static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
-static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ;
static int rt_chain_length_max __read_mostly = 20;
static struct delayed_work expires_work;
static unsigned int rt_hash_log __read_mostly;
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
-#define RT_CACHE_STAT_INC(field) \
- (__raw_get_cpu_var(rt_cache_stat).field++)
+#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
- int genid)
+ int genid)
{
- return jhash_3words((__force u32)(__be32)(daddr),
- (__force u32)(__be32)(saddr),
+ return jhash_3words((__force u32)daddr, (__force u32)saddr,
idx, genid)
& rt_hash_mask;
}
rcu_read_lock_bh();
r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
while (r) {
- if (dev_net(r->u.dst.dev) == seq_file_net(seq) &&
+ if (dev_net(r->dst.dev) == seq_file_net(seq) &&
r->rt_genid == st->genid)
return r;
- r = rcu_dereference_bh(r->u.dst.rt_next);
+ r = rcu_dereference_bh(r->dst.rt_next);
}
rcu_read_unlock_bh();
}
{
struct rt_cache_iter_state *st = seq->private;
- r = r->u.dst.rt_next;
+ r = r->dst.rt_next;
while (!r) {
rcu_read_unlock_bh();
do {
{
struct rt_cache_iter_state *st = seq->private;
while ((r = __rt_cache_get_next(seq, r)) != NULL) {
- if (dev_net(r->u.dst.dev) != seq_file_net(seq))
+ if (dev_net(r->dst.dev) != seq_file_net(seq))
continue;
if (r->rt_genid == st->genid)
break;
struct rtable *r = v;
int len;
- seq_printf(seq, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t"
- "%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
- r->u.dst.dev ? r->u.dst.dev->name : "*",
- (unsigned long)r->rt_dst, (unsigned long)r->rt_gateway,
- r->rt_flags, atomic_read(&r->u.dst.__refcnt),
- r->u.dst.__use, 0, (unsigned long)r->rt_src,
- (dst_metric(&r->u.dst, RTAX_ADVMSS) ?
- (int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0),
- dst_metric(&r->u.dst, RTAX_WINDOW),
- (int)((dst_metric(&r->u.dst, RTAX_RTT) >> 3) +
- dst_metric(&r->u.dst, RTAX_RTTVAR)),
+ 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(&r->dst, RTAX_ADVMSS) ?
+ (int)dst_metric(&r->dst, RTAX_ADVMSS) + 40 : 0),
+ 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->u.dst.hh ? atomic_read(&r->u.dst.hh->hh_refcnt) : -1,
- r->u.dst.hh ? (r->u.dst.hh->hh_output ==
+ 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_spec_dst, &len);
static inline void rt_free(struct rtable *rt)
{
- call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
+ call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
}
static inline void rt_drop(struct rtable *rt)
{
ip_rt_put(rt);
- call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
+ call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
}
static inline int rt_fast_clean(struct rtable *rth)
/* Kill broadcast/multicast entries very aggresively, if they
collide in hash table with more useful entries */
return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) &&
- rth->fl.iif && rth->u.dst.rt_next;
+ rth->fl.iif && rth->dst.rt_next;
}
static inline int rt_valuable(struct rtable *rth)
{
return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
- rth->u.dst.expires;
+ rth->dst.expires;
}
static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
unsigned long age;
int ret = 0;
- if (atomic_read(&rth->u.dst.__refcnt))
+ if (atomic_read(&rth->dst.__refcnt))
goto out;
ret = 1;
- if (rth->u.dst.expires &&
- time_after_eq(jiffies, rth->u.dst.expires))
+ if (rth->dst.expires &&
+ time_after_eq(jiffies, rth->dst.expires))
goto out;
- age = jiffies - rth->u.dst.lastuse;
+ age = jiffies - rth->dst.lastuse;
ret = 0;
if ((age <= tmo1 && !rt_fast_clean(rth)) ||
(age <= tmo2 && rt_valuable(rth)))
*/
static inline u32 rt_score(struct rtable *rt)
{
- u32 score = jiffies - rt->u.dst.lastuse;
+ u32 score = jiffies - rt->dst.lastuse;
score = ~score & ~(3<<30);
static inline bool compare_hash_inputs(const struct flowi *fl1,
const struct flowi *fl2)
{
- return (__force u32)(((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
- (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) |
+ return ((((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(fl1->iif ^ fl2->iif)) == 0);
}
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
- return ((__force u32)((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
- (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr)) |
+ return (((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(fl1->mark ^ fl2->mark) |
- (*(u16 *)&fl1->nl_u.ip4_u.tos ^
- *(u16 *)&fl2->nl_u.ip4_u.tos) |
+ (*(u16 *)&fl1->nl_u.ip4_u.tos ^ *(u16 *)&fl2->nl_u.ip4_u.tos) |
(fl1->oif ^ fl2->oif) |
(fl1->iif ^ fl2->iif)) == 0;
}
static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
{
- return net_eq(dev_net(rt1->u.dst.dev), dev_net(rt2->u.dst.dev));
+ return net_eq(dev_net(rt1->dst.dev), dev_net(rt2->dst.dev));
}
static inline int rt_is_expired(struct rtable *rth)
{
- return rth->rt_genid != rt_genid(dev_net(rth->u.dst.dev));
+ return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
}
/*
rth = rt_hash_table[i].chain;
/* defer releasing the head of the list after spin_unlock */
- for (tail = rth; tail; tail = tail->u.dst.rt_next)
+ for (tail = rth; tail; tail = tail->dst.rt_next)
if (!rt_is_expired(tail))
break;
if (rth != tail)
/* call rt_free on entries after the tail requiring flush */
prev = &rt_hash_table[i].chain;
for (p = *prev; p; p = next) {
- next = p->u.dst.rt_next;
+ next = p->dst.rt_next;
if (!rt_is_expired(p)) {
- prev = &p->u.dst.rt_next;
+ prev = &p->dst.rt_next;
} else {
*prev = next;
rt_free(p);
spin_unlock_bh(rt_hash_lock_addr(i));
for (; rth != tail; rth = next) {
- next = rth->u.dst.rt_next;
+ next = rth->dst.rt_next;
rt_free(rth);
}
}
while (aux != rth) {
if (compare_hash_inputs(&aux->fl, &rth->fl))
return 0;
- aux = aux->u.dst.rt_next;
+ aux = aux->dst.rt_next;
}
return ONE;
}
length = 0;
spin_lock_bh(rt_hash_lock_addr(i));
while ((rth = *rthp) != NULL) {
- prefetch(rth->u.dst.rt_next);
+ prefetch(rth->dst.rt_next);
if (rt_is_expired(rth)) {
- *rthp = rth->u.dst.rt_next;
+ *rthp = rth->dst.rt_next;
rt_free(rth);
continue;
}
- if (rth->u.dst.expires) {
+ if (rth->dst.expires) {
/* Entry is expired even if it is in use */
- if (time_before_eq(jiffies, rth->u.dst.expires)) {
+ if (time_before_eq(jiffies, rth->dst.expires)) {
nofree:
tmo >>= 1;
- rthp = &rth->u.dst.rt_next;
+ rthp = &rth->dst.rt_next;
/*
* We only count entries on
* a chain with equal hash inputs once
goto nofree;
/* Cleanup aged off entries. */
- *rthp = rth->u.dst.rt_next;
+ *rthp = rth->dst.rt_next;
rt_free(rth);
}
spin_unlock_bh(rt_hash_lock_addr(i));
rt_do_flush(!in_softirq());
}
-/*
- * We change rt_genid and let gc do the cleanup
- */
-static void rt_secret_rebuild(unsigned long __net)
-{
- struct net *net = (struct net *)__net;
- rt_cache_invalidate(net);
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
-}
-
-static void rt_secret_rebuild_oneshot(struct net *net)
-{
- del_timer_sync(&net->ipv4.rt_secret_timer);
- rt_cache_invalidate(net);
- if (ip_rt_secret_interval)
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
-}
-
static void rt_emergency_hash_rebuild(struct net *net)
{
- if (net_ratelimit()) {
+ if (net_ratelimit())
printk(KERN_WARNING "Route hash chain too long!\n");
- printk(KERN_WARNING "Adjust your secret_interval!\n");
- }
-
- rt_secret_rebuild_oneshot(net);
+ rt_cache_invalidate(net);
}
/*
if (!rt_is_expired(rth) &&
!rt_may_expire(rth, tmo, expire)) {
tmo >>= 1;
- rthp = &rth->u.dst.rt_next;
+ rthp = &rth->dst.rt_next;
continue;
}
- *rthp = rth->u.dst.rt_next;
+ *rthp = rth->dst.rt_next;
rt_free(rth);
goal--;
}
while (rth) {
length += has_noalias(head, rth);
- rth = rth->u.dst.rt_next;
+ rth = rth->dst.rt_next;
}
return length >> FRACT_BITS;
}
candp = NULL;
now = jiffies;
- if (!rt_caching(dev_net(rt->u.dst.dev))) {
+ if (!rt_caching(dev_net(rt->dst.dev))) {
/*
* If we're not caching, just tell the caller we
* were successful and don't touch the route. The
*/
if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {
- int err = arp_bind_neighbour(&rt->u.dst);
+ int err = arp_bind_neighbour(&rt->dst);
if (err) {
if (net_ratelimit())
printk(KERN_WARNING
spin_lock_bh(rt_hash_lock_addr(hash));
while ((rth = *rthp) != NULL) {
if (rt_is_expired(rth)) {
- *rthp = rth->u.dst.rt_next;
+ *rthp = rth->dst.rt_next;
rt_free(rth);
continue;
}
if (compare_keys(&rth->fl, &rt->fl) && compare_netns(rth, rt)) {
/* Put it first */
- *rthp = rth->u.dst.rt_next;
+ *rthp = rth->dst.rt_next;
/*
* Since lookup is lockfree, the deletion
* must be visible to another weakly ordered CPU before
* the insertion at the start of the hash chain.
*/
- rcu_assign_pointer(rth->u.dst.rt_next,
+ rcu_assign_pointer(rth->dst.rt_next,
rt_hash_table[hash].chain);
/*
* Since lookup is lockfree, the update writes
*/
rcu_assign_pointer(rt_hash_table[hash].chain, rth);
- dst_use(&rth->u.dst, now);
+ dst_use(&rth->dst, now);
spin_unlock_bh(rt_hash_lock_addr(hash));
rt_drop(rt);
if (rp)
*rp = rth;
else
- skb_dst_set(skb, &rth->u.dst);
+ skb_dst_set(skb, &rth->dst);
return 0;
}
- if (!atomic_read(&rth->u.dst.__refcnt)) {
+ if (!atomic_read(&rth->dst.__refcnt)) {
u32 score = rt_score(rth);
if (score <= min_score) {
chain_length++;
- rthp = &rth->u.dst.rt_next;
+ rthp = &rth->dst.rt_next;
}
if (cand) {
* only 2 entries per bucket. We will see.
*/
if (chain_length > ip_rt_gc_elasticity) {
- *candp = cand->u.dst.rt_next;
+ *candp = cand->dst.rt_next;
rt_free(cand);
}
} else {
if (chain_length > rt_chain_length_max &&
slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) {
- struct net *net = dev_net(rt->u.dst.dev);
+ struct net *net = dev_net(rt->dst.dev);
int num = ++net->ipv4.current_rt_cache_rebuild_count;
if (!rt_caching(net)) {
printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
- rt->u.dst.dev->name, num);
+ rt->dst.dev->name, num);
}
rt_emergency_hash_rebuild(net);
spin_unlock_bh(rt_hash_lock_addr(hash));
route or unicast forwarding path.
*/
if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {
- int err = arp_bind_neighbour(&rt->u.dst);
+ int err = arp_bind_neighbour(&rt->dst);
if (err) {
spin_unlock_bh(rt_hash_lock_addr(hash));
}
}
- rt->u.dst.rt_next = rt_hash_table[hash].chain;
+ rt->dst.rt_next = rt_hash_table[hash].chain;
#if RT_CACHE_DEBUG >= 2
- if (rt->u.dst.rt_next) {
+ if (rt->dst.rt_next) {
struct rtable *trt;
printk(KERN_DEBUG "rt_cache @%02x: %pI4",
hash, &rt->rt_dst);
- for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next)
+ for (trt = rt->dst.rt_next; trt; trt = trt->dst.rt_next)
printk(" . %pI4", &trt->rt_dst);
printk("\n");
}
if (rp)
*rp = rt;
else
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
return 0;
}
ip_select_fb_ident(iph);
}
+EXPORT_SYMBOL(__ip_select_ident);
static void rt_del(unsigned hash, struct rtable *rt)
{
ip_rt_put(rt);
while ((aux = *rthp) != NULL) {
if (aux == rt || rt_is_expired(aux)) {
- *rthp = aux->u.dst.rt_next;
+ *rthp = aux->dst.rt_next;
rt_free(aux);
continue;
}
- rthp = &aux->u.dst.rt_next;
+ rthp = &aux->dst.rt_next;
}
spin_unlock_bh(rt_hash_lock_addr(hash));
}
+/* 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 i, k;
- struct in_device *in_dev = in_dev_get(dev);
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
struct rtable *rth, **rthp;
__be32 skeys[2] = { saddr, 0 };
int ikeys[2] = { dev->ifindex, 0 };
rthp=&rt_hash_table[hash].chain;
- rcu_read_lock();
while ((rth = rcu_dereference(*rthp)) != NULL) {
struct rtable *rt;
rth->fl.oif != ikeys[k] ||
rth->fl.iif != 0 ||
rt_is_expired(rth) ||
- !net_eq(dev_net(rth->u.dst.dev), net)) {
- rthp = &rth->u.dst.rt_next;
+ !net_eq(dev_net(rth->dst.dev), net)) {
+ rthp = &rth->dst.rt_next;
continue;
}
if (rth->rt_dst != daddr ||
rth->rt_src != saddr ||
- rth->u.dst.error ||
+ rth->dst.error ||
rth->rt_gateway != old_gw ||
- rth->u.dst.dev != dev)
+ rth->dst.dev != dev)
break;
- dst_hold(&rth->u.dst);
- rcu_read_unlock();
+ dst_hold(&rth->dst);
rt = dst_alloc(&ipv4_dst_ops);
if (rt == NULL) {
ip_rt_put(rth);
- in_dev_put(in_dev);
return;
}
/* Copy all the information. */
*rt = *rth;
- rt->u.dst.__use = 1;
- atomic_set(&rt->u.dst.__refcnt, 1);
- rt->u.dst.child = NULL;
- if (rt->u.dst.dev)
- dev_hold(rt->u.dst.dev);
+ rt->dst.__use = 1;
+ atomic_set(&rt->dst.__refcnt, 1);
+ rt->dst.child = NULL;
+ if (rt->dst.dev)
+ dev_hold(rt->dst.dev);
if (rt->idev)
in_dev_hold(rt->idev);
- rt->u.dst.obsolete = -1;
- rt->u.dst.lastuse = jiffies;
- rt->u.dst.path = &rt->u.dst;
- rt->u.dst.neighbour = NULL;
- rt->u.dst.hh = NULL;
+ 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->u.dst.xfrm = NULL;
+ rt->dst.xfrm = NULL;
#endif
rt->rt_genid = rt_genid(net);
rt->rt_flags |= RTCF_REDIRECTED;
rt->rt_gateway = new_gw;
/* Redirect received -> path was valid */
- dst_confirm(&rth->u.dst);
+ dst_confirm(&rth->dst);
if (rt->peer)
atomic_inc(&rt->peer->refcnt);
- if (arp_bind_neighbour(&rt->u.dst) ||
- !(rt->u.dst.neighbour->nud_state &
+ if (arp_bind_neighbour(&rt->dst) ||
+ !(rt->dst.neighbour->nud_state &
NUD_VALID)) {
- if (rt->u.dst.neighbour)
- neigh_event_send(rt->u.dst.neighbour, NULL);
+ if (rt->dst.neighbour)
+ neigh_event_send(rt->dst.neighbour, NULL);
ip_rt_put(rth);
rt_drop(rt);
goto do_next;
}
- netevent.old = &rth->u.dst;
- netevent.new = &rt->u.dst;
+ netevent.old = &rth->dst;
+ netevent.new = &rt->dst;
call_netevent_notifiers(NETEVENT_REDIRECT,
&netevent);
ip_rt_put(rt);
goto do_next;
}
- rcu_read_unlock();
do_next:
;
}
}
- in_dev_put(in_dev);
return;
reject_redirect:
&old_gw, dev->name, &new_gw,
&saddr, &daddr);
#endif
- in_dev_put(in_dev);
+ ;
}
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
ip_rt_put(rt);
ret = NULL;
} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
- (rt->u.dst.expires &&
- time_after_eq(jiffies, rt->u.dst.expires))) {
+ (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,
rt_genid(dev_net(dst->dev)));
int log_martians;
rcu_read_lock();
- in_dev = __in_dev_get_rcu(rt->u.dst.dev);
+ in_dev = __in_dev_get_rcu(rt->dst.dev);
if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) {
rcu_read_unlock();
return;
/* No redirected packets during ip_rt_redirect_silence;
* reset the algorithm.
*/
- if (time_after(jiffies, rt->u.dst.rate_last + ip_rt_redirect_silence))
- rt->u.dst.rate_tokens = 0;
+ if (time_after(jiffies, rt->dst.rate_last + ip_rt_redirect_silence))
+ rt->dst.rate_tokens = 0;
/* Too many ignored redirects; do not send anything
- * set u.dst.rate_last to the last seen redirected packet.
+ * set dst.rate_last to the last seen redirected packet.
*/
- if (rt->u.dst.rate_tokens >= ip_rt_redirect_number) {
- rt->u.dst.rate_last = jiffies;
+ if (rt->dst.rate_tokens >= ip_rt_redirect_number) {
+ rt->dst.rate_last = jiffies;
return;
}
/* Check for load limit; set rate_last to the latest sent
* redirect.
*/
- if (rt->u.dst.rate_tokens == 0 ||
+ if (rt->dst.rate_tokens == 0 ||
time_after(jiffies,
- (rt->u.dst.rate_last +
- (ip_rt_redirect_load << rt->u.dst.rate_tokens)))) {
+ (rt->dst.rate_last +
+ (ip_rt_redirect_load << rt->dst.rate_tokens)))) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
- rt->u.dst.rate_last = jiffies;
- ++rt->u.dst.rate_tokens;
+ rt->dst.rate_last = jiffies;
+ ++rt->dst.rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (log_martians &&
- rt->u.dst.rate_tokens == ip_rt_redirect_number &&
+ rt->dst.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,
unsigned long now;
int code;
- switch (rt->u.dst.error) {
+ switch (rt->dst.error) {
case EINVAL:
default:
goto out;
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
- IP_INC_STATS_BH(dev_net(rt->u.dst.dev),
+ IP_INC_STATS_BH(dev_net(rt->dst.dev),
IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
}
now = jiffies;
- rt->u.dst.rate_tokens += now - rt->u.dst.rate_last;
- if (rt->u.dst.rate_tokens > ip_rt_error_burst)
- rt->u.dst.rate_tokens = ip_rt_error_burst;
- rt->u.dst.rate_last = now;
- if (rt->u.dst.rate_tokens >= ip_rt_error_cost) {
- rt->u.dst.rate_tokens -= ip_rt_error_cost;
+ 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);
}
rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->u.dst.rt_next)) {
+ rth = rcu_dereference(rth->dst.rt_next)) {
unsigned short mtu = new_mtu;
if (rth->fl.fl4_dst != daddr ||
rth->rt_src != iph->saddr ||
rth->fl.oif != ikeys[k] ||
rth->fl.iif != 0 ||
- dst_metric_locked(&rth->u.dst, RTAX_MTU) ||
- !net_eq(dev_net(rth->u.dst.dev), net) ||
+ dst_metric_locked(&rth->dst, RTAX_MTU) ||
+ !net_eq(dev_net(rth->dst.dev), net) ||
rt_is_expired(rth))
continue;
/* BSD 4.2 compatibility hack :-( */
if (mtu == 0 &&
- old_mtu >= dst_mtu(&rth->u.dst) &&
+ old_mtu >= dst_mtu(&rth->dst) &&
old_mtu >= 68 + (iph->ihl << 2))
old_mtu -= iph->ihl << 2;
mtu = guess_mtu(old_mtu);
}
- if (mtu <= dst_mtu(&rth->u.dst)) {
- if (mtu < dst_mtu(&rth->u.dst)) {
- dst_confirm(&rth->u.dst);
+ if (mtu <= dst_mtu(&rth->dst)) {
+ if (mtu < dst_mtu(&rth->dst)) {
+ dst_confirm(&rth->dst);
if (mtu < ip_rt_min_pmtu) {
mtu = ip_rt_min_pmtu;
- rth->u.dst.metrics[RTAX_LOCK-1] |=
+ rth->dst.metrics[RTAX_LOCK-1] |=
(1 << RTAX_MTU);
}
- rth->u.dst.metrics[RTAX_MTU-1] = mtu;
- dst_set_expires(&rth->u.dst,
+ rth->dst.metrics[RTAX_MTU-1] = mtu;
+ dst_set_expires(&rth->dst,
ip_rt_mtu_expires);
}
est_mtu = mtu;
rt = skb_rtable(skb);
if (rt)
- dst_set_expires(&rt->u.dst, 0);
+ dst_set_expires(&rt->dst, 0);
}
static int ip_rt_bug(struct sk_buff *skb)
if (rt->fl.iif == 0)
src = rt->rt_src;
- else if (fib_lookup(dev_net(rt->u.dst.dev), &rt->fl, &res) == 0) {
+ else if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0) {
src = FIB_RES_PREFSRC(res);
fib_res_put(&res);
} else
- src = inet_select_addr(rt->u.dst.dev, rt->rt_gateway,
+ src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
RT_SCOPE_UNIVERSE);
memcpy(addr, &src, 4);
}
#ifdef CONFIG_NET_CLS_ROUTE
static void set_class_tag(struct rtable *rt, u32 tag)
{
- if (!(rt->u.dst.tclassid & 0xFFFF))
- rt->u.dst.tclassid |= tag & 0xFFFF;
- if (!(rt->u.dst.tclassid & 0xFFFF0000))
- rt->u.dst.tclassid |= tag & 0xFFFF0000;
+ if (!(rt->dst.tclassid & 0xFFFF))
+ rt->dst.tclassid |= tag & 0xFFFF;
+ if (!(rt->dst.tclassid & 0xFFFF0000))
+ rt->dst.tclassid |= tag & 0xFFFF0000;
}
#endif
if (FIB_RES_GW(*res) &&
FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = FIB_RES_GW(*res);
- memcpy(rt->u.dst.metrics, fi->fib_metrics,
- sizeof(rt->u.dst.metrics));
+ memcpy(rt->dst.metrics, fi->fib_metrics,
+ sizeof(rt->dst.metrics));
if (fi->fib_mtu == 0) {
- rt->u.dst.metrics[RTAX_MTU-1] = rt->u.dst.dev->mtu;
- if (dst_metric_locked(&rt->u.dst, RTAX_MTU) &&
+ rt->dst.metrics[RTAX_MTU-1] = rt->dst.dev->mtu;
+ if (dst_metric_locked(&rt->dst, RTAX_MTU) &&
rt->rt_gateway != rt->rt_dst &&
- rt->u.dst.dev->mtu > 576)
- rt->u.dst.metrics[RTAX_MTU-1] = 576;
+ rt->dst.dev->mtu > 576)
+ rt->dst.metrics[RTAX_MTU-1] = 576;
}
#ifdef CONFIG_NET_CLS_ROUTE
- rt->u.dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
+ rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
#endif
} else
- rt->u.dst.metrics[RTAX_MTU-1]= rt->u.dst.dev->mtu;
-
- if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0)
- rt->u.dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl;
- if (dst_mtu(&rt->u.dst) > IP_MAX_MTU)
- rt->u.dst.metrics[RTAX_MTU-1] = IP_MAX_MTU;
- if (dst_metric(&rt->u.dst, RTAX_ADVMSS) == 0)
- rt->u.dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->u.dst.dev->mtu - 40,
+ rt->dst.metrics[RTAX_MTU-1]= rt->dst.dev->mtu;
+
+ if (dst_metric(&rt->dst, RTAX_HOPLIMIT) == 0)
+ rt->dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl;
+ if (dst_mtu(&rt->dst) > IP_MAX_MTU)
+ rt->dst.metrics[RTAX_MTU-1] = IP_MAX_MTU;
+ if (dst_metric(&rt->dst, RTAX_ADVMSS) == 0)
+ rt->dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->dst.dev->mtu - 40,
ip_rt_min_advmss);
- if (dst_metric(&rt->u.dst, RTAX_ADVMSS) > 65535 - 40)
- rt->u.dst.metrics[RTAX_ADVMSS-1] = 65535 - 40;
+ if (dst_metric(&rt->dst, RTAX_ADVMSS) > 65535 - 40)
+ rt->dst.metrics[RTAX_ADVMSS-1] = 65535 - 40;
#ifdef CONFIG_NET_CLS_ROUTE
#ifdef CONFIG_IP_MULTIPLE_TABLES
rt->rt_type = res->type;
}
+/* called in rcu_read_lock() section */
static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, int our)
{
- unsigned hash;
+ unsigned int hash;
struct rtable *rth;
__be32 spec_dst;
- struct in_device *in_dev = in_dev_get(dev);
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
u32 itag = 0;
+ int err;
/* Primary sanity checks. */
if (!ipv4_is_local_multicast(daddr))
goto e_inval;
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
- } else if (fib_validate_source(saddr, 0, tos, 0,
- dev, &spec_dst, &itag, 0) < 0)
- goto e_inval;
-
+ } else {
+ err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
+ &itag, 0);
+ if (err < 0)
+ goto e_err;
+ }
rth = dst_alloc(&ipv4_dst_ops);
if (!rth)
goto e_nobufs;
- rth->u.dst.output = ip_rt_bug;
- rth->u.dst.obsolete = -1;
+ rth->dst.output = ip_rt_bug;
+ rth->dst.obsolete = -1;
- atomic_set(&rth->u.dst.__refcnt, 1);
- rth->u.dst.flags= DST_HOST;
+ atomic_set(&rth->dst.__refcnt, 1);
+ rth->dst.flags= DST_HOST;
if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->u.dst.flags |= DST_NOPOLICY;
+ rth->dst.flags |= DST_NOPOLICY;
rth->fl.fl4_dst = daddr;
rth->rt_dst = daddr;
rth->fl.fl4_tos = tos;
rth->fl.fl4_src = saddr;
rth->rt_src = saddr;
#ifdef CONFIG_NET_CLS_ROUTE
- rth->u.dst.tclassid = itag;
+ rth->dst.tclassid = itag;
#endif
rth->rt_iif =
rth->fl.iif = dev->ifindex;
- rth->u.dst.dev = init_net.loopback_dev;
- dev_hold(rth->u.dst.dev);
- rth->idev = in_dev_get(rth->u.dst.dev);
+ rth->dst.dev = init_net.loopback_dev;
+ dev_hold(rth->dst.dev);
+ rth->idev = in_dev_get(rth->dst.dev);
rth->fl.oif = 0;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
if (our) {
- rth->u.dst.input= ip_local_deliver;
+ rth->dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
}
#ifdef CONFIG_IP_MROUTE
if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev))
- rth->u.dst.input = ip_mr_input;
+ rth->dst.input = ip_mr_input;
#endif
RT_CACHE_STAT_INC(in_slow_mc);
- in_dev_put(in_dev);
hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex);
e_nobufs:
- in_dev_put(in_dev);
return -ENOBUFS;
-
e_inval:
- in_dev_put(in_dev);
return -EINVAL;
+e_err:
+ return err;
}
#endif
}
+/* called in rcu_read_lock() section */
static int __mkroute_input(struct sk_buff *skb,
struct fib_result *res,
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos,
struct rtable **result)
{
-
struct rtable *rth;
int err;
struct in_device *out_dev;
- unsigned flags = 0;
+ unsigned int flags = 0;
__be32 spec_dst;
u32 itag;
/* get a working reference to the output device */
- out_dev = in_dev_get(FIB_RES_DEV(*res));
+ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
if (out_dev == NULL) {
if (net_ratelimit())
printk(KERN_CRIT "Bug in ip_route_input" \
ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
- err = -EINVAL;
goto cleanup;
}
goto cleanup;
}
- atomic_set(&rth->u.dst.__refcnt, 1);
- rth->u.dst.flags= DST_HOST;
+ atomic_set(&rth->dst.__refcnt, 1);
+ rth->dst.flags= DST_HOST;
if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->u.dst.flags |= DST_NOPOLICY;
+ rth->dst.flags |= DST_NOPOLICY;
if (IN_DEV_CONF_GET(out_dev, NOXFRM))
- rth->u.dst.flags |= DST_NOXFRM;
