static int ip_rt_error_cost __read_mostly = HZ;
static int ip_rt_error_burst __read_mostly = 5 * HZ;
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
-static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
+static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
+
+static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU;
+
/*
* Interface to generic destination cache.
*/
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
{
- static u32 ip_idents_hashrnd __read_mostly;
u32 hash, id;
- net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
+ /* Note the following code is not safe, but this is okay. */
+ if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key)))
+ get_random_bytes(&net->ipv4.ip_id_key,
+ sizeof(net->ipv4.ip_id_key));
- hash = jhash_3words((__force u32)iph->daddr,
+ hash = siphash_3u32((__force u32)iph->daddr,
(__force u32)iph->saddr,
- iph->protocol ^ net_hash_mix(net),
- ip_idents_hashrnd);
+ iph->protocol,
+ &net->ipv4.ip_id_key);
id = ip_idents_reserve(hash, segs);
iph->id = htons(id);
}
static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe)
{
rt->rt_pmtu = fnhe->fnhe_pmtu;
+ rt->rt_mtu_locked = fnhe->fnhe_mtu_locked;
rt->dst.expires = fnhe->fnhe_expires;
if (fnhe->fnhe_gw) {
}
static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
- u32 pmtu, unsigned long expires)
+ u32 pmtu, bool lock, unsigned long expires)
{
struct fnhe_hash_bucket *hash;
struct fib_nh_exception *fnhe;
fnhe->fnhe_genid = genid;
if (gw)
fnhe->fnhe_gw = gw;
- if (pmtu)
+ if (pmtu) {
fnhe->fnhe_pmtu = pmtu;
+ fnhe->fnhe_mtu_locked = lock;
+ }
fnhe->fnhe_expires = max(1UL, expires);
/* Update all cached dsts too */
rt = rcu_dereference(fnhe->fnhe_rth_input);
fnhe->fnhe_daddr = daddr;
fnhe->fnhe_gw = gw;
fnhe->fnhe_pmtu = pmtu;
- fnhe->fnhe_expires = expires;
+ fnhe->fnhe_mtu_locked = lock;
+ fnhe->fnhe_expires = max(1UL, expires);
/* Exception created; mark the cached routes for the nexthop
* stale, so anyone caching it rechecks if this exception
struct fib_nh *nh = &FIB_RES_NH(res);
update_or_create_fnhe(nh, fl4->daddr, new_gw,
- 0, jiffies + ip_rt_gc_timeout);
+ 0, false,
+ jiffies + ip_rt_gc_timeout);
}
if (kill_route)
rt->dst.obsolete = DST_OBSOLETE_KILL;
/* No redirected packets during ip_rt_redirect_silence;
* reset the algorithm.
*/
- if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+ if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) {
peer->rate_tokens = 0;
+ peer->n_redirects = 0;
+ }
/* Too many ignored redirects; do not send anything
* set dst.rate_last to the last seen redirected packet.
*/
- if (peer->rate_tokens >= ip_rt_redirect_number) {
+ if (peer->n_redirects >= ip_rt_redirect_number) {
peer->rate_last = jiffies;
goto out_put_peer;
}
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->rate_tokens;
+ ++peer->n_redirects;
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (log_martians &&
peer->rate_tokens == ip_rt_redirect_number)
static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
struct dst_entry *dst = &rt->dst;
+ u32 old_mtu = ipv4_mtu(dst);
struct fib_result res;
+ bool lock = false;
- if (dst_metric_locked(dst, RTAX_MTU))
+ if (ip_mtu_locked(dst))
return;
- if (ipv4_mtu(dst) < mtu)
+ if (old_mtu < mtu)
return;
- if (mtu < ip_rt_min_pmtu)
- mtu = ip_rt_min_pmtu;
+ if (mtu < ip_rt_min_pmtu) {
+ lock = true;
+ mtu = min(old_mtu, ip_rt_min_pmtu);
+ }
- if (rt->rt_pmtu == mtu &&
+ if (rt->rt_pmtu == mtu && !lock &&
time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2))
return;
if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
struct fib_nh *nh = &FIB_RES_NH(res);
- update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
+ update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock,
jiffies + ip_rt_mtu_expires);
}
rcu_read_unlock();
return dst;
}
+static void ipv4_send_dest_unreach(struct sk_buff *skb)
+{
+ struct ip_options opt;
+ int res;
+
+ /* Recompile ip options since IPCB may not be valid anymore.
+ * Also check we have a reasonable ipv4 header.
