Commit 901731b8 authored by David Ahern's avatar David Ahern Committed by Daniel Borkmann

net/ipv6: Add helper to return path MTU based on fib result

Determine path MTU from a FIB lookup result. Logic is based on
ip6_dst_mtu_forward plus lookup of nexthop exception.

Add ip6_dst_mtu_forward to ipv6_stubs to handle access by core
bpf code.
Signed-off-by: default avatarDavid Ahern <dsahern@gmail.com>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
parent 50d889b1
...@@ -236,6 +236,8 @@ struct ipv6_stub { ...@@ -236,6 +236,8 @@ struct ipv6_stub {
struct flowi6 *fl6, int oif, struct flowi6 *fl6, int oif,
const struct sk_buff *skb, const struct sk_buff *skb,
int strict); int strict);
u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr,
struct in6_addr *saddr);
void (*udpv6_encap_enable)(void); void (*udpv6_encap_enable)(void);
void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
......
...@@ -412,6 +412,12 @@ static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) ...@@ -412,6 +412,12 @@ static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i)
return f6i->fib6_nh.nh_dev; return f6i->fib6_nh.nh_dev;
} }
static inline
struct lwtunnel_state *fib6_info_nh_lwt(const struct fib6_info *f6i)
{
return f6i->fib6_nh.nh_lwtstate;
}
void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
unsigned int flags); unsigned int flags);
......
...@@ -300,6 +300,9 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) ...@@ -300,6 +300,9 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
return mtu; return mtu;
} }
u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
struct in6_addr *saddr);
struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
struct net_device *dev, struct sk_buff *skb, struct net_device *dev, struct sk_buff *skb,
const void *daddr); const void *daddr);
......
...@@ -161,12 +161,20 @@ eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i, ...@@ -161,12 +161,20 @@ eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i,
return f6i; return f6i;
} }
static u32
eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
struct in6_addr *saddr)
{
return 0;
}
const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
.ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
.fib6_get_table = eafnosupport_fib6_get_table, .fib6_get_table = eafnosupport_fib6_get_table,
.fib6_table_lookup = eafnosupport_fib6_table_lookup, .fib6_table_lookup = eafnosupport_fib6_table_lookup,
.fib6_lookup = eafnosupport_fib6_lookup, .fib6_lookup = eafnosupport_fib6_lookup,
.fib6_multipath_select = eafnosupport_fib6_multipath_select, .fib6_multipath_select = eafnosupport_fib6_multipath_select,
.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
}; };
EXPORT_SYMBOL_GPL(ipv6_stub); EXPORT_SYMBOL_GPL(ipv6_stub);
......
...@@ -894,6 +894,7 @@ static const struct ipv6_stub ipv6_stub_impl = { ...@@ -894,6 +894,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
.fib6_table_lookup = fib6_table_lookup, .fib6_table_lookup = fib6_table_lookup,
.fib6_lookup = fib6_lookup, .fib6_lookup = fib6_lookup,
.fib6_multipath_select = fib6_multipath_select, .fib6_multipath_select = fib6_multipath_select,
.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
.udpv6_encap_enable = udpv6_encap_enable, .udpv6_encap_enable = udpv6_encap_enable,
.ndisc_send_na = ndisc_send_na, .ndisc_send_na = ndisc_send_na,
.nd_tbl = &nd_tbl, .nd_tbl = &nd_tbl,
......
...@@ -2603,6 +2603,54 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) ...@@ -2603,6 +2603,54 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
return mtu - lwtunnel_headroom(dst->lwtstate, mtu); return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
} }
/* MTU selection:
* 1. mtu on route is locked - use it
* 2. mtu from nexthop exception
* 3. mtu from egress device
*
* based on ip6_dst_mtu_forward and exception logic of
* rt6_find_cached_rt; called with rcu_read_lock
*/
u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
struct in6_addr *saddr)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
struct in6_addr *src_key;
struct inet6_dev *idev;
u32 mtu = 0;
if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) {
mtu = f6i->fib6_pmtu;
if (mtu)
goto out;
}
src_key = NULL;
#ifdef CONFIG_IPV6_SUBTREES
if (f6i->fib6_src.plen)
src_key = saddr;
#endif
bucket = rcu_dereference(f6i->rt6i_exception_bucket);
rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
if (likely(!mtu)) {
struct net_device *dev = fib6_info_nh_dev(f6i);
mtu = IPV6_MIN_MTU;
idev = __in6_dev_get(dev);
if (idev && idev->cnf.mtu6 > mtu)
mtu = idev->cnf.mtu6;
}
mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
out:
return mtu - lwtunnel_headroom(fib6_info_nh_lwt(f6i), mtu);
}
struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
struct flowi6 *fl6) struct flowi6 *fl6)
{ {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment