#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
+#include <net/atmclip.h>
+#include <net/secure_seq.h>
#define RT_FL_TOS(oldflp4) \
((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
u32 *p = NULL;
if (!rt->peer)
- rt_bind_peer(rt, 1);
+ rt_bind_peer(rt, rt->rt_dst, 1);
peer = rt->peer;
if (peer) {
return p;
}
+static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr);
+
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.link_failure = ipv4_link_failure,
.update_pmtu = ip_rt_update_pmtu,
.local_out = __ip_local_out,
+ .neigh_lookup = ipv4_neigh_lookup,
};
#define ECN_OR_COST(class) TC_PRIO_##class
"HHUptod\tSpecDst");
else {
struct rtable *r = v;
- int len;
+ struct neighbour *n;
+ int len, HHUptod;
+
+ rcu_read_lock();
+ n = dst_get_neighbour(&r->dst);
+ HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+ rcu_read_unlock();
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",
dst_metric(&r->dst, RTAX_WINDOW),
(int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
dst_metric(&r->dst, RTAX_RTTVAR)),
- 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,
+ r->rt_key_tos,
+ -1,
+ HHUptod,
r->rt_spec_dst, &len);
seq_printf(seq, "%*s\n", 127 - len, "");
{
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);
+ (rt1->rt_route_iif ^ rt2->rt_route_iif)) == 0);
}
static inline int compare_keys(struct rtable *rt1, struct rtable *rt2)
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;
+ (rt1->rt_key_tos ^ rt2->rt_key_tos) |
+ (rt1->rt_route_iif ^ rt2->rt_route_iif) |
+ (rt1->rt_oif ^ rt2->rt_oif)) == 0;
}
static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
break;
expire >>= 1;
-#if RT_CACHE_DEBUG >= 2
- printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire,
- dst_entries_get_fast(&ipv4_dst_ops), goal, i);
-#endif
if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
goto out;
dst_entries_get_fast(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh ||
dst_entries_get_slow(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh)
expire = ip_rt_gc_timeout;
-#if RT_CACHE_DEBUG >= 2
- printk(KERN_DEBUG "expire++ %u %d %d %d\n", expire,
- dst_entries_get_fast(&ipv4_dst_ops), goal, rover);
-#endif
out: return 0;
}
return length >> FRACT_BITS;
}
+static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr)
+{
+ struct neigh_table *tbl = &arp_tbl;
+ static const __be32 inaddr_any = 0;
+ struct net_device *dev = dst->dev;
+ const __be32 *pkey = daddr;
+ struct neighbour *n;
+
+#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
+ if (dev->type == ARPHRD_ATM)
+ tbl = clip_tbl_hook;
+#endif
+ if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+ pkey = &inaddr_any;
+
+ n = __ipv4_neigh_lookup(tbl, dev, *(__force u32 *)pkey);
+ if (n)
+ return n;
+ return neigh_create(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 hash, struct rtable *rt,
struct sk_buff *skb, int ifindex)
{
rt->dst.flags |= DST_NOCACHE;
if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
- int err = arp_bind_neighbour(&rt->dst);
+ int err = rt_bind_neighbour(rt);
if (err) {
if (net_ratelimit())
printk(KERN_WARNING
route or unicast forwarding path.
*/
if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
- int err = arp_bind_neighbour(&rt->dst);
+ int err = rt_bind_neighbour(rt);
if (err) {
spin_unlock_bh(rt_hash_lock_addr(hash));
rt->dst.rt_next = rt_hash_table[hash].chain;
-#if RT_CACHE_DEBUG >= 2
- if (rt->dst.rt_next) {
- struct rtable *trt;
- printk(KERN_DEBUG "rt_cache @%02x: %pI4",
- hash, &rt->rt_dst);
- for (trt = rt->dst.rt_next; trt; trt = trt->dst.rt_next)
- printk(" . %pI4", &trt->rt_dst);
- printk("\n");
- }
-#endif
/*
* Since lookup is lockfree, we must make sure
* previous writes to rt are committed to memory
return atomic_read(&__rt_peer_genid);
}
-void rt_bind_peer(struct rtable *rt, int create)
+void rt_bind_peer(struct rtable *rt, __be32 daddr, int create)
{
struct inet_peer *peer;
- peer = inet_getpeer_v4(rt->rt_dst, create);
+ peer = inet_getpeer_v4(daddr, create);
if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL)
inet_putpeer(peer);
if (rt) {
if (rt->peer == NULL)
- rt_bind_peer(rt, 1);
+ rt_bind_peer(rt, rt->rt_dst, 1);
/* If peer is attached to destination, it is never detached,
so that we need not to grab a lock to dereference it.
spin_unlock_bh(rt_hash_lock_addr(hash));
}
+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;
+ struct neighbour *n, *old_n;
+
+ dst_confirm(&rt->dst);
+
+ rt->rt_gateway = peer->redirect_learned.a4;
+
+ n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
+ if (IS_ERR(n))
+ return PTR_ERR(n);
+ old_n = xchg(&rt->dst._neighbour, n);
+ if (old_n)
+ neigh_release(old_n);
+ if (!n || !(n->nud_state & NUD_VALID)) {
+ if (n)
+ neigh_event_send(n, NULL);
+ rt->rt_gateway = orig_gw;
+ return -EAGAIN;
+ } else {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
+ }
+ return 0;
+}
+
/* 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;
goto reject_redirect;
}
- peer = inet_getpeer_v4(daddr, 1);
- if (peer) {
- peer->redirect_learned.a4 = new_gw;
+ for (s = 0; s < 2; s++) {
+ for (i = 0; i < 2; i++) {
+ unsigned int hash;
+ struct rtable __rcu **rthp;
+ struct rtable *rt;
- inet_putpeer(peer);
+ hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
+
+ rthp = &rt_hash_table[hash].chain;
- atomic_inc(&__rt_peer_genid);
+ 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;
+
+ if (!rt->peer)
+ rt_bind_peer(rt, rt->rt_dst, 1);
+
+ peer = rt->peer;
+ 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);
+ }
+ }
+ }
}
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;
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->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);
+ } else if (rt->peer && peer_pmtu_expired(rt->peer)) {
+ dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig);
}
}
return ret;
rcu_read_unlock();
if (!rt->peer)
- rt_bind_peer(rt, 1);
+ rt_bind_peer(rt, rt->rt_dst, 1);
peer = rt->peer;
if (!peer) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
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,
+ &ip_hdr(skb)->saddr, rt->rt_iif,
&rt->rt_dst, &rt->rt_gateway);
#endif
}
int code;
switch (rt->dst.error) {
- case EINVAL:
- default:
- goto out;
- case EHOSTUNREACH:
- code = ICMP_HOST_UNREACH;
- break;
- case ENETUNREACH:
- code = ICMP_NET_UNREACH;
- IP_INC_STATS_BH(dev_net(rt->dst.dev),
- IPSTATS_MIB_INNOROUTES);
- break;
- case EACCES:
- code = ICMP_PKT_FILTERED;
- break;
+ case EINVAL:
+ default:
+ goto out;
+ case EHOSTUNREACH:
+ code = ICMP_HOST_UNREACH;
+ break;
+ case ENETUNREACH:
+ code = ICMP_NET_UNREACH;
+ IP_INC_STATS_BH(dev_net(rt->dst.dev),
+ IPSTATS_MIB_INNOROUTES);
+ break;
+ case EACCES:
+ code = ICMP_PKT_FILTERED;
+ break;
}
if (!rt->peer)
- rt_bind_peer(rt, 1);
+ rt_bind_peer(rt, rt->rt_dst, 1);
peer = rt->peer;
send = true;
est_mtu = mtu;
peer->pmtu_learned = mtu;
peer->pmtu_expires = pmtu_expires;
+ atomic_inc(&__rt_peer_genid);
}
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;
+ 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) {
dst_confirm(dst);
if (!rt->peer)
- rt_bind_peer(rt, 1);
+ rt_bind_peer(rt, rt->rt_dst, 1);
peer = rt->peer;
if (peer) {
+ unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires);
+
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
- if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
- unsigned long pmtu_expires;
+ if (!pmtu_expires || mtu < peer->pmtu_learned) {
pmtu_expires = jiffies + ip_rt_mtu_expires;
if (!pmtu_expires)
}
}
-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)
{
struct inet_peer *peer;
if (!rt->peer)
- rt_bind_peer(rt, 0);
+ rt_bind_peer(rt, rt->rt_dst, 0);
peer = rt->peer;
- if (peer && peer->pmtu_expires)
+ if (peer) {
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;
+ if (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();
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
rt = skb_rtable(skb);
- 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);
- }
+ if (rt && rt->peer && peer_pmtu_cleaned(rt->peer))
+ dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig);
}
static int ip_rt_bug(struct sk_buff *skb)
&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
skb->dev ? skb->dev->name : "?");
kfree_skb(skb);
+ WARN_ON(1);
return 0;
}
in IP options!
