blob: d25dc83bac627feea94e35a1f455df8a315f7e16 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Linux INET6 implementation
* FIB front-end.
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*/
/* Changes:
*
* YOSHIFUJI Hideaki @USAGI
* reworked default router selection.
* - respect outgoing interface
* - select from (probably) reachable routers (i.e.
* routers in REACHABLE, STALE, DELAY or PROBE states).
* - always select the same router if it is (probably)
* reachable. otherwise, round-robin the list.
* Ville Nuorvala
* Fixed routing subtrees.
*/
#define pr_fmt(fmt) "IPv6: " fmt
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/types.h>
#include <linux/times.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/route.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/mroute6.h>
#include <linux/init.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/jhash.h>
#include <linux/siphash.h>
#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/tcp.h>
#include <linux/rtnetlink.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/netlink.h>
#include <net/rtnh.h>
#include <net/lwtunnel.h>
#include <net/ip_tunnels.h>
#include <net/l3mdev.h>
#include <net/ip.h>
#include <linux/uaccess.h>
#include <linux/btf_ids.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
static int ip6_rt_type_to_error(u8 fib6_type);
#define CREATE_TRACE_POINTS
#include <trace/events/fib6.h>
EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup);
#undef CREATE_TRACE_POINTS
enum rt6_nud_state {
RT6_NUD_FAIL_HARD = -3,
RT6_NUD_FAIL_PROBE = -2,
RT6_NUD_FAIL_DO_RR = -1,
RT6_NUD_SUCCEED = 1
};
INDIRECT_CALLABLE_SCOPE
struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ip6_default_advmss(const struct dst_entry *dst);
INDIRECT_CALLABLE_SCOPE
unsigned int ip6_mtu(const struct dst_entry *dst);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void ip6_dst_destroy(struct dst_entry *);
static void ip6_dst_ifdown(struct dst_entry *,
struct net_device *dev, int how);
static int ip6_dst_gc(struct dst_ops *ops);
static int ip6_pkt_discard(struct sk_buff *skb);
static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static int ip6_pkt_prohibit(struct sk_buff *skb);
static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static void ip6_link_failure(struct sk_buff *skb);
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu,
bool confirm_neigh);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
int strict);
static size_t rt6_nlmsg_size(struct fib6_info *f6i);
static int rt6_fill_node(struct net *net, struct sk_buff *skb,
struct fib6_info *rt, struct dst_entry *dst,
struct in6_addr *dest, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags);
static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
const struct in6_addr *daddr,
const struct in6_addr *saddr);
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct fib6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref);
static struct fib6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev);
#endif
struct uncached_list {
spinlock_t lock;
struct list_head head;
struct list_head quarantine;
};
static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
void rt6_uncached_list_add(struct rt6_info *rt)
{
struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list);
rt->rt6i_uncached_list = ul;
spin_lock_bh(&ul->lock);
list_add_tail(&rt->rt6i_uncached, &ul->head);
spin_unlock_bh(&ul->lock);
}
void rt6_uncached_list_del(struct rt6_info *rt)
{
if (!list_empty(&rt->rt6i_uncached)) {
struct uncached_list *ul = rt->rt6i_uncached_list;
spin_lock_bh(&ul->lock);
list_del_init(&rt->rt6i_uncached);
spin_unlock_bh(&ul->lock);
}
}
static void rt6_uncached_list_flush_dev(struct net_device *dev)
{
int cpu;
for_each_possible_cpu(cpu) {
struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
struct rt6_info *rt, *safe;
if (list_empty(&ul->head))
continue;
spin_lock_bh(&ul->lock);
list_for_each_entry_safe(rt, safe, &ul->head, rt6i_uncached) {
struct inet6_dev *rt_idev = rt->rt6i_idev;
struct net_device *rt_dev = rt->dst.dev;
bool handled = false;
if (rt_idev->dev == dev) {
rt->rt6i_idev = in6_dev_get(blackhole_netdev);
in6_dev_put(rt_idev);
handled = true;
}
if (rt_dev == dev) {
rt->dst.dev = blackhole_netdev;
dev_replace_track(rt_dev, blackhole_netdev,
&rt->dst.dev_tracker,
GFP_ATOMIC);
handled = true;
}
if (handled)
list_move(&rt->rt6i_uncached,
&ul->quarantine);
}
spin_unlock_bh(&ul->lock);
}
}
static inline const void *choose_neigh_daddr(const struct in6_addr *p,
struct sk_buff *skb,
const void *daddr)
{
if (!ipv6_addr_any(p))
return (const void *) p;
else if (skb)
return &ipv6_hdr(skb)->daddr;
return daddr;
}
struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
struct net_device *dev,
struct sk_buff *skb,
const void *daddr)
{
struct neighbour *n;
daddr = choose_neigh_daddr(gw, skb, daddr);
n = __ipv6_neigh_lookup(dev, daddr);
if (n)
return n;
n = neigh_create(&nd_tbl, daddr, dev);
return IS_ERR(n) ? NULL : n;
}
static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr)
{
const struct rt6_info *rt = container_of(dst, struct rt6_info, dst);
return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any),
dst->dev, skb, daddr);
}
static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr)
{
struct net_device *dev = dst->dev;
struct rt6_info *rt = (struct rt6_info *)dst;
daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr);
if (!daddr)
return;
if (dev->flags & (IFF_NOARP | IFF_LOOPBACK))
return;
if (ipv6_addr_is_multicast((const struct in6_addr *)daddr))
return;
__ipv6_confirm_neigh(dev, daddr);
}
static struct dst_ops ip6_dst_ops_template = {
.family = AF_INET6,
.gc = ip6_dst_gc,
.gc_thresh = 1024,
.check = ip6_dst_check,
.default_advmss = ip6_default_advmss,
.mtu = ip6_mtu,
.cow_metrics = dst_cow_metrics_generic,
.destroy = ip6_dst_destroy,
.ifdown = ip6_dst_ifdown,
.negative_advice = ip6_negative_advice,
.link_failure = ip6_link_failure,
.update_pmtu = ip6_rt_update_pmtu,
.redirect = rt6_do_redirect,
.local_out = __ip6_local_out,
.neigh_lookup = ip6_dst_neigh_lookup,
.confirm_neigh = ip6_confirm_neigh,
};
static struct dst_ops ip6_dst_blackhole_ops = {
.family = AF_INET6,
.default_advmss = ip6_default_advmss,
.neigh_lookup = ip6_dst_neigh_lookup,
.check = ip6_dst_check,
.destroy = ip6_dst_destroy,
.cow_metrics = dst_cow_metrics_generic,
.update_pmtu = dst_blackhole_update_pmtu,
.redirect = dst_blackhole_redirect,
.mtu = dst_blackhole_mtu,
};
static const u32 ip6_template_metrics[RTAX_MAX] = {
[RTAX_HOPLIMIT - 1] = 0,
};
static const struct fib6_info fib6_null_entry_template = {
.fib6_flags = (RTF_REJECT | RTF_NONEXTHOP),
.fib6_protocol = RTPROT_KERNEL,
.fib6_metric = ~(u32)0,
.fib6_ref = REFCOUNT_INIT(1),
.fib6_type = RTN_UNREACHABLE,
.fib6_metrics = (struct dst_metrics *)&dst_default_metrics,
};
static const struct rt6_info ip6_null_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
.obsolete = DST_OBSOLETE_FORCE_CHK,
.error = -ENETUNREACH,
.input = ip6_pkt_discard,
.output = ip6_pkt_discard_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
};
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
static const struct rt6_info ip6_prohibit_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
.obsolete = DST_OBSOLETE_FORCE_CHK,
.error = -EACCES,
.input = ip6_pkt_prohibit,
.output = ip6_pkt_prohibit_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
};
static const struct rt6_info ip6_blk_hole_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
.obsolete = DST_OBSOLETE_FORCE_CHK,
.error = -EINVAL,
.input = dst_discard,
.output = dst_discard_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
};
#endif
static void rt6_info_init(struct rt6_info *rt)
{
memset_after(rt, 0, dst);
INIT_LIST_HEAD(&rt->rt6i_uncached);
}
/* allocate dst with ip6_dst_ops */
struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
int flags)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
1, DST_OBSOLETE_FORCE_CHK, flags);
if (rt) {
rt6_info_init(rt);
atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc);
}
return rt;
}
EXPORT_SYMBOL(ip6_dst_alloc);
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct fib6_info *from;
struct inet6_dev *idev;
ip_dst_metrics_put(dst);
rt6_uncached_list_del(rt);
idev = rt->rt6i_idev;
if (idev) {
rt->rt6i_idev = NULL;
in6_dev_put(idev);
}
from = xchg((__force struct fib6_info **)&rt->from, NULL);
fib6_info_release(from);
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int how)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
if (idev && idev->dev != blackhole_netdev) {
struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev);
if (blackhole_idev) {
rt->rt6i_idev = blackhole_idev;
in6_dev_put(idev);
}
}
}
static bool __rt6_check_expired(const struct rt6_info *rt)
{
if (rt->rt6i_flags & RTF_EXPIRES)
return time_after(jiffies, rt->dst.expires);
else
return false;
}
static bool rt6_check_expired(const struct rt6_info *rt)
{
struct fib6_info *from;
from = rcu_dereference(rt->from);
if (rt->rt6i_flags & RTF_EXPIRES) {
if (time_after(jiffies, rt->dst.expires))
return true;
} else if (from) {
return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK ||
fib6_check_expired(from);
}
return false;
}
void fib6_select_path(const struct net *net, struct fib6_result *res,
struct flowi6 *fl6, int oif, bool have_oif_match,
const struct sk_buff *skb, int strict)
{
struct fib6_info *sibling, *next_sibling;
struct fib6_info *match = res->f6i;
if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
goto out;
if (match->nh && have_oif_match && res->nh)
return;
/* We might have already computed the hash for ICMPv6 errors. In such
* case it will always be non-zero. Otherwise now is the time to do it.
*/
if (!fl6->mp_hash &&
(!match->nh || nexthop_is_multipath(match->nh)))
fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
if (unlikely(match->nh)) {
nexthop_path_fib6_result(res, fl6->mp_hash);
return;
}
if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
goto out;
list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
fib6_siblings) {
const struct fib6_nh *nh = sibling->fib6_nh;
int nh_upper_bound;
nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
if (fl6->mp_hash > nh_upper_bound)
continue;
if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0)
break;
match = sibling;
break;
}
out:
res->f6i = match;
res->nh = match->fib6_nh;
}
/*
* Route lookup. rcu_read_lock() should be held.
*/
static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh,
const struct in6_addr *saddr, int oif, int flags)
{
const struct net_device *dev;
if (nh->fib_nh_flags & RTNH_F_DEAD)
return false;
dev = nh->fib_nh_dev;
if (oif) {
if (dev->ifindex == oif)
return true;
} else {
if (ipv6_chk_addr(net, saddr, dev,
flags & RT6_LOOKUP_F_IFACE))
return true;
}
return false;
}
struct fib6_nh_dm_arg {
struct net *net;
const struct in6_addr *saddr;
int oif;
int flags;
struct fib6_nh *nh;
};
static int __rt6_nh_dev_match(struct fib6_nh *nh, void *_arg)
{
struct fib6_nh_dm_arg *arg = _arg;
arg->nh = nh;
return __rt6_device_match(arg->net, nh, arg->saddr, arg->oif,
arg->flags);
}
/* returns fib6_nh from nexthop or NULL */
static struct fib6_nh *rt6_nh_dev_match(struct net *net, struct nexthop *nh,
struct fib6_result *res,
const struct in6_addr *saddr,
int oif, int flags)
{
struct fib6_nh_dm_arg arg = {
.net = net,
.saddr = saddr,
.oif = oif,
.flags = flags,
};
if (nexthop_is_blackhole(nh))
return NULL;
if (nexthop_for_each_fib6_nh(nh, __rt6_nh_dev_match, &arg))
return arg.nh;
return NULL;
}
static void rt6_device_match(struct net *net, struct fib6_result *res,
const struct in6_addr *saddr, int oif, int flags)
{
struct fib6_info *f6i = res->f6i;
struct fib6_info *spf6i;
struct fib6_nh *nh;
if (!oif && ipv6_addr_any(saddr)) {
if (unlikely(f6i->nh)) {
nh = nexthop_fib6_nh(f6i->nh);
if (nexthop_is_blackhole(f6i->nh))
goto out_blackhole;
} else {
nh = f6i->fib6_nh;
}
if (!(nh->fib_nh_flags & RTNH_F_DEAD))
goto out;
}
for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) {
bool matched = false;
if (unlikely(spf6i->nh)) {
nh = rt6_nh_dev_match(net, spf6i->nh, res, saddr,
oif, flags);
if (nh)
matched = true;
} else {
nh = spf6i->fib6_nh;
if (__rt6_device_match(net, nh, saddr, oif, flags))
matched = true;
}
if (matched) {
res->f6i = spf6i;
goto out;
}
}
if (oif && flags & RT6_LOOKUP_F_IFACE) {
res->f6i = net->ipv6.fib6_null_entry;
nh = res->f6i->fib6_nh;
goto out;
}
if (unlikely(f6i->nh)) {
nh = nexthop_fib6_nh(f6i->nh);
if (nexthop_is_blackhole(f6i->nh))
goto out_blackhole;
} else {
nh = f6i->fib6_nh;
}
if (nh->fib_nh_flags & RTNH_F_DEAD) {
res->f6i = net->ipv6.fib6_null_entry;
nh = res->f6i->fib6_nh;
}
out:
res->nh = nh;
res->fib6_type = res->f6i->fib6_type;
res->fib6_flags = res->f6i->fib6_flags;
return;
out_blackhole:
res->fib6_flags |= RTF_REJECT;
res->fib6_type = RTN_BLACKHOLE;
res->nh = nh;
}
#ifdef CONFIG_IPV6_ROUTER_PREF
struct __rt6_probe_work {
struct work_struct work;
struct in6_addr target;
struct net_device *dev;
netdevice_tracker dev_tracker;
};
static void rt6_probe_deferred(struct work_struct *w)
{
struct in6_addr mcaddr;
struct __rt6_probe_work *work =
container_of(w, struct __rt6_probe_work, work);
addrconf_addr_solict_mult(&work->target, &mcaddr);
ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0);
dev_put_track(work->dev, &work->dev_tracker);
kfree(work);
}
static void rt6_probe(struct fib6_nh *fib6_nh)
{
struct __rt6_probe_work *work = NULL;
const struct in6_addr *nh_gw;
unsigned long last_probe;
struct neighbour *neigh;
struct net_device *dev;
struct inet6_dev *idev;
/*
* Okay, this does not seem to be appropriate
* for now, however, we need to check if it
* is really so; aka Router Reachability Probing.
*
* Router Reachability Probe MUST be rate-limited
* to no more than one per minute.
*/
if (!fib6_nh->fib_nh_gw_family)
return;
nh_gw = &fib6_nh->fib_nh_gw6;
dev = fib6_nh->fib_nh_dev;
rcu_read_lock_bh();
last_probe = READ_ONCE(fib6_nh->last_probe);
idev = __in6_dev_get(dev);
neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
if (neigh) {
if (neigh->nud_state & NUD_VALID)
goto out;
write_lock(&neigh->lock);
if (!(neigh->nud_state & NUD_VALID) &&
time_after(jiffies,
neigh->updated + idev->cnf.rtr_probe_interval)) {
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work)
__neigh_set_probe_once(neigh);
}
write_unlock(&neigh->lock);
} else if (time_after(jiffies, last_probe +
idev->cnf.rtr_probe_interval)) {
work = kmalloc(sizeof(*work), GFP_ATOMIC);
}
if (!work || cmpxchg(&fib6_nh->last_probe,
last_probe, jiffies) != last_probe) {
kfree(work);
} else {
INIT_WORK(&work->work, rt6_probe_deferred);
work->target = *nh_gw;
dev_hold_track(dev, &work->dev_tracker, GFP_ATOMIC);
work->dev = dev;
schedule_work(&work->work);
}
out:
rcu_read_unlock_bh();
}
#else
static inline void rt6_probe(struct fib6_nh *fib6_nh)
{
}
#endif
/*
* Default Router Selection (RFC 2461 6.3.6)
*/
static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh)
{
enum rt6_nud_state ret = RT6_NUD_FAIL_HARD;
struct neighbour *neigh;
rcu_read_lock_bh();
neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev,
&fib6_nh->fib_nh_gw6);
if (neigh) {
read_lock(&neigh->lock);
if (neigh->nud_state & NUD_VALID)
ret = RT6_NUD_SUCCEED;
#ifdef CONFIG_IPV6_ROUTER_PREF
else if (!(neigh->nud_state & NUD_FAILED))
ret = RT6_NUD_SUCCEED;
else
ret = RT6_NUD_FAIL_PROBE;
#endif
read_unlock(&neigh->lock);
} else {
ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ?
RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR;
}
rcu_read_unlock_bh();
return ret;
}
static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
int strict)
{
int m = 0;
if (!oif || nh->fib_nh_dev->ifindex == oif)
m = 2;
if (!m && (strict & RT6_LOOKUP_F_IFACE))
return RT6_NUD_FAIL_HARD;
#ifdef CONFIG_IPV6_ROUTER_PREF
m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(fib6_flags)) << 2;
#endif
if ((strict & RT6_LOOKUP_F_REACHABLE) &&
!(fib6_flags & RTF_NONEXTHOP) && nh->fib_nh_gw_family) {
int n = rt6_check_neigh(nh);
if (n < 0)
return n;
}
return m;
}
static bool find_match(struct fib6_nh *nh, u32 fib6_flags,
int oif, int strict, int *mpri, bool *do_rr)
{
bool match_do_rr = false;
bool rc = false;
int m;
if (nh->fib_nh_flags & RTNH_F_DEAD)
goto out;
if (ip6_ignore_linkdown(nh->fib_nh_dev) &&
nh->fib_nh_flags & RTNH_F_LINKDOWN &&
!(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
goto out;
m = rt6_score_route(nh, fib6_flags, oif, strict);
if (m == RT6_NUD_FAIL_DO_RR) {
match_do_rr = true;
m = 0; /* lowest valid score */
} else if (m == RT6_NUD_FAIL_HARD) {
goto out;
}
if (strict & RT6_LOOKUP_F_REACHABLE)
rt6_probe(nh);
/* note that m can be RT6_NUD_FAIL_PROBE at this point */
if (m > *mpri) {
*do_rr = match_do_rr;
*mpri = m;
rc = true;
}
out:
return rc;
}
struct fib6_nh_frl_arg {
u32 flags;
int oif;
int strict;
int *mpri;
bool *do_rr;
struct fib6_nh *nh;
};
static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg)
{
struct fib6_nh_frl_arg *arg = _arg;
arg->nh = nh;
return find_match(nh, arg->flags, arg->oif, arg->strict,
arg->mpri, arg->do_rr);
}
static void __find_rr_leaf(struct fib6_info *f6i_start,
struct fib6_info *nomatch, u32 metric,
struct fib6_result *res, struct fib6_info **cont,
int oif, int strict, bool *do_rr, int *mpri)
{
struct fib6_info *f6i;
for (f6i = f6i_start;
f6i && f6i != nomatch;
f6i = rcu_dereference(f6i->fib6_next)) {
bool matched = false;
struct fib6_nh *nh;
if (cont && f6i->fib6_metric != metric) {
*cont = f6i;
return;
}
if (fib6_check_expired(f6i))
continue;
if (unlikely(f6i->nh)) {
struct fib6_nh_frl_arg arg = {
.flags = f6i->fib6_flags,
.oif = oif,
.strict = strict,
.mpri = mpri,
.do_rr = do_rr
};
if (nexthop_is_blackhole(f6i->nh)) {
res->fib6_flags = RTF_REJECT;
res->fib6_type = RTN_BLACKHOLE;
res->f6i = f6i;
res->nh = nexthop_fib6_nh(f6i->nh);
return;
}
if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match,
&arg)) {
matched = true;
nh = arg.nh;
}
} else {
nh = f6i->fib6_nh;
if (find_match(nh, f6i->fib6_flags, oif, strict,
mpri, do_rr))
matched = true;
}
if (matched) {
res->f6i = f6i;
res->nh = nh;
res->fib6_flags = f6i->fib6_flags;
res->fib6_type = f6i->fib6_type;
}
}
}
static void find_rr_leaf(struct fib6_node *fn, struct fib6_info *leaf,
struct fib6_info *rr_head, int oif, int strict,
bool *do_rr, struct fib6_result *res)
{
u32 metric = rr_head->fib6_metric;
struct fib6_info *cont = NULL;
int mpri = -1;
__find_rr_leaf(rr_head, NULL, metric, res, &cont,
oif, strict, do_rr, &mpri);
__find_rr_leaf(leaf, rr_head, metric, res, &cont,
oif, strict, do_rr, &mpri);
if (res->f6i || !cont)
return;
__find_rr_leaf(cont, NULL, metric, res, NULL,
oif, strict, do_rr, &mpri);
}
static void rt6_select(struct net *net, struct fib6_node *fn, int oif,
struct fib6_result *res, int strict)
{
struct fib6_info *leaf = rcu_dereference(fn->leaf);
struct fib6_info *rt0;
bool do_rr = false;
int key_plen;
/* make sure this function or its helpers sets f6i */
res->f6i = NULL;
if (!leaf || leaf == net->ipv6.fib6_null_entry)
goto out;
rt0 = rcu_dereference(fn->rr_ptr);
if (!rt0)
rt0 = leaf;
/* Double check to make sure fn is not an intermediate node
* and fn->leaf does not points to its child's leaf
* (This might happen if all routes under fn are deleted from
* the tree and fib6_repair_tree() is called on the node.)
*/
key_plen = rt0->fib6_dst.plen;
#ifdef CONFIG_IPV6_SUBTREES
if (rt0->fib6_src.plen)
key_plen = rt0->fib6_src.plen;
#endif
if (fn->fn_bit != key_plen)
goto out;
find_rr_leaf(fn, leaf, rt0, oif, strict, &do_rr, res);
if (do_rr) {
struct fib6_info *next = rcu_dereference(rt0->fib6_next);
/* no entries matched; do round-robin */
if (!next || next->fib6_metric != rt0->fib6_metric)
next = leaf;
if (next != rt0) {
spin_lock_bh(&leaf->fib6_table->tb6_lock);
/* make sure next is not being deleted from the tree */
if (next->fib6_node)
rcu_assign_pointer(fn->rr_ptr, next);
spin_unlock_bh(&leaf->fib6_table->tb6_lock);
}
}
out:
if (!res->f6i) {
res->f6i = net->ipv6.fib6_null_entry;
res->nh = res->f6i->fib6_nh;
res->fib6_flags = res->f6i->fib6_flags;
res->fib6_type = res->f6i->fib6_type;
}
}
static bool rt6_is_gw_or_nonexthop(const struct fib6_result *res)
{
return (res->f6i->fib6_flags & RTF_NONEXTHOP) ||
res->nh->fib_nh_gw_family;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr)
{
struct net *net = dev_net(dev);
struct route_info *rinfo = (struct route_info *) opt;
struct in6_addr prefix_buf, *prefix;
unsigned int pref;
unsigned long lifetime;
struct fib6_info *rt;
if (len < sizeof(struct route_info)) {
return -EINVAL;
}
/* Sanity check for prefix_len and length */
if (rinfo->length > 3) {
return -EINVAL;
} else if (rinfo->prefix_len > 128) {
return -EINVAL;
} else if (rinfo->prefix_len > 64) {
if (rinfo->length < 2) {
return -EINVAL;
}
} else if (rinfo->prefix_len > 0) {
if (rinfo->length < 1) {
return -EINVAL;
}
}
pref = rinfo->route_pref;
if (pref == ICMPV6_ROUTER_PREF_INVALID)
return -EINVAL;
lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ);
if (rinfo->length == 3)
prefix = (struct in6_addr *)rinfo->prefix;
else {
/* this function is safe */
ipv6_addr_prefix(&prefix_buf,
(struct in6_addr *)rinfo->prefix,
rinfo->prefix_len);
prefix = &prefix_buf;
}
if (rinfo->prefix_len == 0)
rt = rt6_get_dflt_router(net, gwaddr, dev);
else
rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
gwaddr, dev);
if (rt && !lifetime) {
ip6_del_rt(net, rt, false);
rt = NULL;
}
if (!rt && lifetime)
rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr,
dev, pref);
else if (rt)
rt->fib6_flags = RTF_ROUTEINFO |
(rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
if (rt) {
if (!addrconf_finite_timeout(lifetime))
fib6_clean_expires(rt);
else
fib6_set_expires(rt, jiffies + HZ * lifetime);
fib6_info_release(rt);
}
return 0;
}
#endif
/*
* Misc support functions
*/
/* called with rcu_lock held */
static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res)
{
struct net_device *dev = res->nh->fib_nh_dev;
if (res->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
/* for copies of local routes, dst->dev needs to be the
* device if it is a master device, the master device if
* device is enslaved, and the loopback as the default
*/
if (netif_is_l3_slave(dev) &&
!rt6_need_strict(&res->f6i->fib6_dst.addr))
dev = l3mdev_master_dev_rcu(dev);
else if (!netif_is_l3_master(dev))
dev = dev_net(dev)->loopback_dev;
/* last case is netif_is_l3_master(dev) is true in which
* case we want dev returned to be dev
*/
}
return dev;
}
static const int fib6_prop[RTN_MAX + 1] = {
[RTN_UNSPEC] = 0,
[RTN_UNICAST] = 0,
[RTN_LOCAL] = 0,
[RTN_BROADCAST] = 0,
[RTN_ANYCAST] = 0,
[RTN_MULTICAST] = 0,
[RTN_BLACKHOLE] = -EINVAL,
[RTN_UNREACHABLE] = -EHOSTUNREACH,
[RTN_PROHIBIT] = -EACCES,
[RTN_THROW] = -EAGAIN,
[RTN_NAT] = -EINVAL,
[RTN_XRESOLVE] = -EINVAL,
};
static int ip6_rt_type_to_error(u8 fib6_type)
{
return fib6_prop[fib6_type];
}
static unsigned short fib6_info_dst_flags(struct fib6_info *rt)
{
unsigned short flags = 0;
if (rt->dst_nocount)
flags |= DST_NOCOUNT;
if (rt->dst_nopolicy)
flags |= DST_NOPOLICY;
return flags;
}
static void ip6_rt_init_dst_reject(struct rt6_info *rt, u8 fib6_type)
{
rt->dst.error = ip6_rt_type_to_error(fib6_type);
switch (fib6_type) {
case RTN_BLACKHOLE:
rt->dst.output = dst_discard_out;
rt->dst.input = dst_discard;
break;
case RTN_PROHIBIT:
rt->dst.output = ip6_pkt_prohibit_out;
rt->dst.input = ip6_pkt_prohibit;
break;
case RTN_THROW:
case RTN_UNREACHABLE:
default:
rt->dst.output = ip6_pkt_discard_out;
rt->dst.input = ip6_pkt_discard;
break;
}
}
static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res)
{
struct fib6_info *f6i = res->f6i;
if (res->fib6_flags & RTF_REJECT) {
ip6_rt_init_dst_reject(rt, res->fib6_type);
return;
}
rt->dst.error = 0;
rt->dst.output = ip6_output;
if (res->fib6_type == RTN_LOCAL || res->fib6_type == RTN_ANYCAST) {
rt->dst.input = ip6_input;
} else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
rt->dst.input = ip6_mc_input;
} else {
rt->dst.input = ip6_forward;
}
if (res->nh->fib_nh_lws) {
rt->dst.lwtstate = lwtstate_get(res->nh->fib_nh_lws);
lwtunnel_set_redirect(&rt->dst);
}
rt->dst.lastuse = jiffies;
}
/* Caller must already hold reference to @from */
static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
{
rt->rt6i_flags &= ~RTF_EXPIRES;
rcu_assign_pointer(rt->from, from);
ip_dst_init_metrics(&rt->dst, from->fib6_metrics);
}
/* Caller must already hold reference to f6i in result */
static void ip6_rt_copy_init(struct rt6_info *rt, const struct fib6_result *res)
{
const struct fib6_nh *nh = res->nh;
const struct net_device *dev = nh->fib_nh_dev;
struct fib6_info *f6i = res->f6i;
ip6_rt_init_dst(rt, res);
rt->rt6i_dst = f6i->fib6_dst;
rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL;
rt->rt6i_flags = res->fib6_flags;
if (nh->fib_nh_gw_family) {
rt->rt6i_gateway = nh->fib_nh_gw6;
rt->rt6i_flags |= RTF_GATEWAY;
}
rt6_set_from(rt, f6i);
#ifdef CONFIG_IPV6_SUBTREES
rt->rt6i_src = f6i->fib6_src;
#endif
}
static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
struct in6_addr *saddr)
{
struct fib6_node *pn, *sn;
while (1) {
if (fn->fn_flags & RTN_TL_ROOT)
return NULL;
pn = rcu_dereference(fn->parent);
sn = FIB6_SUBTREE(pn);
if (sn && sn != fn)
fn = fib6_node_lookup(sn, NULL, saddr);
else
fn = pn;
if (fn->fn_flags & RTN_RTINFO)
return fn;
}
}
static bool ip6_hold_safe(struct net *net, struct rt6_info **prt)
{
struct rt6_info *rt = *prt;
if (dst_hold_safe(&rt->dst))
return true;
if (net) {
rt = net->ipv6.ip6_null_entry;
dst_hold(&rt->dst);
} else {
rt = NULL;
}
*prt = rt;
return false;
}
/* called with rcu_lock held */
static struct rt6_info *ip6_create_rt_rcu(const struct fib6_result *res)
{
struct net_device *dev = res->nh->fib_nh_dev;
struct fib6_info *f6i = res->f6i;
unsigned short flags;
struct rt6_info *nrt;
if (!fib6_info_hold_safe(f6i))
goto fallback;
flags = fib6_info_dst_flags(f6i);
nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
if (!nrt) {
fib6_info_release(f6i);
goto fallback;
}
ip6_rt_copy_init(nrt, res);
return nrt;
fallback:
nrt = dev_net(dev)->ipv6.ip6_null_entry;
dst_hold(&nrt->dst);
return nrt;
}
INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_lookup(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags)
{
struct fib6_result res = {};
struct fib6_node *fn;
struct rt6_info *rt;
rcu_read_lock();
fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
res.f6i = rcu_dereference(fn->leaf);
if (!res.f6i)
res.f6i = net->ipv6.fib6_null_entry;
else
rt6_device_match(net, &res, &fl6->saddr, fl6->flowi6_oif,
flags);
if (res.f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto restart;
rt = net->ipv6.ip6_null_entry;
dst_hold(&rt->dst);
goto out;
} else if (res.fib6_flags & RTF_REJECT) {
goto do_create;
}
fib6_select_path(net, &res, fl6, fl6->flowi6_oif,
fl6->flowi6_oif != 0, skb, flags);
/* Search through exception table */
rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr);
if (rt) {
if (ip6_hold_safe(net, &rt))
dst_use_noref(&rt->dst, jiffies);
} else {
do_create:
rt = ip6_create_rt_rcu(&res);
}
out:
trace_fib6_table_lookup(net, &res, table, fl6);
rcu_read_unlock();
return rt;
}
struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
const struct sk_buff *skb, int flags)
{
return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_lookup);
}
EXPORT_SYMBOL_GPL(ip6_route_lookup);
struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
const struct in6_addr *saddr, int oif,
const struct sk_buff *skb, int strict)
{
struct flowi6 fl6 = {
.flowi6_oif = oif,
.daddr = *daddr,
};
struct dst_entry *dst;
int flags = strict ? RT6_LOOKUP_F_IFACE : 0;
if (saddr) {
memcpy(&fl6.saddr, saddr, sizeof(*saddr));
flags |= RT6_LOOKUP_F_HAS_SADDR;
}
dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup);
if (dst->error == 0)
return (struct rt6_info *) dst;
dst_release(dst);
return NULL;
}
EXPORT_SYMBOL(rt6_lookup);
/* ip6_ins_rt is called with FREE table->tb6_lock.
* It takes new route entry, the addition fails by any reason the
* route is released.
* Caller must hold dst before calling it.
*/
static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info,
struct netlink_ext_ack *extack)
{
int err;
struct fib6_table *table;
table = rt->fib6_table;
spin_lock_bh(&table->tb6_lock);
err = fib6_add(&table->tb6_root, rt, info, extack);
spin_unlock_bh(&table->tb6_lock);
return err;
}
int ip6_ins_rt(struct net *net, struct fib6_info *rt)
{
struct nl_info info = { .nl_net = net, };
return __ip6_ins_rt(rt, &info, NULL);
}
static struct rt6_info *ip6_rt_cache_alloc(const struct fib6_result *res,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
struct fib6_info *f6i = res->f6i;
struct net_device *dev;
struct rt6_info *rt;
/*
* Clone the route.
*/
if (!fib6_info_hold_safe(f6i))
return NULL;
dev = ip6_rt_get_dev_rcu(res);
rt = ip6_dst_alloc(dev_net(dev), dev, 0);
if (!rt) {
fib6_info_release(f6i);
return NULL;
}
ip6_rt_copy_init(rt, res);
rt->rt6i_flags |= RTF_CACHE;
rt->rt6i_dst.addr = *daddr;
rt->rt6i_dst.plen = 128;
if (!rt6_is_gw_or_nonexthop(res)) {
if (f6i->fib6_dst.plen != 128 &&
ipv6_addr_equal(&f6i->fib6_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen && saddr) {
rt->rt6i_src.addr = *saddr;
rt->rt6i_src.plen = 128;
}
#endif
}
return rt;
}
static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
{
struct fib6_info *f6i = res->f6i;
unsigned short flags = fib6_info_dst_flags(f6i);
struct net_device *dev;
struct rt6_info *pcpu_rt;
if (!fib6_info_hold_safe(f6i))
return NULL;
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(res);
pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags | DST_NOCOUNT);
rcu_read_unlock();
if (!pcpu_rt) {
fib6_info_release(f6i);
return NULL;
}
ip6_rt_copy_init(pcpu_rt, res);
pcpu_rt->rt6i_flags |= RTF_PCPU;
if (f6i->nh)
pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev));
return pcpu_rt;
}
static bool rt6_is_valid(const struct rt6_info *rt6)
{
return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev));
}
/* It should be called with rcu_read_lock() acquired */
static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
{
struct rt6_info *pcpu_rt;
pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) {
struct rt6_info *prev, **p;
p = this_cpu_ptr(res->nh->rt6i_pcpu);
prev = xchg(p, NULL);
if (prev) {
dst_dev_put(&prev->dst);
dst_release(&prev->dst);
}
pcpu_rt = NULL;
}
return pcpu_rt;
}
static struct rt6_info *rt6_make_pcpu_route(struct net *net,
const struct fib6_result *res)
{
struct rt6_info *pcpu_rt, *prev, **p;
pcpu_rt = ip6_rt_pcpu_alloc(res);
if (!pcpu_rt)
return NULL;
p = this_cpu_ptr(res->nh->rt6i_pcpu);
prev = cmpxchg(p, NULL, pcpu_rt);
BUG_ON(prev);
if (res->f6i->fib6_destroying) {
struct fib6_info *from;
from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
fib6_info_release(from);
}
return pcpu_rt;
}
/* exception hash table implementation
*/
static DEFINE_SPINLOCK(rt6_exception_lock);
/* Remove rt6_ex from hash table and free the memory
* Caller must hold rt6_exception_lock
*/
static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
struct rt6_exception *rt6_ex)
{
struct fib6_info *from;
struct net *net;
if (!bucket || !rt6_ex)
return;
net = dev_net(rt6_ex->rt6i->dst.dev);
net->ipv6.rt6_stats->fib_rt_cache--;
/* purge completely the exception to allow releasing the held resources:
* some [sk] cache may keep the dst around for unlimited time
*/
from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
fib6_info_release(from);
dst_dev_put(&rt6_ex->rt6i->dst);
hlist_del_rcu(&rt6_ex->hlist);
dst_release(&rt6_ex->rt6i->dst);
kfree_rcu(rt6_ex, rcu);
WARN_ON_ONCE(!bucket->depth);
bucket->depth--;
}
/* Remove oldest rt6_ex in bucket and free the memory
* Caller must hold rt6_exception_lock
*/
static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket)
{
struct rt6_exception *rt6_ex, *oldest = NULL;
if (!bucket)
return;
hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
if (!oldest || time_before(rt6_ex->stamp, oldest->stamp))
oldest = rt6_ex;
}
rt6_remove_exception(bucket, oldest);
}
static u32 rt6_exception_hash(const struct in6_addr *dst,
const struct in6_addr *src)
{
static siphash_aligned_key_t rt6_exception_key;
struct {
struct in6_addr dst;
struct in6_addr src;
} __aligned(SIPHASH_ALIGNMENT) combined = {
.dst = *dst,
};
u64 val;
net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key));
#ifdef CONFIG_IPV6_SUBTREES
if (src)
combined.src = *src;
#endif
val = siphash(&combined, sizeof(combined), &rt6_exception_key);
return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT);
}
/* Helper function to find the cached rt in the hash table
* and update bucket pointer to point to the bucket for this
* (daddr, saddr) pair
* Caller must hold rt6_exception_lock
*/
static struct rt6_exception *
__rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
struct rt6_exception *rt6_ex;
u32 hval;
if (!(*bucket) || !daddr)
return NULL;
hval = rt6_exception_hash(daddr, saddr);
*bucket += hval;
hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) {
struct rt6_info *rt6 = rt6_ex->rt6i;
bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr);
#ifdef CONFIG_IPV6_SUBTREES
if (matched && saddr)
matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr);
#endif
if (matched)
return rt6_ex;
}
return NULL;
}
/* Helper function to find the cached rt in the hash table
* and update bucket pointer to point to the bucket for this
* (daddr, saddr) pair
* Caller must hold rcu_read_lock()
*/
static struct rt6_exception *
__rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
struct rt6_exception *rt6_ex;
u32 hval;
WARN_ON_ONCE(!rcu_read_lock_held());
if (!(*bucket) || !daddr)
return NULL;
hval = rt6_exception_hash(daddr, saddr);
*bucket += hval;
hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) {
struct rt6_info *rt6 = rt6_ex->rt6i;
bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr);
#ifdef CONFIG_IPV6_SUBTREES
if (matched && saddr)
matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr);
#endif
if (matched)
return rt6_ex;
}
return NULL;
}
static unsigned int fib6_mtu(const struct fib6_result *res)
{
const struct fib6_nh *nh = res->nh;
unsigned int mtu;
if (res->f6i->fib6_pmtu) {
mtu = res->f6i->fib6_pmtu;
} else {
struct net_device *dev = nh->fib_nh_dev;
struct inet6_dev *idev;
rcu_read_lock();
idev = __in6_dev_get(dev);
mtu = idev->cnf.mtu6;
rcu_read_unlock();
}
mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
}
#define FIB6_EXCEPTION_BUCKET_FLUSHED 0x1UL
/* used when the flushed bit is not relevant, only access to the bucket
* (ie., all bucket users except rt6_insert_exception);
*
* called under rcu lock; sometimes called with rt6_exception_lock held
*/
static
struct rt6_exception_bucket *fib6_nh_get_excptn_bucket(const struct fib6_nh *nh,
spinlock_t *lock)
{
struct rt6_exception_bucket *bucket;
if (lock)
bucket = rcu_dereference_protected(nh->rt6i_exception_bucket,
lockdep_is_held(lock));
else
bucket = rcu_dereference(nh->rt6i_exception_bucket);
/* remove bucket flushed bit if set */
if (bucket) {
unsigned long p = (unsigned long)bucket;
p &= ~FIB6_EXCEPTION_BUCKET_FLUSHED;
bucket = (struct rt6_exception_bucket *)p;
}
return bucket;
}
static bool fib6_nh_excptn_bucket_flushed(struct rt6_exception_bucket *bucket)
{
unsigned long p = (unsigned long)bucket;
return !!(p & FIB6_EXCEPTION_BUCKET_FLUSHED);
}
/* called with rt6_exception_lock held */
static void fib6_nh_excptn_bucket_set_flushed(struct fib6_nh *nh,
spinlock_t *lock)
{
struct rt6_exception_bucket *bucket;
unsigned long p;
bucket = rcu_dereference_protected(nh->rt6i_exception_bucket,
lockdep_is_held(lock));
p = (unsigned long)bucket;
p |= FIB6_EXCEPTION_BUCKET_FLUSHED;
bucket = (struct rt6_exception_bucket *)p;
rcu_assign_pointer(nh->rt6i_exception_bucket, bucket);
}
static int rt6_insert_exception(struct rt6_info *nrt,
const struct fib6_result *res)
{
struct net *net = dev_net(nrt->dst.dev);
struct rt6_exception_bucket *bucket;
struct fib6_info *f6i = res->f6i;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
struct fib6_nh *nh = res->nh;
int max_depth;
int err = 0;
spin_lock_bh(&rt6_exception_lock);
bucket = rcu_dereference_protected(nh->rt6i_exception_bucket,
lockdep_is_held(&rt6_exception_lock));
if (!bucket) {
bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket),
GFP_ATOMIC);
if (!bucket) {
err = -ENOMEM;
goto out;
}
rcu_assign_pointer(nh->rt6i_exception_bucket, bucket);
} else if (fib6_nh_excptn_bucket_flushed(bucket)) {
err = -EINVAL;
goto out;
}
#ifdef CONFIG_IPV6_SUBTREES
/* fib6_src.plen != 0 indicates f6i is in subtree
* and exception table is indexed by a hash of
* both fib6_dst and fib6_src.
* Otherwise, the exception table is indexed by
* a hash of only fib6_dst.
*/
if (f6i->fib6_src.plen)
src_key = &nrt->rt6i_src.addr;
#endif
/* rt6_mtu_change() might lower mtu on f6i.
* Only insert this exception route if its mtu
* is less than f6i's mtu value.
*/
if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res)) {
err = -EINVAL;
goto out;
}
rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr,
src_key);
if (rt6_ex)
rt6_remove_exception(bucket, rt6_ex);
rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC);
if (!rt6_ex) {
err = -ENOMEM;
goto out;
}
rt6_ex->rt6i = nrt;
rt6_ex->stamp = jiffies;
hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain);
bucket->depth++;
net->ipv6.rt6_stats->fib_rt_cache++;
/* Randomize max depth to avoid some side channels attacks. */
max_depth = FIB6_MAX_DEPTH + prandom_u32_max(FIB6_MAX_DEPTH);
while (bucket->depth > max_depth)
rt6_exception_remove_oldest(bucket);
out:
spin_unlock_bh(&rt6_exception_lock);
/* Update fn->fn_sernum to invalidate all cached dst */
if (!err) {
spin_lock_bh(&f6i->fib6_table->tb6_lock);
fib6_update_sernum(net, f6i);
spin_unlock_bh(&f6i->fib6_table->tb6_lock);
fib6_force_start_gc(net);
}
return err;
}
static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
struct hlist_node *tmp;
int i;
spin_lock_bh(&rt6_exception_lock);
bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
if (!bucket)
goto out;
/* Prevent rt6_insert_exception() to recreate the bucket list */
if (!from)
fib6_nh_excptn_bucket_set_flushed(nh, &rt6_exception_lock);
for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) {
if (!from ||
rcu_access_pointer(rt6_ex->rt6i->from) == from)
rt6_remove_exception(bucket, rt6_ex);
}
WARN_ON_ONCE(!from && bucket->depth);
bucket++;
}
out:
spin_unlock_bh(&rt6_exception_lock);
}
static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg)
{
struct fib6_info *f6i = arg;
fib6_nh_flush_exceptions(nh, f6i);
return 0;
}
void rt6_flush_exceptions(struct fib6_info *f6i)
{
if (f6i->nh)
nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions,
f6i);
else
fib6_nh_flush_exceptions(f6i->fib6_nh, f6i);
}
/* Find cached rt in the hash table inside passed in rt
* Caller has to hold rcu_read_lock()
*/
static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
const struct in6_addr *src_key = NULL;
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
struct rt6_info *ret = NULL;
#ifdef CONFIG_IPV6_SUBTREES
/* fib6i_src.plen != 0 indicates f6i is in subtree
* and exception table is indexed by a hash of
* both fib6_dst and fib6_src.
* However, the src addr used to create the hash
* might not be exactly the passed in saddr which
* is a /128 addr from the flow.
* So we need to use f6i->fib6_src to redo lookup
* if the passed in saddr does not find anything.
* (See the logic in ip6_rt_cache_alloc() on how
* rt->rt6i_src is updated.)