+ */
+ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) ||
+ ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5)
+ return;
+
+ memset(&opt, 0, sizeof(opt));
+ if (ip_hdr(skb)->ihl > 5) {
+ if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4))
+ return;
+ opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
+
+ rcu_read_lock();
+ res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+ rcu_read_unlock();
+
+ if (res)
+ return;
+ }
+ __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
+}
+
static void ipv4_link_failure(struct sk_buff *skb)
{
struct rtable *rt;
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+ ipv4_send_dest_unreach(skb);
rt = skb_rtable(skb);
if (rt)
mtu = READ_ONCE(dst->dev->mtu);
- if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
+ if (unlikely(ip_mtu_locked(dst))) {
if (rt->rt_uses_gateway && mtu > 576)
mtu = 576;
}
return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
}
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+ struct fnhe_hash_bucket *hash;
+ struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+ u32 hval = fnhe_hashfun(daddr);
+
+ spin_lock_bh(&fnhe_lock);
+
+ hash = rcu_dereference_protected(nh->nh_exceptions,
+ lockdep_is_held(&fnhe_lock));
+ hash += hval;
+
+ fnhe_p = &hash->chain;
+ fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+ while (fnhe) {
+ if (fnhe->fnhe_daddr == daddr) {
+ rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+ fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+ /* set fnhe_daddr to 0 to ensure it won't bind with
+ * new dsts in rt_bind_exception().
+ */
+ fnhe->fnhe_daddr = 0;
+ fnhe_flush_routes(fnhe);
+ kfree_rcu(fnhe, rcu);
+ break;
+ }
+ fnhe_p = &fnhe->fnhe_next;
+ fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+ lockdep_is_held(&fnhe_lock));
+ }
+
+ spin_unlock_bh(&fnhe_lock);
+}
+
static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
{
struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
fnhe = rcu_dereference(fnhe->fnhe_next)) {
- if (fnhe->fnhe_daddr == daddr)
+ if (fnhe->fnhe_daddr == daddr) {
+ if (fnhe->fnhe_expires &&
+ time_after(jiffies, fnhe->fnhe_expires)) {
+ ip_del_fnhe(nh, daddr);
+ break;
+ }
return fnhe;
+ }
}
return NULL;
}
static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
-static void rt_add_uncached_list(struct rtable *rt)
+void rt_add_uncached_list(struct rtable *rt)
{
struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
spin_unlock_bh(&ul->lock);
}
-static void ipv4_dst_destroy(struct dst_entry *dst)
+void rt_del_uncached_list(struct rtable *rt)
{
- struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
- struct rtable *rt = (struct rtable *) dst;
-
- if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
- kfree(p);
-
if (!list_empty(&rt->rt_uncached)) {
struct uncached_list *ul = rt->rt_uncached_list;
}
}
+static void ipv4_dst_destroy(struct dst_entry *dst)
+{
+ struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
+ struct rtable *rt = (struct rtable *)dst;
+
+ if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
+ kfree(p);
+
+ rt_del_uncached_list(rt);
+}
+
void rt_flush_dev(struct net_device *dev)
{
struct net *net = dev_net(dev);
rt->rt_is_input = 0;
rt->rt_iif = 0;
rt->rt_pmtu = 0;
+ rt->rt_mtu_locked = 0;
rt->rt_gateway = 0;
rt->rt_uses_gateway = 0;
rt->rt_table_id = 0;
#endif
}
-static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
-{
- struct fnhe_hash_bucket *hash;
- struct fib_nh_exception *fnhe, __rcu **fnhe_p;
- u32 hval = fnhe_hashfun(daddr);
-
- spin_lock_bh(&fnhe_lock);
-
- hash = rcu_dereference_protected(nh->nh_exceptions,
- lockdep_is_held(&fnhe_lock));
- hash += hval;
-
- fnhe_p = &hash->chain;
- fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
- while (fnhe) {
- if (fnhe->fnhe_daddr == daddr) {
- rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
- fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
- fnhe_flush_routes(fnhe);
- kfree_rcu(fnhe, rcu);
- break;
- }
- fnhe_p = &fnhe->fnhe_next;
- fnhe = rcu_dereference_protected(fnhe->fnhe_next,
- lockdep_is_held(&fnhe_lock));
- }
-
- spin_unlock_bh(&fnhe_lock);
-}
-
static void set_lwt_redirect(struct rtable *rth)
{
if (lwtunnel_output_redirect(rth->dst.lwtstate)) {
fnhe = find_exception(&FIB_RES_NH(*res), daddr);
if (do_cache) {
- if (fnhe) {
+ if (fnhe)
rth = rcu_dereference(fnhe->fnhe_rth_input);
- if (rth && rth->dst.expires &&
- time_after(jiffies, rth->dst.expires)) {
- ip_del_fnhe(&FIB_RES_NH(*res), daddr);
- fnhe = NULL;
- } else {
- goto rt_cache;
- }
- }
-
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-
-rt_cache:
+ else
+ rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
goto out;
return skb_get_hash_raw(skb) >> 1;
memset(&hash_keys, 0, sizeof(hash_keys));
skb_flow_dissect_flow_keys(skb, &keys, flag);
+
+ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
hash_keys.ports.src = keys.ports.src;
int our = 0;
int err = -EINVAL;
- if (in_dev)
- our = ip_check_mc_rcu(in_dev, daddr, saddr,
- ip_hdr(skb)->protocol);
+ if (!in_dev)
+ return err;
+ our = ip_check_mc_rcu(in_dev, daddr, saddr,
+ ip_hdr(skb)->protocol);
/* check l3 master if no match yet */
- if ((!in_dev || !our) && netif_is_l3_slave(dev)) {
+ if (!our && netif_is_l3_slave(dev)) {
struct in_device *l3_in_dev;
l3_in_dev = __in_dev_get_rcu(skb->dev);
* the loopback interface and the IP_PKTINFO ipi_ifindex will
* be set to the loopback interface as well.
*/
- fi = NULL;
+ do_cache = false;
}
fnhe = NULL;
do_cache &= fi != NULL;
- if (do_cache) {
+ if (fi) {
struct rtable __rcu **prth;
struct fib_nh *nh = &FIB_RES_NH(*res);
fnhe = find_exception(nh, fl4->daddr);
+ if (!do_cache)
+ goto add;
if (fnhe) {
prth = &fnhe->fnhe_rth_output;
- rth = rcu_dereference(*prth);
- if (rth && rth->dst.expires &&
- time_after(jiffies, rth->dst.expires)) {
- ip_del_fnhe(nh, fl4->daddr);
- fnhe = NULL;
- } else {
- goto rt_cache;
+ } else {
+ if (unlikely(fl4->flowi4_flags &
+ FLOWI_FLAG_KNOWN_NH &&
+ !(nh->nh_gw &&
+ nh->nh_scope == RT_SCOPE_LINK))) {
+ do_cache = false;
+ goto add;
}
+ prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
}
-
- if (unlikely(fl4->flowi4_flags &
- FLOWI_FLAG_KNOWN_NH &&
- !(nh->nh_gw &&
- nh->nh_scope == RT_SCOPE_LINK))) {
- do_cache = false;
- goto add;
- }
- prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
rth = rcu_dereference(*prth);
-
-rt_cache:
if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))
return rth;
}
const struct sk_buff *skb)
{
__u8 tos = RT_FL_TOS(fl4);
- struct fib_result res;
+ struct fib_result res = {
+ .type = RTN_UNSPEC,
+ .fi = NULL,
+ .table = NULL,
+ .tclassid = 0,
+ };
struct rtable *rth;
- res.tclassid = 0;
- res.fi = NULL;
- res.table = NULL;
-
fl4->flowi4_iif = LOOPBACK_IFINDEX;
fl4->flowi4_tos = tos & IPTOS_RT_MASK;
fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
rt->rt_is_input = ort->rt_is_input;
rt->rt_iif = ort->rt_iif;
rt->rt_pmtu = ort->rt_pmtu;
+ rt->rt_mtu_locked = ort->rt_mtu_locked;
rt->rt_genid = rt_genid_ipv4(net);
rt->rt_flags = ort->rt_flags;
memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
if (rt->rt_pmtu && expires)
metrics[RTAX_MTU - 1] = rt->rt_pmtu;
+ if (rt->rt_mtu_locked && expires)
+ metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU);
if (rtnetlink_put_metrics(skb, metrics) < 0)
goto nla_put_failure;
if (err == 0 && rt->dst.error)
err = -rt->dst.error;
} else {
+ fl4.flowi4_iif = LOOPBACK_IFINDEX;
rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb);
err = 0;
if (IS_ERR(rt))
.data = &ip_rt_min_pmtu,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &ip_min_valid_pmtu,
},
{
.procname = "min_adv_mss",