| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1427403928-1342-2-git-send-email-gospo@cumulusnetworks.com>
Date: Thu, 26 Mar 2015 17:05:27 -0400
From: Andy Gospodarek <gospo@...ulusnetworks.com>
To: netdev@...r.kernel.org, Bjornar Ness <bjornar.ness@...il.com>,
Sowmini Varadhan <sowmini05@...il.com>,
Eric Dumazet <eric.dumazet@...il.com>,
"John W. Linville" <linville@...driver.com>
Cc: Andy Gospodarek <gospo@...ulusnetworks.com>
Subject: [RFC net-next 1/2] net: allow user to set IPv6 nexthop for IPv4 route
This adds kernel infrastructure to allow userspace (read: routing protocols) to
support adding IPv6 next-hops to IPv4 routes. This is essentially added to
support a feature of MP-BGP outlined in RFC-5549.
Thise does not encompass all that is needed to support RFC-5549, but this
demonstrates the netlink infrastructure needed to correctly enable the kernel
infrastructure that would support this RFC. For more informtion the full RFC
is here: http://www.ietf.org/rfc/rfc5549.txt.
Signed-off-by: Andy Gospodarek <gospo@...ulusnetworks.com>
---
I still consider this an RFC as I need to work out details when IPv6 is not
enabled, but I wanted to get eyes on this as quickly as possible to allow
others to comment on the general implementation.
include/net/ip_fib.h | 3 +++
include/net/route.h | 2 ++
include/uapi/linux/rtnetlink.h | 1 +
net/ipv4/fib_frontend.c | 4 ++++
net/ipv4/fib_semantics.c | 24 +++++++++++++++++++-----
net/ipv4/ip_output.c | 30 +++++++++++++++++++++++++-----
net/ipv4/route.c | 12 ++++++++++++
7 files changed, 66 insertions(+), 10 deletions(-)
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 54271ed..a45fbe0 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -22,6 +22,7 @@
#include <net/fib_rules.h>
#include <net/inetpeer.h>
#include <linux/percpu.h>
+#include <linux/in6.h>
struct fib_config {
u8 fc_dst_len;
@@ -44,6 +45,7 @@ struct fib_config {
u32 fc_flow;
u32 fc_nlflags;
struct nl_info fc_nlinfo;
+ struct in6_addr fc_gw6;
};
struct fib_info;
@@ -89,6 +91,7 @@ struct fib_nh {
struct rtable __rcu * __percpu *nh_pcpu_rth_output;
struct rtable __rcu *nh_rth_input;
struct fnhe_hash_bucket __rcu *nh_exceptions;
+ struct in6_addr nh_gw6;
};
/*
diff --git a/include/net/route.h b/include/net/route.h
index fe22d03..b66a6c4 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -35,6 +35,7 @@
#include <linux/ip.h>
#include <linux/cache.h>
#include <linux/security.h>
+#include <linux/in6.h>
/* IPv4 datagram length is stored into 16bit field (tot_len) */
#define IP_MAX_MTU 0xFFFFU
@@ -66,6 +67,7 @@ struct rtable {
struct list_head rt_uncached;
struct uncached_list *rt_uncached_list;
+ struct in6_addr rt_gateway6;
};
static inline bool rt_is_input_route(const struct rtable *rt)
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index bea910f..26cdd01 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -306,6 +306,7 @@ enum rtattr_type_t {
RTA_VIA,
RTA_NEWDST,
RTA_PREF,
+ RTA_GATEWAY6,
__RTA_MAX
};
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index e5b6b05..3775b05 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -591,6 +591,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
[RTA_FLOW] = { .type = NLA_U32 },
+ [RTA_GATEWAY6] = { .len = sizeof(struct in6_addr) },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
@@ -636,6 +637,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
case RTA_GATEWAY:
cfg->fc_gw = nla_get_be32(attr);
break;
+ case RTA_GATEWAY6:
+ nla_memcpy(&cfg->fc_gw6, attr, sizeof(struct in6_addr));
+ break;
case RTA_PRIORITY:
cfg->fc_priority = nla_get_u32(attr);
break;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 66c1e4f..7de2924 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -468,7 +468,11 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
- nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
+ if (nla_len(nla) == 4) {
+ nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
+ } else if (nla_len(nla) == 16) {
+ nla_memcpy(&nexthop_nh->nh_gw6, nla, nla_len(nla));
+ } else return -EINVAL;
#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
@@ -495,9 +499,10 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
return 1;
- if (cfg->fc_oif || cfg->fc_gw) {
+ if (cfg->fc_oif || cfg->fc_gw || !ipv6_addr_any(&cfg->fc_gw6)) {
if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
- (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw))
+ (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw) &&
+ (ipv6_addr_any(&cfg->fc_gw6) || !ipv6_addr_cmp(&cfg->fc_gw6, &fi->fib_nh->nh_gw6)))
return 0;
return 1;
}
@@ -759,7 +764,7 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
struct fib_info *fib_create_info(struct fib_config *cfg)
{
- int err;
+ int err = 0;
struct fib_info *fi = NULL;
struct fib_info *ofi;
int nhs = 1;
@@ -869,6 +874,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
goto err_inval;
if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
