#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/netlink.h>
+#include <net/nexthop.h>
#include <asm/uaccess.h>
[RTAX_HOPLIMIT - 1] = 255,
};
-static struct rt6_info ip6_null_entry_template = {
+static const struct rt6_info ip6_null_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
static int ip6_pkt_prohibit(struct sk_buff *skb);
static int ip6_pkt_prohibit_out(struct sk_buff *skb);
-static struct rt6_info ip6_prohibit_entry_template = {
+static const struct rt6_info ip6_prohibit_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
.rt6i_ref = ATOMIC_INIT(1),
};
-static struct rt6_info ip6_blk_hole_entry_template = {
+static const struct rt6_info ip6_blk_hole_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
rt->rt6i_genid = rt_genid(net);
+ INIT_LIST_HEAD(&rt->rt6i_siblings);
+ rt->rt6i_nsiblings = 0;
}
return rt;
}
static bool rt6_check_expired(const struct rt6_info *rt)
{
- struct rt6_info *ort = NULL;
-
if (rt->rt6i_flags & RTF_EXPIRES) {
if (time_after(jiffies, rt->dst.expires))
return true;
} else if (rt->dst.from) {
- ort = (struct rt6_info *) rt->dst.from;
- return (ort->rt6i_flags & RTF_EXPIRES) &&
- time_after(jiffies, ort->dst.expires);
+ return rt6_check_expired((struct rt6_info *) rt->dst.from);
}
return false;
}
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
}
+/* Multipath route selection:
+ * Hash based function using packet header and flowlabel.
+ * Adapted from fib_info_hashfn()
+ */
+static int rt6_info_hash_nhsfn(unsigned int candidate_count,
+ const struct flowi6 *fl6)
+{
+ unsigned int val = fl6->flowi6_proto;
+
+ val ^= (__force u32)fl6->daddr.s6_addr32[0];
+ val ^= (__force u32)fl6->daddr.s6_addr32[1];
+ val ^= (__force u32)fl6->daddr.s6_addr32[2];
+ val ^= (__force u32)fl6->daddr.s6_addr32[3];
+
+ val ^= (__force u32)fl6->saddr.s6_addr32[0];
+ val ^= (__force u32)fl6->saddr.s6_addr32[1];
+ val ^= (__force u32)fl6->saddr.s6_addr32[2];
+ val ^= (__force u32)fl6->saddr.s6_addr32[3];
+
+ /* Work only if this not encapsulated */
+ switch (fl6->flowi6_proto) {
+ case IPPROTO_UDP:
+ case IPPROTO_TCP:
+ case IPPROTO_SCTP:
+ val ^= (__force u16)fl6->fl6_sport;
+ val ^= (__force u16)fl6->fl6_dport;
+ break;
+
+ case IPPROTO_ICMPV6:
+ val ^= (__force u16)fl6->fl6_icmp_type;
+ val ^= (__force u16)fl6->fl6_icmp_code;
+ break;
+ }
+ /* RFC6438 recommands to use flowlabel */
+ val ^= (__force u32)fl6->flowlabel;
+
+ /* Perhaps, we need to tune, this function? */
+ val = val ^ (val >> 7) ^ (val >> 12);
+ return val % candidate_count;
+}
+
+static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
+ struct flowi6 *fl6)
+{
+ struct rt6_info *sibling, *next_sibling;
+ int route_choosen;
+
+ route_choosen = rt6_info_hash_nhsfn(match->rt6i_nsiblings + 1, fl6);
+ /* Don't change the route, if route_choosen == 0
+ * (siblings does not include ourself)
+ */
+ if (route_choosen)
+ list_for_each_entry_safe(sibling, next_sibling,
+ &match->rt6i_siblings, rt6i_siblings) {
+ route_choosen--;
+ if (route_choosen == 0) {
+ match = sibling;
+ break;
+ }
+ }
+ return match;
+}
+
/*
* Route lookup. Any table->tb6_lock is implied.
*/
* Router Reachability Probe MUST be rate-limited
* to no more than one per minute.
*/
- rcu_read_lock();
neigh = rt ? rt->n : NULL;
if (!neigh || (neigh->nud_state & NUD_VALID))
- goto out;
+ return;
read_lock_bh(&neigh->lock);
if (!(neigh->nud_state & NUD_VALID) &&
time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
} else {
read_unlock_bh(&neigh->lock);
}
-out:
- rcu_read_unlock();
}
#else
static inline void rt6_probe(struct rt6_info *rt)
struct neighbour *neigh;
int m;
- rcu_read_lock();
neigh = rt->n;
if (rt->rt6i_flags & RTF_NONEXTHOP ||
!(rt->rt6i_flags & RTF_GATEWAY))
read_unlock_bh(&neigh->lock);
} else
m = 0;
- rcu_read_unlock();
return m;
}
else
rt6_set_expires(rt, jiffies + HZ * lifetime);
- dst_release(&rt->dst);
+ ip6_rt_put(rt);
}
return 0;
}
restart:
rt = fn->leaf;
rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
+ if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
+ rt = rt6_multipath_select(rt, fl6);
BACKTRACK(net, &fl6->saddr);
out:
dst_use(&rt->dst, jiffies);
restart:
rt = rt6_select(fn, oif, strict | reachable);
-
+ if (rt->rt6i_nsiblings && oif == 0)
+ rt = rt6_multipath_select(rt, fl6);
BACKTRACK(net, &fl6->saddr);
if (rt == net->ipv6.ip6_null_entry ||
rt->rt6i_flags & RTF_CACHE)
else
goto out2;
- dst_release(&rt->dst);
+ ip6_rt_put(rt);
rt = nrt ? : net->ipv6.ip6_null_entry;
dst_hold(&rt->dst);
* Race condition! In the gap, when table->tb6_lock was
* released someone could insert this route. Relookup.
*/
- dst_release(&rt->dst);
+ ip6_rt_put(rt);
goto relookup;
out:
{
int flags = 0;
- fl6->flowi6_iif = net->loopback_dev->ifindex;
+ fl6->flowi6_iif = LOOPBACK_IFINDEX;
if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
flags |= RT6_LOOKUP_F_IFACE;
}
rt->dst.output = ip6_pkt_discard_out;
rt->dst.input = ip6_pkt_discard;
- rt->dst.error = -ENETUNREACH;
rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
+ switch (cfg->fc_type) {
+ case RTN_BLACKHOLE:
+ rt->dst.error = -EINVAL;
+ break;
+ case RTN_PROHIBIT:
+ rt->dst.error = -EACCES;
+ break;
+ case RTN_THROW:
+ rt->dst.error = -EAGAIN;
+ break;
+ default:
+ rt->dst.error = -ENETUNREACH;
+ break;
+ }
goto install_route;
}
goto out;
if (dev) {
if (dev != grt->dst.dev) {
- dst_release(&grt->dst);
+ ip6_rt_put(grt);
goto out;
}
} else {
}
if (!(grt->rt6i_flags & RTF_GATEWAY))
err = 0;
- dst_release(&grt->dst);
+ ip6_rt_put(grt);
if (err)
goto out;
struct fib6_table *table;
struct net *net = dev_net(rt->dst.dev);
- if (rt == net->ipv6.ip6_null_entry)
- return -ENOENT;
+ if (rt == net->ipv6.ip6_null_entry) {
+ err = -ENOENT;
+ goto out;
+ }
table = rt->rt6i_table;
write_lock_bh(&table->tb6_lock);
-
err = fib6_del(rt, info);
- dst_release(&rt->dst);
-
write_unlock_bh(&table->tb6_lock);
+out:
+ ip6_rt_put(rt);
return err;
}
if (!table)
return NULL;
- write_lock_bh(&table->tb6_lock);
+ read_lock_bh(&table->tb6_lock);
fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0);
if (!fn)
goto out;
break;
}
out:
- write_unlock_bh(&table->tb6_lock);
+ read_unlock_bh(&table->tb6_lock);
return rt;
}
.fc_dst_len = prefixlen,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
RTF_UP | RTF_PREF(pref),
- .fc_nlinfo.pid = 0,
+ .fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
.fc_nlinfo.nl_net = net,
};
if (!table)
return NULL;
- write_lock_bh(&table->tb6_lock);
+ read_lock_bh(&table->tb6_lock);
for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) {
if (dev == rt->dst.dev &&
((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
}
if (rt)
dst_hold(&rt->dst);
- write_unlock_bh(&table->tb6_lock);
+ read_unlock_bh(&table->tb6_lock);
return rt;
}
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
- .fc_nlinfo.pid = 0,
+ .fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
.fc_nlinfo.nl_net = dev_net(dev),
};
[RTA_IIF] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
[RTA_METRICS] = { .type = NLA_NESTED },
+ [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg->fc_src_len = rtm->rtm_src_len;
cfg->fc_flags = RTF_UP;
cfg->fc_protocol = rtm->rtm_protocol;
+ cfg->fc_type = rtm->rtm_type;
- if (rtm->rtm_type == RTN_UNREACHABLE)
+ if (rtm->rtm_type == RTN_UNREACHABLE ||
+ rtm->rtm_type == RTN_BLACKHOLE ||
+ rtm->rtm_type == RTN_PROHIBIT ||
+ rtm->rtm_type == RTN_THROW)
cfg->fc_flags |= RTF_REJECT;
if (rtm->rtm_type == RTN_LOCAL)
cfg->fc_flags |= RTF_LOCAL;
- cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
+ cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
cfg->fc_nlinfo.nlh = nlh;
cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
if (tb[RTA_TABLE])
cfg->fc_table = nla_get_u32(tb[RTA_TABLE]);
+ if (tb[RTA_MULTIPATH]) {
+ cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
+ cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
+ }
+
err = 0;
errout:
return err;
}
+static int ip6_route_multipath(struct fib6_config *cfg, int add)
+{
+ struct fib6_config r_cfg;
+ struct rtnexthop *rtnh;
+ int remaining;
+ int attrlen;
+ int err = 0, last_err = 0;
+
+beginning:
+ rtnh = (struct rtnexthop *)cfg->fc_mp;
+ remaining = cfg->fc_mp_len;
+
+ /* Parse a Multipath Entry */
+ while (rtnh_ok(rtnh, remaining)) {
+ memcpy(&r_cfg, cfg, sizeof(*cfg));
+ if (rtnh->rtnh_ifindex)
+ r_cfg.fc_ifindex = rtnh->rtnh_ifindex;
+
+ attrlen = rtnh_attrlen(rtnh);
+ if (attrlen > 0) {
+ struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+
+ nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+ if (nla) {
+ nla_memcpy(&r_cfg.fc_gateway, nla, 16);
+ r_cfg.fc_flags |= RTF_GATEWAY;
+ }
+ }
+ err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg);
+ if (err) {
+ last_err = err;
+ /* If we are trying to remove a route, do not stop the
+ * loop when ip6_route_del() fails (because next hop is
+ * already gone), we should try to remove all next hops.
