#define RT_GC_TIMEOUT (300*HZ)
-static int ip_rt_min_delay = 2 * HZ;
-static int ip_rt_max_delay = 10 * HZ;
static int ip_rt_max_size;
-static int ip_rt_gc_timeout = RT_GC_TIMEOUT;
-static int ip_rt_gc_interval = 60 * HZ;
-static int ip_rt_gc_min_interval = HZ / 2;
-static int ip_rt_redirect_number = 9;
-static int ip_rt_redirect_load = HZ / 50;
-static int ip_rt_redirect_silence = ((HZ / 50) << (9 + 1));
-static int ip_rt_error_cost = HZ;
-static int ip_rt_error_burst = 5 * HZ;
-static int ip_rt_gc_elasticity = 8;
-static int ip_rt_mtu_expires = 10 * 60 * HZ;
-static int ip_rt_min_pmtu = 512 + 20 + 20;
-static int ip_rt_min_advmss = 256;
-static int ip_rt_secret_interval = 10 * 60 * HZ;
-static int ip_rt_flush_expected;
-static unsigned long rt_deadline;
-
-#define RTprint(a...) printk(KERN_DEBUG a)
-
-static struct timer_list rt_flush_timer;
+static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
+static int ip_rt_gc_interval __read_mostly = 60 * HZ;
+static int ip_rt_gc_min_interval __read_mostly = HZ / 2;
+static int ip_rt_redirect_number __read_mostly = 9;
+static int ip_rt_redirect_load __read_mostly = HZ / 50;
+static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1));
+static int ip_rt_error_cost __read_mostly = HZ;
+static int ip_rt_error_burst __read_mostly = 5 * HZ;
+static int ip_rt_gc_elasticity __read_mostly = 8;
+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 void rt_worker_func(struct work_struct *work);
static DECLARE_DELAYED_WORK(expires_work, rt_worker_func);
static struct timer_list rt_secret_timer;
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
-static int rt_garbage_collect(void);
+static int rt_garbage_collect(struct dst_ops *ops);
static struct dst_ops ipv4_dst_ops = {
.update_pmtu = ip_rt_update_pmtu,
.local_out = ip_local_out,
.entry_size = sizeof(struct rtable),
+ .entries = ATOMIC_INIT(0),
};
#define ECN_OR_COST(class) TC_PRIO_##class
}
#endif
-static struct rt_hash_bucket *rt_hash_table;
-static unsigned rt_hash_mask;
-static unsigned int rt_hash_log;
-static unsigned int rt_hash_rnd;
+static struct rt_hash_bucket *rt_hash_table __read_mostly;
+static unsigned rt_hash_mask __read_mostly;
+static unsigned int rt_hash_log __read_mostly;
+static atomic_t rt_genid __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++)
-static int rt_intern_hash(unsigned hash, struct rtable *rth,
- struct rtable **res);
-
static unsigned int rt_hash_code(u32 daddr, u32 saddr)
{
- return (jhash_2words(daddr, saddr, rt_hash_rnd)
- & rt_hash_mask);
+ return jhash_2words(daddr, saddr, atomic_read(&rt_genid))
+ & rt_hash_mask;
}
#define rt_hash(daddr, saddr, idx) \
#ifdef CONFIG_PROC_FS
struct rt_cache_iter_state {
+ struct seq_net_private p;
int bucket;
+ int genid;
};
static struct rtable *rt_cache_get_first(struct seq_file *seq)
{
- struct rtable *r = NULL;
struct rt_cache_iter_state *st = seq->private;
+ struct rtable *r = NULL;
for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
rcu_read_lock_bh();
- r = rt_hash_table[st->bucket].chain;
- if (r)
- break;
+ r = rcu_dereference(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);
+ }
rcu_read_unlock_bh();
}
- return rcu_dereference(r);
+ return r;
}
-static struct rtable *rt_cache_get_next(struct seq_file *seq, struct rtable *r)
+static struct rtable *__rt_cache_get_next(struct seq_file *seq,
+ struct rtable *r)
{
struct rt_cache_iter_state *st = seq->private;
-
r = r->u.dst.rt_next;
while (!r) {
rcu_read_unlock_bh();
return rcu_dereference(r);
}
+static struct rtable *rt_cache_get_next(struct seq_file *seq,
+ struct rtable *r)
+{
+ 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))
+ continue;
+ if (r->rt_genid == st->genid)
+ break;
+ }
+ return r;
+}
+
static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
{
struct rtable *r = rt_cache_get_first(seq);
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
- return *pos ? rt_cache_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
+ struct rt_cache_iter_state *st = seq->private;
+ if (*pos)
+ return rt_cache_get_idx(seq, *pos - 1);
+ st->genid = atomic_read(&rt_genid);
+ return SEQ_START_TOKEN;
}
static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct rtable *r = NULL;
+ struct rtable *r;
if (v == SEQ_START_TOKEN)
r = rt_cache_get_first(seq);
static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
- return seq_open_private(file, &rt_cache_seq_ops,
+ return seq_open_net(inode, file, &rt_cache_seq_ops,
sizeof(struct rt_cache_iter_state));
}
.open = rt_cache_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = seq_release_net,
};
}
#endif
-static __init int ip_rt_proc_init(struct net *net)
+static int __net_init ip_rt_do_proc_init(struct net *net)
{
struct proc_dir_entry *pde;
if (!pde)
goto err1;
- pde = create_proc_entry("rt_cache", S_IRUGO, net->proc_net_stat);
+ pde = proc_create("rt_cache", S_IRUGO,
+ net->proc_net_stat, &rt_cpu_seq_fops);
if (!pde)
goto err2;
- pde->proc_fops = &rt_cpu_seq_fops;
-
#ifdef CONFIG_NET_CLS_ROUTE
pde = create_proc_read_entry("rt_acct", 0, net->proc_net,
ip_rt_acct_read, NULL);
err1:
return -ENOMEM;
}
+
+static void __net_exit ip_rt_do_proc_exit(struct net *net)
+{
+ remove_proc_entry("rt_cache", net->proc_net_stat);
+ remove_proc_entry("rt_cache", net->proc_net);
+ remove_proc_entry("rt_acct", net->proc_net);
+}
+
+static struct pernet_operations ip_rt_proc_ops __net_initdata = {
+ .init = ip_rt_do_proc_init,
+ .exit = ip_rt_do_proc_exit,
+};
+
+static int __init ip_rt_proc_init(void)
+{
+ return register_pernet_subsys(&ip_rt_proc_ops);
+}
+
#else
-static inline int ip_rt_proc_init(struct net *net)
+static inline int ip_rt_proc_init(void)
{
return 0;
}
(fl1->iif ^ fl2->iif)) == 0;
}
+static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
+{
+ return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev);
+}
+
/*
* Perform a full scan of hash table and free all entries.
* Can be called by a softirq or a process.
continue;
spin_lock_bh(rt_hash_lock_addr(i));
while ((rth = *rthp) != NULL) {
+ if (rth->rt_genid != atomic_read(&rt_genid)) {
+ *rthp = rth->u.dst.rt_next;
+ rt_free(rth);
+ continue;
+ }
if (rth->u.dst.expires) {
/* Entry is expired even if it is in use */
if (time_before_eq(jiffies, rth->u.dst.expires)) {
/*
* rt_worker_func() is run in process context.
- * If a whole flush was scheduled, it is done.
- * Else, we call rt_check_expire() to scan part of the hash table
+ * we call rt_check_expire() to scan part of the hash table
*/
static void rt_worker_func(struct work_struct *work)
{
- if (ip_rt_flush_expected) {
- ip_rt_flush_expected = 0;
- rt_do_flush(1);
- } else
- rt_check_expire();
+ rt_check_expire();
schedule_delayed_work(&expires_work, ip_rt_gc_interval);
}
-/* This can run from both BH and non-BH contexts, the latter
- * in the case of a forced flush event.
+/*
+ * Pertubation of rt_genid by a small quantity [1..256]
+ * Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
+ * many times (2^24) without giving recent rt_genid.
+ * Jenkins hash is strong enough that litle changes of rt_genid are OK.
*/
-static void rt_run_flush(unsigned long process_context)
+static void rt_cache_invalidate(void)
{
- rt_deadline = 0;
-
- get_random_bytes(&rt_hash_rnd, 4);
+ unsigned char shuffle;
- rt_do_flush(process_context);
+ get_random_bytes(&shuffle, sizeof(shuffle));
+ atomic_add(shuffle + 1U, &rt_genid);
}
-static DEFINE_SPINLOCK(rt_flush_lock);
-
+/*
+ * delay < 0 : invalidate cache (fast : entries will be deleted later)
+ * delay >= 0 : invalidate & flush cache (can be long)
+ */
void rt_cache_flush(int delay)
{
- unsigned long now = jiffies;
- int user_mode = !in_softirq();
-
- if (delay < 0)
- delay = ip_rt_min_delay;
-
- spin_lock_bh(&rt_flush_lock);
-
- if (del_timer(&rt_flush_timer) && delay > 0 && rt_deadline) {
- long tmo = (long)(rt_deadline - now);
-
- /* If flush timer is already running
- and flush request is not immediate (delay > 0):
-
- if deadline is not achieved, prolongate timer to "delay",
- otherwise fire it at deadline time.
- */
-
- if (user_mode && tmo < ip_rt_max_delay-ip_rt_min_delay)
- tmo = 0;
-
- if (delay > tmo)
- delay = tmo;
- }
-
- if (delay <= 0) {
- spin_unlock_bh(&rt_flush_lock);
- rt_run_flush(user_mode);
- return;
- }
-
- if (rt_deadline == 0)
- rt_deadline = now + ip_rt_max_delay;
-
- mod_timer(&rt_flush_timer, now+delay);
- spin_unlock_bh(&rt_flush_lock);
+ rt_cache_invalidate();
+ if (delay >= 0)
+ rt_do_flush(!in_softirq());
}
/*
- * We change rt_hash_rnd and ask next rt_worker_func() invocation
- * to perform a flush in process context
+ * We change rt_genid and let gc do the cleanup
*/
static void rt_secret_rebuild(unsigned long dummy)
{
- get_random_bytes(&rt_hash_rnd, 4);
- ip_rt_flush_expected = 1;
- cancel_delayed_work(&expires_work);
- schedule_delayed_work(&expires_work, HZ/10);
+ rt_cache_invalidate();
mod_timer(&rt_secret_timer, jiffies + ip_rt_secret_interval);
}
and when load increases it reduces to limit cache size.
*/
-static int rt_garbage_collect(void)
+static int rt_garbage_collect(struct dst_ops *ops)
{
static unsigned long expire = RT_GC_TIMEOUT;
static unsigned long last_gc;
equilibrium = ipv4_dst_ops.gc_thresh;
goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
if (goal > 0) {
- equilibrium += min_t(unsigned int, goal / 2, rt_hash_mask + 1);
+ equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1);
goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
}
} else {
/* We are in dangerous area. Try to reduce cache really
* aggressively.
*/
- goal = max_t(unsigned int, goal / 2, rt_hash_mask + 1);
+ goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1);
equilibrium = atomic_read(&ipv4_dst_ops.entries) - goal;
}
rthp = &rt_hash_table[k].chain;
spin_lock_bh(rt_hash_lock_addr(k));
while ((rth = *rthp) != NULL) {
- if (!rt_may_expire(rth, tmo, expire)) {
+ if (rth->rt_genid == atomic_read(&rt_genid) &&
+ !rt_may_expire(rth, tmo, expire)) {
tmo >>= 1;
rthp = &rth->u.dst.rt_next;
continue;
spin_lock_bh(rt_hash_lock_addr(hash));
while ((rth = *rthp) != NULL) {
- if (compare_keys(&rth->fl, &rt->fl)) {
+ if (rth->rt_genid != atomic_read(&rt_genid)) {
+ *rthp = rth->u.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;
/*
int saved_int = ip_rt_gc_min_interval;
ip_rt_gc_elasticity = 1;
ip_rt_gc_min_interval = 0;
- rt_garbage_collect();
+ rt_garbage_collect(&ipv4_dst_ops);
ip_rt_gc_min_interval = saved_int;
ip_rt_gc_elasticity = saved_elasticity;
goto restart;
static void rt_del(unsigned hash, struct rtable *rt)
{
- struct rtable **rthp;
+ struct rtable **rthp, *aux;
+ rthp = &rt_hash_table[hash].chain;
spin_lock_bh(rt_hash_lock_addr(hash));
ip_rt_put(rt);
- for (rthp = &rt_hash_table[hash].chain; *rthp;
- rthp = &(*rthp)->u.dst.rt_next)
- if (*rthp == rt) {
- *rthp = rt->u.dst.rt_next;
- rt_free(rt);
- break;
+ while ((aux = *rthp) != NULL) {
+ if (aux == rt || (aux->rt_genid != atomic_read(&rt_genid))) {
+ *rthp = aux->u.dst.rt_next;
+ rt_free(aux);
+ continue;
}
+ rthp = &aux->u.dst.rt_next;
+ }
spin_unlock_bh(rt_hash_lock_addr(hash));
}
__be32 skeys[2] = { saddr, 0 };
int ikeys[2] = { dev->ifindex, 0 };
struct netevent_redirect netevent;
+ struct net *net;
if (!in_dev)
return;
+ net = dev_net(dev);
if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev)
- || MULTICAST(new_gw) || BADCLASS(new_gw) || ZERONET(new_gw))
+ || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw)
+ || ipv4_is_zeronet(new_gw))
goto reject_redirect;
if (!IN_DEV_SHARED_MEDIA(in_dev)) {
if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev))
goto reject_redirect;
} else {
- if (inet_addr_type(new_gw) != RTN_UNICAST)
+ if (inet_addr_type(net, new_gw) != RTN_UNICAST)
goto reject_redirect;
}
if (rth->fl.fl4_dst != daddr ||
rth->fl.fl4_src != skeys[i] ||
rth->fl.oif != ikeys[k] ||
- rth->fl.iif != 0) {
+ rth->fl.iif != 0 ||
+ rth->rt_genid != atomic_read(&rt_genid) ||
+ dev_net(rth->u.dst.dev) != net) {
rthp = &rth->u.dst.rt_next;
continue;
}
rt->u.dst.neighbour = NULL;
rt->u.dst.hh = NULL;
rt->u.dst.xfrm = NULL;
-
+ rt->rt_genid = atomic_read(&rt_genid);
rt->rt_flags |= RTCF_REDIRECTED;
/* Gateway is different ... */
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
{
- struct rtable *rt = (struct rtable*)dst;
+ struct rtable *rt = (struct rtable *)dst;
struct dst_entry *ret = dst;
if (rt) {
void ip_rt_send_redirect(struct sk_buff *skb)
{
- struct rtable *rt = (struct rtable*)skb->dst;
+ struct rtable *rt = skb->rtable;
struct in_device *in_dev = in_dev_get(rt->u.dst.dev);
if (!in_dev)
static int ip_error(struct sk_buff *skb)
{
- struct rtable *rt = (struct rtable*)skb->dst;
+ struct rtable *rt = skb->rtable;
unsigned long now;
int code;
return 68;
}
-unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu)
+unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,
+ unsigned short new_mtu)
{
int i;
unsigned short old_mtu = ntohs(iph->tot_len);
rth->rt_dst == daddr &&
rth->rt_src == iph->saddr &&
rth->fl.iif == 0 &&
- !(dst_metric_locked(&rth->u.dst, RTAX_MTU))) {
+ !(dst_metric_locked(&rth->u.dst, RTAX_MTU)) &&
+ dev_net(rth->u.dst.dev) == net &&
+ rth->rt_genid == atomic_read(&rt_genid)) {
unsigned short mtu = new_mtu;
if (new_mtu < 68 || new_mtu >= old_mtu) {
{
struct rtable *rt = (struct rtable *) dst;
struct in_device *idev = rt->idev;
- if (dev != init_net.loopback_dev && idev && idev->dev == dev) {
- struct in_device *loopback_idev = in_dev_get(init_net.loopback_dev);
+ if (dev != dev_net(dev)->loopback_dev && idev && idev->dev == dev) {
+ struct in_device *loopback_idev =
+ in_dev_get(dev_net(dev)->loopback_dev);
if (loopback_idev) {
rt->idev = loopback_idev;
in_dev_put(idev);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
- rt = (struct rtable *) skb->dst;
+ rt = skb->rtable;
if (rt)
dst_set_expires(&rt->u.dst, 0);
}
if (rt->fl.iif == 0)
src = rt->rt_src;
- else if (fib_lookup(&rt->fl, &res) == 0) {
+ else if (fib_lookup(dev_net(rt->u.dst.dev), &rt->fl, &res) == 0) {
src = FIB_RES_PREFSRC(res);
fib_res_put(&res);
} else
if (in_dev == NULL)
return -EINVAL;
- if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr) ||
- skb->protocol != htons(ETH_P_IP))
+ if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
+ ipv4_is_loopback(saddr) || skb->protocol != htons(ETH_P_IP))
goto e_inval;
- if (ZERONET(saddr)) {
- if (!LOCAL_MCAST(daddr))
+ if (ipv4_is_zeronet(saddr)) {
+ if (!ipv4_is_local_multicast(daddr))
goto e_inval;
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
} else if (fib_validate_source(saddr, 0, tos, 0,
rth->fl.oif = 0;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
- rth->rt_type = RTN_MULTICAST;
+ rth->rt_genid = atomic_read(&rt_genid);
rth->rt_flags = RTCF_MULTICAST;
+ rth->rt_type = RTN_MULTICAST;
if (our) {
rth->u.dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
}
#ifdef CONFIG_IP_MROUTE
- if (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
+ if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev))
rth->u.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);
- return rt_intern_hash(hash, rth, (struct rtable**) &skb->dst);
+ return rt_intern_hash(hash, rth, &skb->rtable);
e_nobufs:
in_dev_put(in_dev);
if (err)
flags |= RTCF_DIRECTSRC;
- if (out_dev == in_dev && err && !(flags & (RTCF_NAT | RTCF_MASQ)) &&
+ if (out_dev == in_dev && err && !(flags & RTCF_MASQ) &&
(IN_DEV_SHARED_MEDIA(out_dev) ||
inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
flags |= RTCF_DOREDIRECT;
/* Not IP (i.e. ARP). Do not create route, if it is
* invalid for proxy arp. DNAT routes are always valid.
*/
- if (out_dev == in_dev && !(flags & RTCF_DNAT)) {
+ if (out_dev == in_dev) {
err = -EINVAL;
goto cleanup;
}
rth->u.dst.input = ip_forward;
rth->u.dst.output = ip_output;
+ rth->rt_genid = atomic_read(&rt_genid);
rt_set_nexthop(rth, res, itag);
/* put it into the cache */
hash = rt_hash(daddr, saddr, fl->iif);
- return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
+ return rt_intern_hash(hash, rth, &skb->rtable);
}
/*
__be32 spec_dst;
int err = -EINVAL;
int free_res = 0;
+ struct net * net = dev_net(dev);
/* IP on this device is disabled. */
by fib_lookup.
*/
- if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr))
+ if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
+ ipv4_is_loopback(saddr))
goto martian_source;
if (daddr == htonl(0xFFFFFFFF) || (saddr == 0 && daddr == 0))
/* Accept zero addresses only to limited broadcast;
* I even do not know to fix it or not. Waiting for complains :-)
*/
- if (ZERONET(saddr))
+ if (ipv4_is_zeronet(saddr))
goto martian_source;
- if (BADCLASS(daddr) || ZERONET(daddr) || LOOPBACK(daddr))
+ if (ipv4_is_lbcast(daddr) || ipv4_is_zeronet(daddr) ||
+ ipv4_is_loopback(daddr))
goto martian_destination;
/*
* Now we are ready to route packet.
*/
- if ((err = fib_lookup(&fl, &res)) != 0) {
+ if ((err = fib_lookup(net, &fl, &res)) != 0) {
if (!IN_DEV_FORWARD(in_dev))
goto e_hostunreach;
goto no_route;
if (res.type == RTN_LOCAL) {
int result;
result = fib_validate_source(saddr, daddr, tos,
- init_net.loopback_dev->ifindex,
+ net->loopback_dev->ifindex,
dev, &spec_dst, &itag);
if (result < 0)
goto martian_source;
if (skb->protocol != htons(ETH_P_IP))
goto e_inval;
- if (ZERONET(saddr))
+ if (ipv4_is_zeronet(saddr))
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
else {
err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
goto e_nobufs;
rth->u.dst.output= ip_rt_bug;
+ rth->rt_genid = atomic_read(&rt_genid);
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
#endif
rth->rt_iif =
rth->fl.iif = dev->ifindex;
- rth->u.dst.dev = init_net.loopback_dev;
+ rth->u.dst.dev = net->loopback_dev;
dev_hold(rth->u.dst.dev);
rth->idev = in_dev_get(rth->u.dst.dev);
rth->rt_gateway = daddr;
}
rth->rt_type = res.type;
hash = rt_hash(daddr, saddr, fl.iif);
- err = rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
+ err = rt_intern_hash(hash, rth, &skb->rtable);
goto done;
no_route:
struct rtable * rth;
unsigned hash;
int iif = dev->ifindex;
+ struct net *net;
+ net = dev_net(dev);
tos &= IPTOS_RT_MASK;
hash = rt_hash(daddr, saddr, iif);
rth->fl.iif == iif &&
rth->fl.oif == 0 &&
rth->fl.mark == skb->mark &&
- rth->fl.fl4_tos == tos) {
+ rth->fl.fl4_tos == tos &&
+ dev_net(rth->u.dst.dev) == net &&
+ rth->rt_genid == atomic_read(&rt_genid)) {
dst_use(&rth->u.dst, jiffies);
RT_CACHE_STAT_INC(in_hit);
rcu_read_unlock();
- skb->dst = (struct dst_entry*)rth;
+ skb->rtable = rth;
return 0;
}
RT_CACHE_STAT_INC(in_hlist_search);
Note, that multicast routers are not affected, because
route cache entry is created eventually.
*/
- if (MULTICAST(daddr)) {
+ if (ipv4_is_multicast(daddr)) {
struct in_device *in_dev;
rcu_read_lock();
ip_hdr(skb)->protocol);
if (our
#ifdef CONFIG_IP_MROUTE
- || (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
+ || (!ipv4_is_local_multicast(daddr) &&
+ IN_DEV_MFORWARD(in_dev))
#endif
) {
rcu_read_unlock();
u32 tos = RT_FL_TOS(oldflp);
int err = 0;
- if (LOOPBACK(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK))
+ if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK))
return -EINVAL;
if (fl->fl4_dst == htonl(0xFFFFFFFF))
res->type = RTN_BROADCAST;
- else if (MULTICAST(fl->fl4_dst))
+ else if (ipv4_is_multicast(fl->fl4_dst))
res->type = RTN_MULTICAST;
- else if (BADCLASS(fl->fl4_dst) || ZERONET(fl->fl4_dst))
+ else if (ipv4_is_lbcast(fl->fl4_dst) || ipv4_is_zeronet(fl->fl4_dst))
return -EINVAL;
if (dev_out->flags & IFF_LOOPBACK)
rth->rt_spec_dst= fl->fl4_src;
rth->u.dst.output=ip_output;
+ rth->rt_genid = atomic_read(&rt_genid);
RT_CACHE_STAT_INC(out_slow_tot);
#ifdef CONFIG_IP_MROUTE
if (res->type == RTN_MULTICAST) {
if (IN_DEV_MFORWARD(in_dev) &&
- !LOCAL_MCAST(oldflp->fl4_dst)) {
+ !ipv4_is_local_multicast(oldflp->fl4_dst)) {
rth->u.dst.input = ip_mr_input;
rth->u.dst.output = ip_mc_output;
}
* Major route resolver routine.
*/
-static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
+static int ip_route_output_slow(struct net *net, struct rtable **rp,
+ const struct flowi *oldflp)
{
u32 tos = RT_FL_TOS(oldflp);
struct flowi fl = { .nl_u = { .ip4_u =
RT_SCOPE_UNIVERSE),
} },
.mark = oldflp->mark,
- .iif = init_net.loopback_dev->ifindex,
+ .iif = net->loopback_dev->ifindex,
.oif = oldflp->oif };
struct fib_result res;
unsigned flags = 0;
if (oldflp->fl4_src) {
err = -EINVAL;
- if (MULTICAST(oldflp->fl4_src) ||
- BADCLASS(oldflp->fl4_src) ||
- ZERONET(oldflp->fl4_src))
+ if (ipv4_is_multicast(oldflp->fl4_src) ||
+ ipv4_is_lbcast(oldflp->fl4_src) ||
+ ipv4_is_zeronet(oldflp->fl4_src))
goto out;
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
- dev_out = ip_dev_find(oldflp->fl4_src);
+ dev_out = ip_dev_find(net, oldflp->fl4_src);
if (dev_out == NULL)
goto out;
/* I removed check for oif == dev_out->oif here.
It was wrong for two reasons:
- 1. ip_dev_find(saddr) can return wrong iface, if saddr is
- assigned to multiple interfaces.
+ 1. ip_dev_find(net, saddr) can return wrong iface, if saddr
+ is assigned to multiple interfaces.
2. Moreover, we are allowed to send packets with saddr
of another iface. --ANK
*/
if (oldflp->oif == 0
- && (MULTICAST(oldflp->fl4_dst) || oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
+ && (ipv4_is_multicast(oldflp->fl4_dst) ||
+ oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
/* Special hack: user can direct multicasts
and limited broadcast via necessary interface
without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
if (oldflp->oif) {
- dev_out = dev_get_by_index(&init_net, oldflp->oif);
+ dev_out = dev_get_by_index(net, oldflp->oif);
err = -ENODEV;
if (dev_out == NULL)
goto out;
goto out; /* Wrong error code */
}
- if (LOCAL_MCAST(oldflp->fl4_dst) || oldflp->fl4_dst == htonl(0xFFFFFFFF)) {
+ if (ipv4_is_local_multicast(oldflp->fl4_dst) ||
+ oldflp->fl4_dst == htonl(0xFFFFFFFF)) {
if (!fl.fl4_src)
fl.fl4_src = inet_select_addr(dev_out, 0,
RT_SCOPE_LINK);
goto make_route;
}
if (!fl.fl4_src) {
- if (MULTICAST(oldflp->fl4_dst))
+ if (ipv4_is_multicast(oldflp->fl4_dst))
fl.fl4_src = inet_select_addr(dev_out, 0,
fl.fl4_scope);
else if (!oldflp->fl4_dst)
fl.fl4_dst = fl.fl4_src = htonl(INADDR_LOOPBACK);
if (dev_out)
dev_put(dev_out);
- dev_out = init_net.loopback_dev;
+ dev_out = net->loopback_dev;
dev_hold(dev_out);
- fl.oif = init_net.loopback_dev->ifindex;
+ fl.oif = net->loopback_dev->ifindex;
res.type = RTN_LOCAL;
flags |= RTCF_LOCAL;
goto make_route;
}
- if (fib_lookup(&fl, &res)) {
+ if (fib_lookup(net, &fl, &res)) {
res.fi = NULL;
if (oldflp->oif) {
/* Apparently, routing tables are wrong. Assume,
fl.fl4_src = fl.fl4_dst;
if (dev_out)
dev_put(dev_out);
- dev_out = init_net.loopback_dev;
+ dev_out = net->loopback_dev;
dev_hold(dev_out);
fl.oif = dev_out->ifindex;
if (res.fi)
else
#endif
if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif)
- fib_select_default(&fl, &res);
+ fib_select_default(net, &fl, &res);
if (!fl.fl4_src)
fl.fl4_src = FIB_RES_PREFSRC(res);
out: return err;
}
-int __ip_route_output_key(struct rtable **rp, const struct flowi *flp)
+int __ip_route_output_key(struct net *net, struct rtable **rp,
+ const struct flowi *flp)
{
unsigned hash;
struct rtable *rth;
rth->fl.oif == flp->oif &&
rth->fl.mark == flp->mark &&
!((rth->fl.fl4_tos ^ flp->fl4_tos) &
- (IPTOS_RT_MASK | RTO_ONLINK))) {
+ (IPTOS_RT_MASK | RTO_ONLINK)) &&
+ dev_net(rth->u.dst.dev) == net &&
+ rth->rt_genid == atomic_read(&rt_genid)) {
dst_use(&rth->u.dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
}
rcu_read_unlock_bh();
- return ip_route_output_slow(rp, flp);
+ return ip_route_output_slow(net, rp, flp);
}
EXPORT_SYMBOL_GPL(__ip_route_output_key);
.check = ipv4_dst_check,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
.entry_size = sizeof(struct rtable),
+ .entries = ATOMIC_INIT(0),
};
-static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp, struct sock *sk)
+static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp)
{
struct rtable *ort = *rp;
struct rtable *rt = (struct rtable *)
rt->idev = ort->idev;
if (rt->idev)
in_dev_hold(rt->idev);
+ rt->rt_genid = atomic_read(&rt_genid);
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_dst = ort->rt_dst;
return (rt ? 0 : -ENOMEM);
}
-int ip_route_output_flow(struct rtable **rp, struct flowi *flp, struct sock *sk, int flags)
+int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
+ struct sock *sk, int flags)
{
int err;
- if ((err = __ip_route_output_key(rp, flp)) != 0)
+ if ((err = __ip_route_output_key(net, rp, flp)) != 0)
return err;
if (flp->proto) {
flp->fl4_src = (*rp)->rt_src;
if (!flp->fl4_dst)
flp->fl4_dst = (*rp)->rt_dst;
- err = __xfrm_lookup((struct dst_entry **)rp, flp, sk, flags);
+ err = __xfrm_lookup((struct dst_entry **)rp, flp, sk,
+ flags ? XFRM_LOOKUP_WAIT : 0);
if (err == -EREMOTE)
- err = ipv4_dst_blackhole(rp, flp, sk);
+ err = ipv4_dst_blackhole(rp, flp);
return err;
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
-int ip_route_output_key(struct rtable **rp, struct flowi *flp)
+int ip_route_output_key(struct net *net, struct rtable **rp, struct flowi *flp)
{
- return ip_route_output_flow(rp, flp, NULL, 0);
+ return ip_route_output_flow(net, rp, flp, NULL, 0);
}
static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
{
- struct rtable *rt = (struct rtable*)skb->dst;
+ struct rtable *rt = skb->rtable;
struct rtmsg *r;
struct nlmsghdr *nlh;
long expires;
#ifdef CONFIG_IP_MROUTE
__be32 dst = rt->rt_dst;
- if (MULTICAST(dst) && !LOCAL_MCAST(dst) &&
- IPV4_DEVCONF_ALL(MC_FORWARDING)) {
+ if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
+ IPV4_DEVCONF_ALL(&init_net, MC_FORWARDING)) {
int err = ipmr_get_route(skb, r, nowait);
if (err <= 0) {
if (!nowait) {
static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
- struct net *net = in_skb->sk->sk_net;
+ struct net *net = sock_net(in_skb->sk);
struct rtmsg *rtm;
struct nlattr *tb[RTA_MAX+1];
struct rtable *rt = NULL;
int err;
struct sk_buff *skb;
- if (net != &init_net)
- return -EINVAL;
-
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
goto errout;
if (iif) {
struct net_device *dev;
- dev = __dev_get_by_index(&init_net, iif);
+ dev = __dev_get_by_index(net, iif);
if (dev == NULL) {
err = -ENODEV;
goto errout_free;
err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
local_bh_enable();
- rt = (struct rtable*) skb->dst;
+ rt = skb->rtable;
if (err == 0 && rt->u.dst.error)
err = -rt->u.dst.error;
} else {
},
.oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
};
- err = ip_route_output_key(&rt, &fl);
+ err = ip_route_output_key(net, &rt, &fl);
}
if (err)
goto errout_free;
- skb->dst = &rt->u.dst;
+ skb->rtable = rt;
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
- RTM_NEWROUTE, 0, 0);
+ RTM_NEWROUTE, 0, 0);
if (err <= 0)
goto errout_free;
- err = rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).pid);
+ err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
errout:
return err;
struct rtable *rt;
int h, s_h;
int idx, s_idx;
+ struct net *net;
+
+ net = sock_net(skb->sk);
s_h = cb->args[0];
if (s_h < 0)
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++) {
- if (idx < s_idx)
+ if (dev_net(rt->u.dst.dev) != net || idx < s_idx)
+ continue;
+ if (rt->rt_genid != atomic_read(&rt_genid))
continue;
skb->dst = dst_clone(&rt->u.dst);
if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
.proc_handler = &ipv4_sysctl_rtcache_flush,
.strategy = &ipv4_sysctl_rtcache_flush_strategy,
},
- {
- .ctl_name = NET_IPV4_ROUTE_MIN_DELAY,
- .procname = "min_delay",
- .data = &ip_rt_min_delay,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
- .strategy = &sysctl_jiffies,
- },
- {
- .ctl_name = NET_IPV4_ROUTE_MAX_DELAY,
- .procname = "max_delay",
- .data = &ip_rt_max_delay,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
- .strategy = &sysctl_jiffies,
- },
{
.ctl_name = NET_IPV4_ROUTE_GC_THRESH,
.procname = "gc_thresh",
{
int rc = 0;
- rt_hash_rnd = (int) ((num_physpages ^ (num_physpages>>8)) ^
- (jiffies ^ (jiffies >> 7)));
+ atomic_set(&rt_genid, (int) ((num_physpages ^ (num_physpages>>8)) ^
+ (jiffies ^ (jiffies >> 7))));
#ifdef CONFIG_NET_CLS_ROUTE
ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct));
devinet_init();
ip_fib_init();
- setup_timer(&rt_flush_timer, rt_run_flush, 0);
setup_timer(&rt_secret_timer, rt_secret_rebuild, 0);
/* All the timers, started at system startup tend
ip_rt_secret_interval;
add_timer(&rt_secret_timer);
- if (ip_rt_proc_init(&init_net))
+ if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
xfrm_init();
git://bbs.cooldavid.org / net-next-2.6.git / blobdiff