#include <linux/jhash.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
+#include <linux/slab.h>
#include <net/dst.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
static int rt_garbage_collect(struct dst_ops *ops);
-static void rt_emergency_hash_rebuild(struct net *net);
static struct dst_ops ipv4_dst_ops = {
if (!rt_hash_table[st->bucket].chain)
continue;
rcu_read_lock_bh();
- r = rcu_dereference(rt_hash_table[st->bucket].chain);
+ r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
while (r) {
if (dev_net(r->u.dst.dev) == seq_file_net(seq) &&
r->rt_genid == st->genid)
return r;
- r = rcu_dereference(r->u.dst.rt_next);
+ r = rcu_dereference_bh(r->u.dst.rt_next);
}
rcu_read_unlock_bh();
}
rcu_read_lock_bh();
r = rt_hash_table[st->bucket].chain;
}
- return rcu_dereference(r);
+ return rcu_dereference_bh(r);
}
static struct rtable *rt_cache_get_next(struct seq_file *seq,
};
#ifdef CONFIG_NET_CLS_ROUTE
-static int ip_rt_acct_read(char *buffer, char **start, off_t offset,
- int length, int *eof, void *data)
-{
- unsigned int i;
-
- if ((offset & 3) || (length & 3))
- return -EIO;
-
- if (offset >= sizeof(struct ip_rt_acct) * 256) {
- *eof = 1;
- return 0;
- }
-
- if (offset + length >= sizeof(struct ip_rt_acct) * 256) {
- length = sizeof(struct ip_rt_acct) * 256 - offset;
- *eof = 1;
+static int rt_acct_proc_show(struct seq_file *m, void *v)
+{
+ struct ip_rt_acct *dst, *src;
+ unsigned int i, j;
+
+ dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL);
+ if (!dst)
+ return -ENOMEM;
+
+ for_each_possible_cpu(i) {
+ src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i);
+ for (j = 0; j < 256; j++) {
+ dst[j].o_bytes += src[j].o_bytes;
+ dst[j].o_packets += src[j].o_packets;
+ dst[j].i_bytes += src[j].i_bytes;
+ dst[j].i_packets += src[j].i_packets;
+ }
}
- offset /= sizeof(u32);
-
- if (length > 0) {
- u32 *dst = (u32 *) buffer;
-
- *start = buffer;
- memset(dst, 0, length);
-
- for_each_possible_cpu(i) {
- unsigned int j;
- u32 *src;
+ seq_write(m, dst, 256 * sizeof(struct ip_rt_acct));
+ kfree(dst);
+ return 0;
+}
- src = ((u32 *) per_cpu_ptr(ip_rt_acct, i)) + offset;
- for (j = 0; j < length/4; j++)
- dst[j] += src[j];
- }
- }
- return length;
+static int rt_acct_proc_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, rt_acct_proc_show, NULL);
}
+
+static const struct file_operations rt_acct_proc_fops = {
+ .owner = THIS_MODULE,
+ .open = rt_acct_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
#endif
static int __net_init ip_rt_do_proc_init(struct net *net)
goto err2;
#ifdef CONFIG_NET_CLS_ROUTE
- pde = create_proc_read_entry("rt_acct", 0, net->proc_net,
- ip_rt_acct_read, NULL);
+ pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
if (!pde)
goto err3;
#endif
{
remove_proc_entry("rt_cache", net->proc_net_stat);
remove_proc_entry("rt_cache", net->proc_net);
+#ifdef CONFIG_NET_CLS_ROUTE
remove_proc_entry("rt_acct", net->proc_net);
+#endif
}
static struct pernet_operations ip_rt_proc_ops __net_initdata = {
static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
{
- return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev);
+ return net_eq(dev_net(rt1->u.dst.dev), dev_net(rt2->u.dst.dev));
}
static inline int rt_is_expired(struct rtable *rth)
#define FRACT_BITS 3
#define ONE (1UL << FRACT_BITS)
+/*
+ * Given a hash chain and an item in this hash chain,
+ * find if a previous entry has the same hash_inputs
+ * (but differs on tos, mark or oif)
+ * Returns 0 if an alias is found.
+ * Returns ONE if rth has no alias before itself.
