From: Roopa Prabhu <ro...@cumulusnetworks.com>
Introduces two netlink attributes RTA_ENCAP_TYPE and
RTA_ENCAP to support attaching encap information to ipv4 routes.
RTA_ENCAP is a nested attribute as suggested by Thomas
(and also as Robert had it in his series). RTA_ENCAP
netlink policy is declared by the light weight tunnel
drivers that support this encap type.
fib code calls the following for each nexthop:
- new route handler:
lwt build state (that parses RTA_ENCAP and returns
lwt state that lives in every fib_nh)
- del dump hanlder:
lwt release handler to release lwt state data
- route dump hanlder:
lwt dump encap to fill RTA_ENCAP data
- during input route lookup
sets dst->output to lwtunnel_output which
in turn calls the corresponding lwt tunnel
output function which applies the required
encap and xmits the packet
Signed-off-by: Roopa Prabhu <ro...@cumulusnetworks.com>
---
include/net/ip_fib.h | 7 ++-
include/net/route.h | 3 ++
include/uapi/linux/rtnetlink.h | 3 +-
net/ipv4/fib_frontend.c | 8 ++++
net/ipv4/fib_semantics.c | 93 +++++++++++++++++++++++++++++++++++++++-
net/ipv4/route.c | 33 +++++++++++++-
6 files changed, 142 insertions(+), 5 deletions(-)
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 54271ed..49f18d7 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -44,7 +44,9 @@ struct fib_config {
u32 fc_flow;
u32 fc_nlflags;
struct nl_info fc_nlinfo;
- };
+ struct nlattr *fc_encap;
+ u16 fc_encap_type;
+};
struct fib_info;
struct rtable;
@@ -89,6 +91,9 @@ struct fib_nh {
struct rtable __rcu * __percpu *nh_pcpu_rth_output;
struct rtable __rcu *nh_rth_input;
struct fnhe_hash_bucket __rcu *nh_exceptions;
+#ifdef CONFIG_LWTUNNEL
+ struct lwtunnel_state *nh_lwtstate;
+#endif
};
/*
diff --git a/include/net/route.h b/include/net/route.h
index fe22d03..39a6495 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -66,6 +66,9 @@ struct rtable {
struct list_head rt_uncached;
struct uncached_list *rt_uncached_list;
+#ifdef CONFIG_LWTUNNEL
+ struct lwtunnel_state *rt_lwtstate;
+#endif
};
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 17fb02f..6c089ad 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -308,6 +308,8 @@ enum rtattr_type_t {
RTA_VIA,
RTA_NEWDST,
RTA_PREF,
+ RTA_ENCAP_TYPE,
+ RTA_ENCAP,
__RTA_MAX
};
@@ -357,7 +359,6 @@ struct rtvia {
};
/* RTM_CACHEINFO */
-
struct rta_cacheinfo {
__u32 rta_clntref;
__u32 rta_lastuse;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 872494e..fbe0630 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -591,6 +591,8 @@ 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_ENCAP_TYPE] = { .type = NLA_U16 },
+ [RTA_ENCAP] = { .type = NLA_NESTED },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
@@ -656,6 +658,12 @@ static int rtm_to_fib_config(struct net *net, struct
sk_buff *skb,
case RTA_TABLE:
cfg->fc_table = nla_get_u32(attr);
break;
+ case RTA_ENCAP:
+ cfg->fc_encap = attr;
+ break;
+ case RTA_ENCAP_TYPE:
+ cfg->fc_encap_type = nla_get_u16(attr);
+ break;
}
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 28ec3c1..54dd287 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -42,6 +42,7 @@
#include <net/ip_fib.h>
#include <net/netlink.h>
#include <net/nexthop.h>
+#include <net/lwtunnel.h>
#include "fib_lookup.h"
@@ -208,6 +209,10 @@ static void free_fib_info_rcu(struct rcu_head *head)
change_nexthops(fi) {
if (nexthop_nh->nh_dev)
dev_put(nexthop_nh->nh_dev);
+#ifdef CONFIG_LWTUNNEL
+ if (nexthop_nh->nh_lwtstate)
+ lwtunnel_state_put(nexthop_nh->nh_lwtstate);
+#endif
free_nh_exceptions(nexthop_nh);
rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
rt_fibinfo_free(&nexthop_nh->nh_rth_input);
@@ -366,6 +371,7 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi)
payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
if (fi->fib_nhs) {
+ size_t nh_encapsize = 0;
/* Also handles the special case fib_nhs == 1 */
/* each nexthop is packed in an attribute */
@@ -374,8 +380,23 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi)
/* may contain flow and gateway attribute */
nhsize += 2 * nla_total_size(4);
+#ifdef CONFIG_LWTUNNEL
+ /* grab encap info */
+ for_nexthops(fi) {
+ if (nh->nh_lwtstate) {
+ /* RTA_ENCAP_TYPE */
+ nh_encapsize += lwtunnel_get_encap_size(
+ nh->nh_lwtstate);
+ /* RTA_ENCAP */
+ nh_encapsize += nla_total_size(2);
+ }
+ } endfor_nexthops(fi);
+#endif
+
/* all nexthops are packed in a nested attribute */
- payload += nla_total_size(fi->fib_nhs * nhsize);
+ payload += nla_total_size((fi->fib_nhs * nhsize) +
+ nh_encapsize);
+
}
return payload;
@@ -452,6 +473,9 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int
remaining)
static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
int remaining, struct fib_config *cfg)
{
+ struct net *net = cfg->fc_nlinfo.nl_net;
+ int ret;
+
change_nexthops(fi) {
int attrlen;
@@ -475,12 +499,40 @@ static int fib_get_nhs(struct fib_info *fi, struct
rtnexthop *rtnh,
if (nexthop_nh->nh_tclassid)
fi->fib_net->ipv4.fib_num_tclassid_users++;
#endif
+#ifdef CONFIG_LWTUNNEL
+ nla = nla_find(attrs, attrlen, RTA_ENCAP);
+ if (nla) {
+ struct lwtunnel_state *lwtstate;
+ struct net_device *dev = NULL;
+ struct nlattr *nla_entype;
+
+ nla_entype = nla_find(attrs, attrlen,
+ RTA_ENCAP_TYPE);
+ if (!nla_entype)
+ goto err_inval;
+ if (cfg->fc_oif)
+ dev = __dev_get_by_index(net,
cfg->fc_oif);
+ ret = lwtunnel_build_state(dev, nla_get_u16(
+ nla_entype),
+ nla, &lwtstate);
+ if (ret)
+ goto errout;
+ lwtunnel_state_get(lwtstate);
+ nexthop_nh->nh_lwtstate = lwtstate;
+ }
+#endif
}
rtnh = rtnh_next(rtnh, &remaining);
} endfor_nexthops(fi);
return 0;
+
+err_inval:
+ ret = -EINVAL;
+
+errout:
+ return ret;
}
#endif
@@ -875,6 +927,25 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
} else {
struct fib_nh *nh = fi->fib_nh;
+#ifdef CONFIG_LWTUNNEL
+ if (cfg->fc_encap) {
+ struct lwtunnel_state *lwtstate;
+ struct net_device *dev = NULL;
+ int ret;
+
+ if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE)
+ goto err_inval;
+ if (cfg->fc_oif)
+ dev = __dev_get_by_index(net, cfg->fc_oif);
+ ret = lwtunnel_build_state(dev, cfg->fc_encap_type,
+ cfg->fc_encap, &lwtstate);
+ if (ret)
+ goto err_inval;
+
+ lwtunnel_state_get(lwtstate);
+ nh->nh_lwtstate = lwtstate;
+ }
+#endif
nh->nh_oif = cfg->fc_oif;
nh->nh_gw = cfg->fc_gw;
nh->nh_flags = cfg->fc_flags;
@@ -1034,7 +1105,17 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32
seq, int event,
nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
goto nla_put_failure;
#endif
+#ifdef CONFIG_LWTUNNEL
