ipv4: support for fib route lwtunnel encap attributes

This patch adds support in ipv4 fib functions to parse user
provided encap attributes and attach encap state data to fib_nh
and rtable.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 122 insertions, 4 deletions

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 49c142bdf01e..5e0196084f1e 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 +91,7 @@ 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 lwtunnel_state   *nh_lwtstate;
 };
 
 /*
diff --git a/include/net/route.h b/include/net/route.h
index fe22d03afb6a..2d45f419477f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -66,6 +66,7 @@ struct rtable {
 
         struct list_head        rt_uncached;
         struct uncached_list    *rt_uncached_list;
+        struct lwtunnel_state   *rt_lwtstate;
 };
 
 static inline bool rt_is_input_route(const struct rtable *rt)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 6bbc54940eb4..9b2019cc3586 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 c7358ea4ae93..6754c64b2fe0 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 +209,7 @@ static void free_fib_info_rcu(struct rcu_head *head)
         change_nexthops(fi) {
                 if (nexthop_nh->nh_dev)
                         dev_put(nexthop_nh->nh_dev);
+                lwtunnel_state_put(nexthop_nh->nh_lwtstate);
                 free_nh_exceptions(nexthop_nh);
                 rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
                 rt_fibinfo_free(&nexthop_nh->nh_rth_input);
@@ -266,6 +268,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
 #ifdef CONFIG_IP_ROUTE_CLASSID
                     nh->nh_tclassid != onh->nh_tclassid ||
 #endif
+                    lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) ||
                     ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK))
                         return -1;
                 onh++;
@@ -366,6 +369,7 @@ 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 +378,21 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi)
                 /* may contain flow and gateway attribute */
                 nhsize += 2 * nla_total_size(4);
 
+                /* 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);
+
                 /* 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 +469,9 @@ 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;
 
@@ -475,18 +495,66 @@ 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
+                        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;
+                        }
                 }
 
                 rtnh = rtnh_next(rtnh, &remaining);
         } endfor_nexthops(fi);
 
         return 0;
+
+err_inval:
+        ret = -EINVAL;
+
+errout:
+        return ret;
 }
 
 #endif
 
+int fib_encap_match(struct net *net, u16 encap_type,
+                    struct nlattr *encap,
+                    int oif, const struct fib_nh *nh)
+{
+        struct lwtunnel_state *lwtstate;
+        struct net_device *dev = NULL;
+        int ret;
+
+        if (encap_type == LWTUNNEL_ENCAP_NONE)
+                return 0;
+
+        if (oif)
+                dev = __dev_get_by_index(net, oif);
+        ret = lwtunnel_build_state(dev, encap_type,
+                                   encap, &lwtstate);
+        if (!ret)
+                return lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate);
+
+        return 0;
+}
+
 int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 {
+        struct net *net = cfg->fc_nlinfo.nl_net;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
         struct rtnexthop *rtnh;
         int remaining;
@@ -496,6 +564,12 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
                 return 1;
 
         if (cfg->fc_oif || cfg->fc_gw) {
+                if (cfg->fc_encap) {
+                        if (fib_encap_match(net, cfg->fc_encap_type,
+                                            cfg->fc_encap, cfg->fc_oif,
+                                            fi->fib_nh))
+                            return 1;
+                }
                 if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
                     (!cfg->fc_gw  || cfg->fc_gw == fi->fib_nh->nh_gw))
                         return 0;
@@ -882,6 +956,22 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
         } else {
                 struct fib_nh *nh = fi->fib_nh;
 
+                if (cfg->fc_encap) {
+                        struct lwtunnel_state *lwtstate;
+                        struct net_device *dev = NULL;
+
+                        if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE)
+                                goto err_inval;
+                        if (cfg->fc_oif)
+                                dev = __dev_get_by_index(net, cfg->fc_oif);
+                        err = lwtunnel_build_state(dev, cfg->fc_encap_type,
+                                                   cfg->fc_encap, &lwtstate);
+                        if (err)
+                                goto failure;
+
+                        lwtunnel_state_get(lwtstate);
+                        nh->nh_lwtstate = lwtstate;
+                }
                 nh->nh_oif = cfg->fc_oif;
                 nh->nh_gw = cfg->fc_gw;
                 nh->nh_flags = cfg->fc_flags;
@@ -1055,6 +1145,8 @@ 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
+                if (fi->fib_nh->nh_lwtstate)
+                        lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate);
         }
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
         if (fi->fib_nhs > 1) {
@@ -1090,6 +1182,8 @@ 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
+                        if (nh->nh_lwtstate)
+                                lwtunnel_fill_encap(skb, nh->nh_lwtstate);
                         /* 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 04c83de4f79e..226570ba1ced 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 +1356,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
                 list_del(&rt->rt_uncached);
                 spin_unlock_bh(&ul->lock);
         }
+        lwtunnel_state_put(rt->rt_lwtstate);
 }
 
 void rt_flush_dev(struct net_device *dev)
@@ -1403,6 +1405,12 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 #ifdef CONFIG_IP_ROUTE_CLASSID
                 rt->dst.tclassid = nh->nh_tclassid;
 #endif
+                if (nh->nh_lwtstate) {
+                        lwtunnel_state_get(nh->nh_lwtstate);
+                        rt->rt_lwtstate = nh->nh_lwtstate;
+                } else {
+                        rt->rt_lwtstate = NULL;
+                }
                 if (unlikely(fnhe))
                         cached = rt_bind_exception(rt, fnhe, daddr);
                 else if (!(rt->dst.flags & DST_NOCACHE))
@@ -1488,6 +1496,7 @@ 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);
+        rth->rt_lwtstate = NULL;
         if (our) {
                 rth->dst.input= ip_local_deliver;
                 rth->rt_flags |= RTCF_LOCAL;
@@ -1617,6 +1626,7 @@ static int __mkroute_input(struct sk_buff *skb,
         rth->rt_gateway = 0;
         rth->rt_uses_gateway = 0;
         INIT_LIST_HEAD(&rth->rt_uncached);
+        rth->rt_lwtstate = NULL;
         RT_CACHE_STAT_INC(in_slow_tot);
 
         rth->dst.input = ip_forward;
@@ -1791,6 +1801,8 @@ local_input:
         rth->rt_gateway = 0;
         rth->rt_uses_gateway = 0;
         INIT_LIST_HEAD(&rth->rt_uncached);
+        rth->rt_lwtstate = NULL;
+
         RT_CACHE_STAT_INC(in_slow_tot);
         if (res.type == RTN_UNREACHABLE) {
                 rth->dst.input= ip_error;
@@ -1980,7 +1992,7 @@ add:
         rth->rt_gateway = 0;
         rth->rt_uses_gateway = 0;
         INIT_LIST_HEAD(&rth->rt_uncached);
-
+        rth->rt_lwtstate = NULL;
         RT_CACHE_STAT_INC(out_slow_tot);
 
         if (flags & RTCF_LOCAL)
@@ -2260,7 +2272,7 @@ 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);
-
+                rt->rt_lwtstate = NULL;
                 dst_free(new);
         }