+ */
+static int has_noalias(const struct rtable *head, const struct rtable *rth)
+{
+ const struct rtable *aux = head;
+
+ while (aux != rth) {
+ if (compare_hash_inputs(&aux->fl, &rth->fl))
+ return 0;
+ aux = aux->u.dst.rt_next;
+ }
+ return ONE;
+}
+
static void rt_check_expire(void)
{
static unsigned int rover;
unsigned int i = rover, goal;
- struct rtable *rth, *aux, **rthp;
+ struct rtable *rth, **rthp;
unsigned long samples = 0;
unsigned long sum = 0, sum2 = 0;
unsigned long delta;
* attributes don't unfairly skew
* the length computation
*/
- for (aux = rt_hash_table[i].chain;;) {
- if (aux == rth) {
- length += ONE;
- break;
- }
- if (compare_hash_inputs(&aux->fl, &rth->fl))
- break;
- aux = aux->u.dst.rt_next;
- }
+ length += has_noalias(rt_hash_table[i].chain, rth);
continue;
}
} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
rt_do_flush(!in_softirq());
}
+/* Flush previous cache invalidated entries from the cache */
+void rt_cache_flush_batch(void)
+{
+ rt_do_flush(!in_softirq());
+}
+
/*
* We change rt_genid and let gc do the cleanup
*/
{
del_timer_sync(&net->ipv4.rt_secret_timer);
rt_cache_invalidate(net);
- if (ip_rt_secret_interval) {
- net->ipv4.rt_secret_timer.expires += ip_rt_secret_interval;
- add_timer(&net->ipv4.rt_secret_timer);
- }
+ 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)
out: return 0;
}
+/*
+ * Returns number of entries in a hash chain that have different hash_inputs
+ */
+static int slow_chain_length(const struct rtable *head)
+{
+ int length = 0;
+ const struct rtable *rth = head;
+
+ while (rth) {
+ length += has_noalias(head, rth);
+ rth = rth->u.dst.rt_next;
+ }
+ return length >> FRACT_BITS;
+}
+
static int rt_intern_hash(unsigned hash, struct rtable *rt,
- struct rtable **rp, struct sk_buff *skb)
+ struct rtable **rp, struct sk_buff *skb, int ifindex)
{
struct rtable *rth, **rthp;
unsigned long now;
rt_free(cand);
}
} else {
- if (chain_length > rt_chain_length_max) {
+ 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);
int num = ++net->ipv4.current_rt_cache_rebuild_count;
- if (!rt_caching(dev_net(rt->u.dst.dev))) {
+ if (!rt_caching(net)) {
printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
rt->u.dst.dev->name, num);
}
- rt_emergency_hash_rebuild(dev_net(rt->u.dst.dev));
+ rt_emergency_hash_rebuild(net);
+ spin_unlock_bh(rt_hash_lock_addr(hash));
+
+ hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
+ ifindex, rt_genid(net));
+ goto restart;
}
}
return;
net = dev_net(dev);
- if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev)
- || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw)
- || ipv4_is_zeronet(new_gw))
+ if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) ||
+ ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) ||
+ ipv4_is_zeronet(new_gw))
goto reject_redirect;
if (!rt_caching(net))
dev_hold(rt->u.dst.dev);
if (rt->idev)
in_dev_hold(rt->idev);
- rt->u.dst.obsolete = 0;
+ rt->u.dst.obsolete = -1;
rt->u.dst.lastuse = jiffies;
rt->u.dst.path = &rt->u.dst;
rt->u.dst.neighbour = NULL;
&netevent);
rt_del(hash, rth);
- if (!rt_intern_hash(hash, rt, &rt, NULL))
+ if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif))
ip_rt_put(rt);
goto do_next;
}
struct dst_entry *ret = dst;
if (rt) {
- if (dst->obsolete) {
+ if (dst->obsolete > 0) {
ip_rt_put(rt);
ret = NULL;
} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
- rt->u.dst.expires) {
+ (rt->u.dst.expires &&
+ time_after_eq(jiffies, rt->u.dst.expires))) {
unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
rt->fl.oif,
rt_genid(dev_net(dst->dev)));
__be32 daddr = iph->daddr;
unsigned short est_mtu = 0;
- if (ipv4_config.no_pmtu_disc)
- return 0;
-
for (k = 0; k < 2; k++) {
for (i = 0; i < 2; i++) {
unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
{
- return NULL;
+ if (rt_is_expired((struct rtable *)dst))
+ return NULL;
+ return dst;
}
static void ipv4_dst_destroy(struct dst_entry *dst)
if (!rth)
goto e_nobufs;
- rth->u.dst.output= ip_rt_bug;
+ rth->u.dst.output = ip_rt_bug;
+ rth->u.dst.obsolete = -1;
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
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);
+ return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex);
e_nobufs:
in_dev_put(in_dev);
if (skb->protocol != htons(ETH_P_IP)) {
/* Not IP (i.e. ARP). Do not create route, if it is
* invalid for proxy arp. DNAT routes are always valid.