*/
-void ip_rt_get_source(u8 *addr, struct rtable *rt)
+void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
{
__be32 src;
- struct fib_result res;
if (rt_is_output_route(rt))
- src = rt->rt_src;
+ src = ip_hdr(skb)->saddr;
else {
- struct flowi4 fl4 = {
- .daddr = rt->rt_key_dst,
- .saddr = rt->rt_key_src,
- .flowi4_tos = rt->rt_tos,
- .flowi4_oif = rt->rt_oif,
- .flowi4_iif = rt->rt_iif,
- .flowi4_mark = rt->rt_mark,
- };
+ struct fib_result res;
+ struct flowi4 fl4;
+ struct iphdr *iph;
+
+ iph = ip_hdr(skb);
+
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.daddr = iph->daddr;
+ fl4.saddr = iph->saddr;
+ fl4.flowi4_tos = RT_TOS(iph->tos);
+ fl4.flowi4_oif = rt->dst.dev->ifindex;
+ fl4.flowi4_iif = skb->dev->ifindex;
+ fl4.flowi4_mark = skb->mark;
rcu_read_lock();
if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0)
return mtu;
}
-static void rt_init_metrics(struct rtable *rt, const struct flowi4 *oldflp4,
+static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
struct fib_info *fi)
{
struct inet_peer *peer;
/* If a peer entry exists for this destination, we must hook
* it up in order to get at cached metrics.
*/
- if (oldflp4 && (oldflp4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS))
+ if (fl4 && (fl4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS))
create = 1;
rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create);
sizeof(u32) * RTAX_MAX);
dst_init_metrics(&rt->dst, peer->metrics, false);
- if (peer->pmtu_expires)
- check_peer_pmtu(&rt->dst, peer);
+ 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;
}
}
-static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4,
+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)
{
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, oldflp4, fi);
+ rt_init_metrics(rt, fl4, fi);
#ifdef CONFIG_IP_ROUTE_CLASSID
dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
#endif
#endif
set_class_tag(rt, itag);
#endif
- rt->rt_type = type;
}
-static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm)
+static struct rtable *rt_dst_alloc(struct net_device *dev,
+ 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;
+ return dst_alloc(&ipv4_dst_ops, dev, 1, -1,
+ DST_HOST |
+ (nopolicy ? DST_NOPOLICY : 0) |
+ (noxfrm ? DST_NOXFRM : 0));
}
/* called in rcu_read_lock() section */
if (err < 0)
goto e_err;
}
- rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ rth = rt_dst_alloc(init_net.loopback_dev,
+ IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ rth->dst.tclassid = itag;
+#endif
rth->dst.output = ip_rt_bug;
rth->rt_key_dst = daddr;
- rth->rt_dst = daddr;
- rth->rt_tos = tos;
- rth->rt_mark = skb->mark;
rth->rt_key_src = saddr;
+ rth->rt_genid = rt_genid(dev_net(dev));
+ rth->rt_flags = RTCF_MULTICAST;
+ rth->rt_type = RTN_MULTICAST;
+ 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->dst.dev = init_net.loopback_dev;
- dev_hold(rth->dst.dev);
rth->rt_oif = 0;
+ rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
- rth->rt_genid = rt_genid(dev_net(dev));
- rth->rt_flags = RTCF_MULTICAST;
- rth->rt_type = RTN_MULTICAST;
+ rth->rt_peer_genid = 0;
+ rth->peer = NULL;
+ rth->fi = NULL;
if (our) {
rth->dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
rth = rt_intern_hash(hash, rth, skb, dev->ifindex);