+ rth->dst.flags |= DST_NOXFRM;
rth->fl.fl4_dst = daddr;
rth->rt_dst = daddr;
rth->fl.fl4_tos = tos;
rth->rt_gateway = daddr;
rth->rt_iif =
rth->fl.iif = in_dev->dev->ifindex;
- rth->u.dst.dev = (out_dev)->dev;
- dev_hold(rth->u.dst.dev);
- rth->idev = in_dev_get(rth->u.dst.dev);
+ rth->dst.dev = (out_dev)->dev;
+ dev_hold(rth->dst.dev);
+ rth->idev = in_dev_get(rth->dst.dev);
rth->fl.oif = 0;
rth->rt_spec_dst= spec_dst;
- rth->u.dst.obsolete = -1;
- rth->u.dst.input = ip_forward;
- rth->u.dst.output = ip_output;
- rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev));
+ 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);
*result = rth;
err = 0;
cleanup:
- /* release the working reference to the output device */
- in_dev_put(out_dev);
return err;
}
/* put it into the cache */
hash = rt_hash(daddr, saddr, fl->iif,
- rt_genid(dev_net(rth->u.dst.dev)));
+ rt_genid(dev_net(rth->dst.dev)));
return rt_intern_hash(hash, rth, NULL, skb, fl->iif);
}
u8 tos, struct net_device *dev)
{
struct fib_result res;
- struct in_device *in_dev = in_dev_get(dev);
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
struct flowi fl = { .nl_u = { .ip4_u =
{ .daddr = daddr,
.saddr = saddr,
goto brd_input;
if (res.type == RTN_LOCAL) {
- int result;
- result = fib_validate_source(saddr, daddr, tos,
+ err = fib_validate_source(saddr, daddr, tos,
net->loopback_dev->ifindex,
dev, &spec_dst, &itag, skb->mark);
- if (result < 0)
- goto martian_source;
- if (result)
+ if (err < 0)
+ goto martian_source_keep_err;
+ if (err)
flags |= RTCF_DIRECTSRC;
spec_dst = daddr;
goto local_input;
err = ip_mkroute_input(skb, &res, &fl, in_dev, daddr, saddr, tos);
done:
- in_dev_put(in_dev);
if (free_res)
fib_res_put(&res);
out: return err;
err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
&itag, skb->mark);
if (err < 0)
- goto martian_source;
+ goto martian_source_keep_err;
if (err)
flags |= RTCF_DIRECTSRC;
}
if (!rth)
goto e_nobufs;
- rth->u.dst.output= ip_rt_bug;
- rth->u.dst.obsolete = -1;
+ rth->dst.output= ip_rt_bug;
+ rth->dst.obsolete = -1;
rth->rt_genid = rt_genid(net);
- atomic_set(&rth->u.dst.__refcnt, 1);
- rth->u.dst.flags= DST_HOST;
+ atomic_set(&rth->dst.__refcnt, 1);
+ rth->dst.flags= DST_HOST;
if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->u.dst.flags |= DST_NOPOLICY;
+ rth->dst.flags |= DST_NOPOLICY;
rth->fl.fl4_dst = daddr;
rth->rt_dst = daddr;
rth->fl.fl4_tos = tos;
rth->fl.fl4_src = saddr;
rth->rt_src = saddr;
#ifdef CONFIG_NET_CLS_ROUTE
- rth->u.dst.tclassid = itag;
+ rth->dst.tclassid = itag;
#endif
rth->rt_iif =
rth->fl.iif = dev->ifindex;
- rth->u.dst.dev = net->loopback_dev;
- dev_hold(rth->u.dst.dev);
- rth->idev = in_dev_get(rth->u.dst.dev);
+ rth->dst.dev = net->loopback_dev;
+ dev_hold(rth->dst.dev);
+ rth->idev = in_dev_get(rth->dst.dev);
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
- rth->u.dst.input= ip_local_deliver;
+ rth->dst.input= ip_local_deliver;
rth->rt_flags = flags|RTCF_LOCAL;
if (res.type == RTN_UNREACHABLE) {
- rth->u.dst.input= ip_error;
- rth->u.dst.error= -err;
+ rth->dst.input= ip_error;
+ rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
rth->rt_type = res.type;
goto done;
martian_source:
+ err = -EINVAL;
+martian_source_keep_err:
ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
- goto e_inval;
+ goto done;
}
-int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
- u8 tos, struct net_device *dev)
+int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+ u8 tos, struct net_device *dev, bool noref)
{
struct rtable * rth;
unsigned hash;
int iif = dev->ifindex;
struct net *net;
+ int res;
net = dev_net(dev);
+ rcu_read_lock();
+
if (!rt_caching(net))
goto skip_cache;
tos &= IPTOS_RT_MASK;
hash = rt_hash(daddr, saddr, iif, rt_genid(net));
- rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->u.dst.rt_next)) {
- if (((rth->fl.fl4_dst ^ daddr) |
- (rth->fl.fl4_src ^ saddr) |
+ 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 &&
- net_eq(dev_net(rth->u.dst.dev), net) &&
+ net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
- dst_use(&rth->u.dst, jiffies);
+ if (noref) {
+ dst_use_noref(&rth->dst, jiffies);
+ skb_dst_set_noref(skb, &rth->dst);
+ } else {
+ dst_use(&rth->dst, jiffies);
+ skb_dst_set(skb, &rth->dst);
+ }
RT_CACHE_STAT_INC(in_hit);
rcu_read_unlock();
- skb_dst_set(skb, &rth->u.dst);
return 0;
}
RT_CACHE_STAT_INC(in_hlist_search);
}
- rcu_read_unlock();
skip_cache:
/* Multicast recognition logic is moved from route cache to here.
route cache entry is created eventually.