+ *
+ * Proxy arp feature have been extended to allow, ARP
+ * replies back to the same interface, to support
+ * Private VLAN switch technologies. See arp.c.
*/
- if (out_dev == in_dev) {
+ if (out_dev == in_dev &&
+ IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) {
err = -EINVAL;
goto cleanup;
}
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));
/* put it into the cache */
hash = rt_hash(daddr, saddr, fl->iif,
rt_genid(dev_net(rth->u.dst.dev)));
- return rt_intern_hash(hash, rth, NULL, skb);
+ return rt_intern_hash(hash, rth, NULL, skb, fl->iif);
}
/*
goto e_nobufs;
rth->u.dst.output= ip_rt_bug;
+ rth->u.dst.obsolete = -1;
rth->rt_genid = rt_genid(net);
atomic_set(&rth->u.dst.__refcnt, 1);
}
rth->rt_type = res.type;
hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
- err = rt_intern_hash(hash, rth, NULL, skb);
+ err = rt_intern_hash(hash, rth, NULL, skb, fl.iif);
goto done;
no_route:
ip_hdr(skb)->protocol);
if (our
#ifdef CONFIG_IP_MROUTE
- || (!ipv4_is_local_multicast(daddr) &&
- IN_DEV_MFORWARD(in_dev))
+ ||
+ (!ipv4_is_local_multicast(daddr) &&
+ IN_DEV_MFORWARD(in_dev))
#endif
- ) {
+ ) {
rcu_read_unlock();
return ip_route_input_mc(skb, daddr, saddr,
tos, dev, our);
rth->rt_spec_dst= fl->fl4_src;
rth->u.dst.output=ip_output;
+ rth->u.dst.obsolete = -1;
rth->rt_genid = rt_genid(dev_net(dev_out));
RT_CACHE_STAT_INC(out_slow_tot);
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);
+ err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif);
}
return err;
of another iface. --ANK
*/
- if (oldflp->oif == 0
- && (ipv4_is_multicast(oldflp->fl4_dst) ||
- oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
+ if (oldflp->oif == 0 &&
+ (ipv4_is_multicast(oldflp->fl4_dst) ||
+ oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
dev_out = ip_dev_find(net, oldflp->fl4_src);
if (dev_out == NULL)
hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net));
rcu_read_lock_bh();
- for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->u.dst.rt_next)) {
+ for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
+ rth = rcu_dereference_bh(rth->u.dst.rt_next)) {
if (rth->fl.fl4_dst == flp->fl4_dst &&
rth->fl.fl4_src == flp->fl4_src &&
rth->fl.iif == 0 &&
error = rt->u.dst.error;
expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0;
if (rt->peer) {
- id = rt->peer->ip_id_count;
+ 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;
if (!rt_hash_table[h].chain)
continue;
rcu_read_lock_bh();
- for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt;
- rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
+ 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)
continue;
if (rt_is_expired(rt))
rtnl_lock();
for_each_net(net) {
int deleted = del_timer_sync(&net->ipv4.rt_secret_timer);
+ long time;
if (!new)
continue;
if (deleted) {
- long time = net->ipv4.rt_secret_timer.expires - jiffies;
+ time = net->ipv4.rt_secret_timer.expires - jiffies;
if (time <= 0 || (time += diff) <= 0)
time = 0;
-
- net->ipv4.rt_secret_timer.expires = time;
} else
- net->ipv4.rt_secret_timer.expires = new;
+ time = new;
- net->ipv4.rt_secret_timer.expires += jiffies;
- add_timer(&net->ipv4.rt_secret_timer);
+ mod_timer(&net->ipv4.rt_secret_timer, jiffies + time);
}
rtnl_unlock();
}
struct ctl_table *tbl;
tbl = ipv4_route_flush_table;
- if (net != &init_net) {
+ if (!net_eq(net, &init_net)) {
tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL);
if (tbl == NULL)
goto err_dup;
#ifdef CONFIG_NET_CLS_ROUTE
-struct ip_rt_acct *ip_rt_acct __read_mostly;
+struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
#endif /* CONFIG_NET_CLS_ROUTE */
static __initdata unsigned long rhash_entries;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff