leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
8ee821aea3
linux/include/net/ip6_route.h
Vincent Bernat ccdb2d17df ip6: fix PMTU discovery when using /127 subnets 
The definition of an "anycast destination address" has been tweaked as a
side-effect of commit 2647a9b070 ("ipv6: Remove external dependency on
rt6i_gateway and RTF_ANYCAST"). The first address of a point-to-point
/127 subnet is now considered as an anycast address. This prevents
ICMPv6 errors to be returned to a sender of such a subnet and breaks
PMTU discovery.

This can be reproduced with:

    ip link add name out6 type veth peer name in6
    ip link add name out7 type veth peer name in7
    ip link set mtu 1400 dev out7
    ip link set mtu 1400 dev in7
    ip netns add next-hop
    ip netns add next-next-hop
    ip link set netns next-hop dev in6
    ip link set netns next-hop dev out7
    ip link set netns next-next-hop dev in7
    ip link set up dev out6
    ip addr add 2001:db8:1::12/127 dev out6
    ip netns exec next-hop ip link set up dev in6
    ip netns exec next-hop ip link set up dev out7
    ip netns exec next-hop ip addr add 2001:db8:1::13/127 dev in6
    ip netns exec next-hop ip addr add 2001:db8:1::14/127 dev out7
    ip netns exec next-hop ip route add default via 2001:db8:1::15
    ip netns exec next-hop sysctl -qw net.ipv6.conf.all.forwarding=1
    ip netns exec next-next-hop ip link set up dev in7
    ip netns exec next-next-hop ip addr add 2001:db8:1::15/127 dev in7
    ip netns exec next-next-hop ip addr add 2001:db8:1::50/128 dev in7
    ip netns exec next-next-hop ip route add default via 2001:db8:1::14
    ip netns exec next-next-hop sysctl -qw net.ipv6.conf.all.forwarding=1
    ip route add 2001:db8:1::48/123 via 2001:db8:1::13
    sleep 4
    ping -M do -s 1452 -c 3 2001:db8:1::50 || true
    ip route get 2001:db8:1::50

Before the patch, we get:

    2001:db8:1::50 from :: via 2001:db8:1::13 dev out6 src 2001:db8:1::12 metric 1024  pref medium

After the patch, we get:

    2001:db8:1::50 via 2001:db8:1::13 dev out6 src 2001:db8:1::12 metric 0
        cache  expires 578sec mtu 1400 pref medium

Fixes: 2647a9b070 ("ipv6: Remove external dependency on rt6i_gateway and RTF_ANYCAST")
Signed-off-by: Vincent Bernat <vincent@bernat.im>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-16 16:36:01 -07:00

244 lines
6.9 KiB
C
Raw Blame History

#ifndef _NET_IP6_ROUTE_H
#define _NET_IP6_ROUTE_H
struct route_info {
__u8 type;
__u8 length;
__u8 prefix_len;
#if defined(__BIG_ENDIAN_BITFIELD)
__u8 reserved_h:3,
route_pref:2,
reserved_l:3;
#elif defined(__LITTLE_ENDIAN_BITFIELD)
__u8 reserved_l:3,
route_pref:2,
reserved_h:3;
#endif
__be32 lifetime;
__u8 prefix[0]; /* 0,8 or 16 */
};
#include <net/addrconf.h>
#include <net/flow.h>
#include <net/ip6_fib.h>
#include <net/sock.h>
#include <net/lwtunnel.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/route.h>
#define RT6_LOOKUP_F_IFACE 0x00000001
#define RT6_LOOKUP_F_REACHABLE 0x00000002
#define RT6_LOOKUP_F_HAS_SADDR 0x00000004
#define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008
#define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010
#define RT6_LOOKUP_F_SRCPREF_COA 0x00000020
#define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040
/* We do not (yet ?) support IPv6 jumbograms (RFC 2675)
* Unlike IPv4, hdr->seg_len doesn't include the IPv6 header
*/
#define IP6_MAX_MTU (0xFFFF + sizeof(struct ipv6hdr))
/*
* rt6_srcprefs2flags() and rt6_flags2srcprefs() translate
* between IPV6_ADDR_PREFERENCES socket option values
* IPV6_PREFER_SRC_TMP = 0x1
* IPV6_PREFER_SRC_PUBLIC = 0x2
* IPV6_PREFER_SRC_COA = 0x4
* and above RT6_LOOKUP_F_SRCPREF_xxx flags.
*/
static inline int rt6_srcprefs2flags(unsigned int srcprefs)
{
/* No need to bitmask because srcprefs have only 3 bits. */
return srcprefs << 3;
}
static inline unsigned int rt6_flags2srcprefs(int flags)
{
return (flags >> 3) & 7;
}
static inline bool rt6_need_strict(const struct in6_addr *daddr)
{
return ipv6_addr_type(daddr) &
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
}
void ip6_route_input(struct sk_buff *skb);
struct dst_entry *ip6_route_input_lookup(struct net *net,
struct net_device *dev,
struct flowi6 *fl6, int flags);
struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
struct flowi6 *fl6, int flags);
static inline struct dst_entry *ip6_route_output(struct net *net,
const struct sock *sk,
struct flowi6 *fl6)
{
return ip6_route_output_flags(net, sk, fl6, 0);
}
struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
int flags);
struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
int ifindex, struct flowi6 *fl6, int flags);
void ip6_route_init_special_entries(void);
int ip6_route_init(void);
void ip6_route_cleanup(void);
int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg);
int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack);
int ip6_ins_rt(struct rt6_info *);
int ip6_del_rt(struct rt6_info *);
static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
const struct in6_addr *daddr,
unsigned int prefs,
struct in6_addr *saddr)
{
struct inet6_dev *idev =
rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
int err = 0;
if (rt && rt->rt6i_prefsrc.plen)
*saddr = rt->rt6i_prefsrc.addr;
else
err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
daddr, prefs, saddr);
return err;
}
struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
const struct in6_addr *saddr, int oif, int flags);
struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
void fib6_force_start_gc(struct net *net);
struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
const struct in6_addr *addr, bool anycast);
struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
int flags);
/*
* support functions for ND
*
*/
struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr,
struct net_device *dev);
struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
struct net_device *dev, unsigned int pref);
void rt6_purge_dflt_routers(struct net *net);
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr);
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif,
u32 mark, kuid_t uid);
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu);
void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
kuid_t uid);
void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
u32 mark);
void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk);
struct netlink_callback;
struct rt6_rtnl_dump_arg {
struct sk_buff *skb;
struct netlink_callback *cb;
struct net *net;
};
int rt6_dump_route(struct rt6_info *rt, void *p_arg);
void rt6_ifdown(struct net *net, struct net_device *dev);
void rt6_mtu_change(struct net_device *dev, unsigned int mtu);
void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);
void rt6_clean_tohost(struct net *net, struct in6_addr *gateway);
/*
* Store a destination cache entry in a socket
*/
static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
struct ipv6_pinfo *np = inet6_sk(sk);
np->dst_cookie = rt6_get_cookie((struct rt6_info *)dst);
sk_setup_caps(sk, dst);
np->daddr_cache = daddr;
#ifdef CONFIG_IPV6_SUBTREES
np->saddr_cache = saddr;
#endif
}
static inline bool ipv6_unicast_destination(const struct sk_buff *skb)
{
struct rt6_info *rt = (struct rt6_info *) skb_dst(skb);
return rt->rt6i_flags & RTF_LOCAL;
}
static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
const struct in6_addr *daddr)
{
struct rt6_info *rt = (struct rt6_info *)dst;
return rt->rt6i_flags & RTF_ANYCAST ||
(rt->rt6i_dst.plen < 127 &&
ipv6_addr_equal(&rt->rt6i_dst.addr, daddr));
}
int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(struct net *, struct sock *, struct sk_buff *));
static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
{
struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
inet6_sk(skb->sk) : NULL;
return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ?
skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
}
static inline bool ip6_sk_accept_pmtu(const struct sock *sk)
{
return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE &&
inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_OMIT;
}
static inline bool ip6_sk_ignore_df(const struct sock *sk)
{
return inet6_sk(sk)->pmtudisc < IPV6_PMTUDISC_DO ||
inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT;
}
static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
struct in6_addr *daddr)
{
if (rt->rt6i_flags & RTF_GATEWAY)
return &rt->rt6i_gateway;
else if (unlikely(rt->rt6i_flags & RTF_CACHE))
return &rt->rt6i_dst.addr;
else
return daddr;
}
static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
{
return a->dst.dev == b->dst.dev &&
a->rt6i_idev == b->rt6i_idev &&
ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) &&
!lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate);
}
#endif
Reference in New Issue View Git Blame Copy Permalink