static int ip_rt_min_advmss __read_mostly = 256;
static int rt_chain_length_max __read_mostly = 20;
-static struct delayed_work expires_work;
-static unsigned long expires_ljiffies;
-
/*
* Interface to generic destination cache.
*/
{
}
+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;
+
+ if (!rt->peer)
+ rt_bind_peer(rt, 1);
+
+ peer = rt->peer;
+ 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;
+}
+
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.check = ipv4_dst_check,
.default_advmss = ipv4_default_advmss,
.default_mtu = ipv4_default_mtu,
+ .cow_metrics = ipv4_cow_metrics,
.destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
.negative_advice = ipv4_negative_advice,
dst_metric(&r->dst, RTAX_WINDOW),
(int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
dst_metric(&r->dst, RTAX_RTTVAR)),
- r->fl.fl4_tos,
+ r->rt_tos,
r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1,
r->dst.hh ? (r->dst.hh->hh_output ==
dev_queue_xmit) : 0,
.release = seq_release,
};
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
static int rt_acct_proc_show(struct seq_file *m, void *v)
{
struct ip_rt_acct *dst, *src;
if (!pde)
goto err2;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
if (!pde)
goto err3;
#endif
return 0;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
err3:
remove_proc_entry("rt_cache", net->proc_net_stat);
#endif
{
remove_proc_entry("rt_cache", net->proc_net_stat);
remove_proc_entry("rt_cache", net->proc_net);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
remove_proc_entry("rt_acct", net->proc_net);
#endif
}
static inline int rt_valuable(struct rtable *rth)
{
return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
- rth->dst.expires;
+ (rth->peer && rth->peer->pmtu_expires);
}
static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
if (atomic_read(&rth->dst.__refcnt))
goto out;
- ret = 1;
- if (rth->dst.expires &&
- time_after_eq(jiffies, rth->dst.expires))
- goto out;
-
age = jiffies - rth->dst.lastuse;
- ret = 0;
if ((age <= tmo1 && !rt_fast_clean(rth)) ||
(age <= tmo2 && rt_valuable(rth)))
goto out;
net->ipv4.sysctl_rt_cache_rebuild_count;
}
-static inline bool compare_hash_inputs(const struct flowi *fl1,
- const struct flowi *fl2)
+static inline bool compare_hash_inputs(const struct rtable *rt1,
+ const struct rtable *rt2)
{
- return ((((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) |
- ((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) |
- (fl1->iif ^ fl2->iif)) == 0);
+ return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
+ ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
+ (rt1->rt_iif ^ rt2->rt_iif)) == 0);
}
-static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
+static inline int compare_keys(struct rtable *rt1, struct rtable *rt2)
{
- return (((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) |
- ((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) |
- (fl1->mark ^ fl2->mark) |
- (*(u16 *)&fl1->fl4_tos ^ *(u16 *)&fl2->fl4_tos) |
- (fl1->oif ^ fl2->oif) |
- (fl1->iif ^ fl2->iif)) == 0;
+ return (((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
+ ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
+ (rt1->rt_mark ^ rt2->rt_mark) |
+ (rt1->rt_tos ^ rt2->rt_tos) |
+ (rt1->rt_oif ^ rt2->rt_oif) |
+ (rt1->rt_iif ^ rt2->rt_iif)) == 0;
}
static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
const struct rtable *aux = head;
while (aux != rth) {
- if (compare_hash_inputs(&aux->fl, &rth->fl))
+ if (compare_hash_inputs(aux, rth))
return 0;
aux = rcu_dereference_protected(aux->dst.rt_next, 1);
}
return ONE;
}
-static void rt_check_expire(void)
-{
- static unsigned int rover;
- unsigned int i = rover, goal;
- struct rtable *rth;
- struct rtable __rcu **rthp;
- unsigned long samples = 0;
- unsigned long sum = 0, sum2 = 0;
- unsigned long delta;
- u64 mult;
-
- delta = jiffies - expires_ljiffies;
- expires_ljiffies = jiffies;
- mult = ((u64)delta) << rt_hash_log;
- if (ip_rt_gc_timeout > 1)
- do_div(mult, ip_rt_gc_timeout);
- goal = (unsigned int)mult;
- if (goal > rt_hash_mask)
- goal = rt_hash_mask + 1;
- for (; goal > 0; goal--) {
- unsigned long tmo = ip_rt_gc_timeout;
- unsigned long length;
-
- i = (i + 1) & rt_hash_mask;
- rthp = &rt_hash_table[i].chain;
-
- if (need_resched())
- cond_resched();
-
- samples++;
-
- if (rcu_dereference_raw(*rthp) == NULL)
- continue;
- length = 0;
- spin_lock_bh(rt_hash_lock_addr(i));
- 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)) {
- *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);
- }
- spin_unlock_bh(rt_hash_lock_addr(i));
- sum += length;
- sum2 += length*length;
- }
- if (samples) {
- unsigned long avg = sum / samples;
- unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
- rt_chain_length_max = max_t(unsigned long,
- ip_rt_gc_elasticity,
- (avg + 4*sd) >> FRACT_BITS);
- }
- rover = i;
-}
-
-/*
- * rt_worker_func() is run in process context.
- * we call rt_check_expire() to scan part of the hash table
- */
-static void rt_worker_func(struct work_struct *work)
-{
- rt_check_expire();
- schedule_delayed_work(&expires_work, ip_rt_gc_interval);
-}
-
/*
* Pertubation of rt_genid by a small quantity [1..256]
* Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
return length >> FRACT_BITS;
}
-static int rt_intern_hash(unsigned hash, struct rtable *rt,
- struct rtable **rp, struct sk_buff *skb, int ifindex)
+static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt,
+ struct sk_buff *skb, int ifindex)
{
struct rtable *rth, *cand;
struct rtable __rcu **rthp, **candp;
printk(KERN_WARNING
"Neighbour table failure & not caching routes.\n");
ip_rt_put(rt);
- return err;
+ return ERR_PTR(err);
}
}
rt_free(rth);
continue;
}
- if (compare_keys(&rth->fl, &rt->fl) && compare_netns(rth, rt)) {
+ if (compare_keys(rth, rt) && compare_netns(rth, rt)) {
/* Put it first */
*rthp = rth->dst.rt_next;
/*
spin_unlock_bh(rt_hash_lock_addr(hash));
rt_drop(rt);
- if (rp)
- *rp = rth;
- else
+ if (skb)
skb_dst_set(skb, &rth->dst);
- return 0;
+ return rth;
}
if (!atomic_read(&rth->dst.__refcnt)) {
rt_emergency_hash_rebuild(net);
spin_unlock_bh(rt_hash_lock_addr(hash));
- hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
+ hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
ifindex, rt_genid(net));
goto restart;
}
if (err != -ENOBUFS) {
rt_drop(rt);
- return err;
+ return ERR_PTR(err);
}
/* Neighbour tables are full and nothing
if (net_ratelimit())
printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
rt_drop(rt);
- return -ENOBUFS;
+ return ERR_PTR(-ENOBUFS);
}
}
spin_unlock_bh(rt_hash_lock_addr(hash));
skip_hashing:
- if (rp)
- *rp = rt;
- else
+ if (skb)
skb_dst_set(skb, &rt->dst);
- return 0;
+ 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, int create)
if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL)
inet_putpeer(peer);
+ else
+ rt->rt_peer_genid = rt_peer_genid();
}
/*
void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
__be32 saddr, struct net_device *dev)
{
- int i, k;
struct in_device *in_dev = __in_dev_get_rcu(dev);
- struct rtable *rth;
- struct rtable __rcu **rthp;
- __be32 skeys[2] = { saddr, 0 };
- int ikeys[2] = { dev->ifindex, 0 };
- struct netevent_redirect netevent;
+ struct inet_peer *peer;
struct net *net;
if (!in_dev)
ipv4_is_zeronet(new_gw))
goto reject_redirect;
- if (!rt_caching(net))
- goto reject_redirect;
-
if (!IN_DEV_SHARED_MEDIA(in_dev)) {
if (!inet_addr_onlink(in_dev, new_gw, old_gw))
goto reject_redirect;
goto reject_redirect;
}
- for (i = 0; i < 2; i++) {
- for (k = 0; k < 2; k++) {
- unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],
- rt_genid(net));
-
- rthp = &rt_hash_table[hash].chain;
-
- while ((rth = rcu_dereference(*rthp)) != NULL) {
- struct rtable *rt;
-
- if (rth->fl.fl4_dst != daddr ||
- rth->fl.fl4_src != skeys[i] ||
- rth->fl.oif != ikeys[k] ||
- rt_is_input_route(rth) ||
- rt_is_expired(rth) ||
- !net_eq(dev_net(rth->dst.dev), net)) {
- rthp = &rth->dst.rt_next;
- continue;
- }
-
- if (rth->rt_dst != daddr ||
- rth->rt_src != saddr ||
- rth->dst.error ||
- rth->rt_gateway != old_gw ||
- rth->dst.dev != dev)
- break;
-
- dst_hold(&rth->dst);
-
- rt = dst_alloc(&ipv4_dst_ops);
- if (rt == NULL) {
- ip_rt_put(rth);
- return;
- }
-
- /* Copy all the information. */
- *rt = *rth;
- rt->dst.__use = 1;
- atomic_set(&rt->dst.__refcnt, 1);
- rt->dst.child = NULL;
- if (rt->dst.dev)
- dev_hold(rt->dst.dev);
- rt->dst.obsolete = -1;
- rt->dst.lastuse = jiffies;
- rt->dst.path = &rt->dst;
- rt->dst.neighbour = NULL;
- rt->dst.hh = NULL;
-#ifdef CONFIG_XFRM
- rt->dst.xfrm = NULL;
-#endif
- rt->rt_genid = rt_genid(net);
- rt->rt_flags |= RTCF_REDIRECTED;
-
- /* Gateway is different ... */
- rt->rt_gateway = new_gw;
-
- /* Redirect received -> path was valid */
- dst_confirm(&rth->dst);
-
- if (rt->peer)
- atomic_inc(&rt->peer->refcnt);
-
- if (arp_bind_neighbour(&rt->dst) ||
- !(rt->dst.neighbour->nud_state &
- NUD_VALID)) {
- if (rt->dst.neighbour)
- neigh_event_send(rt->dst.neighbour, NULL);
- ip_rt_put(rth);
- rt_drop(rt);
- goto do_next;
- }
+ peer = inet_getpeer_v4(daddr, 1);
+ if (peer) {
+ peer->redirect_learned.a4 = new_gw;
- netevent.old = &rth->dst;
- netevent.new = &rt->dst;
- call_netevent_notifiers(NETEVENT_REDIRECT,
- &netevent);
+ inet_putpeer(peer);
- rt_del(hash, rth);
- if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif))
- ip_rt_put(rt);
- goto do_next;
- }
- do_next:
- ;
- }
+ atomic_inc(&__rt_peer_genid);
}
return;
if (dst->obsolete > 0) {
ip_rt_put(rt);
ret = NULL;
- } else if ((rt->rt_flags & RTCF_REDIRECTED) ||
- (rt->dst.expires &&
- time_after_eq(jiffies, rt->dst.expires))) {
- unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
- rt->fl.oif,
+ } else if (rt->rt_flags & RTCF_REDIRECTED) {
+ unsigned hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
+ rt->rt_oif,
rt_genid(dev_net(dst->dev)));
#if RT_CACHE_DEBUG >= 1
printk(KERN_DEBUG "ipv4_negative_advice: redirect to %pI4/%02x dropped\n",
- &rt->rt_dst, rt->fl.fl4_tos);
+ &rt->rt_dst, rt->rt_tos);
#endif
rt_del(hash, rt);
ret = NULL;
+ } else if (rt->peer &&
+ rt->peer->pmtu_expires &&
+ time_after_eq(jiffies, rt->peer->pmtu_expires)) {
+ unsigned long orig = rt->peer->pmtu_expires;
+
+ if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig)
+ dst_metric_set(dst, RTAX_MTU,
+ rt->peer->pmtu_orig);
}
}
return ret;
{
struct rtable *rt = skb_rtable(skb);
struct in_device *in_dev;
+ struct inet_peer *peer;
int log_martians;
rcu_read_lock();
log_martians = IN_DEV_LOG_MARTIANS(in_dev);
rcu_read_unlock();
+ if (!rt->peer)
+ rt_bind_peer(rt, 1);
+ peer = rt->peer;
+ if (!peer) {
+ icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+ return;
+ }
+
/* No redirected packets during ip_rt_redirect_silence;
* reset the algorithm.
*/
- if (time_after(jiffies, rt->dst.rate_last + ip_rt_redirect_silence))
- rt->dst.rate_tokens = 0;
+ if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+ peer->rate_tokens = 0;
/* Too many ignored redirects; do not send anything
* set dst.rate_last to the last seen redirected packet.
*/
- if (rt->dst.rate_tokens >= ip_rt_redirect_number) {
- rt->dst.rate_last = jiffies;
+ if (peer->rate_tokens >= ip_rt_redirect_number) {
+ peer->rate_last = jiffies;
return;
}
/* Check for load limit; set rate_last to the latest sent
* redirect.
*/
- if (rt->dst.rate_tokens == 0 ||
+ if (peer->rate_tokens == 0 ||
time_after(jiffies,
- (rt->dst.rate_last +
- (ip_rt_redirect_load << rt->dst.rate_tokens)))) {
+ (peer->rate_last +
+ (ip_rt_redirect_load << peer->rate_tokens)))) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
- rt->dst.rate_last = jiffies;
- ++rt->dst.rate_tokens;
+ peer->rate_last = jiffies;
+ ++peer->rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (log_martians &&
- rt->dst.rate_tokens == ip_rt_redirect_number &&
+ peer->rate_tokens == ip_rt_redirect_number &&
net_ratelimit())
printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n",
&rt->rt_src, rt->rt_iif,
static int ip_error(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
+ struct inet_peer *peer;
unsigned long now;
+ bool send;
int code;
switch (rt->dst.error) {
break;
}
- now = jiffies;
- rt->dst.rate_tokens += now - rt->dst.rate_last;
- if (rt->dst.rate_tokens > ip_rt_error_burst)
- rt->dst.rate_tokens = ip_rt_error_burst;
- rt->dst.rate_last = now;
- if (rt->dst.rate_tokens >= ip_rt_error_cost) {
- rt->dst.rate_tokens -= ip_rt_error_cost;
- icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
+ if (!rt->peer)
+ rt_bind_peer(rt, 1);
+ peer = rt->peer;
+
+ send = true;
+ if (peer) {
+ now = jiffies;
+ peer->rate_tokens += now - peer->rate_last;
+ if (peer->rate_tokens > ip_rt_error_burst)
+ peer->rate_tokens = ip_rt_error_burst;
+ peer->rate_last = now;
+ if (peer->rate_tokens >= ip_rt_error_cost)
+ peer->rate_tokens -= ip_rt_error_cost;
+ else
+ send = false;
}
+ if (send)
+ icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
out: kfree_skb(skb);
return 0;
unsigned short new_mtu,
struct net_device *dev)
{
- int i, k;
unsigned short old_mtu = ntohs(iph->tot_len);
- struct rtable *rth;
- int ikeys[2] = { dev->ifindex, 0 };
- __be32 skeys[2] = { iph->saddr, 0, };
- __be32 daddr = iph->daddr;
unsigned short est_mtu = 0;
+ struct inet_peer *peer;
- for (k = 0; k < 2; k++) {
- for (i = 0; i < 2; i++) {
- unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],
- rt_genid(net));
-
- rcu_read_lock();
- for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->dst.rt_next)) {
- unsigned short mtu = new_mtu;
-
- if (rth->fl.fl4_dst != daddr ||
- rth->fl.fl4_src != skeys[i] ||
- rth->rt_dst != daddr ||
- rth->rt_src != iph->saddr ||
- rth->fl.oif != ikeys[k] ||
- rt_is_input_route(rth) ||
- dst_metric_locked(&rth->dst, RTAX_MTU) ||
- !net_eq(dev_net(rth->dst.dev), net) ||
- rt_is_expired(rth))
- continue;
-
- if (new_mtu < 68 || new_mtu >= old_mtu) {
+ peer = inet_getpeer_v4(iph->daddr, 1);
+ if (peer) {
+ unsigned short mtu = new_mtu;
- /* BSD 4.2 compatibility hack :-( */
- if (mtu == 0 &&
- old_mtu >= dst_mtu(&rth->dst) &&
- old_mtu >= 68 + (iph->ihl << 2))
- old_mtu -= iph->ihl << 2;
+ if (new_mtu < 68 || new_mtu >= old_mtu) {
+ /* BSD 4.2 derived systems incorrectly adjust
+ * tot_len by the IP header length, and report
+ * a zero MTU in the ICMP message.
+ */
+ if (mtu == 0 &&
+ old_mtu >= 68 + (iph->ihl << 2))
+ old_mtu -= iph->ihl << 2;
+ mtu = guess_mtu(old_mtu);
+ }
- mtu = guess_mtu(old_mtu);
- }
- if (mtu <= dst_mtu(&rth->dst)) {
- if (mtu < dst_mtu(&rth->dst)) {
- dst_confirm(&rth->dst);
- if (mtu < ip_rt_min_pmtu) {
- u32 lock = dst_metric(&rth->dst,
- RTAX_LOCK);
- mtu = ip_rt_min_pmtu;
- lock |= (1 << RTAX_MTU);
- dst_metric_set(&rth->dst, RTAX_LOCK,
- lock);
- }
- dst_metric_set(&rth->dst, RTAX_MTU, mtu);
- dst_set_expires(&rth->dst,
- ip_rt_mtu_expires);
- }
- est_mtu = mtu;
- }
- }
- rcu_read_unlock();
+ if (mtu < ip_rt_min_pmtu)
+ mtu = ip_rt_min_pmtu;
+ if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
+ est_mtu = mtu;
+ peer->pmtu_learned = mtu;
+ peer->pmtu_expires = jiffies + ip_rt_mtu_expires;
}
+
+ inet_putpeer(peer);
+
+ atomic_inc(&__rt_peer_genid);
}
return est_mtu ? : new_mtu;
}
+static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer)
+{
+ unsigned long expires = peer->pmtu_expires;
+
+ if (time_before(expires, jiffies)) {
+ 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)
{
- if (dst_mtu(dst) > mtu && mtu >= 68 &&
- !(dst_metric_locked(dst, RTAX_MTU))) {
- if (mtu < ip_rt_min_pmtu) {
- u32 lock = dst_metric(dst, RTAX_LOCK);
+ struct rtable *rt = (struct rtable *) dst;
+ struct inet_peer *peer;
+
+ dst_confirm(dst);
+
+ if (!rt->peer)
+ rt_bind_peer(rt, 1);
+ peer = rt->peer;
+ if (peer) {
+ if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
- dst_metric_set(dst, RTAX_LOCK, lock | (1 << RTAX_MTU));
+ if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
+ peer->pmtu_learned = mtu;
+ peer->pmtu_expires = jiffies + ip_rt_mtu_expires;
+
+ atomic_inc(&__rt_peer_genid);
+ rt->rt_peer_genid = rt_peer_genid();
+
+ check_peer_pmtu(dst, peer);
}
- dst_metric_set(dst, RTAX_MTU, mtu);
- dst_set_expires(dst, ip_rt_mtu_expires);
- call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
+ inet_putpeer(peer);
+ }
+}
+
+static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+{
+ struct rtable *rt = (struct rtable *) dst;
+ __be32 orig_gw = rt->rt_gateway;
+
+ dst_confirm(&rt->dst);
+
+ neigh_release(rt->dst.neighbour);
+ rt->dst.neighbour = NULL;
+
+ rt->rt_gateway = peer->redirect_learned.a4;
+ if (arp_bind_neighbour(&rt->dst) ||
+ !(rt->dst.neighbour->nud_state & NUD_VALID)) {
+ if (rt->dst.neighbour)
+ neigh_event_send(rt->dst.neighbour, NULL);
+ rt->rt_gateway = orig_gw;
+ return -EAGAIN;
+ } else {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ call_netevent_notifiers(NETEVENT_NEIGH_UPDATE,
+ rt->dst.neighbour);
}
+ return 0;
}
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
{
- if (rt_is_expired((struct rtable *)dst))
+ struct rtable *rt = (struct rtable *) dst;
+
+ if (rt_is_expired(rt))
return NULL;
+ if (rt->rt_peer_genid != rt_peer_genid()) {
+ struct inet_peer *peer;
+
+ if (!rt->peer)
+ rt_bind_peer(rt, 0);
+
+ peer = rt->peer;
+ if (peer && peer->pmtu_expires)
+ check_peer_pmtu(dst, peer);
+
+ if (peer && peer->redirect_learned.a4 &&
+ peer->redirect_learned.a4 != rt->rt_gateway) {
+ if (check_peer_redir(dst, peer))
+ return NULL;
+ }
+
+ rt->rt_peer_genid = rt_peer_genid();
+ }
return dst;
}
struct rtable *rt = (struct rtable *) dst;
struct inet_peer *peer = rt->peer;
+ if (rt->fi) {
+ fib_info_put(rt->fi);
+ rt->fi = NULL;
+ }
if (peer) {
rt->peer = NULL;
inet_putpeer(peer);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
rt = skb_rtable(skb);
- if (rt)
- dst_set_expires(&rt->dst, 0);
+ if (rt &&
+ rt->peer &&
+ rt->peer->pmtu_expires) {
+ unsigned long orig = rt->peer->pmtu_expires;
+
+ if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig)
+ dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig);
+ }
}
static int ip_rt_bug(struct sk_buff *skb)
if (rt_is_output_route(rt))
src = rt->rt_src;
else {
+ struct flowi fl = {
+ .fl4_dst = rt->rt_key_dst,
+ .fl4_src = rt->rt_key_src,
+ .fl4_tos = rt->rt_tos,
+ .oif = rt->rt_oif,
+ .iif = rt->rt_iif,
+ .mark = rt->rt_mark,
+ };
+
rcu_read_lock();
- if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0)
+ if (fib_lookup(dev_net(rt->dst.dev), &fl, &res) == 0)
src = FIB_RES_PREFSRC(res);
else
src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
memcpy(addr, &src, 4);
}
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
static void set_class_tag(struct rtable *rt, u32 tag)
{
if (!(rt->dst.tclassid & 0xFFFF))
return mtu;
}
-static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
+static void rt_init_metrics(struct rtable *rt, const struct flowi *oldflp,
+ struct fib_info *fi)
+{
+ 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 (oldflp && (oldflp->flags & FLOWI_FLAG_PRECOW_METRICS))
+ create = 1;
+
+ rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create);
+ if (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);
+
+ if (peer->pmtu_expires)
+ 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);
+ }
+}
+
+static void rt_set_nexthop(struct rtable *rt, const struct flowi *oldflp,
+ const struct fib_result *res,
+ struct fib_info *fi, u16 type, u32 itag)
{
struct dst_entry *dst = &rt->dst;
- struct fib_info *fi = res->fi;
if (fi) {
if (FIB_RES_GW(*res) &&
FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = FIB_RES_GW(*res);
- dst_import_metrics(dst, fi->fib_metrics);
-#ifdef CONFIG_NET_CLS_ROUTE
+ rt_init_metrics(rt, oldflp, fi);
+#ifdef CONFIG_IP_ROUTE_CLASSID
dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
#endif
}
if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40)
dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
#ifdef CONFIG_IP_MULTIPLE_TABLES
set_class_tag(rt, fib_rules_tclass(res));
#endif
set_class_tag(rt, itag);
#endif
- rt->rt_type = res->type;
+ rt->rt_type = type;
+}
+
+static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm)
+{
+ struct rtable *rt = dst_alloc(&ipv4_dst_ops, 1);
+ if (rt) {
+ rt->dst.obsolete = -1;
+
+ rt->dst.flags = DST_HOST |
+ (nopolicy ? DST_NOPOLICY : 0) |
+ (noxfrm ? DST_NOXFRM : 0);
+ }
+ return rt;
}
/* called in rcu_read_lock() section */
if (err < 0)
goto e_err;
}
- rth = dst_alloc(&ipv4_dst_ops);
+ rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
rth->dst.output = ip_rt_bug;
- rth->dst.obsolete = -1;
- atomic_set(&rth->dst.__refcnt, 1);
- rth->dst.flags= DST_HOST;
- if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->dst.flags |= DST_NOPOLICY;
- rth->fl.fl4_dst = daddr;
+ rth->rt_key_dst = daddr;
rth->rt_dst = daddr;
- rth->fl.fl4_tos = tos;
- rth->fl.mark = skb->mark;
- rth->fl.fl4_src = saddr;
+ rth->rt_tos = tos;
+ rth->rt_mark = skb->mark;
+ rth->rt_key_src = saddr;
rth->rt_src = saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
rth->dst.tclassid = itag;
#endif
- rth->rt_iif =
- rth->fl.iif = dev->ifindex;
+ rth->rt_iif = dev->ifindex;
rth->dst.dev = init_net.loopback_dev;
dev_hold(rth->dst.dev);
- rth->fl.oif = 0;
+ rth->rt_oif = 0;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->rt_genid = rt_genid(dev_net(dev));
RT_CACHE_STAT_INC(in_slow_mc);
hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
- return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex);
+ rth = rt_intern_hash(hash, rth, skb, dev->ifindex);
+ err = 0;
+ if (IS_ERR(rth))
+ err = PTR_ERR(rth);
e_nobufs:
return -ENOBUFS;
/* called in rcu_read_lock() section */
static int __mkroute_input(struct sk_buff *skb,
- struct fib_result *res,
+ const struct fib_result *res,
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos,
struct rtable **result)
}
}
-
- rth = dst_alloc(&ipv4_dst_ops);
+ rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+ IN_DEV_CONF_GET(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
goto cleanup;
}
- atomic_set(&rth->dst.__refcnt, 1);
- rth->dst.flags= DST_HOST;
- if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->dst.flags |= DST_NOPOLICY;
- if (IN_DEV_CONF_GET(out_dev, NOXFRM))
- rth->dst.flags |= DST_NOXFRM;
- rth->fl.fl4_dst = daddr;
+ rth->rt_key_dst = daddr;
rth->rt_dst = daddr;
- rth->fl.fl4_tos = tos;
- rth->fl.mark = skb->mark;
- rth->fl.fl4_src = saddr;
+ rth->rt_tos = tos;
+ rth->rt_mark = skb->mark;
+ rth->rt_key_src = saddr;
rth->rt_src = saddr;
rth->rt_gateway = daddr;
- rth->rt_iif =
- rth->fl.iif = in_dev->dev->ifindex;
+ rth->rt_iif = in_dev->dev->ifindex;
rth->dst.dev = (out_dev)->dev;
dev_hold(rth->dst.dev);
- rth->fl.oif = 0;
+ rth->rt_oif = 0;
rth->rt_spec_dst= spec_dst;
- rth->dst.obsolete = -1;
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
- rt_set_nexthop(rth, res, itag);
+ rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag);
rth->rt_flags = flags;
/* put it into the cache */
hash = rt_hash(daddr, saddr, fl->iif,
rt_genid(dev_net(rth->dst.dev)));
- return rt_intern_hash(hash, rth, NULL, skb, fl->iif);
+ rth = rt_intern_hash(hash, rth, skb, fl->iif);
+ if (IS_ERR(rth))
+ return PTR_ERR(rth);
+ return 0;
}
/*
RT_CACHE_STAT_INC(in_brd);
local_input:
- rth = dst_alloc(&ipv4_dst_ops);
+ rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
rth->dst.output= ip_rt_bug;
- rth->dst.obsolete = -1;
rth->rt_genid = rt_genid(net);
- atomic_set(&rth->dst.__refcnt, 1);
- rth->dst.flags= DST_HOST;
- if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->dst.flags |= DST_NOPOLICY;
- rth->fl.fl4_dst = daddr;
+ rth->rt_key_dst = daddr;
rth->rt_dst = daddr;
- rth->fl.fl4_tos = tos;
- rth->fl.mark = skb->mark;
- rth->fl.fl4_src = saddr;
+ rth->rt_tos = tos;
+ rth->rt_mark = skb->mark;
+ rth->rt_key_src = saddr;
rth->rt_src = saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
rth->dst.tclassid = itag;
#endif
- rth->rt_iif =
- rth->fl.iif = dev->ifindex;
+ rth->rt_iif = dev->ifindex;
rth->dst.dev = net->loopback_dev;
dev_hold(rth->dst.dev);
rth->rt_gateway = daddr;
}
rth->rt_type = res.type;
hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
- err = rt_intern_hash(hash, rth, NULL, skb, fl.iif);
+ rth = rt_intern_hash(hash, rth, skb, fl.iif);
+ err = 0;
+ if (IS_ERR(rth))
+ err = PTR_ERR(rth);
goto out;
no_route:
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
rth = rcu_dereference(rth->dst.rt_next)) {
- if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) |
- ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) |
- (rth->fl.iif ^ iif) |
- rth->fl.oif |
- (rth->fl.fl4_tos ^ tos)) == 0 &&
- rth->fl.mark == skb->mark &&
+ if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) |
+ ((__force u32)rth->rt_key_src ^ (__force u32)saddr) |
+ (rth->rt_iif ^ iif) |
+ rth->rt_oif |
+ (rth->rt_tos ^ tos)) == 0 &&
+ rth->rt_mark == skb->mark &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
if (noref) {
EXPORT_SYMBOL(ip_route_input_common);
/* called with rcu_read_lock() */
-static int __mkroute_output(struct rtable **result,
- struct fib_result *res,
- const struct flowi *fl,
- const struct flowi *oldflp,
- struct net_device *dev_out,
- unsigned flags)
+static struct rtable *__mkroute_output(const struct fib_result *res,
+ const struct flowi *fl,
+ const struct flowi *oldflp,
+ struct net_device *dev_out,
+ unsigned int flags)
{
- struct rtable *rth;
- struct in_device *in_dev;
+ struct fib_info *fi = res->fi;
u32 tos = RT_FL_TOS(oldflp);
+ struct in_device *in_dev;
+ u16 type = res->type;
+ struct rtable *rth;
if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags & IFF_LOOPBACK))
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
if (ipv4_is_lbcast(fl->fl4_dst))
- res->type = RTN_BROADCAST;
+ type = RTN_BROADCAST;
else if (ipv4_is_multicast(fl->fl4_dst))
- res->type = RTN_MULTICAST;
+ type = RTN_MULTICAST;
else if (ipv4_is_zeronet(fl->fl4_dst))
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
in_dev = __in_dev_get_rcu(dev_out);
if (!in_dev)
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
- if (res->type == RTN_BROADCAST) {
+ if (type == RTN_BROADCAST) {
flags |= RTCF_BROADCAST | RTCF_LOCAL;
- res->fi = NULL;
- } else if (res->type == RTN_MULTICAST) {
+ fi = NULL;
+ } else if (type == RTN_MULTICAST) {
flags |= RTCF_MULTICAST | RTCF_LOCAL;
if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src,
oldflp->proto))
* default one, but do not gateway in this case.
* Yes, it is hack.
*/
- if (res->fi && res->prefixlen < 4)
- res->fi = NULL;
+ if (fi && res->prefixlen < 4)
+ fi = NULL;
}
-
- rth = dst_alloc(&ipv4_dst_ops);
+ rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+ IN_DEV_CONF_GET(in_dev, NOXFRM));
if (!rth)
- return -ENOBUFS;
-
- atomic_set(&rth->dst.__refcnt, 1);
- rth->dst.flags= DST_HOST;
- if (IN_DEV_CONF_GET(in_dev, NOXFRM))
- rth->dst.flags |= DST_NOXFRM;
- if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->dst.flags |= DST_NOPOLICY;
-
- rth->fl.fl4_dst = oldflp->fl4_dst;
- rth->fl.fl4_tos = tos;
- rth->fl.fl4_src = oldflp->fl4_src;
- rth->fl.oif = oldflp->oif;
- rth->fl.mark = oldflp->mark;
+ return ERR_PTR(-ENOBUFS);
+
+ rth->rt_key_dst = oldflp->fl4_dst;
+ rth->rt_tos = tos;
+ rth->rt_key_src = oldflp->fl4_src;
+ rth->rt_oif = oldflp->oif;
+ rth->rt_mark = oldflp->mark;
rth->rt_dst = fl->fl4_dst;
rth->rt_src = fl->fl4_src;
- rth->rt_iif = oldflp->oif ? : dev_out->ifindex;
+ rth->rt_iif = 0;
/* get references to the devices that are to be hold by the routing
cache entry */
rth->dst.dev = dev_out;
rth->rt_spec_dst= fl->fl4_src;
rth->dst.output=ip_output;
- rth->dst.obsolete = -1;
rth->rt_genid = rt_genid(dev_net(dev_out));
RT_CACHE_STAT_INC(out_slow_tot);
RT_CACHE_STAT_INC(out_slow_mc);
}
#ifdef CONFIG_IP_MROUTE
- if (res->type == RTN_MULTICAST) {
+ if (type == RTN_MULTICAST) {
if (IN_DEV_MFORWARD(in_dev) &&
!ipv4_is_local_multicast(oldflp->fl4_dst)) {
rth->dst.input = ip_mr_input;
#endif
}
- rt_set_nexthop(rth, res, 0);
+ rt_set_nexthop(rth, oldflp, res, fi, type, 0);
rth->rt_flags = flags;
- *result = rth;
- return 0;
-}
-
-/* called with rcu_read_lock() */
-static int ip_mkroute_output(struct rtable **rp,
- struct fib_result *res,
- const struct flowi *fl,
- const struct flowi *oldflp,
- struct net_device *dev_out,
- unsigned flags)
-{
- struct rtable *rth = NULL;
- int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags);
- unsigned hash;
- if (err == 0) {
- hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
- rt_genid(dev_net(dev_out)));
- err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif);
- }
-
- return err;
+ return rth;
}
/*
* called with rcu_read_lock();
*/
-static int ip_route_output_slow(struct net *net, struct rtable **rp,
- const struct flowi *oldflp)
+static struct rtable *ip_route_output_slow(struct net *net,
+ const struct flowi *oldflp)
{
u32 tos = RT_FL_TOS(oldflp);
- struct flowi fl = { .fl4_dst = oldflp->fl4_dst,
- .fl4_src = oldflp->fl4_src,
- .fl4_tos = tos & IPTOS_RT_MASK,
- .fl4_scope = ((tos & RTO_ONLINK) ?
- RT_SCOPE_LINK : RT_SCOPE_UNIVERSE),
- .mark = oldflp->mark,
- .iif = net->loopback_dev->ifindex,
- .oif = oldflp->oif };
+ struct flowi fl;
struct fib_result res;
unsigned int flags = 0;
struct net_device *dev_out = NULL;
- int err;
-
+ struct rtable *rth;
res.fi = NULL;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
+ fl.oif = oldflp->oif;
+ fl.iif = net->loopback_dev->ifindex;
+ fl.mark = oldflp->mark;
+ fl.fl4_dst = oldflp->fl4_dst;
+ fl.fl4_src = oldflp->fl4_src;
+ fl.fl4_tos = tos & IPTOS_RT_MASK;
+ fl.fl4_scope = ((tos & RTO_ONLINK) ?
+ RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+
+ rcu_read_lock();
if (oldflp->fl4_src) {
- err = -EINVAL;
+ rth = ERR_PTR(-EINVAL);
if (ipv4_is_multicast(oldflp->fl4_src) ||
ipv4_is_lbcast(oldflp->fl4_src) ||
ipv4_is_zeronet(oldflp->fl4_src))
if (oldflp->oif) {
dev_out = dev_get_by_index_rcu(net, oldflp->oif);
- err = -ENODEV;
+ rth = ERR_PTR(-ENODEV);
if (dev_out == NULL)
goto out;
/* RACE: Check return value of inet_select_addr instead. */
if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) {
- err = -ENETUNREACH;
+ rth = ERR_PTR(-ENETUNREACH);
goto out;
}
if (ipv4_is_local_multicast(oldflp->fl4_dst) ||
res.type = RTN_UNICAST;
goto make_route;
}
- err = -ENETUNREACH;
+ rth = ERR_PTR(-ENETUNREACH);
goto out;
}
else
#endif
if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif)
- fib_select_default(net, &fl, &res);
+ fib_select_default(&res);
if (!fl.fl4_src)
fl.fl4_src = FIB_RES_PREFSRC(res);
make_route:
- err = ip_mkroute_output(rp, &res, &fl, oldflp, dev_out, flags);
+ rth = __mkroute_output(&res, &fl, oldflp, dev_out, flags);
+ if (!IS_ERR(rth)) {
+ unsigned int hash;
-out: return err;
+ hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
+ rt_genid(dev_net(dev_out)));
+ rth = rt_intern_hash(hash, rth, NULL, oldflp->oif);
+ }
+
+out:
+ rcu_read_unlock();
+ return rth;
}
-int __ip_route_output_key(struct net *net, struct rtable **rp,
- const struct flowi *flp)
+struct rtable *__ip_route_output_key(struct net *net, const struct flowi *flp)
{
- unsigned int hash;
- int res;
struct rtable *rth;
+ unsigned int hash;
if (!rt_caching(net))
goto slow_output;
rcu_read_lock_bh();
for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
rth = rcu_dereference_bh(rth->dst.rt_next)) {
- if (rth->fl.fl4_dst == flp->fl4_dst &&
- rth->fl.fl4_src == flp->fl4_src &&
+ if (rth->rt_key_dst == flp->fl4_dst &&
+ rth->rt_key_src == flp->fl4_src &&
rt_is_output_route(rth) &&
- rth->fl.oif == flp->oif &&
- rth->fl.mark == flp->mark &&
- !((rth->fl.fl4_tos ^ flp->fl4_tos) &
+ rth->rt_oif == flp->oif &&
+ rth->rt_mark == flp->mark &&
+ !((rth->rt_tos ^ flp->fl4_tos) &
(IPTOS_RT_MASK | RTO_ONLINK)) &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
dst_use(&rth->dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
- *rp = rth;
- return 0;
+ return rth;
}
RT_CACHE_STAT_INC(out_hlist_search);
}
rcu_read_unlock_bh();
slow_output:
- rcu_read_lock();
- res = ip_route_output_slow(net, rp, flp);
- rcu_read_unlock();
- return res;
+ return ip_route_output_slow(net, flp);
}
EXPORT_SYMBOL_GPL(__ip_route_output_key);
.destroy = ipv4_dst_destroy,
.check = ipv4_blackhole_dst_check,
.default_mtu = ipv4_blackhole_default_mtu,
+ .default_advmss = ipv4_default_advmss,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
};
-
-static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi *flp)
+struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
- struct rtable *ort = *rp;
- struct rtable *rt = (struct rtable *)
- dst_alloc(&ipv4_dst_blackhole_ops);
+ struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, 1);
+ struct rtable *ort = (struct rtable *) dst_orig;
if (rt) {
struct dst_entry *new = &rt->dst;
- atomic_set(&new->__refcnt, 1);
new->__use = 1;
new->input = dst_discard;
new->output = dst_discard;
if (new->dev)
dev_hold(new->dev);
- rt->fl = ort->fl;
+ rt->rt_key_dst = ort->rt_key_dst;
+ rt->rt_key_src = ort->rt_key_src;
+ rt->rt_tos = ort->rt_tos;
+ rt->rt_iif = ort->rt_iif;
+ rt->rt_oif = ort->rt_oif;
+ rt->rt_mark = ort->rt_mark;
rt->rt_genid = rt_genid(net);
rt->rt_flags = ort->rt_flags;
rt->peer = ort->peer;
if (rt->peer)
atomic_inc(&rt->peer->refcnt);
+ rt->fi = ort->fi;
+ if (rt->fi)
+ atomic_inc(&rt->fi->fib_clntref);
dst_free(new);
}
- dst_release(&(*rp)->dst);
- *rp = rt;
- return rt ? 0 : -ENOMEM;
+ dst_release(dst_orig);
+
+ return rt ? &rt->dst : ERR_PTR(-ENOMEM);
}
-int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
- struct sock *sk, int flags)
+struct rtable *ip_route_output_flow(struct net *net, struct flowi *flp,
+ struct sock *sk)
{
- int err;
+ struct rtable *rt = __ip_route_output_key(net, flp);
- if ((err = __ip_route_output_key(net, rp, flp)) != 0)
- return err;
+ if (IS_ERR(rt))
+ return rt;
if (flp->proto) {
if (!flp->fl4_src)
- flp->fl4_src = (*rp)->rt_src;
+ flp->fl4_src = rt->rt_src;
if (!flp->fl4_dst)
- flp->fl4_dst = (*rp)->rt_dst;
- err = __xfrm_lookup(net, (struct dst_entry **)rp, flp, sk,
- flags ? XFRM_LOOKUP_WAIT : 0);
- if (err == -EREMOTE)
- err = ipv4_dst_blackhole(net, rp, flp);
-
- return err;
+ flp->fl4_dst = rt->rt_dst;
+ rt = (struct rtable *) xfrm_lookup(net, &rt->dst, flp, sk, 0);
}
- return 0;
+ return rt;
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
-int ip_route_output_key(struct net *net, struct rtable **rp, struct flowi *flp)
-{
- return ip_route_output_flow(net, rp, flp, NULL, 0);
-}
-EXPORT_SYMBOL(ip_route_output_key);
-
static int rt_fill_info(struct net *net,
struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
r->rtm_family = AF_INET;
r->rtm_dst_len = 32;
r->rtm_src_len = 0;
- r->rtm_tos = rt->fl.fl4_tos;
+ r->rtm_tos = rt->rt_tos;
r->rtm_table = RT_TABLE_MAIN;
NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN);
r->rtm_type = rt->rt_type;
NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst);
- if (rt->fl.fl4_src) {
+ if (rt->rt_key_src) {
r->rtm_src_len = 32;
- NLA_PUT_BE32(skb, RTA_SRC, rt->fl.fl4_src);
+ NLA_PUT_BE32(skb, RTA_SRC, rt->rt_key_src);
}
if (rt->dst.dev)
NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
if (rt->dst.tclassid)
NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid);
#endif
if (rt_is_input_route(rt))
NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst);
- else if (rt->rt_src != rt->fl.fl4_src)
+ else if (rt->rt_src != rt->rt_key_src)
NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src);
if (rt->rt_dst != rt->rt_gateway)
if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
- if (rt->fl.mark)
- NLA_PUT_BE32(skb, RTA_MARK, rt->fl.mark);
+ if (rt->rt_mark)
+ NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark);
error = rt->dst.error;
- expires = rt->dst.expires ? rt->dst.expires - jiffies : 0;
+ expires = (rt->peer && rt->peer->pmtu_expires) ?
+ rt->peer->pmtu_expires - jiffies : 0;
if (rt->peer) {
inet_peer_refcheck(rt->peer);
id = atomic_read(&rt->peer->ip_id_count) & 0xffff;
}
} else
#endif
- NLA_PUT_U32(skb, RTA_IIF, rt->fl.iif);
+ NLA_PUT_U32(skb, RTA_IIF, rt->rt_iif);
}
if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage,
.oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
.mark = mark,
};
- err = ip_route_output_key(net, &rt, &fl);
+ rt = ip_route_output_key(net, &fl);
+
+ err = 0;
+ if (IS_ERR(rt))
+ err = PTR_ERR(rt);
}
if (err)
};
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
-#endif /* CONFIG_NET_CLS_ROUTE */
+#endif /* CONFIG_IP_ROUTE_CLASSID */
static __initdata unsigned long rhash_entries;
static int __init set_rhash_entries(char *str)
{
int rc = 0;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
if (!ip_rt_acct)
panic("IP: failed to allocate ip_rt_acct\n");
devinet_init();
ip_fib_init();
- /* All the timers, started at system startup tend
- to synchronize. Perturb it a bit.
- */
- INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func);
- expires_ljiffies = jiffies;
- schedule_delayed_work(&expires_work,
- net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
-
if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
projects / mv-sheeva.git / blobdiff