*/
if (res->f6i->fib6_src.plen)
src_key = saddr;
find_ex:
#endif
bucket = fib6_nh_get_excptn_bucket(res->nh, NULL);
rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
ret = rt6_ex->rt6i;
#ifdef CONFIG_IPV6_SUBTREES
/* Use fib6_src as src_key and redo lookup */
if (!ret && src_key && src_key != &res->f6i->fib6_src.addr) {
src_key = &res->f6i->fib6_src.addr;
goto find_ex;
}
#endif
return ret;
}
/* Remove the passed in cached rt from the hash table that contains it */
static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen,
const struct rt6_info *rt)
{
const struct in6_addr *src_key = NULL;
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
int err;
if (!rcu_access_pointer(nh->rt6i_exception_bucket))
return -ENOENT;
spin_lock_bh(&rt6_exception_lock);
bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
#ifdef CONFIG_IPV6_SUBTREES
/* rt6i_src.plen != 0 indicates 'from' is in subtree
* and exception table is indexed by a hash of
* both rt6i_dst and rt6i_src.
* Otherwise, the exception table is indexed by
* a hash of only rt6i_dst.
*/
if (plen)
src_key = &rt->rt6i_src.addr;
#endif
rt6_ex = __rt6_find_exception_spinlock(&bucket,
&rt->rt6i_dst.addr,
src_key);
if (rt6_ex) {
rt6_remove_exception(bucket, rt6_ex);
err = 0;
} else {
err = -ENOENT;
}
spin_unlock_bh(&rt6_exception_lock);
return err;
}
struct fib6_nh_excptn_arg {
struct rt6_info *rt;
int plen;
};
static int rt6_nh_remove_exception_rt(struct fib6_nh *nh, void *_arg)
{
struct fib6_nh_excptn_arg *arg = _arg;
int err;
err = fib6_nh_remove_exception(nh, arg->plen, arg->rt);
if (err == 0)
return 1;
return 0;
}
static int rt6_remove_exception_rt(struct rt6_info *rt)
{
struct fib6_info *from;
from = rcu_dereference(rt->from);
if (!from || !(rt->rt6i_flags & RTF_CACHE))
return -EINVAL;
if (from->nh) {
struct fib6_nh_excptn_arg arg = {
.rt = rt,
.plen = from->fib6_src.plen
};
int rc;
/* rc = 1 means an entry was found */
rc = nexthop_for_each_fib6_nh(from->nh,
rt6_nh_remove_exception_rt,
&arg);
return rc ? 0 : -ENOENT;
}
return fib6_nh_remove_exception(from->fib6_nh,
from->fib6_src.plen, rt);
}
/* Find rt6_ex which contains the passed in rt cache and
* refresh its stamp
*/
static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen,
const struct rt6_info *rt)
{
const struct in6_addr *src_key = NULL;
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
bucket = fib6_nh_get_excptn_bucket(nh, NULL);
#ifdef CONFIG_IPV6_SUBTREES
/* rt6i_src.plen != 0 indicates 'from' is in subtree
* and exception table is indexed by a hash of
* both rt6i_dst and rt6i_src.
* Otherwise, the exception table is indexed by
* a hash of only rt6i_dst.
*/
if (plen)
src_key = &rt->rt6i_src.addr;
#endif
rt6_ex = __rt6_find_exception_rcu(&bucket, &rt->rt6i_dst.addr, src_key);
if (rt6_ex)
rt6_ex->stamp = jiffies;
}
struct fib6_nh_match_arg {
const struct net_device *dev;
const struct in6_addr *gw;
struct fib6_nh *match;
};
/* determine if fib6_nh has given device and gateway */
static int fib6_nh_find_match(struct fib6_nh *nh, void *_arg)
{
struct fib6_nh_match_arg *arg = _arg;
if (arg->dev != nh->fib_nh_dev ||
(arg->gw && !nh->fib_nh_gw_family) ||
(!arg->gw && nh->fib_nh_gw_family) ||
(arg->gw && !ipv6_addr_equal(arg->gw, &nh->fib_nh_gw6)))
return 0;
arg->match = nh;
/* found a match, break the loop */
return 1;
}
static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
{
struct fib6_info *from;
struct fib6_nh *fib6_nh;
rcu_read_lock();
from = rcu_dereference(rt->from);
if (!from || !(rt->rt6i_flags & RTF_CACHE))
goto unlock;
if (from->nh) {
struct fib6_nh_match_arg arg = {
.dev = rt->dst.dev,
.gw = &rt->rt6i_gateway,
};
nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg);
if (!arg.match)
goto unlock;
fib6_nh = arg.match;
} else {
fib6_nh = from->fib6_nh;
}
fib6_nh_update_exception(fib6_nh, from->fib6_src.plen, rt);
unlock:
rcu_read_unlock();
}
static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
struct rt6_info *rt, int mtu)
{
/* If the new MTU is lower than the route PMTU, this new MTU will be the
* lowest MTU in the path: always allow updating the route PMTU to
* reflect PMTU decreases.
*
* If the new MTU is higher, and the route PMTU is equal to the local
* MTU, this means the old MTU is the lowest in the path, so allow
* updating it: if other nodes now have lower MTUs, PMTU discovery will
* handle this.
*/
if (dst_mtu(&rt->dst) >= mtu)
return true;
if (dst_mtu(&rt->dst) == idev->cnf.mtu6)
return true;
return false;
}
static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
const struct fib6_nh *nh, int mtu)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
int i;
bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
if (!bucket)
return;
for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
struct rt6_info *entry = rt6_ex->rt6i;
/* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected
* route), the metrics of its rt->from have already
* been updated.
*/
if (dst_metric_raw(&entry->dst, RTAX_MTU) &&
rt6_mtu_change_route_allowed(idev, entry, mtu))
dst_metric_set(&entry->dst, RTAX_MTU, mtu);
}
bucket++;
}
}
#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE)
static void fib6_nh_exceptions_clean_tohost(const struct fib6_nh *nh,
const struct in6_addr *gateway)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
struct hlist_node *tmp;
int i;
if (!rcu_access_pointer(nh->rt6i_exception_bucket))
return;
spin_lock_bh(&rt6_exception_lock);
bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
if (bucket) {
for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
hlist_for_each_entry_safe(rt6_ex, tmp,
&bucket->chain, hlist) {
struct rt6_info *entry = rt6_ex->rt6i;
if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) ==
RTF_CACHE_GATEWAY &&
ipv6_addr_equal(gateway,
&entry->rt6i_gateway)) {
rt6_remove_exception(bucket, rt6_ex);
}
}
bucket++;
}
}
spin_unlock_bh(&rt6_exception_lock);
}
static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
struct rt6_exception *rt6_ex,
struct fib6_gc_args *gc_args,
unsigned long now)
{
struct rt6_info *rt = rt6_ex->rt6i;
/* we are pruning and obsoleting aged-out and non gateway exceptions
* even if others have still references to them, so that on next
* dst_check() such references can be dropped.
* EXPIRES exceptions - e.g. pmtu-generated ones are pruned when
* expired, independently from their aging, as per RFC 8201 section 4
*/
if (!(rt->rt6i_flags & RTF_EXPIRES)) {
if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
RT6_TRACE("aging clone %p\n", rt);
rt6_remove_exception(bucket, rt6_ex);
return;
}
} else if (time_after(jiffies, rt->dst.expires)) {
RT6_TRACE("purging expired route %p\n", rt);
rt6_remove_exception(bucket, rt6_ex);
return;
}
if (rt->rt6i_flags & RTF_GATEWAY) {
struct neighbour *neigh;
neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
if (!(neigh && (neigh->flags & NTF_ROUTER))) {
RT6_TRACE("purging route %p via non-router but gateway\n",
rt);
rt6_remove_exception(bucket, rt6_ex);
return;
}
}
gc_args->more++;
}
static void fib6_nh_age_exceptions(const struct fib6_nh *nh,
struct fib6_gc_args *gc_args,
unsigned long now)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
struct hlist_node *tmp;
int i;
if (!rcu_access_pointer(nh->rt6i_exception_bucket))
return;
rcu_read_lock_bh();
spin_lock(&rt6_exception_lock);
bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
if (bucket) {
for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
hlist_for_each_entry_safe(rt6_ex, tmp,
&bucket->chain, hlist) {
rt6_age_examine_exception(bucket, rt6_ex,
gc_args, now);
}
bucket++;
}
}
spin_unlock(&rt6_exception_lock);
rcu_read_unlock_bh();
}
struct fib6_nh_age_excptn_arg {
struct fib6_gc_args *gc_args;
unsigned long now;
};
static int rt6_nh_age_exceptions(struct fib6_nh *nh, void *_arg)
{
struct fib6_nh_age_excptn_arg *arg = _arg;
fib6_nh_age_exceptions(nh, arg->gc_args, arg->now);
return 0;
}
void rt6_age_exceptions(struct fib6_info *f6i,
struct fib6_gc_args *gc_args,
unsigned long now)
{
if (f6i->nh) {
struct fib6_nh_age_excptn_arg arg = {
.gc_args = gc_args,
.now = now
};
nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_age_exceptions,
&arg);
} else {
fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now);
}
}
/* must be called with rcu lock held */
int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif,
struct flowi6 *fl6, struct fib6_result *res, int strict)
{
struct fib6_node *fn, *saved_fn;
fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
saved_fn = fn;
redo_rt6_select:
rt6_select(net, fn, oif, res, strict);
if (res->f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto redo_rt6_select;
else if (strict & RT6_LOOKUP_F_REACHABLE) {
/* also consider unreachable route */
strict &= ~RT6_LOOKUP_F_REACHABLE;
fn = saved_fn;
goto redo_rt6_select;
}
}
trace_fib6_table_lookup(net, res, table, fl6);
return 0;
}
struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
int oif, struct flowi6 *fl6,
const struct sk_buff *skb, int flags)
{
struct fib6_result res = {};
struct rt6_info *rt = NULL;
int strict = 0;
WARN_ON_ONCE((flags & RT6_LOOKUP_F_DST_NOREF) &&
!rcu_read_lock_held());
strict |= flags & RT6_LOOKUP_F_IFACE;
strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
if (net->ipv6.devconf_all->forwarding == 0)
strict |= RT6_LOOKUP_F_REACHABLE;
rcu_read_lock();
fib6_table_lookup(net, table, oif, fl6, &res, strict);
if (res.f6i == net->ipv6.fib6_null_entry)
goto out;
fib6_select_path(net, &res, fl6, oif, false, skb, strict);
/*Search through exception table */
rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr);
if (rt) {
goto out;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
!res.nh->fib_nh_gw_family)) {
/* Create a RTF_CACHE clone which will not be
* owned by the fib6 tree. It is for the special case where
* the daddr in the skb during the neighbor look-up is different
* from the fl6->daddr used to look-up route here.
*/
rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL);
if (rt) {
/* 1 refcnt is taken during ip6_rt_cache_alloc().
* As rt6_uncached_list_add() does not consume refcnt,
* this refcnt is always returned to the caller even
* if caller sets RT6_LOOKUP_F_DST_NOREF flag.
*/
rt6_uncached_list_add(rt);
rcu_read_unlock();
return rt;
}
} else {
/* Get a percpu copy */
local_bh_disable();
rt = rt6_get_pcpu_route(&res);
if (!rt)
rt = rt6_make_pcpu_route(net, &res);
local_bh_enable();
}
out:
if (!rt)
rt = net->ipv6.ip6_null_entry;
if (!(flags & RT6_LOOKUP_F_DST_NOREF))
ip6_hold_safe(net, &rt);
rcu_read_unlock();
return rt;
}
EXPORT_SYMBOL_GPL(ip6_pol_route);
INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_input(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags)
{
return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, skb, flags);
}
struct dst_entry *ip6_route_input_lookup(struct net *net,
struct net_device *dev,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags)
{
if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG)
flags |= RT6_LOOKUP_F_IFACE;
return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_input);
}
EXPORT_SYMBOL_GPL(ip6_route_input_lookup);
static void ip6_multipath_l3_keys(const struct sk_buff *skb,
struct flow_keys *keys,
struct flow_keys *flkeys)
{
const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
const struct ipv6hdr *key_iph = outer_iph;
struct flow_keys *_flkeys = flkeys;
const struct ipv6hdr *inner_iph;
const struct icmp6hdr *icmph;
struct ipv6hdr _inner_iph;
struct icmp6hdr _icmph;
if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6))
goto out;
icmph = skb_header_pointer(skb, skb_transport_offset(skb),
sizeof(_icmph), &_icmph);
if (!icmph)
goto out;
if (!icmpv6_is_err(icmph->icmp6_type))
goto out;
inner_iph = skb_header_pointer(skb,
skb_transport_offset(skb) + sizeof(*icmph),
sizeof(_inner_iph), &_inner_iph);
if (!inner_iph)
goto out;
key_iph = inner_iph;
_flkeys = NULL;
out:
if (_flkeys) {
keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src;
keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst;
keys->tags.flow_label = _flkeys->tags.flow_label;
keys->basic.ip_proto = _flkeys->basic.ip_proto;
} else {
keys->addrs.v6addrs.src = key_iph->saddr;
keys->addrs.v6addrs.dst = key_iph->daddr;
keys->tags.flow_label = ip6_flowlabel(key_iph);
keys->basic.ip_proto = key_iph->nexthdr;
}
}
static u32 rt6_multipath_custom_hash_outer(const struct net *net,
const struct sk_buff *skb,
bool *p_has_inner)
{
u32 hash_fields = ip6_multipath_hash_fields(net);
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_IPV6_ADDRS;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP)
hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP)
hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.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_FLOWLABEL)
hash_keys.tags.flow_label = keys.tags.flow_label;
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 rt6_multipath_custom_hash_inner(const struct net *net,
const struct sk_buff *skb,
bool has_inner)
{
u32 hash_fields = ip6_multipath_hash_fields(net);
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 rt6_multipath_custom_hash_skb(const struct net *net,
const struct sk_buff *skb)
{
u32 mhash, mhash_inner;
bool has_inner = true;
mhash = rt6_multipath_custom_hash_outer(net, skb, &has_inner);
mhash_inner = rt6_multipath_custom_hash_inner(net, skb, has_inner);
return jhash_2words(mhash, mhash_inner, 0);
}
static u32 rt6_multipath_custom_hash_fl6(const struct net *net,
const struct flowi6 *fl6)
{
u32 hash_fields = ip6_multipath_hash_fields(net);
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_IPV6_ADDRS;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP)
hash_keys.addrs.v6addrs.src = fl6->saddr;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP)
hash_keys.addrs.v6addrs.dst = fl6->daddr;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
hash_keys.basic.ip_proto = fl6->flowi6_proto;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL)
hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
hash_keys.ports.src = fl6->fl6_sport;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
hash_keys.ports.dst = fl6->fl6_dport;
return flow_hash_from_keys(&hash_keys);
}
/* if skb is set it will be used and fl6 can be NULL */
u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
const struct sk_buff *skb, struct flow_keys *flkeys)
{
struct flow_keys hash_keys;
u32 mhash = 0;
switch (ip6_multipath_hash_policy(net)) {
case 0:
memset(&hash_keys, 0, sizeof(hash_keys));
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
if (skb) {
ip6_multipath_l3_keys(skb, &hash_keys, flkeys);
} else {
hash_keys.addrs.v6addrs.src = fl6->saddr;
hash_keys.addrs.v6addrs.dst = fl6->daddr;
hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
hash_keys.basic.ip_proto = fl6->flowi6_proto;
}
mhash = flow_hash_from_keys(&hash_keys);
break;
case 1:
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_IPV6_ADDRS;
hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src;
hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.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_IPV6_ADDRS;
hash_keys.addrs.v6addrs.src = fl6->saddr;
hash_keys.addrs.v6addrs.dst = fl6->daddr;
hash_keys.ports.src = fl6->fl6_sport;
hash_keys.ports.dst = fl6->fl6_dport;
hash_keys.basic.ip_proto = fl6->flowi6_proto;
}
mhash = flow_hash_from_keys(&hash_keys);
break;
case 2:
memset(&hash_keys, 0, sizeof(hash_keys));
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
if (skb) {
struct flow_keys keys;
if (!flkeys) {
skb_flow_dissect_flow_keys(skb, &keys, 0);
flkeys = &keys;
}
/* Inner can be v4 or v6 */
if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
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;
} else if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src;
hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst;
hash_keys.tags.flow_label = flkeys->tags.flow_label;
hash_keys.basic.ip_proto = flkeys->basic.ip_proto;
} else {
/* Same as case 0 */
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
ip6_multipath_l3_keys(skb, &hash_keys, flkeys);
}
} else {
/* Same as case 0 */
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
hash_keys.addrs.v6addrs.src = fl6->saddr;
hash_keys.addrs.v6addrs.dst = fl6->daddr;
hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
hash_keys.basic.ip_proto = fl6->flowi6_proto;
}
mhash = flow_hash_from_keys(&hash_keys);
break;
case 3:
if (skb)
mhash = rt6_multipath_custom_hash_skb(net, skb);
else
mhash = rt6_multipath_custom_hash_fl6(net, fl6);
break;
}
return mhash >> 1;
}
/* Called with rcu held */
void ip6_route_input(struct sk_buff *skb)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
int flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_DST_NOREF;
struct ip_tunnel_info *tun_info;
struct flowi6 fl6 = {
.flowi6_iif = skb->dev->ifindex,
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
};
struct flow_keys *flkeys = NULL, _flkeys;
tun_info = skb_tunnel_info(skb);
if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX))
fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id;
if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys))
flkeys = &_flkeys;
if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6))
fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys);
skb_dst_drop(skb);
skb_dst_set_noref(skb, ip6_route_input_lookup(net, skb->dev,
&fl6, skb, flags));
}
INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_output(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags)
{
return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags);
}
struct dst_entry *ip6_route_output_flags_noref(struct net *net,
const struct sock *sk,
struct flowi6 *fl6, int flags)
{
bool any_src;
if (ipv6_addr_type(&fl6->daddr) &
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) {
struct dst_entry *dst;
/* This function does not take refcnt on the dst */
dst = l3mdev_link_scope_lookup(net, fl6);
if (dst)
return dst;
}
fl6->flowi6_iif = LOOPBACK_IFINDEX;
flags |= RT6_LOOKUP_F_DST_NOREF;
any_src = ipv6_addr_any(&fl6->saddr);
if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
(fl6->flowi6_oif && any_src))
flags |= RT6_LOOKUP_F_IFACE;
if (!any_src)
flags |= RT6_LOOKUP_F_HAS_SADDR;
else if (sk)
flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs);
return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output);
}
EXPORT_SYMBOL_GPL(ip6_route_output_flags_noref);
struct dst_entry *ip6_route_output_flags(struct net *net,
const struct sock *sk,
struct flowi6 *fl6,
int flags)
{
struct dst_entry *dst;
struct rt6_info *rt6;
rcu_read_lock();
dst = ip6_route_output_flags_noref(net, sk, fl6, flags);
rt6 = (struct rt6_info *)dst;
/* For dst cached in uncached_list, refcnt is already taken. */
if (list_empty(&rt6->rt6i_uncached) && !dst_hold_safe(dst)) {
dst = &net->ipv6.ip6_null_entry->dst;
dst_hold(dst);
}
rcu_read_unlock();
return dst;
}
EXPORT_SYMBOL_GPL(ip6_route_output_flags);
struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig;
struct net_device *loopback_dev = net->loopback_dev;
struct dst_entry *new = NULL;
rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1,
DST_OBSOLETE_DEAD, 0);
if (rt) {
rt6_info_init(rt);
atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc);
new = &rt->dst;
new->__use = 1;
new->input = dst_discard;
new->output = dst_discard_out;
dst_copy_metrics(new, &ort->dst);
rt->rt6i_idev = in6_dev_get(loopback_dev);
rt->rt6i_gateway = ort->rt6i_gateway;
rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU;
memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
#ifdef CONFIG_IPV6_SUBTREES
memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
#endif
}
dst_release(dst_orig);
return new ? new : ERR_PTR(-ENOMEM);
}
/*
* Destination cache support functions
*/
static bool fib6_check(struct fib6_info *f6i, u32 cookie)
{
u32 rt_cookie = 0;
if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie)
return false;
if (fib6_check_expired(f6i))
return false;
return true;
}
static struct dst_entry *rt6_check(struct rt6_info *rt,
struct fib6_info *from,
u32 cookie)
{
u32 rt_cookie = 0;
if (!from || !fib6_get_cookie_safe(from, &rt_cookie) ||
rt_cookie != cookie)
return NULL;
if (rt6_check_expired(rt))
return NULL;
return &rt->dst;
}
static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt,
struct fib6_info *from,
u32 cookie)
{
if (!__rt6_check_expired(rt) &&
rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
fib6_check(from, cookie))
return &rt->dst;
else
return NULL;
}
INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst,
u32 cookie)
{
struct dst_entry *dst_ret;
struct fib6_info *from;
struct rt6_info *rt;
rt = container_of(dst, struct rt6_info, dst);
if (rt->sernum)
return rt6_is_valid(rt) ? dst : NULL;
rcu_read_lock();
/* All IPV6 dsts are created with ->obsolete set to the value
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*/
from = rcu_dereference(rt->from);
if (from && (rt->rt6i_flags & RTF_PCPU ||
unlikely(!list_empty(&rt->rt6i_uncached))))
dst_ret = rt6_dst_from_check(rt, from, cookie);
else
dst_ret = rt6_check(rt, from, cookie);
rcu_read_unlock();
return dst_ret;
}
EXPORT_INDIRECT_CALLABLE(ip6_dst_check);
static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *) dst;
if (rt) {
if (rt->rt6i_flags & RTF_CACHE) {
rcu_read_lock();
if (rt6_check_expired(rt)) {
rt6_remove_exception_rt(rt);
dst = NULL;
}
rcu_read_unlock();
} else {
dst_release(dst);
dst = NULL;
}
}
return dst;
}
static void ip6_link_failure(struct sk_buff *skb)
{
struct rt6_info *rt;
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
rt = (struct rt6_info *) skb_dst(skb);
if (rt) {
rcu_read_lock();
if (rt->rt6i_flags & RTF_CACHE) {
rt6_remove_exception_rt(rt);
} else {
struct fib6_info *from;
struct fib6_node *fn;
from = rcu_dereference(rt->from);
if (from) {
fn = rcu_dereference(from->fib6_node);
if (fn && (rt->rt6i_flags & RTF_DEFAULT))
WRITE_ONCE(fn->fn_sernum, -1);
}
}
rcu_read_unlock();
}
}
static void rt6_update_expires(struct rt6_info *rt0, int timeout)
{
if (!(rt0->rt6i_flags & RTF_EXPIRES)) {
struct fib6_info *from;
rcu_read_lock();
from = rcu_dereference(rt0->from);
if (from)
rt0->dst.expires = from->expires;
rcu_read_unlock();
}
dst_set_expires(&rt0->dst, timeout);
rt0->rt6i_flags |= RTF_EXPIRES;
}
static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
{
struct net *net = dev_net(rt->dst.dev);
dst_metric_set(&rt->dst, RTAX_MTU, mtu);
rt->rt6i_flags |= RTF_MODIFIED;
rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
{
return !(rt->rt6i_flags & RTF_CACHE) &&
(rt->rt6i_flags & RTF_PCPU || rcu_access_pointer(rt->from));
}
static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
const struct ipv6hdr *iph, u32 mtu,
bool confirm_neigh)
{
const struct in6_addr *daddr, *saddr;
struct rt6_info *rt6 = (struct rt6_info *)dst;
/* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU)
* IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it.
* [see also comment in rt6_mtu_change_route()]
*/
if (iph) {
daddr = &iph->daddr;
saddr = &iph->saddr;
} else if (sk) {
daddr = &sk->sk_v6_daddr;
saddr = &inet6_sk(sk)->saddr;
} else {
daddr = NULL;
saddr = NULL;
}
if (confirm_neigh)
dst_confirm_neigh(dst, daddr);
if (mtu < IPV6_MIN_MTU)
return;
if (mtu >= dst_mtu(dst))
return;
if (!rt6_cache_allowed_for_pmtu(rt6)) {
rt6_do_update_pmtu(rt6, mtu);
/* update rt6_ex->stamp for cache */
if (rt6->rt6i_flags & RTF_CACHE)
rt6_update_exception_stamp_rt(rt6);
} else if (daddr) {
struct fib6_result res = {};
struct rt6_info *nrt6;
rcu_read_lock();
res.f6i = rcu_dereference(rt6->from);
if (!res.f6i)
goto out_unlock;
res.fib6_flags = res.f6i->fib6_flags;
res.fib6_type = res.f6i->fib6_type;
if (res.f6i->nh) {
struct fib6_nh_match_arg arg = {
.dev = dst->dev,
.gw = &rt6->rt6i_gateway,
};
nexthop_for_each_fib6_nh(res.f6i->nh,
fib6_nh_find_match, &arg);
/* fib6_info uses a nexthop that does not have fib6_nh
* using the dst->dev + gw. Should be impossible.
*/
if (!arg.match)
goto out_unlock;
res.nh = arg.match;
} else {
res.nh = res.f6i->fib6_nh;
}
nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr);
if (nrt6) {
rt6_do_update_pmtu(nrt6, mtu);
if (rt6_insert_exception(nrt6, &res))
dst_release_immediate(&nrt6->dst);
}
out_unlock:
rcu_read_unlock();
}
}
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu,
bool confirm_neigh)
{
__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu,
confirm_neigh);
}
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
int oif, u32 mark, kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
struct flowi6 fl6 = {
.flowi6_oif = oif,
.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark),
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
.flowi6_uid = uid,
};
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true);
dst_release(dst);
}
EXPORT_SYMBOL_GPL(ip6_update_pmtu);
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
{
int oif = sk->sk_bound_dev_if;
struct dst_entry *dst;
if (!oif && skb->dev)
oif = l3mdev_master_ifindex(skb->dev);
ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
dst->ops->check(dst, inet6_sk(sk)->dst_cookie))
return;
bh_lock_sock(sk);
if (!sock_owned_by_user(sk) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr))
ip6_datagram_dst_update(sk, false);
bh_unlock_sock(sk);
}
EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst,
const struct flowi6 *fl6)
{
#ifdef CONFIG_IPV6_SUBTREES
struct ipv6_pinfo *np = inet6_sk(sk);
#endif
ip6_dst_store(sk, dst,
ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr) ?
&sk->sk_v6_daddr : NULL,
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_equal(&fl6->saddr, &np->saddr) ?
&np->saddr :
#endif
NULL);
}
static bool ip6_redirect_nh_match(const struct fib6_result *res,
struct flowi6 *fl6,
const struct in6_addr *gw,
struct rt6_info **ret)
{
const struct fib6_nh *nh = res->