- err = 0;
- if (IS_ERR(rth))
- err = PTR_ERR(rth);
+ return IS_ERR(rth) ? PTR_ERR(rth) : 0;
e_nobufs:
return -ENOBUFS;
}
}
- rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+ rth = rt_dst_alloc(out_dev->dev,
+ IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
}
rth->rt_key_dst = daddr;
- rth->rt_dst = daddr;
- rth->rt_tos = tos;
- rth->rt_mark = skb->mark;
rth->rt_key_src = saddr;
+ rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
+ rth->rt_flags = flags;
+ rth->rt_type = res->type;
+ rth->rt_key_tos = tos;
+ rth->rt_dst = daddr;
rth->rt_src = saddr;
- rth->rt_gateway = daddr;
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
- rth->dst.dev = (out_dev)->dev;
- dev_hold(rth->dst.dev);
rth->rt_oif = 0;
+ rth->rt_mark = skb->mark;
+ rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
+ rth->rt_peer_genid = 0;
+ rth->peer = NULL;
+ rth->fi = NULL;
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
- rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag);
- rth->rt_flags = flags;
-
*result = rth;
err = 0;
cleanup:
RT_CACHE_STAT_INC(in_brd);
local_input:
- rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ rth = rt_dst_alloc(net->loopback_dev,
+ IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
+ rth->dst.input= ip_local_deliver;
rth->dst.output= ip_rt_bug;
- rth->rt_genid = rt_genid(net);
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ rth->dst.tclassid = itag;
+#endif
rth->rt_key_dst = daddr;
- rth->rt_dst = daddr;
- rth->rt_tos = tos;
- rth->rt_mark = skb->mark;
rth->rt_key_src = saddr;
+ rth->rt_genid = rt_genid(net);
+ rth->rt_flags = flags|RTCF_LOCAL;
+ rth->rt_type = res.type;
+ 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->dst.dev = net->loopback_dev;
- dev_hold(rth->dst.dev);
+ rth->rt_oif = 0;
+ rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
- rth->dst.input= ip_local_deliver;
- rth->rt_flags = flags|RTCF_LOCAL;
+ rth->rt_peer_genid = 0;
+ rth->peer = NULL;
+ rth->fi = NULL;
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
- rth->rt_type = res.type;
hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net));
rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif);
err = 0;
rth = rcu_dereference(rth->dst.rt_next)) {
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_route_iif ^ iif) |
+ (rth->rt_key_tos ^ tos)) == 0 &&
rth->rt_mark == skb->mark &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
/* called with rcu_read_lock() */
static struct rtable *__mkroute_output(const struct fib_result *res,
const struct flowi4 *fl4,
- const struct flowi4 *oldflp4,
- struct net_device *dev_out,
+ __be32 orig_daddr, __be32 orig_saddr,
+ int orig_oif, struct net_device *dev_out,
unsigned int flags)
{
struct fib_info *fi = res->fi;
- u32 tos = RT_FL_TOS(oldflp4);
+ u32 tos = RT_FL_TOS(fl4);
struct in_device *in_dev;
u16 type = res->type;
struct rtable *rth;
fi = NULL;
} else if (type == RTN_MULTICAST) {
flags |= RTCF_MULTICAST | RTCF_LOCAL;
- if (!ip_check_mc_rcu(in_dev, oldflp4->daddr, oldflp4->saddr,
- oldflp4->flowi4_proto))
+ if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr,
+ fl4->flowi4_proto))
flags &= ~RTCF_LOCAL;
/* If multicast route do not exist use
* default one, but do not gateway in this case.
fi = NULL;
}
- rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+ rth = rt_dst_alloc(dev_out,
+ IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(in_dev, NOXFRM));
if (!rth)
return ERR_PTR(-ENOBUFS);
- rth->rt_key_dst = oldflp4->daddr;
- rth->rt_tos = tos;
- rth->rt_key_src = oldflp4->saddr;
- rth->rt_oif = oldflp4->flowi4_oif;
- rth->rt_mark = oldflp4->flowi4_mark;
+ rth->dst.output = ip_output;
+
+ rth->rt_key_dst = orig_daddr;
+ rth->rt_key_src = orig_saddr;
+ rth->rt_genid = rt_genid(dev_net(dev_out));
+ rth->rt_flags = flags;
+ rth->rt_type = type;
+ rth->rt_key_tos = tos;
rth->rt_dst = fl4->daddr;
rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
- rth->rt_iif = oldflp4->flowi4_oif ? : dev_out->ifindex;
- /* get references to the devices that are to be hold by the routing
- cache entry */
- rth->dst.dev = dev_out;
- dev_hold(dev_out);
+ rth->rt_iif = orig_oif ? : dev_out->ifindex;
+ rth->rt_oif = orig_oif;
+ rth->rt_mark = fl4->flowi4_mark;
rth->rt_gateway = fl4->daddr;
rth->rt_spec_dst= fl4->saddr;
-
- rth->dst.output=ip_output;
- rth->rt_genid = rt_genid(dev_net(dev_out));
+ rth->rt_peer_genid = 0;
+ rth->peer = NULL;
+ rth->fi = NULL;
RT_CACHE_STAT_INC(out_slow_tot);
#ifdef CONFIG_IP_MROUTE
if (type == RTN_MULTICAST) {
if (IN_DEV_MFORWARD(in_dev) &&
- !ipv4_is_local_multicast(oldflp4->daddr)) {
+ !ipv4_is_local_multicast(fl4->daddr)) {
rth->dst.input = ip_mr_input;
rth->dst.output = ip_mc_output;
}
#endif
}
- rt_set_nexthop(rth, oldflp4, res, fi, type, 0);
+ rt_set_nexthop(rth, fl4, res, fi, type, 0);
- rth->rt_flags = flags;
return rth;
}
* called with rcu_read_lock();
*/
-static struct rtable *ip_route_output_slow(struct net *net,
- const struct flowi4 *oldflp4)
+static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
{
- u32 tos = RT_FL_TOS(oldflp4);
- struct flowi4 fl4;
- struct fib_result res;
- unsigned int flags = 0;
struct net_device *dev_out = NULL;
+ u32 tos = RT_FL_TOS(fl4);
+ unsigned int flags = 0;
+ struct fib_result res;
struct rtable *rth;
+ __be32 orig_daddr;
+ __be32 orig_saddr;
+ int orig_oif;
res.fi = NULL;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
- fl4.flowi4_oif = oldflp4->flowi4_oif;
- fl4.flowi4_iif = net->loopback_dev->ifindex;
- fl4.flowi4_mark = oldflp4->flowi4_mark;
- fl4.daddr = oldflp4->daddr;
- fl4.saddr = oldflp4->saddr;
- fl4.flowi4_tos = tos & IPTOS_RT_MASK;
- fl4.flowi4_scope = ((tos & RTO_ONLINK) ?
- RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+ orig_daddr = fl4->daddr;
+ orig_saddr = fl4->saddr;
+ orig_oif = fl4->flowi4_oif;
+
+ fl4->flowi4_iif = net->loopback_dev->ifindex;
+ fl4->flowi4_tos = tos & IPTOS_RT_MASK;
+ fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
+ RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
rcu_read_lock();
- if (oldflp4->saddr) {
+ if (fl4->saddr) {
rth = ERR_PTR(-EINVAL);
- if (ipv4_is_multicast(oldflp4->saddr) ||
- ipv4_is_lbcast(oldflp4->saddr) ||
- ipv4_is_zeronet(oldflp4->saddr))
+ if (ipv4_is_multicast(fl4->saddr) ||
+ ipv4_is_lbcast(fl4->saddr) ||
+ ipv4_is_zeronet(fl4->saddr))
goto out;
/* I removed check for oif == dev_out->oif here.
of another iface. --ANK
*/
- if (oldflp4->flowi4_oif == 0 &&
- (ipv4_is_multicast(oldflp4->daddr) ||
- ipv4_is_lbcast(oldflp4->daddr))) {
+ if (fl4->flowi4_oif == 0 &&
+ (ipv4_is_multicast(fl4->daddr) ||
+ ipv4_is_lbcast(fl4->daddr))) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
- dev_out = __ip_dev_find(net, oldflp4->saddr, false);
+ dev_out = __ip_dev_find(net, fl4->saddr, false);
if (dev_out == NULL)
goto out;
Luckily, this hack is good workaround.