goto err_inval;
+ if (!ipv6_addr_any(&cfg->fc_gw6) && ipv6_addr_cmp(&cfg->fc_gw6, &fi->fib_nh->nh_gw6))
+ goto err_inval;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
goto err_inval;
@@ -882,6 +889,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
nh->nh_oif = cfg->fc_oif;
nh->nh_gw = cfg->fc_gw;
nh->nh_flags = cfg->fc_flags;
+ memcpy(&nh->nh_gw6,&cfg->fc_gw6,sizeof(struct in6_addr));
#ifdef CONFIG_IP_ROUTE_CLASSID
nh->nh_tclassid = cfg->fc_flow;
if (nh->nh_tclassid)
@@ -893,7 +901,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
}
if (fib_props[cfg->fc_type].error) {
- if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp)
+ if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp || !ipv6_addr_any(&cfg->fc_gw6))
goto err_inval;
goto link_it;
} else {
@@ -1033,6 +1041,9 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
if (fi->fib_nh->nh_oif &&
nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
goto nla_put_failure;
+ if (!ipv6_addr_any(&fi->fib_nh->nh_gw6) &&
+ nla_put(skb, RTA_GATEWAY, 16, &fi->fib_nh->nh_gw6))
+ goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (fi->fib_nh[0].nh_tclassid &&
nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
@@ -1060,6 +1071,9 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
if (nh->nh_gw &&
nla_put_be32(skb, RTA_GATEWAY, nh->nh_gw))
goto nla_put_failure;
+ if (!ipv6_addr_any(&nh->nh_gw6) &&
+ nla_put(skb, RTA_GATEWAY, 16, &nh->nh_gw6))
+ goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (nh->nh_tclassid &&
nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8259e77..1b63e6a 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -79,6 +79,9 @@
#include <linux/mroute.h>
#include <linux/netlink.h>
#include <linux/tcp.h>
+#include <net/ndisc.h>
+#include <linux/in6.h>
+#include <net/ipv6.h>
int sysctl_ip_default_ttl __read_mostly = IPDEFTTL;
EXPORT_SYMBOL(sysctl_ip_default_ttl);
@@ -169,7 +172,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
struct rtable *rt = (struct rtable *)dst;
struct net_device *dev = dst->dev;
unsigned int hh_len = LL_RESERVED_SPACE(dev);
- struct neighbour *neigh;
+ struct neighbour *neigh = NULL;
u32 nexthop;
if (rt->rt_type == RTN_MULTICAST) {
@@ -193,10 +196,27 @@ static inline int ip_finish_output2(struct sk_buff *skb)
}
rcu_read_lock_bh();
- nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
- neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
- if (unlikely(!neigh))
- neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
+
+#if IS_ENABLED(CONFIG_IPV6)
+ /* If there is an ipv6 gateway specified, use it */
+ if (!rt->rt_gateway && !ipv6_addr_any(&rt->rt_gateway6)) {
+ neigh = __ipv6_neigh_lookup_noref(dst->dev, &rt->rt_gateway6);
+
+ if (unlikely(!neigh)) {
+ neigh = __neigh_create(&nd_tbl, &rt->rt_gateway6, dst->dev, false);
+ }
+ }
+#endif
+ /* No ipv6 gateway created, so use ipv4 */
+ if (likely(!neigh)) {
+ nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
+ neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
+
+ if (unlikely(!neigh)) {
+ neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
+ }
+ }
+
if (!IS_ERR(neigh)) {
int res = dst_neigh_output(dst, neigh, skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index be8703d..c654b41 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1400,6 +1400,10 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
rt->rt_gateway = nh->nh_gw;
rt->rt_uses_gateway = 1;
}
+ if (!ipv6_addr_any(&nh->nh_gw6)) {
+ memcpy(&rt->rt_gateway6, &nh->nh_gw6, sizeof(struct in6_addr));
+ rt->rt_uses_gateway = 1;
+ }
dst_init_metrics(&rt->dst, fi->fib_metrics, true);
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
@@ -1417,6 +1421,10 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
rt->dst.flags |= DST_NOCACHE;
if (!rt->rt_gateway)
rt->rt_gateway = daddr;
+ if (ipv6_addr_any(&rt->rt_gateway6)) {
+ memcpy(&rt->rt_gateway6, &nh->nh_gw6, sizeof(struct in6_addr));
+ rt->rt_uses_gateway = 1;
+ }
rt_add_uncached_list(rt);
}
} else
@@ -1488,6 +1496,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
+ memset(&rth->rt_gateway6, 0, sizeof(struct in6_addr));
INIT_LIST_HEAD(&rth->rt_uncached);
if (our) {
rth->dst.input= ip_local_deliver;
@@ -1618,6 +1627,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
+ memset(&rth->rt_gateway6, 0, sizeof(struct in6_addr));
INIT_LIST_HEAD(&rth->rt_uncached);
RT_CACHE_STAT_INC(in_slow_tot);
@@ -1792,6 +1802,7 @@ local_input:
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
+ memset(&rth->rt_gateway6, 0, sizeof(struct in6_addr));
INIT_LIST_HEAD(&rth->rt_uncached);
RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_UNREACHABLE) {
@@ -1981,6 +1992,7 @@ add:
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
+ memset(&rth->rt_gateway6, 0, sizeof(struct in6_addr));
INIT_LIST_HEAD(&rth->rt_uncached);
RT_CACHE_STAT_INC(out_slow_tot);
--
1.9.3
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists