* 2 of the License, or (at your option) any later version.
*/
+#define pr_fmt(fmt) "IPv4: " fmt
+
#include <linux/module.h>
#include <asm/uaccess.h>
-#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <linux/slab.h>
+#include <linux/prefetch.h>
#include <net/dst.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/rtnetlink.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
+#include <linux/kmemleak.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)))
+ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
#define IP_MAX_MTU 0xFFF0
static int ip_rt_max_size;
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_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_min_advmss __read_mostly = 256;
static int rt_chain_length_max __read_mostly = 20;
+static struct delayed_work expires_work;
+static unsigned long expires_ljiffies;
+
/*
* Interface to generic destination cache.
*/
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ipv4_default_advmss(const struct dst_entry *dst);
-static unsigned int ipv4_default_mtu(const struct dst_entry *dst);
+static unsigned int ipv4_mtu(const struct dst_entry *dst);
static void ipv4_dst_destroy(struct dst_entry *dst);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
struct inet_peer *peer;
u32 *p = NULL;
- if (!rt->peer)
- rt_bind_peer(rt, rt->rt_dst, 1);
-
- peer = rt->peer;
+ peer = rt_get_peer_create(rt, rt->rt_dst);
if (peer) {
u32 *old_p = __DST_METRICS_PTR(old);
unsigned long prev, new;
.gc = rt_garbage_collect,
.check = ipv4_dst_check,
.default_advmss = ipv4_default_advmss,
- .default_mtu = ipv4_default_mtu,
+ .mtu = ipv4_mtu,
.cow_metrics = ipv4_cow_metrics,
.destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
TC_PRIO_INTERACTIVE_BULK,
ECN_OR_COST(INTERACTIVE_BULK)
};
-
+EXPORT_SYMBOL(ip_tos2prio);
/*
* Route cache.
#endif
static struct rt_hash_bucket *rt_hash_table __read_mostly;
-static unsigned rt_hash_mask __read_mostly;
+static unsigned int rt_hash_mask __read_mostly;
static unsigned int rt_hash_log __read_mostly;
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
else {
struct rtable *r = v;
struct neighbour *n;
- int len;
+ int len, HHUptod;
+
+ rcu_read_lock();
+ n = dst_get_neighbour_noref(&r->dst);
+ HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+ rcu_read_unlock();
- n = dst_get_neighbour(&r->dst);
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 : "*",
dst_metric(&r->dst, RTAX_RTTVAR)),
r->rt_key_tos,
-1,
- (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0,
+ HHUptod,
r->rt_spec_dst, &len);
seq_printf(seq, "%*s\n", 127 - len, "");
static inline int rt_valuable(struct rtable *rth)
{
return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
- (rth->peer && rth->peer->pmtu_expires);
+ (rt_has_peer(rth) && rt_peer_ptr(rth)->pmtu_expires);
}
static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
{
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)
(rt1->rt_mark ^ rt2->rt_mark) |
(rt1->rt_key_tos ^ rt2->rt_key_tos) |
(rt1->rt_route_iif ^ rt2->rt_route_iif) |
- (rt1->rt_oif ^ rt2->rt_oif) |
- (rt1->rt_iif ^ rt2->rt_iif)) == 0;
+ (rt1->rt_oif ^ rt2->rt_oif)) == 0;
}
static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
return ONE;
}
+static void rt_check_expire(void)
+{
+ static unsigned int rover;
+ unsigned int i = rover, goal;
+ struct rtable *rth;
+ struct rtable __rcu **rthp;
+ unsigned long samples = 0;
+ unsigned long sum = 0, sum2 = 0;
+ unsigned long delta;
+ u64 mult;
+
+ delta = jiffies - expires_ljiffies;
+ expires_ljiffies = jiffies;
+ mult = ((u64)delta) << rt_hash_log;
+ if (ip_rt_gc_timeout > 1)
+ do_div(mult, ip_rt_gc_timeout);
+ goal = (unsigned int)mult;
+ if (goal > rt_hash_mask)
+ goal = rt_hash_mask + 1;
+ for (; goal > 0; goal--) {
+ unsigned long tmo = ip_rt_gc_timeout;
+ unsigned long length;
+
+ i = (i + 1) & rt_hash_mask;
+ rthp = &rt_hash_table[i].chain;
+
+ if (need_resched())
+ cond_resched();
+
+ samples++;
+
+ if (rcu_dereference_raw(*rthp) == NULL)
+ continue;
+ length = 0;
+ spin_lock_bh(rt_hash_lock_addr(i));
+ while ((rth = rcu_dereference_protected(*rthp,
+ lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) {
+ prefetch(rth->dst.rt_next);
+ if (rt_is_expired(rth) ||
+ rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
+ *rthp = rth->dst.rt_next;
+ rt_free(rth);
+ continue;
+ }
+
+ /* We only count entries on a chain with equal
+ * hash inputs once so that entries for
+ * different QOS levels, and other non-hash
+ * input attributes don't unfairly skew the
+ * length computation
+ */
+ tmo >>= 1;
+ rthp = &rth->dst.rt_next;
+ length += has_noalias(rt_hash_table[i].chain, rth);
+ }
+ spin_unlock_bh(rt_hash_lock_addr(i));
+ sum += length;
+ sum2 += length*length;
+ }
+ if (samples) {
+ unsigned long avg = sum / samples;
+ unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
+ rt_chain_length_max = max_t(unsigned long,
+ ip_rt_gc_elasticity,
+ (avg + 4*sd) >> FRACT_BITS);
+ }
+ rover = i;
+}
+
+/*
+ * rt_worker_func() is run in process context.
+ * we call rt_check_expire() to scan part of the hash table
+ */
+static void rt_worker_func(struct work_struct *work)
+{
+ rt_check_expire();
+ schedule_delayed_work(&expires_work, ip_rt_gc_interval);
+}
+
/*
* Perturbation of rt_genid by a small quantity [1..256]
* Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
get_random_bytes(&shuffle, sizeof(shuffle));
atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
+ inetpeer_invalidate_family(AF_INET);
}
/*
static void rt_emergency_hash_rebuild(struct net *net)
{
- if (net_ratelimit())
- printk(KERN_WARNING "Route hash chain too long!\n");
+ net_warn_ratelimited("Route hash chain too long!\n");
rt_cache_invalidate(net);
}
goto out;
if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size)
goto out;
- if (net_ratelimit())
- printk(KERN_WARNING "dst cache overflow\n");
+ net_warn_ratelimited("dst cache overflow\n");
RT_CACHE_STAT_INC(gc_dst_overflow);
return 1;
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;
+ const struct rtable *rt;
struct neighbour *n;
-#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
- if (dev->type == ARPHRD_ATM)
- tbl = clip_tbl_hook;
-#endif
+ rt = (const struct rtable *) dst;
+
if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
pkey = &inaddr_any;
+ else if (rt->rt_gateway)
+ pkey = (const __be32 *) &rt->rt_gateway;
- n = __ipv4_neigh_lookup(tbl, dev, *(__force u32 *)pkey);
+ n = __ipv4_neigh_lookup(dev, *(__force u32 *)pkey);
if (n)
return n;
- return neigh_create(tbl, pkey, dev);
+ return neigh_create(&arp_tbl, pkey, dev);
}
static int rt_bind_neighbour(struct rtable *rt)
return 0;
}
-static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt,
+static struct rtable *rt_intern_hash(unsigned int hash, struct rtable *rt,
struct sk_buff *skb, int ifindex)
{
struct rtable *rth, *cand;
candp = NULL;
now = jiffies;
- if (!rt_caching(dev_net(rt->dst.dev))) {
+ if (!rt_caching(dev_net(rt->dst.dev)) || (rt->dst.flags & DST_NOCACHE)) {
/*
* 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_is_output_route(rt)) {
int err = rt_bind_neighbour(rt);
if (err) {
- if (net_ratelimit())
- printk(KERN_WARNING
- "Neighbour table failure & not caching routes.\n");
+ net_warn_ratelimited("Neighbour table failure & not caching routes\n");
ip_rt_put(rt);
return ERR_PTR(err);
}
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",
+ pr_warn("%s: %d rebuilds is over limit, route caching disabled\n",
rt->dst.dev->name, num);
}
rt_emergency_hash_rebuild(net);
goto restart;
}
- if (net_ratelimit())
- printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
+ net_warn_ratelimited("Neighbour table overflow\n");
rt_drop(rt);
return ERR_PTR(-ENOBUFS);
}
void rt_bind_peer(struct rtable *rt, __be32 daddr, int create)
{
+ struct inet_peer_base *base;
struct inet_peer *peer;
- peer = inet_getpeer_v4(daddr, create);
+ base = inetpeer_base_ptr(rt->_peer);
+ if (!base)
+ return;
- if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL)
- inet_putpeer(peer);
- else
- rt->rt_peer_genid = rt_peer_genid();
+ peer = inet_getpeer_v4(base, daddr, create);
+ if (peer) {
+ if (!rt_set_peer(rt, peer))
+ inet_putpeer(peer);
+ else
+ rt->rt_peer_genid = rt_peer_genid();
+ }
}
/*
{
struct rtable *rt = (struct rtable *) dst;
- if (rt) {
- if (rt->peer == NULL)
- rt_bind_peer(rt, rt->rt_dst, 1);
+ if (rt && !(rt->dst.flags & DST_NOPEER)) {
+ struct inet_peer *peer = rt_get_peer_create(rt, rt->rt_dst);
/* If peer is attached to destination, it is never detached,
so that we need not to grab a lock to dereference it.
*/
- if (rt->peer) {
- iph->id = htons(inet_getid(rt->peer, more));
+ if (peer) {
+ iph->id = htons(inet_getid(peer, more));
return;
}
- } else
- printk(KERN_DEBUG "rt_bind_peer(0) @%p\n",
- __builtin_return_address(0));
+ } else if (!rt)
+ pr_debug("rt_bind_peer(0) @%p\n", __builtin_return_address(0));
ip_select_fb_ident(iph);
}
EXPORT_SYMBOL(__ip_select_ident);
-static void rt_del(unsigned hash, struct rtable *rt)
+static void rt_del(unsigned int hash, struct rtable *rt)
{
struct rtable __rcu **rthp;
struct rtable *aux;
spin_unlock_bh(rt_hash_lock_addr(hash));
}
+static void 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)) {
+ rt->rt_gateway = orig_gw;
+ return;
+ }
+ old_n = xchg(&rt->dst._neighbour, n);
+ if (old_n)
+ neigh_release(old_n);
+ if (!(n->nud_state & NUD_VALID)) {
+ neigh_event_send(n, NULL);
+ } else {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
+ }
+}
+
/* 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;
+
+ while ((rt = rcu_dereference(*rthp)) != NULL) {
+ rthp = &rt->dst.rt_next;
- atomic_inc(&__rt_peer_genid);
+ 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;
+
+ peer = rt_get_peer_create(rt, rt->rt_dst);
+ 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;
reject_redirect:
#ifdef CONFIG_IP_ROUTE_VERBOSE
- if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
- printk(KERN_INFO "Redirect from %pI4 on %s about %pI4 ignored.\n"
- " Advised path = %pI4 -> %pI4\n",
- &old_gw, dev->name, &new_gw,
- &saddr, &daddr);
+ if (IN_DEV_LOG_MARTIANS(in_dev))
+ net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n"
+ " Advised path = %pI4 -> %pI4\n",
+ &old_gw, dev->name, &new_gw,
+ &saddr, &daddr);
#endif
;
}
ip_rt_put(rt);
ret = NULL;
} else if (rt->rt_flags & RTCF_REDIRECTED) {
- unsigned hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
+ unsigned int hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
rt->rt_oif,
rt_genid(dev_net(dst->dev)));
rt_del(hash, rt);
ret = NULL;
- } else if (rt->peer && peer_pmtu_expired(rt->peer)) {
- dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig);
+ } else if (rt_has_peer(rt)) {
+ struct inet_peer *peer = rt_peer_ptr(rt);
+ if (peer_pmtu_expired(peer))
+ dst_metric_set(dst, RTAX_MTU, peer->pmtu_orig);
}
}
return ret;
log_martians = IN_DEV_LOG_MARTIANS(in_dev);
rcu_read_unlock();
- if (!rt->peer)
- rt_bind_peer(rt, rt->rt_dst, 1);
- peer = rt->peer;
+ peer = rt_get_peer_create(rt, rt->rt_dst);
if (!peer) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
return;
++peer->rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (log_martians &&
- peer->rate_tokens == ip_rt_redirect_number &&
- net_ratelimit())
- printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n",
- &ip_hdr(skb)->saddr, rt->rt_iif,
- &rt->rt_dst, &rt->rt_gateway);
+ peer->rate_tokens == ip_rt_redirect_number)
+ net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
+ &ip_hdr(skb)->saddr, rt->rt_iif,
+ &rt->rt_dst, &rt->rt_gateway);
#endif
}
}
static int ip_error(struct sk_buff *skb)
{
+ struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
struct rtable *rt = skb_rtable(skb);
struct inet_peer *peer;
unsigned long now;
+ struct net *net;
bool send;
int code;
+ net = dev_net(rt->dst.dev);
+ if (!IN_DEV_FORWARD(in_dev)) {
+ switch (rt->dst.error) {
+ case EHOSTUNREACH:
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INADDRERRORS);
+ break;
+
+ case ENETUNREACH:
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INNOROUTES);
+ break;
+ }
+ goto out;
+ }
+
switch (rt->dst.error) {
case EINVAL:
default:
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
- IP_INC_STATS_BH(dev_net(rt->dst.dev),
- IPSTATS_MIB_INNOROUTES);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
code = ICMP_PKT_FILTERED;
break;
}
- if (!rt->peer)
- rt_bind_peer(rt, rt->rt_dst, 1);
- peer = rt->peer;
+ peer = rt_get_peer_create(rt, rt->rt_dst);
send = true;
if (peer) {
return 0;
}
-/*
- * The last two values are not from the RFC but
- * are needed for AMPRnet AX.25 paths.
- */
-
-static const unsigned short mtu_plateau[] =
-{32000, 17914, 8166, 4352, 2002, 1492, 576, 296, 216, 128 };
-
-static inline unsigned short guess_mtu(unsigned short old_mtu)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(mtu_plateau); i++)
- if (old_mtu > mtu_plateau[i])
- return mtu_plateau[i];
- return 68;
-}
-
-unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph,
- unsigned short new_mtu,
- struct net_device *dev)
-{
- unsigned short old_mtu = ntohs(iph->tot_len);
- unsigned short est_mtu = 0;
- struct inet_peer *peer;
-
- peer = inet_getpeer_v4(iph->daddr, 1);
- if (peer) {
- unsigned short mtu = new_mtu;
-
- if (new_mtu < 68 || new_mtu >= old_mtu) {
- /* BSD 4.2 derived systems incorrectly adjust
- * tot_len by the IP header length, and report
- * a zero MTU in the ICMP message.
- */
- if (mtu == 0 &&
- old_mtu >= 68 + (iph->ihl << 2))
- old_mtu -= iph->ihl << 2;
- mtu = guess_mtu(old_mtu);
- }
-
- if (mtu < ip_rt_min_pmtu)
- mtu = ip_rt_min_pmtu;
- if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
- unsigned long pmtu_expires;
-
- pmtu_expires = jiffies + ip_rt_mtu_expires;
- if (!pmtu_expires)
- pmtu_expires = 1UL;
-
- est_mtu = mtu;
- peer->pmtu_learned = mtu;
- peer->pmtu_expires = pmtu_expires;
- }
-
- inet_putpeer(peer);
-
- atomic_inc(&__rt_peer_genid);
- }
- return est_mtu ? : new_mtu;
-}
-
static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer)
{
unsigned long expires = ACCESS_ONCE(peer->pmtu_expires);
dst_confirm(dst);
- if (!rt->peer)
- rt_bind_peer(rt, rt->rt_dst, 1);
- peer = rt->peer;
+ peer = rt_get_peer_create(rt, rt->rt_dst);
if (peer) {
unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires);
}
}
-static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
+ int oif, u32 mark, u8 protocol, int flow_flags)
{
- 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;
+ const struct iphdr *iph = (const struct iphdr *)skb->data;
+ struct flowi4 fl4;
+ struct rtable *rt;
- 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);
+ flowi4_init_output(&fl4, oif, mark, RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
+ protocol, flow_flags | FLOWI_FLAG_PRECOW_METRICS,
+ iph->daddr, iph->saddr, 0, 0);
+ rt = __ip_route_output_key(net, &fl4);
+ if (!IS_ERR(rt)) {
+ ip_rt_update_pmtu(&rt->dst, mtu);
+ ip_rt_put(rt);
}
- return 0;
}
+EXPORT_SYMBOL_GPL(ipv4_update_pmtu);
-static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
{
- struct rtable *rt = (struct rtable *) dst;
+ const struct inet_sock *inet = inet_sk(sk);
- if (rt_is_expired(rt))
- return NULL;
- if (rt->rt_peer_genid != rt_peer_genid()) {
- struct inet_peer *peer;
+ return ipv4_update_pmtu(skb, sock_net(sk), mtu,
+ sk->sk_bound_dev_if, sk->sk_mark,
+ inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ inet_sk_flowi_flags(sk));
+}
+EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
- if (!rt->peer)
- rt_bind_peer(rt, rt->rt_dst, 0);
+static void ipv4_validate_peer(struct rtable *rt)
+{
+ if (rt->rt_peer_genid != rt_peer_genid()) {
+ struct inet_peer *peer = rt_get_peer(rt, rt->rt_dst);
- peer = rt->peer;
if (peer) {
- check_peer_pmtu(dst, peer);
+ check_peer_pmtu(&rt->dst, peer);
if (peer->redirect_learned.a4 &&
- peer->redirect_learned.a4 != rt->rt_gateway) {
- if (check_peer_redir(dst, peer))
- return NULL;
- }
+ peer->redirect_learned.a4 != rt->rt_gateway)
+ check_peer_redir(&rt->dst, peer);
}
rt->rt_peer_genid = rt_peer_genid();
}
+}
+
+static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+{
+ struct rtable *rt = (struct rtable *) dst;
+
+ if (rt_is_expired(rt))
+ return NULL;
+ ipv4_validate_peer(rt);
return dst;
}
static void ipv4_dst_destroy(struct dst_entry *dst)
{
struct rtable *rt = (struct rtable *) dst;
- struct inet_peer *peer = rt->peer;
if (rt->fi) {
fib_info_put(rt->fi);
rt->fi = NULL;
}
- if (peer) {
- rt->peer = NULL;
+ if (rt_has_peer(rt)) {
+ struct inet_peer *peer = rt_peer_ptr(rt);
inet_putpeer(peer);
}
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
rt = skb_rtable(skb);
- if (rt && rt->peer && peer_pmtu_cleaned(rt->peer))
- dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig);
+ if (rt && rt_has_peer(rt)) {
+ struct inet_peer *peer = rt_peer_ptr(rt);
+ if (peer_pmtu_cleaned(peer))
+ dst_metric_set(&rt->dst, RTAX_MTU, peer->pmtu_orig);
+ }
}
static int ip_rt_bug(struct sk_buff *skb)
{
- printk(KERN_DEBUG "ip_rt_bug: %pI4 -> %pI4, %s\n",
- &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
- skb->dev ? skb->dev->name : "?");
+ pr_debug("%s: %pI4 -> %pI4, %s\n",
+ __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
+ skb->dev ? skb->dev->name : "?");
kfree_skb(skb);
WARN_ON(1);
return 0;
return advmss;
}
-static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_mtu(const struct dst_entry *dst)
{
- unsigned int mtu = dst->dev->mtu;
+ const struct rtable *rt = (const struct rtable *) dst;
+ unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+ if (mtu && rt_is_output_route(rt))
+ return mtu;
+
+ mtu = dst->dev->mtu;
if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
- const struct rtable *rt = (const struct rtable *) dst;
if (rt->rt_gateway != rt->rt_dst && mtu > 576)
mtu = 576;
static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
struct fib_info *fi)
{
+ struct inet_peer_base *base;
struct inet_peer *peer;
int create = 0;
if (fl4 && (fl4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS))
create = 1;
- rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create);
+ base = inetpeer_base_ptr(rt->_peer);
+ BUG_ON(!base);
+
+ peer = inet_getpeer_v4(base, rt->rt_dst, create);
if (peer) {
+ __rt_set_peer(rt, peer);
rt->rt_peer_genid = rt_peer_genid();
if (inet_metrics_new(peer))
memcpy(peer->metrics, fi->fib_metrics,
dst_init_metrics(&rt->dst, peer->metrics, false);
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;
if (dst_mtu(dst) > IP_MAX_MTU)
dst_metric_set(dst, RTAX_MTU, IP_MAX_MTU);
- if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40)
- dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40);
#ifdef CONFIG_IP_ROUTE_CLASSID
#ifdef CONFIG_IP_MULTIPLE_TABLES
return -EINVAL;
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
- ipv4_is_loopback(saddr) || skb->protocol != htons(ETH_P_IP))
+ skb->protocol != htons(ETH_P_IP))
goto e_inval;
+ if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev)))
+ if (ipv4_is_loopback(saddr))
+ goto e_inval;
+
if (ipv4_is_zeronet(saddr)) {
if (!ipv4_is_local_multicast(daddr))
goto e_inval;
if (err < 0)
goto e_err;
}
- rth = rt_dst_alloc(init_net.loopback_dev,
+ rth = rt_dst_alloc(dev_net(dev)->loopback_dev,
IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->rt_peer_genid = 0;
- rth->peer = NULL;
+ rt_init_peer(rth, dev_net(dev)->ipv4.peers);
rth->fi = NULL;
if (our) {
rth->dst.input= ip_local_deliver;
* RFC1812 recommendation, if source is martian,
* the only hint is MAC header.
*/
- printk(KERN_WARNING "martian source %pI4 from %pI4, on dev %s\n",
+ pr_warn("martian source %pI4 from %pI4, on dev %s\n",
&daddr, &saddr, dev->name);
if (dev->hard_header_len && skb_mac_header_was_set(skb)) {
- int i;
- const unsigned char *p = skb_mac_header(skb);
- printk(KERN_WARNING "ll header: ");
- for (i = 0; i < dev->hard_header_len; i++, p++) {
- printk("%02x", *p);
- if (i < (dev->hard_header_len - 1))
- printk(":");
- }
- printk("\n");
+ print_hex_dump(KERN_WARNING, "ll header: ",
+ DUMP_PREFIX_OFFSET, 16, 1,
+ skb_mac_header(skb),
+ dev->hard_header_len, true);
}
}
#endif
/* get a working reference to the output device */
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" \
- "_slow(). Please, report\n");
+ net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n");
return -EINVAL;
}
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->rt_peer_genid = 0;
- rth->peer = NULL;
+ rt_init_peer(rth, &res->table->tb_peers);
rth->fi = NULL;
rth->dst.input = ip_forward;
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos)
{
- struct rtable* rth = NULL;
+ struct rtable *rth = NULL;
int err;
- unsigned hash;
+ unsigned int hash;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && res->fi->fib_nhs > 1)
struct fib_result res;
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct flowi4 fl4;
- unsigned flags = 0;
+ unsigned int flags = 0;
u32 itag = 0;
- struct rtable * rth;
- unsigned hash;
+ struct rtable *rth;
+ unsigned int hash;
__be32 spec_dst;
int err = -EINVAL;
- struct net * net = dev_net(dev);
+ struct net *net = dev_net(dev);
/* IP on this device is disabled. */
by fib_lookup.
*/
- if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
- ipv4_is_loopback(saddr))
+ if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
goto martian_source;
if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0))
if (ipv4_is_zeronet(saddr))
goto martian_source;
- if (ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr))
+ if (ipv4_is_zeronet(daddr))
goto martian_destination;
+ if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) {
+ if (ipv4_is_loopback(daddr))
+ goto martian_destination;
+
+ if (ipv4_is_loopback(saddr))
+ goto martian_source;
+ }
+
/*
* Now we are ready to route packet.
*/
fl4.daddr = daddr;
fl4.saddr = saddr;
err = fib_lookup(net, &fl4, &res);
- if (err != 0) {
- if (!IN_DEV_FORWARD(in_dev))
- goto e_hostunreach;
+ if (err != 0)
goto no_route;
- }
RT_CACHE_STAT_INC(in_slow_tot);
}
if (!IN_DEV_FORWARD(in_dev))
- goto e_hostunreach;
+ goto no_route;
if (res.type != RTN_UNICAST)
goto martian_destination;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->rt_peer_genid = 0;
- rth->peer = NULL;
+ rt_init_peer(rth, net->ipv4.peers);
rth->fi = NULL;
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
martian_destination:
RT_CACHE_STAT_INC(in_martian_dst);
#ifdef CONFIG_IP_ROUTE_VERBOSE
- if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
- printk(KERN_WARNING "martian destination %pI4 from %pI4, dev %s\n",
- &daddr, &saddr, dev->name);
+ if (IN_DEV_LOG_MARTIANS(in_dev))
+ net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n",
+ &daddr, &saddr, dev->name);
#endif
-e_hostunreach:
- err = -EHOSTUNREACH;
- goto out;
-
e_inval:
err = -EINVAL;
goto out;
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;
+ struct rtable *rth;
+ unsigned int hash;
int iif = dev->ifindex;
struct net *net;
int res;
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_route_iif ^ iif) |
(rth->rt_key_tos ^ tos)) == 0 &&
- rt_is_input_route(rth) &&
rth->rt_mark == skb->mark &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
+ ipv4_validate_peer(rth);
if (noref) {
dst_use_noref(&rth->dst, jiffies);
skb_dst_set_noref(skb, &rth->dst);
static struct rtable *__mkroute_output(const struct fib_result *res,
const struct flowi4 *fl4,
__be32 orig_daddr, __be32 orig_saddr,
- int orig_oif, struct net_device *dev_out,
+ int orig_oif, __u8 orig_rtos,
+ struct net_device *dev_out,
unsigned int flags)
{
struct fib_info *fi = res->fi;
- u32 tos = RT_FL_TOS(fl4);
struct in_device *in_dev;
u16 type = res->type;
struct rtable *rth;
- if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK))
+ in_dev = __in_dev_get_rcu(dev_out);
+ if (!in_dev)
return ERR_PTR(-EINVAL);
+ if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev)))
+ if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK))
+ return ERR_PTR(-EINVAL);
+
if (ipv4_is_lbcast(fl4->daddr))
type = RTN_BROADCAST;
else if (ipv4_is_multicast(fl4->daddr))
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
- in_dev = __in_dev_get_rcu(dev_out);
- if (!in_dev)
- return ERR_PTR(-EINVAL);
-
if (type == RTN_BROADCAST) {
flags |= RTCF_BROADCAST | RTCF_LOCAL;
fi = NULL;
rth->rt_genid = rt_genid(dev_net(dev_out));
rth->rt_flags = flags;
rth->rt_type = type;
- rth->rt_key_tos = tos;
+ rth->rt_key_tos = orig_rtos;
rth->rt_dst = fl4->daddr;
rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
rth->rt_gateway = fl4->daddr;
rth->rt_spec_dst= fl4->saddr;
rth->rt_peer_genid = 0;
- rth->peer = NULL;
+ rt_init_peer(rth, (res->table ?
+ &res->table->tb_peers :
+ dev_net(dev_out)->ipv4.peers));
rth->fi = NULL;
RT_CACHE_STAT_INC(out_slow_tot);
rt_set_nexthop(rth, fl4, res, fi, type, 0);
+ if (fl4->flowi4_flags & FLOWI_FLAG_RT_NOCACHE)
+ rth->dst.flags |= DST_NOCACHE;
+
return rth;
}
static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
{
struct net_device *dev_out = NULL;
- u32 tos = RT_FL_TOS(fl4);
+ __u8 tos = RT_FL_TOS(fl4);
unsigned int flags = 0;
struct fib_result res;
struct rtable *rth;
int orig_oif;
res.fi = NULL;
+ res.table = NULL;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
if (fib_lookup(net, fl4, &res)) {
res.fi = NULL;
+ res.table = NULL;
if (fl4->flowi4_oif) {
/* Apparently, routing tables are wrong. Assume,
that the destination is on link.
make_route:
rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
- dev_out, flags);
+ tos, dev_out, flags);
if (!IS_ERR(rth)) {
unsigned int hash;
(IPTOS_RT_MASK | RTO_ONLINK)) &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
+ ipv4_validate_peer(rth);
dst_use(&rth->dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
return NULL;
}
-static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
{
- return 0;
+ unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+ return mtu ? : dst->dev->mtu;
}
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
.protocol = cpu_to_be16(ETH_P_IP),
.destroy = ipv4_dst_destroy,
.check = ipv4_blackhole_dst_check,
- .default_mtu = ipv4_blackhole_default_mtu,
+ .mtu = ipv4_blackhole_mtu,
.default_advmss = ipv4_default_advmss,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
.cow_metrics = ipv4_rt_blackhole_cow_metrics,
rt->rt_src = ort->rt_src;
rt->rt_gateway = ort->rt_gateway;
rt->rt_spec_dst = ort->rt_spec_dst;
- rt->peer = ort->peer;
- if (rt->peer)
- atomic_inc(&rt->peer->refcnt);
+ rt_transfer_peer(rt, ort);
rt->fi = ort->fi;
if (rt->fi)
atomic_inc(&rt->fi->fib_clntref);
struct rtable *rt = skb_rtable(skb);
struct rtmsg *r;
struct nlmsghdr *nlh;
- long expires = 0;
- const struct inet_peer *peer = rt->peer;
+ unsigned long expires = 0;
u32 id = 0, ts = 0, tsage = 0, error;
nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
r->rtm_src_len = 0;
r->rtm_tos = rt->rt_key_tos;
r->rtm_table = RT_TABLE_MAIN;
- NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN);
+ if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN))
+ goto nla_put_failure;
r->rtm_type = rt->rt_type;
r->rtm_scope = RT_SCOPE_UNIVERSE;
r->rtm_protocol = RTPROT_UNSPEC;
if (rt->rt_flags & RTCF_NOTIFY)
r->rtm_flags |= RTM_F_NOTIFY;
- NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst);
-
+ if (nla_put_be32(skb, RTA_DST, rt->rt_dst))
+ goto nla_put_failure;
if (rt->rt_key_src) {
r->rtm_src_len = 32;
- NLA_PUT_BE32(skb, RTA_SRC, rt->rt_key_src);
+ if (nla_put_be32(skb, RTA_SRC, rt->rt_key_src))
+ goto nla_put_failure;
}
- if (rt->dst.dev)
- NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
+ if (rt->dst.dev &&
+ nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
+ goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
- if (rt->dst.tclassid)
- NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid);
+ if (rt->dst.tclassid &&
+ nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid))
+ goto nla_put_failure;
#endif
- if (rt_is_input_route(rt))
- NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst);
- else if (rt->rt_src != rt->rt_key_src)
- NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src);
-
- if (rt->rt_dst != rt->rt_gateway)
- NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway);
+ if (rt_is_input_route(rt)) {
+ if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_spec_dst))
+ goto nla_put_failure;
+ } else if (rt->rt_src != rt->rt_key_src) {
+ if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src))
+ goto nla_put_failure;
+ }
+ if (rt->rt_dst != rt->rt_gateway &&
+ nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
+ goto nla_put_failure;
if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
- if (rt->rt_mark)
- NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark);
+ if (rt->rt_mark &&
+ nla_put_be32(skb, RTA_MARK, rt->rt_mark))
+ goto nla_put_failure;
error = rt->dst.error;
- if (peer) {
- inet_peer_refcheck(rt->peer);
+ if (rt_has_peer(rt)) {
+ const struct inet_peer *peer = rt_peer_ptr(rt);
+ inet_peer_refcheck(peer);
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 (expires) {
+ if (time_before(jiffies, expires))
+ expires -= jiffies;
+ else
+ expires = 0;
+ }
}
if (rt_is_input_route(rt)) {
}
} else
#endif
- NLA_PUT_U32(skb, RTA_IIF, rt->rt_iif);
+ if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
+ goto nla_put_failure;
}
if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage,
return -EMSGSIZE;
}
-static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
+static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(in_skb->sk);
struct rtmsg *rtm;
{ }
};
-static struct ctl_table empty[1];
-
-static struct ctl_table ipv4_skeleton[] =
-{
- { .procname = "route",
- .mode = 0555, .child = ipv4_route_table},
- { .procname = "neigh",
- .mode = 0555, .child = empty},
- { }
-};
-
-static __net_initdata struct ctl_path ipv4_path[] = {
- { .procname = "net", },
- { .procname = "ipv4", },
- { },
-};
-
static struct ctl_table ipv4_route_flush_table[] = {
{
.procname = "flush",
{ },
};
-static __net_initdata struct ctl_path ipv4_route_path[] = {
- { .procname = "net", },
- { .procname = "ipv4", },
- { .procname = "route", },
- { },
-};
-
static __net_init int sysctl_route_net_init(struct net *net)
{
struct ctl_table *tbl;
}
tbl[0].extra1 = net;
- net->ipv4.route_hdr =
- register_net_sysctl_table(net, ipv4_route_path, tbl);
+ net->ipv4.route_hdr = register_net_sysctl(net, "net/ipv4/route", tbl);
if (net->ipv4.route_hdr == NULL)
goto err_reg;
return 0;
.init = rt_genid_init,
};
+static int __net_init ipv4_inetpeer_init(struct net *net)
+{
+ struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL);
+
+ if (!bp)
+ return -ENOMEM;
+ inet_peer_base_init(bp);
+ net->ipv4.peers = bp;
+ return 0;
+}
+
+static void __net_exit ipv4_inetpeer_exit(struct net *net)
+{
+ struct inet_peer_base *bp = net->ipv4.peers;
+
+ net->ipv4.peers = NULL;
+ inetpeer_invalidate_tree(bp);
+ kfree(bp);
+}
+
+static __net_initdata struct pernet_operations ipv4_inetpeer_ops = {
+ .init = ipv4_inetpeer_init,
+ .exit = ipv4_inetpeer_exit,
+};
#ifdef CONFIG_IP_ROUTE_CLASSID
struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
static __initdata unsigned long rhash_entries;
static int __init set_rhash_entries(char *str)
{
+ ssize_t ret;
+
if (!str)
return 0;
- rhash_entries = simple_strtoul(str, &str, 0);
+
+ ret = kstrtoul(str, 0, &rhash_entries);
+ if (ret)
+ return 0;
+
return 1;
}
__setup("rhash_entries=", set_rhash_entries);
0,
&rt_hash_log,
&rt_hash_mask,
+ 0,
rhash_entries ? 0 : 512 * 1024);
memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
rt_hash_lock_init();
devinet_init();
ip_fib_init();
+ INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func);
+ expires_ljiffies = jiffies;
+ schedule_delayed_work(&expires_work,
+ net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
+
if (ip_rt_proc_init())
- printk(KERN_ERR "Unable to create route proc files\n");
+ pr_err("Unable to create route proc files\n");
#ifdef CONFIG_XFRM
xfrm_init();
xfrm4_init(ip_rt_max_size);
register_pernet_subsys(&sysctl_route_ops);
#endif
register_pernet_subsys(&rt_genid_ops);
+ register_pernet_subsys(&ipv4_inetpeer_ops);
return rc;
}
*/
void __init ip_static_sysctl_init(void)
{
- register_sysctl_paths(ipv4_path, ipv4_skeleton);
+ register_net_sysctl(&init_net, "net/ipv4/route", ipv4_route_table);
}
#endif