+ */
+ if (add) {
+ /* If add fails, we should try to delete all
+ * next hops that have been already added.
+ */
+ add = 0;
+ goto beginning;
+ }
+ }
+ /* Because each route is added like a single route we remove
+ * this flag after the first nexthop (if there is a collision,
+ * we have already fail to add the first nexthop:
+ * fib6_add_rt2node() has reject it).
+ */
+ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL;
+ rtnh = rtnh_next(rtnh, &remaining);
+ }
+
+ return last_err;
+}
+
static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
struct fib6_config cfg;
if (err < 0)
return err;
- return ip6_route_del(&cfg);
+ if (cfg.fc_mp)
+ return ip6_route_multipath(&cfg, 0);
+ else
+ return ip6_route_del(&cfg);
}
static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
if (err < 0)
return err;
- return ip6_route_add(&cfg);
+ if (cfg.fc_mp)
+ return ip6_route_multipath(&cfg, 1);
+ else
+ return ip6_route_add(&cfg);
}
static inline size_t rt6_nlmsg_size(void)
static int rt6_fill_node(struct net *net,
struct sk_buff *skb, struct rt6_info *rt,
struct in6_addr *dst, struct in6_addr *src,
- int iif, int type, u32 pid, u32 seq,
+ int iif, int type, u32 portid, u32 seq,
int prefix, int nowait, unsigned int flags)
{
struct rtmsg *rtm;
}
}
- nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags);
+ nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags);
if (!nlh)
return -EMSGSIZE;
rtm->rtm_table = table;
if (nla_put_u32(skb, RTA_TABLE, table))
goto nla_put_failure;
- if (rt->rt6i_flags & RTF_REJECT)
- rtm->rtm_type = RTN_UNREACHABLE;
+ if (rt->rt6i_flags & RTF_REJECT) {
+ switch (rt->dst.error) {
+ case -EINVAL:
+ rtm->rtm_type = RTN_BLACKHOLE;
+ break;
+ case -EACCES:
+ rtm->rtm_type = RTN_PROHIBIT;
+ break;
+ case -EAGAIN:
+ rtm->rtm_type = RTN_THROW;
+ break;
+ default:
+ rtm->rtm_type = RTN_UNREACHABLE;
+ break;
+ }
+ }
else if (rt->rt6i_flags & RTF_LOCAL)
rtm->rtm_type = RTN_LOCAL;
else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK))
if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
- rcu_read_lock();
n = rt->n;
if (n) {
- if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) {
- rcu_read_unlock();
+ if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0)
goto nla_put_failure;
- }
}
- rcu_read_unlock();
if (rt->dst.dev &&
nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
return rt6_fill_node(arg->net,
arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
- NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq,
+ NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq,
prefix, 0, NLM_F_MULTI);
}
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
- dst_release(&rt->dst);
+ ip6_rt_put(rt);
err = -ENOBUFS;
goto errout;
}
skb_dst_set(skb, &rt->dst);
err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
- RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
+ RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, 0, 0);
if (err < 0) {
kfree_skb(skb);
goto errout;
}
- err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
+ err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
errout:
return err;
}
goto errout;
err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
- event, info->pid, seq, 0, 0, 0);
+ event, info->portid, seq, 0, 0, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
- rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE,
+ rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
info->nlh, gfp_any());
return;
errout:
#else
seq_puts(m, "00000000000000000000000000000000 00 ");
#endif
- rcu_read_lock();
n = rt->n;
if (n) {
seq_printf(m, "%pi6", n->primary_key);
} else {
seq_puts(m, "00000000000000000000000000000000");
}
- rcu_read_unlock();
seq_printf(m, " %08x %08x %08x %08x %8s\n",
rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
rt->dst.__use, rt->rt6i_flags,