blob: cd1fa9f70f1a17276648f1ec693c3b40cb6e11b4 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* ROUTE - implementation of the IP router.
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Linus Torvalds, <Linus.Torvalds@helsinki.fi>
* Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* Fixes:
* Alan Cox : Verify area fixes.
* Alan Cox : cli() protects routing changes
* Rui Oliveira : ICMP routing table updates
* (rco@di.uminho.pt) Routing table insertion and update
* Linus Torvalds : Rewrote bits to be sensible
* Alan Cox : Added BSD route gw semantics
* Alan Cox : Super /proc >4K
* Alan Cox : MTU in route table
* Alan Cox : MSS actually. Also added the window
* clamper.
* Sam Lantinga : Fixed route matching in rt_del()
* Alan Cox : Routing cache support.
* Alan Cox : Removed compatibility cruft.
* Alan Cox : RTF_REJECT support.
* Alan Cox : TCP irtt support.
* Jonathan Naylor : Added Metric support.
* Miquel van Smoorenburg : BSD API fixes.
* Miquel van Smoorenburg : Metrics.
* Alan Cox : Use __u32 properly
* Alan Cox : Aligned routing errors more closely with BSD
* our system is still very different.
* Alan Cox : Faster /proc handling
* Alexey Kuznetsov : Massive rework to support tree based routing,
* routing caches and better behaviour.
*
* Olaf Erb : irtt wasn't being copied right.
* Bjorn Ekwall : Kerneld route support.
* Alan Cox : Multicast fixed (I hope)
* Pavel Krauz : Limited broadcast fixed
* Mike McLagan : Routing by source
* Alexey Kuznetsov : End of old history. Split to fib.c and
* route.c and rewritten from scratch.
* Andi Kleen : Load-limit warning messages.
* Vitaly E. Lavrov : Transparent proxy revived after year coma.
* Vitaly E. Lavrov : Race condition in ip_route_input_slow.
* Tobias Ringstrom : Uninitialized res.type in ip_route_output_slow.
* Vladimir V. Ivanov : IP rule info (flowid) is really useful.
* Marc Boucher : routing by fwmark
* Robert Olsson : Added rt_cache statistics
* Arnaldo C. Melo : Convert proc stuff to seq_file
* Eric Dumazet : hashed spinlocks and rt_check_expire() fixes.
* Ilia Sotnikov : Ignore TOS on PMTUD and Redirect
* Ilia Sotnikov : Removed TOS from hash calculations
*/
#define pr_fmt(fmt) "IPv4: " fmt
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/memblock.h>
#include <linux/socket.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/pkt_sched.h>
#include <linux/mroute.h>
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <linux/jhash.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
#include <net/inet_dscp.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/inetpeer.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/nexthop.h>
#include <net/tcp.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/lwtunnel.h>
#include <net/netevent.h>
#include <net/rtnetlink.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <net/secure_seq.h>
#include <net/ip_tunnels.h>
#include "fib_lookup.h"
#define RT_FL_TOS(oldflp4) \
((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
#define RT_GC_TIMEOUT (300*HZ)
#define DEFAULT_MIN_PMTU (512 + 20 + 20)
#define DEFAULT_MTU_EXPIRES (10 * 60 * HZ)
#define DEFAULT_MIN_ADVMSS 256
static int ip_rt_max_size;
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_timeout __read_mostly = RT_GC_TIMEOUT;
/*
* Interface to generic destination cache.
*/
INDIRECT_CALLABLE_SCOPE
struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ipv4_default_advmss(const struct dst_entry *dst);
INDIRECT_CALLABLE_SCOPE
unsigned int ipv4_mtu(const struct dst_entry *dst);
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, struct sock *sk,
struct sk_buff *skb, u32 mtu,
bool confirm_neigh);
static void ip_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
static void ipv4_dst_destroy(struct dst_entry *dst);
static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old)
{
WARN_ON(1);
return NULL;
}
static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr);
static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr);
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.check = ipv4_dst_check,
.default_advmss = ipv4_default_advmss,
.mtu = ipv4_mtu,
.cow_metrics = ipv4_cow_metrics,
.destroy = ipv4_dst_destroy,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
.update_pmtu = ip_rt_update_pmtu,
.redirect = ip_do_redirect,
.local_out = __ip_local_out,
.neigh_lookup = ipv4_neigh_lookup,
.confirm_neigh = ipv4_confirm_neigh,
};
#define ECN_OR_COST(class) TC_PRIO_##class
const __u8 ip_tos2prio[16] = {
TC_PRIO_BESTEFFORT,
ECN_OR_COST(BESTEFFORT),
TC_PRIO_BESTEFFORT,
ECN_OR_COST(BESTEFFORT),
TC_PRIO_BULK,
ECN_OR_COST(BULK),
TC_PRIO_BULK,
ECN_OR_COST(BULK),
TC_PRIO_INTERACTIVE,
ECN_OR_COST(INTERACTIVE),
TC_PRIO_INTERACTIVE,
ECN_OR_COST(INTERACTIVE),
TC_PRIO_INTERACTIVE_BULK,
ECN_OR_COST(INTERACTIVE_BULK),
TC_PRIO_INTERACTIVE_BULK,
ECN_OR_COST(INTERACTIVE_BULK)
};
EXPORT_SYMBOL(ip_tos2prio);
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
#define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field)
#ifdef CONFIG_PROC_FS
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
if (*pos)
return NULL;
return SEQ_START_TOKEN;
}
static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
return NULL;
}
static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
}
static int rt_cache_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
seq_printf(seq, "%-127s\n",
"Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
"Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
"HHUptod\tSpecDst");
return 0;
}
static const struct seq_operations rt_cache_seq_ops = {
.start = rt_cache_seq_start,
.next = rt_cache_seq_next,
.stop = rt_cache_seq_stop,
.show = rt_cache_seq_show,
};
static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos)
{
int cpu;
if (*pos == 0)
return SEQ_START_TOKEN;
for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) {
if (!cpu_possible(cpu))
continue;
*pos = cpu+1;
return &per_cpu(rt_cache_stat, cpu);
}
return NULL;
}
static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
int cpu;
for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) {
if (!cpu_possible(cpu))
continue;
*pos = cpu+1;
return &per_cpu(rt_cache_stat, cpu);
}
(*pos)++;
return NULL;
}
static void rt_cpu_seq_stop(struct seq_file *seq, void *v)
{
}
static int rt_cpu_seq_show(struct seq_file *seq, void *v)
{
struct rt_cache_stat *st = v;
if (v == SEQ_START_TOKEN) {
seq_puts(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n");
return 0;
}
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x "
"%08x %08x %08x %08x %08x %08x "
"%08x %08x %08x %08x\n",
dst_entries_get_slow(&ipv4_dst_ops),
0, /* st->in_hit */
st->in_slow_tot,
st->in_slow_mc,
st->in_no_route,
st->in_brd,
st->in_martian_dst,
st->in_martian_src,
0, /* st->out_hit */
st->out_slow_tot,
st->out_slow_mc,
0, /* st->gc_total */
0, /* st->gc_ignored */
0, /* st->gc_goal_miss */
0, /* st->gc_dst_overflow */
0, /* st->in_hlist_search */
0 /* st->out_hlist_search */
);
return 0;
}
static const struct seq_operations rt_cpu_seq_ops = {
.start = rt_cpu_seq_start,
.next = rt_cpu_seq_next,
.stop = rt_cpu_seq_stop,
.show = rt_cpu_seq_show,
};
#ifdef CONFIG_IP_ROUTE_CLASSID
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;
}
}
seq_write(m, dst, 256 * sizeof(struct ip_rt_acct));
kfree(dst);
return 0;
}
#endif
static int __net_init ip_rt_do_proc_init(struct net *net)
{
struct proc_dir_entry *pde;
pde = proc_create_seq("rt_cache", 0444, net->proc_net,
&rt_cache_seq_ops);
if (!pde)
goto err1;
pde = proc_create_seq("rt_cache", 0444, net->proc_net_stat,
&rt_cpu_seq_ops);
if (!pde)
goto err2;
#ifdef CONFIG_IP_ROUTE_CLASSID
pde = proc_create_single("rt_acct", 0, net->proc_net,
rt_acct_proc_show);
if (!pde)
goto err3;
#endif
return 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
err3:
remove_proc_entry("rt_cache", net->proc_net_stat);
#endif
err2:
remove_proc_entry("rt_cache", net->proc_net);
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);
#ifdef CONFIG_IP_ROUTE_CLASSID
remove_proc_entry("rt_acct", net->proc_net);
#endif
}
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(void)
{
return 0;
}
#endif /* CONFIG_PROC_FS */
static inline bool rt_is_expired(const struct rtable *rth)
{
return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev));
}
void rt_cache_flush(struct net *net)
{
rt_genid_bump_ipv4(net);
}
static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr)
{
const struct rtable *rt = container_of(dst, struct rtable, dst);
struct net_device *dev = dst->dev;
struct neighbour *n;
rcu_read_lock_bh();
if (likely(rt->rt_gw_family == AF_INET)) {
n = ip_neigh_gw4(dev, rt->rt_gw4);
} else if (rt->rt_gw_family == AF_INET6) {
n = ip_neigh_gw6(dev, &rt->rt_gw6);
} else {
__be32 pkey;
pkey = skb ? ip_hdr(skb)->daddr : *((__be32 *) daddr);
n = ip_neigh_gw4(dev, pkey);
}
if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt))
n = NULL;
rcu_read_unlock_bh();
return n;
}
static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr)
{
const struct rtable *rt = container_of(dst, struct rtable, dst);
struct net_device *dev = dst->dev;
const __be32 *pkey = daddr;
if (rt->rt_gw_family == AF_INET) {
pkey = (const __be32 *)&rt->rt_gw4;
} else if (rt->rt_gw_family == AF_INET6) {
return __ipv6_confirm_neigh_stub(dev, &rt->rt_gw6);
} else if (!daddr ||
(rt->rt_flags &
(RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL))) {
return;
}
__ipv4_confirm_neigh(dev, *(__force u32 *)pkey);
}
/* Hash tables of size 2048..262144 depending on RAM size.
* Each bucket uses 8 bytes.
*/
static u32 ip_idents_mask __read_mostly;
static atomic_t *ip_idents __read_mostly;
static u32 *ip_tstamps __read_mostly;
/* In order to protect privacy, we add a perturbation to identifiers
* if one generator is seldom used. This makes hard for an attacker
* to infer how many packets were sent between two points in time.
*/
static u32 ip_idents_reserve(u32 hash, int segs)
{
u32 bucket, old, now = (u32)jiffies;
atomic_t *p_id;
u32 *p_tstamp;
u32 delta = 0;
bucket = hash & ip_idents_mask;
p_tstamp = ip_tstamps + bucket;
p_id = ip_idents + bucket;
old = READ_ONCE(*p_tstamp);
if (old != now && cmpxchg(p_tstamp, old, now) == old)
delta = prandom_u32_max(now - old);
/* If UBSAN reports an error there, please make sure your compiler
* supports -fno-strict-overflow before reporting it that was a bug
* in UBSAN, and it has been fixed in GCC-8.
*/
return atomic_add_return(segs + delta, p_id) - segs;
}
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
{
u32 hash, id;
/* 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 = siphash_3u32((__force u32)iph->daddr,
(__force u32)iph->saddr,
iph->protocol,
&net->ipv4.ip_id_key);
id = ip_idents_reserve(hash, segs);
iph->id = htons(id);
}
EXPORT_SYMBOL(__ip_select_ident);
static void ip_rt_fix_tos(struct flowi4 *fl4)
{
__u8 tos = RT_FL_TOS(fl4);
fl4->flowi4_tos = tos & IPTOS_RT_MASK;
if (tos & RTO_ONLINK)
fl4->flowi4_scope = RT_SCOPE_LINK;
}
static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
const struct sock *sk, const struct iphdr *iph,
int oif, __u8 tos, u8 prot, u32 mark,
int flow_flags)
{
__u8 scope = RT_SCOPE_UNIVERSE;
if (sk) {
const struct inet_sock *inet = inet_sk(sk);
oif = sk->sk_bound_dev_if;
mark = sk->sk_mark;
tos = ip_sock_rt_tos(sk);
scope = ip_sock_rt_scope(sk);
prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol;
}
flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope,
prot, flow_flags, iph->daddr, iph->saddr, 0, 0,
sock_net_uid(net, sk));
}
static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
const struct sock *sk)
{
const struct net *net = dev_net(skb->dev);
const struct iphdr *iph = ip_hdr(skb);
int oif = skb->dev->ifindex;
u8 prot = iph->protocol;
u32 mark = skb->mark;
__u8 tos = iph->tos;
__build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0);
}
static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
__be32 daddr = inet->inet_daddr;
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
ip_sock_rt_tos(sk) & IPTOS_RT_MASK,
ip_sock_rt_scope(sk),
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk),
daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
rcu_read_unlock();
}
static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk,
const struct sk_buff *skb)
{
if (skb)
build_skb_flow_key(fl4, skb, sk);
else
build_sk_flow_key(fl4, sk);
}
static DEFINE_SPINLOCK(fnhe_lock);
static void fnhe_flush_routes(struct fib_nh_exception *fnhe)
{
struct rtable *rt;
rt = rcu_dereference(fnhe->fnhe_rth_input);
if (rt) {
RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL);
dst_dev_put(&rt->dst);
dst_release(&rt->dst);
}
rt = rcu_dereference(fnhe->fnhe_rth_output);
if (rt) {
RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL);
dst_dev_put(&rt->dst);
dst_release(&rt->dst);
}
}
static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash)
{
struct fib_nh_exception __rcu **fnhe_p, **oldest_p;
struct fib_nh_exception *fnhe, *oldest = NULL;
for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) {
fnhe = rcu_dereference_protected(*fnhe_p,
lockdep_is_held(&fnhe_lock));
if (!fnhe)
break;
if (!oldest ||
time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) {
oldest = fnhe;
oldest_p = fnhe_p;
}
}
fnhe_flush_routes(oldest);
*oldest_p = oldest->fnhe_next;
kfree_rcu(oldest, rcu);
}
static u32 fnhe_hashfun(__be32 daddr)
{
static siphash_aligned_key_t fnhe_hash_key;
u64 hval;
net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key));
hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key);
return hash_64(hval, FNHE_HASH_SHIFT);
}
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) {
rt->rt_flags |= RTCF_REDIRECTED;
rt->rt_uses_gateway = 1;
rt->rt_gw_family = AF_INET;
rt->rt_gw4 = fnhe->fnhe_gw;
}
}
static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
__be32 gw, u32 pmtu, bool lock,
unsigned long expires)
{
struct fnhe_hash_bucket *hash;
struct fib_nh_exception *fnhe;
struct rtable *rt;
u32 genid, hval;
unsigned int i;
int depth;
genid = fnhe_genid(dev_net(nhc->nhc_dev));
hval = fnhe_hashfun(daddr);
spin_lock_bh(&fnhe_lock);
hash = rcu_dereference(nhc->nhc_exceptions);
if (!hash) {
hash = kcalloc(FNHE_HASH_SIZE, sizeof(*hash), GFP_ATOMIC);
if (!hash)
goto out_unlock;
rcu_assign_pointer(nhc->nhc_exceptions, hash);
}
hash += hval;
depth = 0;
for (fnhe = rcu_dereference(hash->chain); fnhe;
fnhe = rcu_dereference(fnhe->fnhe_next)) {
if (fnhe->fnhe_daddr == daddr)
break;
depth++;
}
if (fnhe) {
if (fnhe->fnhe_genid != genid)
fnhe->fnhe_genid = genid;
if (gw)
fnhe->fnhe_gw = gw;
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);
if (rt)
fill_route_from_fnhe(rt, fnhe);
rt = rcu_dereference(fnhe->fnhe_rth_output);
if (rt)
fill_route_from_fnhe(rt, fnhe);
} else {
/* Randomize max depth to avoid some side channels attacks. */
int max_depth = FNHE_RECLAIM_DEPTH +
prandom_u32_max(FNHE_RECLAIM_DEPTH);
while (depth > max_depth) {
fnhe_remove_oldest(hash);
depth--;
}
fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC);
if (!fnhe)
goto out_unlock;
fnhe->fnhe_next = hash->chain;
fnhe->fnhe_genid = genid;
fnhe->fnhe_daddr = daddr;
fnhe->fnhe_gw = gw;
fnhe->fnhe_pmtu = pmtu;
fnhe->fnhe_mtu_locked = lock;
fnhe->fnhe_expires = max(1UL, expires);
rcu_assign_pointer(hash->chain, fnhe);
/* Exception created; mark the cached routes for the nexthop
* stale, so anyone caching it rechecks if this exception
* applies to them.
*/
rt = rcu_dereference(nhc->nhc_rth_input);
if (rt)
rt->dst.obsolete = DST_OBSOLETE_KILL;
for_each_possible_cpu(i) {
struct rtable __rcu **prt;
prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i);
rt = rcu_dereference(*prt);
if (rt)
rt->dst.obsolete = DST_OBSOLETE_KILL;
}
}
fnhe->fnhe_stamp = jiffies;
out_unlock:
spin_unlock_bh(&fnhe_lock);
}
static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4,
bool kill_route)
{
__be32 new_gw = icmp_hdr(skb)->un.gateway;
__be32 old_gw = ip_hdr(skb)->saddr;
struct net_device *dev = skb->dev;
struct in_device *in_dev;
struct fib_result res;
struct neighbour *n;
struct net *net;
switch (icmp_hdr(skb)->code & 7) {
case ICMP_REDIR_NET:
case ICMP_REDIR_NETTOS:
case ICMP_REDIR_HOST:
case ICMP_REDIR_HOSTTOS:
break;
default:
return;
}
if (rt->rt_gw_family != AF_INET || rt->rt_gw4 != old_gw)
return;
in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
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))
goto reject_redirect;
if (!IN_DEV_SHARED_MEDIA(in_dev)) {
if (!inet_addr_onlink(in_dev, new_gw, old_gw))
goto reject_redirect;
if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev))
goto reject_redirect;
} else {
if (inet_addr_type(net, new_gw) != RTN_UNICAST)
goto reject_redirect;
}
n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
if (!n)
n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
if (!IS_ERR(n)) {
if (!(n->nud_state & NUD_VALID)) {
neigh_event_send(n, NULL);
} else {
if (fib_lookup(net, fl4, &res, 0) == 0) {
struct fib_nh_common *nhc;
fib_select_path(net, &res, fl4, skb);
nhc = FIB_RES_NHC(res);
update_or_create_fnhe(nhc, fl4->daddr, new_gw,
0, false,
jiffies + ip_rt_gc_timeout);
}
if (kill_route)
rt->dst.obsolete = DST_OBSOLETE_KILL;
call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
}
neigh_release(n);
}
return;
reject_redirect:
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (IN_DEV_LOG_MARTIANS(in_dev)) {
const struct iphdr *iph = (const struct iphdr *) skb->data;
__be32 daddr = iph->daddr;
__be32 saddr = iph->saddr;
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
;
}
static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
{
struct rtable *rt;
struct flowi4 fl4;
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct net *net = dev_net(skb->dev);
int oif = skb->dev->ifindex;
u8 prot = iph->protocol;
u32 mark = skb->mark;
__u8 tos = iph->tos;
rt = (struct rtable *) dst;
__build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
__ip_do_redirect(rt, skb, &fl4, true);
}
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
{
struct rtable *rt = (struct rtable *)dst;
struct dst_entry *ret = dst;
if (rt) {
if (dst->obsolete > 0) {
ip_rt_put(rt);
ret = NULL;
} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
rt->dst.expires) {
ip_rt_put(rt);
ret = NULL;
}
}
return ret;
}
/*
* Algorithm:
* 1. The first ip_rt_redirect_number redirects are sent
* with exponential backoff, then we stop sending them at all,
* assuming that the host ignores our redirects.
* 2. If we did not see packets requiring redirects
* during ip_rt_redirect_silence, we assume that the host
* forgot redirected route and start to send redirects again.
*
* This algorithm is much cheaper and more intelligent than dumb load limiting
* in icmp.c.
*
* NOTE. Do not forget to inhibit load limiting for redirects (redundant)
* and "frag. need" (breaks PMTU discovery) in icmp.c.
*/
void ip_rt_send_redirect(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct in_device *in_dev;
struct inet_peer *peer;
struct net *net;
int log_martians;
int vif;
rcu_read_lock();
in_dev = __in_dev_get_rcu(rt->dst.dev);
if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) {
rcu_read_unlock();
return;
}
log_martians = IN_DEV_LOG_MARTIANS(in_dev);
vif = l3mdev_master_ifindex_rcu(rt->dst.dev);
rcu_read_unlock();
net = dev_net(rt->dst.dev);
peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1);
if (!peer) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST,
rt_nexthop(rt, ip_hdr(skb)->daddr));
return;
}
/* No redirected packets during ip_rt_redirect_silence;
* reset the algorithm.
*/
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->n_redirects >= ip_rt_redirect_number) {
peer->rate_last = jiffies;
goto out_put_peer;
}
/* Check for load limit; set rate_last to the latest sent
* redirect.
*/
if (peer->n_redirects == 0 ||
time_after(jiffies,
(peer->rate_last +
(ip_rt_redirect_load << peer->n_redirects)))) {
__be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->n_redirects;
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (log_martians &&
peer->n_redirects == ip_rt_redirect_number)
net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
&ip_hdr(skb)->saddr, inet_iif(skb),
&ip_hdr(skb)->daddr, &gw);
#endif
}
out_put_peer:
inet_putpeer(peer);
}
static int ip_error(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = skb->dev;
struct in_device *in_dev;
struct inet_peer *peer;
unsigned long now;
struct net *net;
SKB_DR(reason);
bool send;
int code;
if (netif_is_l3_master(skb->dev)) {
dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif);
if (!dev)
goto out;
}
in_dev = __in_dev_get_rcu(dev);
/* IP on this device is disabled. */
if (!in_dev)
goto out;
net = dev_net(rt->dst.dev);
if (!IN_DEV_FORWARD(in_dev)) {
switch (rt->dst.error) {
case EHOSTUNREACH:
SKB_DR_SET(reason, IP_INADDRERRORS);
__IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS);
break;
case ENETUNREACH:
SKB_DR_SET(reason, IP_INNOROUTES);
__IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES);
break;
}
goto out;
}
switch (rt->dst.error) {
case EINVAL:
default:
goto out;
case EHOSTUNREACH:
code = ICMP_HOST_UNREACH;
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
SKB_DR_SET(reason, IP_INNOROUTES);
__IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
code = ICMP_PKT_FILTERED;
break;
}
peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr,
l3mdev_master_ifindex(skb->dev), 1);
send = true;
if (peer) {
now = jiffies;
peer->rate_tokens += now - peer->rate_last;
if (peer->rate_tokens > ip_rt_error_burst)
peer->rate_tokens = ip_rt_error_burst;
peer->rate_last = now;
if (peer->rate_tokens >= ip_rt_error_cost)
peer->rate_tokens -= ip_rt_error_cost;
else
send = false;
inet_putpeer(peer);
}
if (send)
icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
out: kfree_skb_reason(skb, reason);
return 0;
}
static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
struct dst_entry *dst = &rt->dst;
struct net *net = dev_net(dst->dev);
struct fib_result res;
bool lock = false;
u32 old_mtu;
if (ip_mtu_locked(dst))
return;
old_mtu = ipv4_mtu(dst);
if (old_mtu < mtu)
return;
if (mtu < net->ipv4.ip_rt_min_pmtu) {
lock = true;
mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu);
}
if (rt->rt_pmtu == mtu && !lock &&
time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2))
return;
rcu_read_lock();
if (fib_lookup(net, fl4, &res, 0) == 0) {
struct fib_nh_common *nhc;
fib_select_path(net, &res, fl4, NULL);
nhc = FIB_RES_NHC(res);
update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
jiffies + net->ipv4.ip_rt_mtu_expires);
}
rcu_read_unlock();
}
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
struct rtable *rt = (struct rtable *) dst;
struct flowi4 fl4;
ip_rt_build_flow_key(&fl4, sk, skb);
/* Don't make lookup fail for bridged encapsulations */
if (skb && netif_is_any_bridge_port(skb->dev))
fl4.flowi4_oif = 0;
__ip_rt_update_pmtu(rt, &fl4, mtu);
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
int oif, u8 protocol)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
struct flowi4 fl4;
struct rtable *rt;
u32 mark = IP4_REPLY_MARK(net, skb->mark);
__build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, mark,
0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_rt_update_pmtu(rt, &fl4, mtu);
ip_rt_put(rt);
}
}
EXPORT_SYMBOL_GPL(ipv4_update_pmtu);
static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
struct flowi4 fl4;
struct rtable *rt;
__build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0);
if (!fl4.flowi4_mark)
fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark);
rt = __ip_route_output_key(sock_net(sk), &fl4);
if (!IS_ERR(rt)) {
__ip_rt_update_pmtu(rt, &fl4, mtu);
ip_rt_put(rt);
}
}
void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
struct flowi4 fl4;
struct rtable *rt;
struct dst_entry *odst = NULL;
bool new = false;
struct net *net = sock_net(sk);
bh_lock_sock(sk);
if (!ip_sk_accept_pmtu(sk))
goto out;
odst = sk_dst_get(sk);
if (sock_owned_by_user(sk) || !odst) {
__ipv4_sk_update_pmtu(skb, sk, mtu);
goto out;
}
__build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
rt = (struct rtable *)odst;
if (odst->obsolete && !odst->ops->check(odst, 0)) {
rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
if (IS_ERR(rt))
goto out;
new = true;
}
__ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu);
if (!dst_check(&rt->dst, 0)) {
if (new)
dst_release(&rt->dst);
rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
if (IS_ERR(rt))
goto out;
new = true;
}
if (new)
sk_dst_set(sk, &rt->dst);
out:
bh_unlock_sock(sk);
dst_release(odst);
}
EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
void ipv4_redirect(struct sk_buff *skb, struct net *net,
int oif, u8 protocol)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
struct flowi4 fl4;
struct rtable *rt;
__build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, 0, 0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_do_redirect(rt, skb, &fl4, false);
ip_rt_put(rt);
}
}
EXPORT_SYMBOL_GPL(ipv4_redirect);
void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
struct flowi4 fl4;
struct rtable *rt;
struct net *net = sock_net(sk);
__build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_do_redirect(rt, skb, &fl4, false);
ip_rt_put(rt);
}
}
EXPORT_SYMBOL_GPL(ipv4_sk_redirect);
INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst,
u32 cookie)
{
struct rtable *rt = (struct rtable *) dst;
/* All IPV4 dsts are created with ->obsolete set to the value
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*
* When a PMTU/redirect information update invalidates a route,
* this is indicated by setting obsolete to DST_OBSOLETE_KILL or
* DST_OBSOLETE_DEAD.
*/
if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt))
return NULL;
return dst;
}
EXPORT_INDIRECT_CALLABLE(ipv4_dst_check);
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;
ipv4_send_dest_unreach(skb);
rt = skb_rtable(skb);
if (rt)
dst_set_expires(&rt->dst, 0);
}
static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb)
{
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;
}
/*
* We do not cache source address of outgoing interface,
* because it is used only by IP RR, TS and SRR options,
* so that it out of fast path.
*
* BTW remember: "addr" is allowed to be not aligned
* in IP options!
*/
void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
{
__be32 src;
if (rt_is_output_route(rt))
src = ip_hdr(skb)->saddr;
else {
struct fib_result res;
struct iphdr *iph = ip_hdr(skb);
struct flowi4 fl4 = {
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowi4_tos = RT_TOS(iph->tos),
.flowi4_oif = rt->dst.dev->ifindex,
.flowi4_iif = skb->dev->ifindex,
.flowi4_mark = skb->mark,
};
rcu_read_lock();
if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0)
src = fib_result_prefsrc(dev_net(rt->dst.dev), &res);
else
src = inet_select_addr(rt->dst.dev,
rt_nexthop(rt, iph->daddr),
RT_SCOPE_UNIVERSE);
rcu_read_unlock();
}
memcpy(addr, &src, 4);
}
#ifdef CONFIG_IP_ROUTE_CLASSID
static void set_class_tag(struct rtable *rt, u32 tag)
{
if (!(rt->dst.tclassid & 0xFFFF))
rt->dst.tclassid |= tag & 0xFFFF;
if (!(rt->dst.tclassid & 0xFFFF0000))
rt->dst.tclassid |= tag & 0xFFFF0000;
}
#endif
static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
{
struct net *net = dev_net(dst->dev);
unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr);
unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
net->ipv4.ip_rt_min_advmss);
return min(advmss, IPV4_MAX_PMTU - header_size);
}
INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst)
{
return ip_dst_mtu_maybe_forward(dst, false);
}
EXPORT_INDIRECT_CALLABLE(ipv4_mtu);
static void ip_del_fnhe(struct fib_nh_common *nhc, __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(nhc->nhc_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_common *nhc,
__be32 daddr)
{
struct fnhe_hash_bucket *hash = rcu_dereference(nhc->nhc_exceptions);
struct fib_nh_exception *fnhe;
u32 hval;
if (!hash)
return NULL;
hval = fnhe_hashfun(daddr);
for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
fnhe = rcu_dereference(fnhe->fnhe_next)) {
if (fnhe->fnhe_daddr == daddr) {
if (fnhe->fnhe_expires &&
time_after(jiffies, fnhe->fnhe_expires)) {
ip_del_fnhe(nhc, daddr);
break;
}
return fnhe;
}
}
return NULL;
}
/* MTU selection:
* 1. mtu on route is locked - use it
* 2. mtu from nexthop exception
* 3. mtu from egress device
*/
u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
{
struct fib_nh_common *nhc = res->nhc;
struct net_device *dev = nhc->nhc_dev;
struct fib_info *fi = res->fi;
u32 mtu = 0;
if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) ||
fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU))
mtu = fi->fib_mtu;
if (likely(!mtu)) {
struct fib_nh_exception *fnhe;
fnhe = find_exception(nhc, daddr);
if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires))
mtu = fnhe->fnhe_pmtu;
}
if (likely(!mtu))
mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU);
return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu);
}
static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
__be32 daddr, const bool do_cache)
{
bool ret = false;
spin_lock_bh(&fnhe_lock);
if (daddr == fnhe->fnhe_daddr) {
struct rtable __rcu **porig;
struct rtable *orig;
int genid = fnhe_genid(dev_net(rt->dst.dev));
if (rt_is_input_route(rt))
porig = &fnhe->fnhe_rth_input;
else
porig = &fnhe->fnhe_rth_output;
orig = rcu_dereference(*porig);
if (fnhe->fnhe_genid != genid) {
fnhe->fnhe_genid = genid;
fnhe->fnhe_gw = 0;
fnhe->fnhe_pmtu = 0;
fnhe->fnhe_expires = 0;
fnhe->fnhe_mtu_locked = false;
fnhe_flush_routes(fnhe);
orig = NULL;
}
fill_route_from_fnhe(rt, fnhe);
if (!rt->rt_gw4) {
rt->rt_gw4 = daddr;
rt->rt_gw_family = AF_INET;
}
if (do_cache) {
dst_hold(&rt->dst);
rcu_assign_pointer(*porig, rt);
if (orig) {
dst_dev_put(&orig->dst);
dst_release(&orig->dst);
}
ret = true;
}
fnhe->fnhe_stamp = jiffies;
}
spin_unlock_bh(&fnhe_lock);
return ret;
}
static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt)
{
struct rtable *orig, *prev, **p;
bool ret = true;
if (rt_is_input_route(rt)) {
p = (struct rtable **)&nhc->nhc_rth_input;
} else {
p = (struct rtable **)raw_cpu_ptr(nhc->nhc_pcpu_rth_output);
}
orig = *p;
/* hold dst before doing cmpxchg() to avoid race condition
* on this dst
*/
dst_hold(&rt->dst);
prev = cmpxchg(p, orig, rt);
if (prev == orig) {
if (orig) {
rt_add_uncached_list(orig);
dst_release(&orig->dst);
}
} else {
dst_release(&rt->dst);
ret = false;
}
return ret;
}
struct uncached_list {
spinlock_t lock;
struct list_head head;
struct list_head quarantine;
};
static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
void rt_add_uncached_list(struct rtable *rt)
{
struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
rt->rt_uncached_list = ul;
spin_lock_bh(&ul->lock);
list_add_tail(&rt->rt_uncached, &ul->head);
spin_unlock_bh(&ul->lock);
}
void rt_del_uncached_list(struct rtable *rt)
{
if (!list_empty(&rt->rt_uncached)) {
struct uncached_list *ul = rt->rt_uncached_list;
spin_lock_bh(&ul->lock);
list_del_init(&rt->rt_uncached);
spin_unlock_bh(&ul->lock);
}
}
static void ipv4_dst_destroy(struct dst_entry *dst)
{
struct rtable *rt = (struct rtable *)dst;
ip_dst_metrics_put(dst);
rt_del_uncached_list(rt);
}
void rt_flush_dev(struct net_device *dev)
{
struct rtable *rt, *safe;
int cpu;
for_each_possible_cpu(cpu) {
struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
if (list_empty(&ul->head))
continue;
spin_lock_bh(&ul->lock);
list_for_each_entry_safe(rt, safe, &ul->head, rt_uncached) {
if (rt->dst.dev != dev)
continue;
rt->dst.dev = blackhole_netdev;
netdev_ref_replace(dev, blackhole_netdev,
&rt->dst.dev_tracker, GFP_ATOMIC);
list_move(&rt->rt_uncached, &ul->quarantine);
}
spin_unlock_bh(&ul->lock);
}
}
static bool rt_cache_valid(const struct rtable *rt)
{
return rt &&
rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
!rt_is_expired(rt);
}
static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
const struct fib_result *res,
struct fib_nh_exception *fnhe,
struct fib_info *fi, u16 type, u32 itag,
const bool do_cache)
{
bool cached = false;
if (fi) {
struct fib_nh_common *nhc = FIB_RES_NHC(*res);
if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) {
rt->rt_uses_gateway = 1;
rt->rt_gw_family = nhc->nhc_gw_family;
/* only INET and INET6 are supported */
if (likely(nhc->nhc_gw_family == AF_INET))
rt->rt_gw4 = nhc->nhc_gw.ipv4;
else
rt->rt_gw6 = nhc->nhc_gw.ipv6;
}
ip_dst_init_metrics(&rt->dst, fi->fib_metrics);
#ifdef CONFIG_IP_ROUTE_CLASSID
if (nhc->nhc_family == AF_INET) {
struct fib_nh *nh;
nh = container_of(nhc, struct fib_nh, nh_common);
rt->dst.tclassid = nh->nh_tclassid;
}
#endif
rt->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate);
if (unlikely(fnhe))
cached = rt_bind_exception(rt, fnhe, daddr, do_cache);
else if (do_cache)
cached = rt_cache_route(nhc, rt);
if (unlikely(!cached)) {
/* Routes we intend to cache in nexthop exception or
* FIB nexthop have the DST_NOCACHE bit clear.
* However, if we are unsuccessful at storing this
* route into the cache we really need to set it.
*/
if (!rt->rt_gw4) {
rt->rt_gw_family = AF_INET;
rt->rt_gw4 = daddr;
}
rt_add_uncached_list(rt);
}
} else
rt_add_uncached_list(rt);
#ifdef CONFIG_IP_ROUTE_CLASSID
#ifdef CONFIG_IP_MULTIPLE_TABLES
set_class_tag(rt, res->tclassid);
#endif
set_class_tag(rt, itag);
#endif
}
struct rtable *rt_dst_alloc(struct net_device *dev,
unsigned int flags, u16 type,
bool noxfrm)
{
struct rtable *rt;
rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
(noxfrm ? DST_NOXFRM : 0));
if (rt) {
rt->rt_genid = rt_genid_ipv4(dev_net(dev));
rt->rt_flags = flags;
rt->rt_type = type;
rt->rt_is_input = 0;
rt->rt_iif = 0;
rt->rt_pmtu = 0;
rt->rt_mtu_locked = 0;
rt->rt_uses_gateway = 0;
rt->rt_gw_family = 0;
rt->rt_gw4 = 0;
INIT_LIST_HEAD(&rt->rt_uncached);
rt->dst.output = ip_output;
if (flags & RTCF_LOCAL)
rt->dst.input = ip_local_deliver;
}
return rt;
}
EXPORT_SYMBOL(rt_dst_alloc);
struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
{
struct rtable *new_rt;
new_rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
rt->dst.flags);
if (new_rt) {
new_rt->rt_genid = rt_genid_ipv4(dev_net(dev));
new_rt->rt_flags = rt->rt_flags;
new_rt->rt_type = rt->rt_type;
new_rt->rt_is_input = rt->rt_is_input;
new_rt->rt_iif = rt->rt_iif;
new_rt->rt_pmtu = rt->rt_pmtu;
new_rt->rt_mtu_locked = rt->rt_mtu_locked;
new_rt->rt_gw_family = rt->rt_gw_family;
if (rt->rt_gw_family == AF_INET)
new_rt->rt_gw4 = rt->rt_gw4;
else if (rt->rt_gw_family == AF_INET6)
new_rt->rt_gw6 = rt->rt_gw6;
INIT_LIST_HEAD(&new_rt->rt_uncached);
new_rt->dst.input = rt->dst.input;
new_rt->dst.output = rt->dst.output;
new_rt->dst.error = rt->dst.error;
new_rt->dst.lastuse = jiffies;
new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate);
}
return new_rt;
}
EXPORT_SYMBOL(rt_dst_clone);
/* called in rcu_read_lock() section */
int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev,
struct in_device *in_dev, u32 *itag)
{
int err;
/* Primary sanity checks. */
if (!in_dev)
return -EINVAL;
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
skb->protocol != htons(ETH_P_IP))
return -EINVAL;
if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev))
return -EINVAL;
if (ipv4_is_zeronet(saddr)) {
if (!ipv4_is_local_multicast(daddr) &&
ip_hdr(skb)->protocol != IPPROTO_IGMP)
return -EINVAL;
} else {
err = fib_validate_source(skb, saddr, 0, tos, 0, dev,
in_dev, itag);
if (err < 0)
return err;
}
return 0;
}
/* 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)
{
struct in_device *in_dev = __in_dev_get_rcu(dev);
unsigned int flags = RTCF_MULTICAST;
struct rtable *rth;
u32 itag = 0;
int err;
err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag);
if (err)
return err;
if (our)
flags |= RTCF_LOCAL;
if (IN_DEV_ORCONF(in_dev, NOPOLICY))
IPCB(skb)->flags |= IPSKB_NOPOLICY;
rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
false);
if (!rth)
return -ENOBUFS;
#ifdef CONFIG_IP_ROUTE_CLASSID
rth->dst.tclassid = itag;
#endif
rth->dst.output = ip_rt_bug;
rth->rt_is_input= 1;
#ifdef CONFIG_IP_MROUTE
if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev))
rth->dst.input = ip_mr_input;
#endif
RT_CACHE_STAT_INC(in_slow_mc);
skb_dst_drop(skb);
skb_dst_set(skb, &rth->dst);
return 0;
}
static void ip_handle_martian_source(struct net_device *dev,
struct in_device *in_dev,
struct sk_buff *skb,
__be32 daddr,
__be32 saddr)
{
RT_CACHE_STAT_INC(in_martian_src);
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) {
/*
* RFC1812 recommendation, if source is martian,
* the only hint is MAC header.
*/
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)) {
print_hex_dump(KERN_WARNING, "ll header: ",
DUMP_PREFIX_OFFSET, 16, 1,
skb_mac_header(skb),
dev->hard_header_len, false);
}
}
#endif
}
/* called in rcu_read_lock() section */
static int __mkroute_input(struct sk_buff *skb,
const struct fib_result *res,
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos)
{
struct fib_nh_common *nhc = FIB_RES_NHC(*res);
struct net_device *dev = nhc->nhc_dev;
struct fib_nh_exception *fnhe;
struct rtable *rth;
int err;
struct in_device *out_dev;
bool do_cache;
u32 itag = 0;
/* get a working reference to the output device */
out_dev = __in_dev_get_rcu(dev);
if (!out_dev) {
net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n");
return -EINVAL;
}
err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
in_dev->dev, in_dev, &itag);
if (err < 0) {
ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
goto cleanup;
}
do_cache = res->fi && !itag;
if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
skb->protocol == htons(ETH_P_IP)) {
__be32 gw;
gw = nhc->nhc_gw_family == AF_INET ? nhc->nhc_gw.ipv4 : 0;
if (IN_DEV_SHARED_MEDIA(out_dev) ||
inet_addr_onlink(out_dev, saddr, gw))
IPCB(skb)->flags |= IPSKB_DOREDIRECT;
}
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 &&
IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) {
err = -EINVAL;
goto cleanup;
}
}
if (IN_DEV_ORCONF(in_dev, NOPOLICY))
IPCB(skb)->flags |= IPSKB_NOPOLICY;
fnhe = find_exception(nhc, daddr);
if (do_cache) {
if (fnhe)
rth = rcu_dereference(fnhe->fnhe_rth_input);
else
rth = rcu_dereference(nhc->nhc_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
goto out;
}
}
rth = rt_dst_alloc(out_dev->dev, 0, res->type,
IN_DEV_ORCONF(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
goto cleanup;
}
rth->rt_is_input = 1;
RT_CACHE_STAT_INC(in_slow_tot);
rth->dst.input = ip_forward;
rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag,
do_cache);
lwtunnel_set_redirect(&rth->dst);
skb_dst_set(skb, &rth->dst);
out:
err = 0;
cleanup:
return err;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
/* To make ICMP packets follow the right flow, the multipath hash is
* calculated from the inner IP addresses.
*/
static void ip_multipath_l3_keys(const struct sk_buff *skb,
struct flow_keys *hash_keys)
{
const struct iphdr *outer_iph = ip_hdr(skb);
const struct iphdr *key_iph = outer_iph;
const struct iphdr *inner_iph;
const struct icmphdr *icmph;
struct iphdr _inner_iph;
struct icmphdr _icmph;
if (likely(outer_iph->protocol != IPPROTO_ICMP))
goto out;
if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0))
goto out;
icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph),
&_icmph);
if (!icmph)
goto out;
if (!icmp_is_err(icmph->type))
goto out;
inner_iph = skb_header_pointer(skb,
outer_iph->ihl * 4 + sizeof(_icmph),
sizeof(_inner_iph), &_inner_iph);
if (!inner_iph)
goto out;
key_iph = inner_iph;
out:
hash_keys->addrs.v4addrs.src = key_iph->saddr;
hash_keys->addrs.v4addrs.dst = key_iph->daddr;
}
static u32 fib_multipath_custom_hash_outer(const struct net *net,
const struct sk_buff *skb,
bool *p_has_inner)
{
u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
struct flow_keys keys, hash_keys;
if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
return 0;
memset(&hash_keys, 0, sizeof(hash_keys));
skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP);
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP)
hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP)
hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
hash_keys.basic.ip_proto = keys.basic.ip_proto;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
hash_keys.ports.src = keys.ports.src;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
hash_keys.ports.dst = keys.ports.dst;
*p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION);
return flow_hash_from_keys(&hash_keys);
}
static u32 fib_multipath_custom_hash_inner(const struct net *net,
const struct sk_buff *skb,
bool has_inner)
{
u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
struct flow_keys keys, hash_keys;
/* We assume the packet carries an encapsulation, but if none was
* encountered during dissection of the outer flow, then there is no
* point in calling the flow dissector again.
*/
if (!has_inner)
return 0;
if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK))
return 0;
memset(&hash_keys, 0, sizeof(hash_keys));
skb_flow_dissect_flow_keys(skb, &keys, 0);
if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION))
return 0;
if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP)
hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP)
hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
} else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP)
hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP)
hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL)
hash_keys.tags.flow_label = keys.tags.flow_label;
}
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO)
hash_keys.basic.ip_proto = keys.basic.ip_proto;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT)
hash_keys.ports.src = keys.ports.src;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT)
hash_keys.ports.dst = keys.ports.dst;
return flow_hash_from_keys(&hash_keys);
}
static u32 fib_multipath_custom_hash_skb(const struct net *net,
const struct sk_buff *skb)
{
u32 mhash, mhash_inner;
bool has_inner = true;
mhash = fib_multipath_custom_hash_outer(net, skb, &has_inner);
mhash_inner = fib_multipath_custom_hash_inner(net, skb, has_inner);
return jhash_2words(mhash, mhash_inner, 0);
}
static u32 fib_multipath_custom_hash_fl4(const struct net *net,
const struct flowi4 *fl4)
{
u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
struct flow_keys hash_keys;
if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
return 0;
memset(&hash_keys, 0, sizeof(hash_keys));
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP)
hash_keys.addrs.v4addrs.src = fl4->saddr;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP)
hash_keys.addrs.v4addrs.dst = fl4->daddr;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
hash_keys.basic.ip_proto = fl4->flowi4_proto;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
hash_keys.ports.src = fl4->fl4_sport;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
hash_keys.ports.dst = fl4->fl4_dport;
return flow_hash_from_keys(&hash_keys);
}
/* if skb is set it will be used and fl4 can be NULL */
int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
const struct sk_buff *skb, struct flow_keys *flkeys)
{
u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0;
struct flow_keys hash_keys;
u32 mhash = 0;
switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) {
case 0:
memset(&hash_keys, 0, sizeof(hash_keys));
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
if (skb) {
ip_multipath_l3_keys(skb, &hash_keys);
} else {
hash_keys.addrs.v4addrs.src = fl4->saddr;
hash_keys.addrs.v4addrs.dst = fl4->daddr;
}
mhash = flow_hash_from_keys(&hash_keys);
break;
case 1:
/* skb is currently provided only when forwarding */
if (skb) {
unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
struct flow_keys keys;
/* short-circuit if we already have L4 hash present */
if (skb->l4_hash)
return skb_get_hash_raw(skb) >> 1;
memset(&hash_keys, 0, sizeof(hash_keys));
if (!flkeys) {
skb_flow_dissect_flow_keys(skb, &keys, flag);
flkeys = &keys;
}
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src;
hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst;
hash_keys.ports.src = flkeys->ports.src;
hash_keys.ports.dst = flkeys->ports.dst;
hash_keys.basic.ip_proto = flkeys->basic.ip_proto;
} else {
memset(&hash_keys, 0, sizeof(hash_keys));
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
hash_keys.addrs.v4addrs.src = fl4->saddr;
hash_keys.addrs.v4addrs.dst = fl4->daddr;
hash_keys.ports.src = fl4->fl4_sport;
hash_keys.ports.dst = fl4->fl4_dport;
hash_keys.basic.ip_proto = fl4->flowi4_proto;
}
mhash = flow_hash_from_keys(&hash_keys);
break;
case 2:
memset(&hash_keys, 0, sizeof(hash_keys));
/* skb is currently provided only when forwarding */
if (skb) {
struct flow_keys keys;
skb_flow_dissect_flow_keys(skb, &keys, 0);
/* Inner can be v4 or v6 */
if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
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;
} else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src;
hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst;
hash_keys.tags.flow_label = keys.tags.flow_label;
hash_keys.basic.ip_proto = keys.basic.ip_proto;
} else {
/* Same as case 0 */
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
ip_multipath_l3_keys(skb, &hash_keys);
}
} else {
/* Same as case 0 */
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
hash_keys.addrs.v4addrs.src = fl4->saddr;
hash_keys.addrs.v4addrs.dst = fl4->daddr;
}
mhash = flow_hash_from_keys(&hash_keys);
break;
case 3:
if (skb)
mhash = fib_multipath_custom_hash_skb(net, skb);
else
mhash = fib_multipath_custom_hash_fl4(net, fl4);
break;
}
if (multipath_hash)
mhash = jhash_2words(mhash, multipath_hash, 0);
return mhash >> 1;
}
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
static int ip_mkroute_input(struct sk_buff *skb,
struct fib_result *res,
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos,
struct flow_keys *hkeys)
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && fib_info_num_path(res->fi) > 1) {
int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys);
fib_select_multipath(res, h);
}
#endif
/* create a routing cache entry */
return __mkroute_input(skb, res, in_dev, daddr, saddr, tos);
}
/* Implements all the saddr-related checks as ip_route_input_slow(),
* assuming daddr is valid and the destination is not a local broadcast one.
* Uses the provided hint instead of performing a route lookup.
*/
int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev,
const struct sk_buff *hint)
{
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct rtable *rt = skb_rtable(hint);
struct net *net = dev_net(dev);
int err = -EINVAL;
u32 tag = 0;
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
goto martian_source;
if (ipv4_is_zeronet(saddr))
goto martian_source;
if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
goto martian_source;
if (rt->rt_type != RTN_LOCAL)
goto skip_validate_source;
tos &= IPTOS_RT_MASK;
err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag);
if (err < 0)
goto martian_source;
skip_validate_source:
skb_dst_copy(skb, hint);
return 0;
martian_source:
ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
return err;
}
/* get device for dst_alloc with local routes */
static struct net_device *ip_rt_get_dev(struct net *net,
const struct fib_result *res)
{
struct fib_nh_common *nhc = res->fi ? res->nhc : NULL;
struct net_device *dev = NULL;
if (nhc)
dev = l3mdev_master_dev_rcu(nhc->nhc_dev);
return dev ? : net->loopback_dev;
}
/*
* NOTE. We drop all the packets that has local source
* addresses, because every properly looped back packet
* must have correct destination already attached by output routine.
* Changes in the enforced policies must be applied also to
* ip_route_use_hint().
*
* Such approach solves two big problems:
* 1. Not simplex devices are handled properly.
* 2. IP spoofing attempts are filtered with 100% of guarantee.
* called with rcu_read_lock()
*/
static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev,
struct fib_result *res)
{
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct flow_keys *flkeys = NULL, _flkeys;
struct net *net = dev_net(dev);
struct ip_tunnel_info *tun_info;
int err = -EINVAL;
unsigned int flags = 0;
u32 itag = 0;
struct rtable *rth;
struct flowi4 fl4;
bool do_cache = true;
/* IP on this device is disabled. */
if (!in_dev)
goto out;
/* Check for the most weird martians, which can be not detected
* by fib_lookup.
*/
tun_info = skb_tunnel_info(skb);
if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX))
fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id;
else
fl4.flowi4_tun_key.tun_id = 0;
skb_dst_drop(skb);
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
goto martian_source;
res->fi = NULL;
res->table = NULL;
if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0))
goto brd_input;
/* Accept zero addresses only to limited broadcast;
* I even do not know to fix it or not. Waiting for complains :-)
*/
if (ipv4_is_zeronet(saddr))
goto martian_source;
if (ipv4_is_zeronet(daddr))
goto martian_destination;
/* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(),
* and call it once if daddr or/and saddr are loopback addresses
*/
if (ipv4_is_loopback(daddr)) {
if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
goto martian_destination;
} else if (ipv4_is_loopback(saddr)) {
if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
goto martian_source;
}
/*
* Now we are ready to route packet.
*/
fl4.flowi4_l3mdev = 0;
fl4.flowi4_oif = 0;
fl4.flowi4_iif = dev->ifindex;
fl4.flowi4_mark = skb->mark;
fl4.flowi4_tos = tos;
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
fl4.flowi4_flags = 0;
fl4.daddr = daddr;
fl4.saddr = saddr;
fl4.flowi4_uid = sock_net_uid(net, NULL);
fl4.flowi4_multipath_hash = 0;
if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) {
flkeys = &_flkeys;
} else {
fl4.flowi4_proto = 0;
fl4.fl4_sport = 0;
fl4.fl4_dport = 0;
}
err = fib_lookup(net, &fl4, res, 0);
if (err != 0) {
if (!IN_DEV_FORWARD(in_dev))
err = -EHOSTUNREACH;
goto no_route;
}
if (res->type == RTN_BROADCAST) {
if (IN_DEV_BFORWARD(in_dev))
goto make_route;
/* not do cache if bc_forwarding is enabled */
if (IPV4_DEVCONF_ALL(net, BC_FORWARDING))
do_cache = false;
goto brd_input;
}
if (res->type == RTN_LOCAL) {
err = fib_validate_source(skb, saddr, daddr, tos,
0, dev, in_dev, &itag);
if (err < 0)
goto martian_source;
goto local_input;
}
if (!IN_DEV_FORWARD(in_dev)) {
err = -EHOSTUNREACH;
goto no_route;
}
if (res->type != RTN_UNICAST)
goto martian_destination;
make_route:
err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys);
out: return err;
brd_input:
if (skb->protocol != htons(ETH_P_IP))
goto e_inval;
if (!ipv4_is_zeronet(saddr)) {
err = fib_validate_source(skb, saddr, 0, tos, 0, dev,
in_dev, &itag);
if (err < 0)
goto martian_source;
}
flags |= RTCF_BROADCAST;
res->type = RTN_BROADCAST;
RT_CACHE_STAT_INC(in_brd);
local_input:
if (IN_DEV_ORCONF(in_dev, NOPOLICY))
IPCB(skb)->flags |= IPSKB_NOPOLICY;
do_cache &= res->fi && !itag;
if (do_cache) {
struct fib_nh_common *nhc = FIB_RES_NHC(*res);
rth = rcu_dereference(nhc->nhc_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
err = 0;
goto out;
}
}
rth = rt_dst_alloc(ip_rt_get_dev(net, res),
flags | RTCF_LOCAL, res->type, false);
if (!rth)
goto e_nobufs;
rth->dst.output= ip_rt_bug;
#ifdef CONFIG_IP_ROUTE_CLASSID
rth->dst.tclassid = itag;
#endif
rth->rt_is_input = 1;
RT_CACHE_STAT_INC(in_slow_tot);
if (res->type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
if (do_cache) {
struct fib_nh_common *nhc = FIB_RES_NHC(*res);
rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate);
if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
WARN_ON(rth->dst.input == lwtunnel_input);
rth->dst.lwtstate->orig_input = rth->dst.input;
rth->dst.input = lwtunnel_input;
}
if (unlikely(!rt_cache_route(nhc, rth)))
rt_add_uncached_list(rth);
}
skb_dst_set(skb, &rth->dst);
err = 0;
goto out;
no_route:
RT_CACHE_STAT_INC(in_no_route);
res->type = RTN_UNREACHABLE;
res->fi = NULL;
res->table = NULL;
goto local_input;
/*
* Do not cache martian addresses: they should be logged (RFC1812)
*/
martian_destination:
RT_CACHE_STAT_INC(in_martian_dst);
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (IN_DEV_LOG_MARTIANS(in_dev))
net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n",
&daddr, &saddr, dev->name);
#endif
e_inval:
err = -EINVAL;
goto out;
e_nobufs:
err = -ENOBUFS;
goto out;
martian_source:
ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
goto out;
}
/* called with rcu_read_lock held */
static int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, struct fib_result *res)
{
/* Multicast recognition logic is moved from route cache to here.
* The problem was that too many Ethernet cards have broken/missing
* hardware multicast filters :-( As result the host on multicasting
* network acquires a lot of useless route cache entries, sort of
* SDR messages from all the world. Now we try to get rid of them.
* Really, provided software IP multicast filter is organized
* reasonably (at least, hashed), it does not result in a slowdown
* comparing with route cache reject entries.
* Note, that multicast routers are not affected, because
* route cache entry is created eventually.
*/
if (ipv4_is_multicast(daddr)) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
int our = 0;
int err = -EINVAL;
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 (!our && netif_is_l3_slave(dev)) {
struct in_device *l3_in_dev;
l3_in_dev = __in_dev_get_rcu(skb->dev);
if (l3_in_dev)
our = ip_check_mc_rcu(l3_in_dev, daddr, saddr,
ip_hdr(skb)->protocol);
}
if (our
#ifdef CONFIG_IP_MROUTE
||
(!ipv4_is_local_multicast(daddr) &&
IN_DEV_MFORWARD(in_dev))
#endif
) {
err = ip_route_input_mc(skb, daddr, saddr,
tos, dev, our);
}
return err;
}
return ip_route_input_slow(skb, daddr, saddr, tos, dev, res);
}
int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev)
{
struct fib_result res;
int err;
tos &= IPTOS_RT_MASK;
rcu_read_lock();
err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res);
rcu_read_unlock();
return err;
}
EXPORT_SYMBOL(ip_route_input_noref);
/* called with rcu_read_lock() */
static struct rtable *__mkroute_output(const struct fib_result *res,
const struct flowi4 *fl4, int orig_oif,
struct net_device *dev_out,
unsigned int flags)
{
struct fib_info *fi = res->fi;
struct fib_nh_exception *fnhe;
struct in_device *in_dev;
u16 type = res->type;
struct rtable *rth;
bool do_cache;
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) &&
!netif_is_l3_master(dev_out))
return ERR_PTR(-EINVAL);
if (ipv4_is_lbcast(fl4->daddr))
type = RTN_BROADCAST;
else if (ipv4_is_multicast(fl4->daddr))
type = RTN_MULTICAST;
else if (ipv4_is_zeronet(fl4->daddr))
return ERR_PTR(-EINVAL);
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
do_cache = true;
if (type == RTN_BROADCAST) {
flags |= RTCF_BROADCAST | RTCF_LOCAL;
fi = NULL;
} else if (type == RTN_MULTICAST) {
flags |= RTCF_MULTICAST | RTCF_LOCAL;
if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr,
fl4->flowi4_proto))
flags &= ~RTCF_LOCAL;
else
do_cache = false;
/* If multicast route do not exist use
* default one, but do not gateway in this case.
* Yes, it is hack.
*/
if (fi && res->prefixlen < 4)
fi = NULL;
} else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
(orig_oif != dev_out->ifindex)) {
/* For local routes that require a particular output interface
* we do not want to cache the result. Caching the result
* causes incorrect behaviour when there are multiple source
* addresses on the interface, the end result being that if the
* intended recipient is waiting on that interface for the
* packet he won't receive it because it will be delivered on
* the loopback interface and the IP_PKTINFO ipi_ifindex will
* be set to the loopback interface as well.
*/
do_cache = false;
}
fnhe = NULL;
do_cache &= fi != NULL;
if (fi) {
struct fib_nh_common *nhc = FIB_RES_NHC(*res);
struct rtable __rcu **prth;
fnhe = find_exception(nhc, fl4->daddr);
if (!do_cache)
goto add;
if (fnhe) {
prth = &fnhe->fnhe_rth_output;
} else {
if (unlikely(fl4->flowi4_flags &
FLOWI_FLAG_KNOWN_NH &&
!(nhc->nhc_gw_family &&
nhc->nhc_scope == RT_SCOPE_LINK))) {
do_cache = false;
goto add;
}
prth = raw_cpu_ptr(nhc->nhc_pcpu_rth_output);
}
rth = rcu_dereference(*prth);
if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))
return rth;
}
add:
rth = rt_dst_alloc(dev_out, flags, type,
IN_DEV_ORCONF(in_dev, NOXFRM));
if (!rth)
return ERR_PTR(-ENOBUFS);
rth->rt_iif = orig_oif;
RT_CACHE_STAT_INC(out_slow_tot);
if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
if (flags & RTCF_LOCAL &&
!(dev_out->flags & IFF_LOOPBACK)) {
rth->dst.output = ip_mc_output;
RT_CACHE_STAT_INC(out_slow_mc);
}
#ifdef CONFIG_IP_MROUTE
if (type == RTN_MULTICAST) {
if (IN_DEV_MFORWARD(in_dev) &&
!ipv4_is_local_multicast(fl4->daddr)) {
rth->dst.input = ip_mr_input;
rth->dst.output = ip_mc_output;
}
}
#endif
}
rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache);
lwtunnel_set_redirect(&rth->dst);
return rth;
}
/*
* Major route resolver routine.
*/
struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
const struct sk_buff *skb)
{
struct fib_result res = {
.type = RTN_UNSPEC,
.fi = NULL,
.table = NULL,
.tclassid = 0,
};
struct rtable *rth;
fl4->flowi4_iif = LOOPBACK_IFINDEX;
ip_rt_fix_tos(fl4);
rcu_read_lock();
rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb);
rcu_read_unlock();
return rth;
}
EXPORT_SYMBOL_GPL(ip_route_output_key_hash);
struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
struct fib_result *res,
const struct sk_buff *skb)
{
struct net_device *dev_out = NULL;
int orig_oif = fl4->flowi4_oif;
unsigned int flags = 0;
struct rtable *rth;
int err;
if (fl4->saddr) {
if (ipv4_is_multicast(fl4->saddr) ||
ipv4_is_lbcast(fl4->saddr) ||
ipv4_is_zeronet(fl4->saddr)) {
rth = ERR_PTR(-EINVAL);
goto out;
}
rth = ERR_PTR(-ENETUNREACH);
/* I removed check for oif == dev_out->oif here.
* It was wrong for two reasons:
* 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 (fl4->flowi4_oif == 0 &&
(ipv4_is_multicast(fl4->daddr) ||
ipv4_is_lbcast(fl4->daddr))) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
dev_out = __ip_dev_find(net, fl4->saddr, false);
if (!dev_out)
goto out;
/* Special hack: user can direct multicasts
* and limited broadcast via necessary interface
* without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
* This hack is not just for fun, it allows
* vic,vat and friends to work.
* They bind socket to loopback, set ttl to zero
* and expect that it will work.
* From the viewpoint of routing cache they are broken,
* because we are not allowed to build multicast path
* with loopback source addr (look, routing cache
* cannot know, that ttl is zero, so that packet
* will not leave this host and route is valid).
* Luckily, this hack is good workaround.
*/
fl4->flowi4_oif = dev_out->ifindex;
goto make_route;
}
if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
if (!__ip_dev_find(net, fl4->saddr, false))
goto out;
}
}
if (fl4->flowi4_oif) {
dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif);
rth = ERR_PTR(-ENODEV);
if (!dev_out)
goto out;
/* RACE: Check return value of inet_select_addr instead. */
if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) {
rth = ERR_PTR(-ENETUNREACH);
goto out;
}
if (ipv4_is_local_multicast(fl4->daddr) ||
ipv4_is_lbcast(fl4->daddr) ||
fl4->flowi4_proto == IPPROTO_IGMP) {
if (!fl4->saddr)
fl4->saddr = inet_select_addr(dev_out, 0,
RT_SCOPE_LINK);
goto make_route;
}
if (!fl4->saddr) {
if (ipv4_is_multicast(fl4->daddr))
fl4->saddr = inet_select_addr(dev_out, 0,
fl4->flowi4_scope);
else if (!fl4->daddr)
fl4->saddr = inet_select_addr(dev_out, 0,
RT_SCOPE_HOST);
}
}
if (!fl4->daddr) {
fl4->daddr = fl4->saddr;
if (!fl4->daddr)
fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK);
dev_out = net->loopback_dev;
fl4->flowi4_oif = LOOPBACK_IFINDEX;
res->type = RTN_LOCAL;
flags |= RTCF_LOCAL;
goto make_route;
}
err = fib_lookup(net, fl4, res, 0);
if (err) {
res->fi = NULL;
res->table = NULL;
if (fl4->flowi4_oif &&
(ipv4_is_multicast(fl4->daddr) || !fl4->flowi4_l3mdev)) {
/* Apparently, routing tables are wrong. Assume,
* that the destination is on link.
*
* WHY? DW.
* Because we are allowed to send to iface
* even if it has NO routes and NO assigned
* addresses. When oif is specified, routing
* tables are looked up with only one purpose:
* to catch if destination is gatewayed, rather than
* direct. Moreover, if MSG_DONTROUTE is set,
* we send packet, ignoring both routing tables
* and ifaddr state. --ANK
*
*
* We could make it even if oif is unknown,
* likely IPv6, but we do not.
*/
if (fl4->saddr == 0)
fl4->saddr = inet_select_addr(dev_out, 0,
RT_SCOPE_LINK);
res->type = RTN_UNICAST;
goto make_route;
}
rth = ERR_PTR(err);
goto out;
}
if (res->type == RTN_LOCAL) {
if (!fl4->saddr) {
if (res->fi->fib_prefsrc)
fl4->saddr = res->fi->fib_prefsrc;
else
fl4->saddr = fl4->daddr;
}
/* L3 master device is the loopback for that domain */
dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? :
net->loopback_dev;
/* make sure orig_oif points to fib result device even
* though packet rx/tx happens over loopback or l3mdev
*/
orig_oif = FIB_RES_OIF(*res);
fl4->flowi4_oif = dev_out->ifindex;
flags |= RTCF_LOCAL;
goto make_route;
}
fib_select_path(net, res, fl4, skb);
dev_out = FIB_RES_DEV(*res);
make_route:
rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);
out:
return rth;
}
static struct dst_ops ipv4_dst_blackhole_ops = {
.family = AF_INET,
.default_advmss = ipv4_default_advmss,
.neigh_lookup = ipv4_neigh_lookup,
.check = dst_blackhole_check,
.cow_metrics = dst_blackhole_cow_metrics,
.update_pmtu = dst_blackhole_update_pmtu,
.redirect = dst_blackhole_redirect,
.mtu = dst_blackhole_mtu,
};
struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
struct rtable *ort = (struct rtable *) dst_orig;
struct rtable *rt;
rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0);
if (rt) {
struct dst_entry *new = &rt->dst;
new->__use = 1;
new->input = dst_discard;
new->output = dst_discard_out;
new->dev = net->loopback_dev;
netdev_hold(new->dev, &new->dev_tracker, GFP_ATOMIC);
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;
rt->rt_type = ort->rt_type;
rt->rt_uses_gateway = ort->rt_uses_gateway;
rt->rt_gw_family = ort->rt_gw_family;
if (rt->rt_gw_family == AF_INET)
rt->rt_gw4 = ort->rt_gw4;
else if (rt->rt_gw_family == AF_INET6)
rt->rt_gw6 = ort->rt_gw6;
INIT_LIST_HEAD(&rt->rt_uncached);
}
dst_release(dst_orig);
return rt ? &rt->dst : ERR_PTR(-ENOMEM);
}
struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
const struct sock *sk)
{
struct rtable *rt = __ip_route_output_key(net, flp4);
if (IS_ERR(rt))
return rt;
if (flp4->flowi4_proto) {
flp4->flowi4_oif = rt->dst.dev->ifindex;
rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst,
flowi4_to_flowi(flp4),
sk, 0);
}
return rt;
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
struct rtable *ip_route_output_tunnel(struct sk_buff *skb,
struct net_device *dev,
struct net *net, __be32 *saddr,
const struct ip_tunnel_info *info,
u8 protocol, bool use_cache)
{
#ifdef CONFIG_DST_CACHE
struct dst_cache *dst_cache;
#endif
struct rtable *rt = NULL;
struct flowi4 fl4;
__u8 tos;
#ifdef CONFIG_DST_CACHE
dst_cache = (struct dst_cache *)&info->dst_cache;
if (use_cache) {
rt = dst_cache_get_ip4(dst_cache, saddr);
if (rt)
return rt;
}
#endif
memset(&fl4, 0, sizeof(fl4));
fl4.flowi4_mark = skb->mark;
fl4.flowi4_proto = protocol;
fl4.daddr = info->key.u.ipv4.dst;
fl4.saddr = info->key.u.ipv4.src;
tos = info->key.tos;
fl4.flowi4_tos = RT_TOS(tos);
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
return ERR_PTR(-ENETUNREACH);
}
if (rt->dst.dev == dev) { /* is this necessary? */
netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr);
ip_rt_put(rt);
return ERR_PTR(-ELOOP);
}
#ifdef CONFIG_DST_CACHE
if (use_cache)
dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
#endif
*saddr = fl4.saddr;
return rt;
}
EXPORT_SYMBOL_GPL(ip_route_output_tunnel);
/* called with rcu_read_lock held */
static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
struct rtable *rt, u32 table_id, struct flowi4 *fl4,
struct sk_buff *skb, u32 portid, u32 seq,
unsigned int flags)
{
struct rtmsg *r;
struct nlmsghdr *nlh;
unsigned long expires = 0;
u32 error;
u32 metrics[RTAX_MAX];
nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
r->rtm_family = AF_INET;
r->rtm_dst_len = 32;
r->rtm_src_len = 0;
r->rtm_tos = fl4 ? fl4->flowi4_tos : 0;
r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT;
if (nla_put_u32(skb, RTA_TABLE, table_id))
goto nla_put_failure;
r->rtm_type = rt->rt_type;
r->rtm_scope = RT_SCOPE_UNIVERSE;
r->rtm_protocol = RTPROT_UNSPEC;
r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
if (rt->rt_flags & RTCF_NOTIFY)
r->rtm_flags |= RTM_F_NOTIFY;
if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
r->rtm_flags |= RTCF_DOREDIRECT;
if (nla_put_in_addr(skb, RTA_DST, dst))
goto nla_put_failure;
if (src) {
r->rtm_src_len = 32;
if (nla_put_in_addr(skb, RTA_SRC, src))
goto nla_put_failure;
}
if (rt->dst.dev &&
nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
goto nla_put_failure;
if (rt->dst.lwtstate &&
lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (rt->dst.tclassid &&
nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid))
goto nla_put_failure;
#endif
if (fl4 && !rt_is_input_route(rt) &&
fl4->saddr != src) {