*/
if (ipv4_is_multicast(daddr)) {
- struct in_device *in_dev;
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
- rcu_read_lock();
- if ((in_dev = __in_dev_get_rcu(dev)) != NULL) {
+ if (in_dev) {
int our = ip_check_mc(in_dev, daddr, saddr,
- ip_hdr(skb)->protocol);
+ ip_hdr(skb)->protocol);
if (our
#ifdef CONFIG_IP_MROUTE
||
IN_DEV_MFORWARD(in_dev))
#endif
) {
+ int res = ip_route_input_mc(skb, daddr, saddr,
+ tos, dev, our);
rcu_read_unlock();
- return ip_route_input_mc(skb, daddr, saddr,
- tos, dev, our);
+ return res;
}
}
rcu_read_unlock();
return -EINVAL;
}
- return ip_route_input_slow(skb, daddr, saddr, tos, dev);
+ res = ip_route_input_slow(skb, daddr, saddr, tos, dev);
+ rcu_read_unlock();
+ return res;
}
+EXPORT_SYMBOL(ip_route_input_common);
static int __mkroute_output(struct rtable **result,
struct fib_result *res,
goto cleanup;
}
- atomic_set(&rth->u.dst.__refcnt, 1);
- rth->u.dst.flags= DST_HOST;
+ atomic_set(&rth->dst.__refcnt, 1);
+ rth->dst.flags= DST_HOST;
if (IN_DEV_CONF_GET(in_dev, NOXFRM))
- rth->u.dst.flags |= DST_NOXFRM;
+ rth->dst.flags |= DST_NOXFRM;
if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->u.dst.flags |= DST_NOPOLICY;
+ rth->dst.flags |= DST_NOPOLICY;
rth->fl.fl4_dst = oldflp->fl4_dst;
rth->fl.fl4_tos = tos;
rth->rt_iif = oldflp->oif ? : dev_out->ifindex;
/* get references to the devices that are to be hold by the routing
cache entry */
- rth->u.dst.dev = dev_out;
+ rth->dst.dev = dev_out;
dev_hold(dev_out);
rth->idev = in_dev_get(dev_out);
rth->rt_gateway = fl->fl4_dst;
rth->rt_spec_dst= fl->fl4_src;
- rth->u.dst.output=ip_output;
- rth->u.dst.obsolete = -1;
+ 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);
if (flags & RTCF_LOCAL) {
- rth->u.dst.input = ip_local_deliver;
+ rth->dst.input = ip_local_deliver;
rth->rt_spec_dst = fl->fl4_dst;
}
if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
rth->rt_spec_dst = fl->fl4_src;
if (flags & RTCF_LOCAL &&
!(dev_out->flags & IFF_LOOPBACK)) {
- rth->u.dst.output = ip_mc_output;
+ rth->dst.output = ip_mc_output;
RT_CACHE_STAT_INC(out_slow_mc);
}
#ifdef CONFIG_IP_MROUTE
if (res->type == RTN_MULTICAST) {
if (IN_DEV_MFORWARD(in_dev) &&
!ipv4_is_local_multicast(oldflp->fl4_dst)) {
- rth->u.dst.input = ip_mr_input;
- rth->u.dst.output = ip_mc_output;
+ rth->dst.input = ip_mr_input;
+ rth->dst.output = ip_mc_output;
}
}
#endif
rcu_read_lock_bh();
for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference_bh(rth->u.dst.rt_next)) {
+ rth = rcu_dereference_bh(rth->dst.rt_next)) {
if (rth->fl.fl4_dst == flp->fl4_dst &&
rth->fl.fl4_src == flp->fl4_src &&
rth->fl.iif == 0 &&
rth->fl.mark == flp->mark &&
!((rth->fl.fl4_tos ^ flp->fl4_tos) &
(IPTOS_RT_MASK | RTO_ONLINK)) &&
- net_eq(dev_net(rth->u.dst.dev), net) &&
+ net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
- dst_use(&rth->u.dst, jiffies);
+ dst_use(&rth->dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
*rp = rth;
slow_output:
return ip_route_output_slow(net, rp, flp);
}
-
EXPORT_SYMBOL_GPL(__ip_route_output_key);
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
dst_alloc(&ipv4_dst_blackhole_ops);
if (rt) {
- struct dst_entry *new = &rt->u.dst;
+ struct dst_entry *new = &rt->dst;
atomic_set(&new->__refcnt, 1);
new->__use = 1;
new->input = dst_discard;
new->output = dst_discard;
- memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));
+ memcpy(new->metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32));
- new->dev = ort->u.dst.dev;
+ new->dev = ort->dst.dev;
if (new->dev)
dev_hold(new->dev);
dst_free(new);
}
- dst_release(&(*rp)->u.dst);
+ dst_release(&(*rp)->dst);
*rp = rt;
return (rt ? 0 : -ENOMEM);
}
return 0;
}
-
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,
r->rtm_src_len = 32;
NLA_PUT_BE32(skb, RTA_SRC, rt->fl.fl4_src);
}
- if (rt->u.dst.dev)
- NLA_PUT_U32(skb, RTA_OIF, rt->u.dst.dev->ifindex);
+ if (rt->dst.dev)
+ NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
#ifdef CONFIG_NET_CLS_ROUTE
- if (rt->u.dst.tclassid)
- NLA_PUT_U32(skb, RTA_FLOW, rt->u.dst.tclassid);
+ if (rt->dst.tclassid)
+ NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid);
#endif
if (rt->fl.iif)
NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst);
if (rt->rt_dst != rt->rt_gateway)
NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway);
- if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0)
+ if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0)
goto nla_put_failure;
- error = rt->u.dst.error;
- expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0;
+ if (rt->fl.mark)
+ NLA_PUT_BE32(skb, RTA_MARK, rt->fl.mark);
+
+ error = rt->dst.error;
+ expires = rt->dst.expires ? rt->dst.expires - jiffies : 0;
if (rt->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;
NLA_PUT_U32(skb, RTA_IIF, rt->fl.iif);
}
- if (rtnl_put_cacheinfo(skb, &rt->u.dst, id, ts, tsage,
+ if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage,
expires, error) < 0)
goto nla_put_failure;
__be32 src = 0;
u32 iif;
int err;
+ int mark;
struct sk_buff *skb;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
src = tb[RTA_SRC] ? nla_get_be32(tb[RTA_SRC]) : 0;
dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
+ mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
if (iif) {
struct net_device *dev;
skb->protocol = htons(ETH_P_IP);
skb->dev = dev;
+ skb->mark = mark;
local_bh_disable();
err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
local_bh_enable();
rt = skb_rtable(skb);
- if (err == 0 && rt->u.dst.error)
- err = -rt->u.dst.error;
+ if (err == 0 && rt->dst.error)
+ err = -rt->dst.error;
} else {
struct flowi fl = {
.nl_u = {
},
},
.oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
+ .mark = mark,
};
err = ip_route_output_key(net, &rt, &fl);
}
if (err)
goto errout_free;
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
continue;
rcu_read_lock_bh();
for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt;
- rt = rcu_dereference_bh(rt->u.dst.rt_next), idx++) {
- if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx)
+ rt = rcu_dereference_bh(rt->dst.rt_next), idx++) {
+ if (!net_eq(dev_net(rt->dst.dev), net) || idx < s_idx)
continue;
if (rt_is_expired(rt))
continue;
- skb_dst_set(skb, dst_clone(&rt->u.dst));
+ skb_dst_set_noref(skb, &rt->dst);
if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, RTM_NEWROUTE,
1, NLM_F_MULTI) <= 0) {
return -EINVAL;
}
-static void rt_secret_reschedule(int old)
-{
- struct net *net;
- int new = ip_rt_secret_interval;
- int diff = new - old;
-
- if (!diff)
- return;
-
- rtnl_lock();
- for_each_net(net) {
- int deleted = del_timer_sync(&net->ipv4.rt_secret_timer);
- long time;
-
- if (!new)
- continue;
-
- if (deleted) {
- time = net->ipv4.rt_secret_timer.expires - jiffies;
-
- if (time <= 0 || (time += diff) <= 0)
- time = 0;
- } else
- time = new;
-
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + time);
- }
- rtnl_unlock();
-}
-
-static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
-{
- int old = ip_rt_secret_interval;
- int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
-
- rt_secret_reschedule(old);
-
- return ret;
-}
-
static ctl_table ipv4_route_table[] = {
{
.procname = "gc_thresh",
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "secret_interval",
- .data = &ip_rt_secret_interval,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = ipv4_sysctl_rt_secret_interval,
- },
{ }
};
};
#endif
-
-static __net_init int rt_secret_timer_init(struct net *net)
+static __net_init int rt_genid_init(struct net *net)
{
- atomic_set(&net->ipv4.rt_genid,
- (int) ((num_physpages ^ (num_physpages>>8)) ^
- (jiffies ^ (jiffies >> 7))));
-
- net->ipv4.rt_secret_timer.function = rt_secret_rebuild;
- net->ipv4.rt_secret_timer.data = (unsigned long)net;
- init_timer_deferrable(&net->ipv4.rt_secret_timer);
-
- if (ip_rt_secret_interval) {
- net->ipv4.rt_secret_timer.expires =
- jiffies + net_random() % ip_rt_secret_interval +
- ip_rt_secret_interval;
- add_timer(&net->ipv4.rt_secret_timer);
- }
+ get_random_bytes(&net->ipv4.rt_genid,
+ sizeof(net->ipv4.rt_genid));
return 0;
}
-static __net_exit void rt_secret_timer_exit(struct net *net)
-{
- del_timer_sync(&net->ipv4.rt_secret_timer);
-}
-
-static __net_initdata struct pernet_operations rt_secret_timer_ops = {
- .init = rt_secret_timer_init,
- .exit = rt_secret_timer_exit,
+static __net_initdata struct pernet_operations rt_genid_ops = {
+ .init = rt_genid_init,
};
schedule_delayed_work(&expires_work,
net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
- if (register_pernet_subsys(&rt_secret_timer_ops))
- printk(KERN_ERR "Unable to setup rt_secret_timer\n");
-
if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&sysctl_route_ops);
#endif
+ register_pernet_subsys(&rt_genid_ops);
return rc;
}
register_sysctl_paths(ipv4_path, ipv4_skeleton);
}
#endif
-
-EXPORT_SYMBOL(__ip_select_ident);
-EXPORT_SYMBOL(ip_route_input);
-EXPORT_SYMBOL(ip_route_output_key);
git://bbs.cooldavid.org / net-next-2.6.git / blobdiff