+ if (fi->fib_nh->nh_lwtstate) {
+ struct lwtunnel_state *lwtstate;
+
+ lwtstate = fi->fib_nh->nh_lwtstate;
+ if (nla_put_u16(skb, RTA_ENCAP_TYPE, lwtstate->type))
+ goto nla_put_failure;
+ lwtunnel_fill_encap(skb, lwtstate);
+ }
}
+#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (fi->fib_nhs > 1) {
struct rtnexthop *rtnh;
@@ -1061,6 +1142,16 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32
seq, int event,
nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
goto nla_put_failure;
#endif
+#ifdef CONFIG_LWTUNNEL
+ if (nh->nh_lwtstate) {
+ struct lwtunnel_state *lwtstate;
+
+ lwtstate = nh->nh_lwtstate;
+ if (nla_put_u16(skb, RTA_ENCAP_TYPE,
lwtstate->type))
+ goto nla_put_failure;
+ lwtunnel_fill_encap(skb, lwtstate);
+ }
+#endif
/* length of rtnetlink header + attributes */
rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
} endfor_nexthops(fi);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f605598..c6549f9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -102,6 +102,7 @@
#include <net/tcp.h>
#include <net/icmp.h>
#include <net/xfrm.h>
+#include <net/lwtunnel.h>
#include <net/netevent.h>
#include <net/rtnetlink.h>
#ifdef CONFIG_SYSCTL
@@ -1355,6 +1356,9 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
list_del(&rt->rt_uncached);
spin_unlock_bh(&ul->lock);
}
+#ifdef CONFIG_LWTUNNEL
+ lwtunnel_state_put(rt->rt_lwtstate);
+#endif
}
void rt_flush_dev(struct net_device *dev)
@@ -1403,6 +1407,14 @@ static void rt_set_nexthop(struct rtable *rt, __be32
daddr,
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
#endif
+#ifdef CONFIG_LWTUNNEL
+ if (nh->nh_lwtstate) {
+ lwtunnel_state_get(nh->nh_lwtstate);
+ rt->rt_lwtstate = nh->nh_lwtstate;
+ } else {
+ rt->rt_lwtstate = NULL;
+ }
+#endif
if (unlikely(fnhe))
cached = rt_bind_exception(rt, fnhe, daddr);
else if (!(rt->dst.flags & DST_NOCACHE))
@@ -1488,6 +1500,9 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32
daddr, __be32 saddr,
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+#ifdef CONFIG_LWTUNNEL
+ rth->rt_lwtstate = NULL;
+#endif
if (our) {
rth->dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
@@ -1618,12 +1633,19 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+#ifdef CONFIG_LWTUNNEL
+ rth->rt_lwtstate = NULL;
+#endif
RT_CACHE_STAT_INC(in_slow_tot);
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag);
+#ifdef CONFIG_LWTUNNEL
+ if (lwtunnel_output_redirect(rth->rt_lwtstate))
+ rth->dst.output = lwtunnel_output;
+#endif
skb_dst_set(skb, &rth->dst);
out:
err = 0;
@@ -1792,6 +1814,9 @@ local_input:
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+#ifdef CONFIG_LWTUNNEL
+ rth->rt_lwtstate = NULL;
+#endif
RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
@@ -1981,7 +2006,9 @@ add:
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
-
+#ifdef CONFIG_LWTUNNEL
+ rth->rt_lwtstate = NULL;
+#endif
RT_CACHE_STAT_INC(out_slow_tot);
if (flags & RTCF_LOCAL)
@@ -2261,7 +2288,9 @@ struct dst_entry *ipv4_blackhole_route(struct net *net,
struct dst_entry *dst_or
rt->rt_uses_gateway = ort->rt_uses_gateway;
INIT_LIST_HEAD(&rt->rt_uncached);
-
+#ifdef CONFIG_LWTUNNEL
+ rt->rt_lwtstate = NULL;
+#endif
dst_free(new);
}
--
1.7.10.4
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
