rt->rt_gateway);
#endif
}
+out_put_peer:
+ inet_putpeer(peer);
}
static int ip_error(struct sk_buff *skb)
{
+ struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
struct rtable *rt = skb_rtable(skb);
struct inet_peer *peer;
unsigned long now;
+ struct net *net;
bool send;
int code;
+ net = dev_net(rt->dst.dev);
+ if (!IN_DEV_FORWARD(in_dev)) {
+ switch (rt->dst.error) {
+ case EHOSTUNREACH:
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INADDRERRORS);
+ break;
+
+ case ENETUNREACH:
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INNOROUTES);
+ break;
+ }
+ goto out;
+ }
+
switch (rt->dst.error) {
case EINVAL:
default:
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
- IP_INC_STATS_BH(dev_net(rt->dst.dev),
- IPSTATS_MIB_INNOROUTES);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
code = ICMP_PKT_FILTERED;
break;
}
- peer = rt_get_peer_create(rt, rt->rt_dst);
+ peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1);
send = true;
if (peer) {
peer->rate_tokens -= ip_rt_error_cost;
else
send = false;
+ inet_putpeer(peer);
}
if (send)
icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
return 0;
}
-static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer)
-{
- unsigned long expires = ACCESS_ONCE(peer->pmtu_expires);
-
- if (!expires)
- return;
- if (time_before(jiffies, expires)) {
- u32 orig_dst_mtu = dst_mtu(dst);
- if (peer->pmtu_learned < orig_dst_mtu) {
- if (!peer->pmtu_orig)
- peer->pmtu_orig = dst_metric_raw(dst, RTAX_MTU);
- dst_metric_set(dst, RTAX_MTU, peer->pmtu_learned);
- }
- } else if (cmpxchg(&peer->pmtu_expires, expires, 0) == expires)
- dst_metric_set(dst, RTAX_MTU, peer->pmtu_orig);
-}
-
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
{
struct rtable *rt = (struct rtable *) dst;
- struct inet_peer *peer;
dst_confirm(dst);
- peer = rt_get_peer_create(rt, rt->rt_dst);
- if (peer) {
- unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires);
-
- if (mtu < ip_rt_min_pmtu)
- mtu = ip_rt_min_pmtu;
- if (!pmtu_expires || mtu < peer->pmtu_learned) {
-
- pmtu_expires = jiffies + ip_rt_mtu_expires;
- if (!pmtu_expires)
- pmtu_expires = 1UL;
-
- peer->pmtu_learned = mtu;
- peer->pmtu_expires = pmtu_expires;
+ if (mtu < ip_rt_min_pmtu)
+ mtu = ip_rt_min_pmtu;
- atomic_inc(&__rt_peer_genid);
- rt->rt_peer_genid = rt_peer_genid();
- }
- check_peer_pmtu(dst, peer);
- }
+ rt->rt_pmtu = mtu;
+ dst_set_expires(&rt->dst, ip_rt_mtu_expires);
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
struct rtable *rt;
flowi4_init_output(&fl4, oif, mark, RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
- protocol, flow_flags | FLOWI_FLAG_PRECOW_METRICS,
+ protocol, flow_flags,
iph->daddr, iph->saddr, 0, 0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
}
EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
-static void ipv4_validate_peer(struct rtable *rt)
+void ipv4_redirect(struct sk_buff *skb, struct net *net,
+ int oif, u32 mark, u8 protocol, int flow_flags)
{
- if (rt->rt_peer_genid != rt_peer_genid()) {
- struct inet_peer *peer = rt_get_peer(rt, rt->rt_dst);
+ const struct iphdr *iph = (const struct iphdr *)skb->data;
+ struct flowi4 fl4;
+ struct rtable *rt;
- if (peer) {
- check_peer_pmtu(&rt->dst, peer);
+ flowi4_init_output(&fl4, oif, mark, RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
+ protocol, flow_flags, iph->daddr, iph->saddr, 0, 0);
+ rt = __ip_route_output_key(net, &fl4);
+ if (!IS_ERR(rt)) {
+ ip_do_redirect(&rt->dst, skb);
+ ip_rt_put(rt);
+ }
+}
+EXPORT_SYMBOL_GPL(ipv4_redirect);
- if (peer->redirect_learned.a4 &&
- peer->redirect_learned.a4 != rt->rt_gateway)
- check_peer_redir(&rt->dst, peer);
- }
+void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
+{
+ const struct inet_sock *inet = inet_sk(sk);
- rt->rt_peer_genid = rt_peer_genid();
- }
+ return ipv4_redirect(skb, sock_net(sk), sk->sk_bound_dev_if,
+ sk->sk_mark,
+ inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ inet_sk_flowi_flags(sk));
}
+EXPORT_SYMBOL_GPL(ipv4_sk_redirect);
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
{
if (rt_is_expired(rt))
return NULL;
- ipv4_validate_peer(rt);
return dst;
}
fib_info_put(rt->fi);
rt->fi = NULL;
}
- if (rt_has_peer(rt)) {
- struct inet_peer *peer = rt_peer_ptr(rt);
- inet_putpeer(peer);
- }
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
rt = skb_rtable(skb);
- if (rt && rt_has_peer(rt)) {
- struct inet_peer *peer = rt_peer_ptr(rt);
- if (peer_pmtu_cleaned(peer))
- dst_metric_set(&rt->dst, RTAX_MTU, peer->pmtu_orig);
- }
+ if (rt)
+ dst_set_expires(&rt->dst, 0);
}
static int ip_rt_bug(struct sk_buff *skb)
static unsigned int ipv4_mtu(const struct dst_entry *dst)
{
const struct rtable *rt = (const struct rtable *) dst;
- unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+ unsigned int mtu = rt->rt_pmtu;
+
+ if (mtu && time_after_eq(jiffies, rt->dst.expires))
+ mtu = 0;
+
+ if (!mtu)
+ mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu && rt_is_output_route(rt))
return mtu;
static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
struct fib_info *fi)
{
- struct inet_peer_base *base;
- struct inet_peer *peer;
- int create = 0;
-
- /* If a peer entry exists for this destination, we must hook
- * it up in order to get at cached metrics.
- */
- if (fl4 && (fl4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS))
- create = 1;
-
- base = inetpeer_base_ptr(rt->_peer);
- BUG_ON(!base);
-
- peer = inet_getpeer_v4(base, rt->rt_dst, create);
- if (peer) {
- __rt_set_peer(rt, peer);
- rt->rt_peer_genid = rt_peer_genid();
- if (inet_metrics_new(peer))
- memcpy(peer->metrics, fi->fib_metrics,
- sizeof(u32) * RTAX_MAX);
- dst_init_metrics(&rt->dst, peer->metrics, false);
-
- check_peer_pmtu(&rt->dst, peer);
-
- if (peer->redirect_learned.a4 &&
- peer->redirect_learned.a4 != rt->rt_gateway) {
- rt->rt_gateway = peer->redirect_learned.a4;
- rt->rt_flags |= RTCF_REDIRECTED;
- }
- } else {
- if (fi->fib_metrics != (u32 *) dst_default_metrics) {
- rt->fi = fi;
- atomic_inc(&fi->fib_clntref);
- }
- dst_init_metrics(&rt->dst, fi->fib_metrics, true);
+ if (fi->fib_metrics != (u32 *) dst_default_metrics) {
+ rt->fi = fi;
+ atomic_inc(&fi->fib_clntref);
}
+ dst_init_metrics(&rt->dst, fi->fib_metrics, true);
}
static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4,
const struct fib_result *res,
struct fib_info *fi, u16 type, u32 itag)
{
- struct dst_entry *dst = &rt->dst;
-
if (fi) {
if (FIB_RES_GW(*res) &&
FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = FIB_RES_GW(*res);
rt_init_metrics(rt, fl4, fi);
#ifdef CONFIG_IP_ROUTE_CLASSID
- dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
+ rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
#endif
}
- if (dst_mtu(dst) > IP_MAX_MTU)
- dst_metric_set(dst, RTAX_MTU, IP_MAX_MTU);
-
#ifdef CONFIG_IP_ROUTE_CLASSID
#ifdef CONFIG_IP_MULTIPLE_TABLES
set_class_tag(rt, fib_rules_tclass(res));
{
unsigned int hash;
struct rtable *rth;
- __be32 spec_dst;
struct in_device *in_dev = __in_dev_get_rcu(dev);
u32 itag = 0;
int err;
if (ipv4_is_zeronet(saddr)) {
if (!ipv4_is_local_multicast(daddr))
goto e_inval;
- spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
} else {
- err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst,
- &itag);
+ err = fib_validate_source(skb, saddr, 0, tos, 0, dev,
+ in_dev, &itag);
if (err < 0)
goto e_err;
}
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
rth->rt_mark = skb->mark;
+ rth->rt_pmtu = 0;
rth->rt_gateway = daddr;
- rth->rt_spec_dst= spec_dst;
- rth->rt_peer_genid = 0;
- rt_init_peer(rth, dev_net(dev)->ipv4.peers);
rth->fi = NULL;
if (our) {
rth->dst.input= ip_local_deliver;
int err;
struct in_device *out_dev;
unsigned int flags = 0;
- __be32 spec_dst;
u32 itag;
/* get a working reference to the output device */
err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
- in_dev->dev, &spec_dst, &itag);
+ in_dev->dev, in_dev, &itag);
if (err < 0) {
ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_oif = 0;
rth->rt_mark = skb->mark;
+ rth->rt_pmtu = 0;
rth->rt_gateway = daddr;
- rth->rt_spec_dst= spec_dst;
- rth->rt_peer_genid = 0;
- rt_init_peer(rth, &res->table->tb_peers);
rth->fi = NULL;
rth->dst.input = ip_forward;
u32 itag = 0;
struct rtable *rth;
unsigned int hash;
- __be32 spec_dst;
int err = -EINVAL;
struct net *net = dev_net(dev);
fl4.daddr = daddr;
fl4.saddr = saddr;
err = fib_lookup(net, &fl4, &res);
- if (err != 0) {
- if (!IN_DEV_FORWARD(in_dev))
- goto e_hostunreach;
+ if (err != 0)
goto no_route;
- }
RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_LOCAL) {
err = fib_validate_source(skb, saddr, daddr, tos,
net->loopback_dev->ifindex,
- dev, &spec_dst, &itag);
+ dev, in_dev, &itag);
if (err < 0)
goto martian_source_keep_err;
if (err)
flags |= RTCF_DIRECTSRC;
- spec_dst = daddr;
goto local_input;
}
if (!IN_DEV_FORWARD(in_dev))
- goto e_hostunreach;
+ goto no_route;
if (res.type != RTN_UNICAST)
goto martian_destination;
if (skb->protocol != htons(ETH_P_IP))
goto e_inval;
- if (ipv4_is_zeronet(saddr))
- spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
- else {
- err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst,
- &itag);
+ if (!ipv4_is_zeronet(saddr)) {
+ err = fib_validate_source(skb, saddr, 0, tos, 0, dev,
+ in_dev, &itag);
if (err < 0)
goto martian_source_keep_err;
if (err)
rth->rt_key_tos = tos;
rth->rt_dst = daddr;
rth->rt_src = saddr;
-#ifdef CONFIG_IP_ROUTE_CLASSID
- rth->dst.tclassid = itag;
-#endif
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
rth->rt_mark = skb->mark;
+ rth->rt_pmtu = 0;
rth->rt_gateway = daddr;
- rth->rt_spec_dst= spec_dst;
- rth->rt_peer_genid = 0;
- rt_init_peer(rth, net->ipv4.peers);
rth->fi = NULL;
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
no_route:
RT_CACHE_STAT_INC(in_no_route);
- spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
res.type = RTN_UNREACHABLE;
if (err == -ESRCH)
err = -ENETUNREACH;
&daddr, &saddr, dev->name);
#endif
-e_hostunreach:
- err = -EHOSTUNREACH;
- goto out;
-
e_inval:
err = -EINVAL;
goto out;
rth->rt_mark == skb->mark &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
- ipv4_validate_peer(rth);
if (noref) {
dst_use_noref(&rth->dst, jiffies);
skb_dst_set_noref(skb, &rth->dst);
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_oif = orig_oif;
rth->rt_mark = fl4->flowi4_mark;
+ rth->rt_pmtu = 0;
rth->rt_gateway = fl4->daddr;
- rth->rt_spec_dst= fl4->saddr;
- rth->rt_peer_genid = 0;
- rt_init_peer(rth, (res->table ?
- &res->table->tb_peers :
- dev_net(dev_out)->ipv4.peers));
rth->fi = NULL;
RT_CACHE_STAT_INC(out_slow_tot);
- if (flags & RTCF_LOCAL) {
+ if (flags & RTCF_LOCAL)
rth->dst.input = ip_local_deliver;
- rth->rt_spec_dst = fl4->daddr;
- }
if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
- rth->rt_spec_dst = fl4->saddr;
if (flags & RTCF_LOCAL &&
!(dev_out->flags & IFF_LOOPBACK)) {
rth->dst.output = ip_mc_output;
(IPTOS_RT_MASK | RTO_ONLINK)) &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
- ipv4_validate_peer(rth);
dst_use(&rth->dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
{
}
+static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sk_buff *skb)
+{
+}
+
static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
unsigned long old)
{
.mtu = ipv4_blackhole_mtu,
.default_advmss = ipv4_default_advmss,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
+ .redirect = ipv4_rt_blackhole_redirect,
.cow_metrics = ipv4_rt_blackhole_cow_metrics,
.neigh_lookup = ipv4_neigh_lookup,
};
new->__use = 1;
new->input = dst_discard;
new->output = dst_discard;
- dst_copy_metrics(new, &ort->dst);
new->dev = ort->dst.dev;
if (new->dev)
rt->rt_iif = ort->rt_iif;
rt->rt_oif = ort->rt_oif;
rt->rt_mark = ort->rt_mark;
+ rt->rt_pmtu = ort->rt_pmtu;
rt->rt_genid = rt_genid(net);
rt->rt_flags = ort->rt_flags;
rt->rt_dst = ort->rt_dst;
rt->rt_src = ort->rt_src;
rt->rt_gateway = ort->rt_gateway;
- rt->rt_spec_dst = ort->rt_spec_dst;
- rt_transfer_peer(rt, ort);
rt->fi = ort->fi;
if (rt->fi)
atomic_inc(&rt->fi->fib_clntref);
struct rtmsg *r;
struct nlmsghdr *nlh;
unsigned long expires = 0;
- u32 id = 0, ts = 0, tsage = 0, error;
+ u32 error;
nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
if (nlh == NULL)
nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid))
goto nla_put_failure;
#endif
- if (rt_is_input_route(rt)) {
- if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_spec_dst))
- goto nla_put_failure;
- } else if (rt->rt_src != rt->rt_key_src) {
+ if (!rt_is_input_route(rt) &&
+ rt->rt_src != rt->rt_key_src) {
if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src))
goto nla_put_failure;
}
goto nla_put_failure;
error = rt->dst.error;
- if (rt_has_peer(rt)) {
- const struct inet_peer *peer = rt_peer_ptr(rt);
- inet_peer_refcheck(peer);
- id = atomic_read(&peer->ip_id_count) & 0xffff;
- if (peer->tcp_ts_stamp) {
- ts = peer->tcp_ts;
- tsage = get_seconds() - peer->tcp_ts_stamp;
- }
- expires = ACCESS_ONCE(peer->pmtu_expires);
- if (expires) {
- if (time_before(jiffies, expires))
- expires -= jiffies;
- else
- expires = 0;
- }
+ expires = rt->dst.expires;
+ if (expires) {
+ if (time_before(jiffies, expires))
+ expires -= jiffies;
+ else
+ expires = 0;
}
if (rt_is_input_route(rt)) {
goto nla_put_failure;
}
- if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage,
- expires, error) < 0)
+ if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0)
goto nla_put_failure;
return nlmsg_end(skb, nlh);
projects / karo-tx-linux.git / blobdiff