*/
- fl4.flowi4_oif = dev_out->ifindex;
+ fl4->flowi4_oif = dev_out->ifindex;
goto make_route;
}
- if (!(oldflp4->flowi4_flags & FLOWI_FLAG_ANYSRC)) {
+ if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
- if (!__ip_dev_find(net, oldflp4->saddr, false))
+ if (!__ip_dev_find(net, fl4->saddr, false))
goto out;
}
}
- if (oldflp4->flowi4_oif) {
- dev_out = dev_get_by_index_rcu(net, oldflp4->flowi4_oif);
+ if (fl4->flowi4_oif) {
+ dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif);
rth = ERR_PTR(-ENODEV);
if (dev_out == NULL)
goto out;
rth = ERR_PTR(-ENETUNREACH);
goto out;
}
- if (ipv4_is_local_multicast(oldflp4->daddr) ||
- ipv4_is_lbcast(oldflp4->daddr)) {
- if (!fl4.saddr)
- fl4.saddr = inet_select_addr(dev_out, 0,
- RT_SCOPE_LINK);
+ if (ipv4_is_local_multicast(fl4->daddr) ||
+ ipv4_is_lbcast(fl4->daddr)) {
+ if (!fl4->saddr)
+ fl4->saddr = inet_select_addr(dev_out, 0,
+ RT_SCOPE_LINK);
goto make_route;
}
- if (!fl4.saddr) {
- if (ipv4_is_multicast(oldflp4->daddr))
- fl4.saddr = inet_select_addr(dev_out, 0,
- fl4.flowi4_scope);
- else if (!oldflp4->daddr)
- fl4.saddr = inet_select_addr(dev_out, 0,
- RT_SCOPE_HOST);
+ if (fl4->saddr) {
+ if (ipv4_is_multicast(fl4->daddr))
+ fl4->saddr = inet_select_addr(dev_out, 0,
+ fl4->flowi4_scope);
+ else if (!fl4->daddr)
+ fl4->saddr = inet_select_addr(dev_out, 0,
+ RT_SCOPE_HOST);
}
}
- if (!fl4.daddr) {
- fl4.daddr = fl4.saddr;
- if (!fl4.daddr)
- fl4.daddr = fl4.saddr = htonl(INADDR_LOOPBACK);
+ if (!fl4->daddr) {
+ fl4->daddr = fl4->saddr;
+ if (!fl4->daddr)
+ fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK);
dev_out = net->loopback_dev;
- fl4.flowi4_oif = net->loopback_dev->ifindex;
+ fl4->flowi4_oif = net->loopback_dev->ifindex;
res.type = RTN_LOCAL;
flags |= RTCF_LOCAL;
goto make_route;
}
- if (fib_lookup(net, &fl4, &res)) {
+ if (fib_lookup(net, fl4, &res)) {
res.fi = NULL;
- if (oldflp4->flowi4_oif) {
+ if (fl4->flowi4_oif) {
/* Apparently, routing tables are wrong. Assume,
that the destination is on link.
likely IPv6, but we do not.
*/
- if (fl4.saddr == 0)
- fl4.saddr = inet_select_addr(dev_out, 0,
- RT_SCOPE_LINK);
+ if (fl4->saddr == 0)
+ fl4->saddr = inet_select_addr(dev_out, 0,
+ RT_SCOPE_LINK);
res.type = RTN_UNICAST;
goto make_route;
}
}
if (res.type == RTN_LOCAL) {
- if (!fl4.saddr) {
+ if (!fl4->saddr) {
if (res.fi->fib_prefsrc)
- fl4.saddr = res.fi->fib_prefsrc;
+ fl4->saddr = res.fi->fib_prefsrc;
else
- fl4.saddr = fl4.daddr;
+ fl4->saddr = fl4->daddr;
}
dev_out = net->loopback_dev;
- fl4.flowi4_oif = dev_out->ifindex;
+ fl4->flowi4_oif = dev_out->ifindex;
res.fi = NULL;
flags |= RTCF_LOCAL;
goto make_route;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
- if (res.fi->fib_nhs > 1 && fl4.flowi4_oif == 0)
+ if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0)
fib_select_multipath(&res);
else
#endif
if (!res.prefixlen &&
res.table->tb_num_default > 1 &&
- res.type == RTN_UNICAST && !fl4.flowi4_oif)
+ res.type == RTN_UNICAST && !fl4->flowi4_oif)
fib_select_default(&res);
- if (!fl4.saddr)
- fl4.saddr = FIB_RES_PREFSRC(net, res);
+ if (!fl4->saddr)
+ fl4->saddr = FIB_RES_PREFSRC(net, res);
dev_out = FIB_RES_DEV(res);
- fl4.flowi4_oif = dev_out->ifindex;
+ fl4->flowi4_oif = dev_out->ifindex;
make_route:
- rth = __mkroute_output(&res, &fl4, oldflp4, dev_out, flags);
+ rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
+ dev_out, flags);
if (!IS_ERR(rth)) {
unsigned int hash;
- hash = rt_hash(oldflp4->daddr, oldflp4->saddr, oldflp4->flowi4_oif,
+ hash = rt_hash(orig_daddr, orig_saddr, orig_oif,
rt_genid(dev_net(dev_out)));
- rth = rt_intern_hash(hash, rth, NULL, oldflp4->flowi4_oif);
+ rth = rt_intern_hash(hash, rth, NULL, orig_oif);
}
out:
return rth;
}
-struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *flp4)
+struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4)
{
struct rtable *rth;
unsigned int hash;
rt_is_output_route(rth) &&
rth->rt_oif == flp4->flowi4_oif &&
rth->rt_mark == flp4->flowi4_mark &&
- !((rth->rt_tos ^ flp4->flowi4_tos) &
+ !((rth->rt_key_tos ^ flp4->flowi4_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();
+ if (!flp4->saddr)
+ flp4->saddr = rth->rt_src;
+ if (!flp4->daddr)
+ flp4->daddr = rth->rt_dst;
return rth;
}
RT_CACHE_STAT_INC(out_hlist_search);
.default_advmss = ipv4_default_advmss,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
.cow_metrics = ipv4_rt_blackhole_cow_metrics,
+ .neigh_lookup = ipv4_neigh_lookup,
};
struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
- struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, 1);
+ struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, 0, 0);
struct rtable *ort = (struct rtable *) dst_orig;
if (rt) {
rt->rt_key_dst = ort->rt_key_dst;
rt->rt_key_src = ort->rt_key_src;
- rt->rt_tos = ort->rt_tos;
+ rt->rt_key_tos = ort->rt_key_tos;
rt->rt_route_iif = ort->rt_route_iif;
rt->rt_iif = ort->rt_iif;
rt->rt_oif = ort->rt_oif;
if (IS_ERR(rt))
return rt;
- if (flp4->flowi4_proto) {
- if (!flp4->saddr)
- flp4->saddr = rt->rt_src;
- if (!flp4->daddr)
- flp4->daddr = rt->rt_dst;
+ if (flp4->flowi4_proto)
rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
flowi4_to_flowi(flp4),
sk, 0);
- }
return rt;
}
struct rtable *rt = skb_rtable(skb);
struct rtmsg *r;
struct nlmsghdr *nlh;
- long expires;
+ long expires = 0;
+ const struct inet_peer *peer = rt->peer;
u32 id = 0, ts = 0, tsage = 0, error;
nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
r->rtm_family = AF_INET;
r->rtm_dst_len = 32;
r->rtm_src_len = 0;
- r->rtm_tos = rt->rt_tos;
+ r->rtm_tos = rt->rt_key_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_MARK, rt->rt_mark);
error = rt->dst.error;
- expires = (rt->peer && rt->peer->pmtu_expires) ?
- rt->peer->pmtu_expires - jiffies : 0;
- if (rt->peer) {
+ if (peer) {
inet_peer_refcheck(rt->peer);
- id = atomic_read(&rt->peer->ip_id_count) & 0xffff;
- if (rt->peer->tcp_ts_stamp) {
- ts = rt->peer->tcp_ts;
- tsage = get_seconds() - rt->peer->tcp_ts_stamp;
+ 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)
+ expires -= jiffies;
}
if (rt_is_input_route(rt)) {
if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
- int err = ipmr_get_route(net, skb, r, nowait);
+ int err = ipmr_get_route(net, skb,
+ rt->rt_src, rt->rt_dst,
+ r, nowait);
if (err <= 0) {
if (!nowait) {
if (err == 0)
xfrm_init();
xfrm4_init(ip_rt_max_size);
#endif
- rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL);
+ rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL);
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&sysctl_route_ops);
Code Review / linux-2.6.git / blobdiff