nexthop: support for fdb ecmp nexthops

This patch introduces ecmp nexthops and nexthop groups
for mac fdb entries. In subsequent patches this is used
by the vxlan driver fdb entries. The use case is
E-VPN multihoming [1,2,3] which requires bridged vxlan traffic
to be load balanced to remote switches (vteps) belonging to
the same multi-homed ethernet segment (This is analogous to
a multi-homed LAG but over vxlan).

Changes include new nexthop flag NHA_FDB for nexthops
referenced by fdb entries. These nexthops only have ip.
This patch includes appropriate checks to avoid routes
referencing such nexthops.

example:
$ip nexthop add id 12 via 172.16.1.2 fdb
$ip nexthop add id 13 via 172.16.1.3 fdb
$ip nexthop add id 102 group 12/13 fdb

$bridge fdb add 02:02:00:00:00:13 dev vxlan1000 nhid 101 self

[1] E-VPN https://tools.ietf.org/html/rfc7432
[2] E-VPN VxLAN: https://tools.ietf.org/html/rfc8365
[3] LPC talk with mention of nexthop groups for L2 ecmp
http://vger.kernel.org/lpc_net2018_talks/scaling_bridge_fdb_database_slidesV3.pdf

v4 - fixed uninitialized variable reported by kernel test robot
Reported-by: kernel test robot <rong.a.chen@intel.com>

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

3 files changed, 36 insertions, 0 deletions

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index fdaf975e3331..3f615a29766e 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -65,6 +65,7 @@ struct fib6_config {
 	struct nl_info	fc_nlinfo;
 	struct nlattr	*fc_encap;
 	u16		fc_encap_type;
+	bool		fc_is_fdb;
 };
 
 struct fib6_node {
diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index c440ccc861fc..d929c98931ad 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -26,6 +26,7 @@ struct nh_config {
 	u8		nh_family;
 	u8		nh_protocol;
 	u8		nh_blackhole;
+	u8		nh_fdb;
 	u32		nh_flags;
 
 	int		nh_ifindex;
@@ -52,6 +53,7 @@ struct nh_info {
 
 	u8			family;
 	bool			reject_nh;
+	bool			fdb_nh;
 
 	union {
 		struct fib_nh_common	fib_nhc;
@@ -80,6 +82,7 @@ struct nexthop {
 	struct rb_node		rb_node;    /* entry on netns rbtree */
 	struct list_head	fi_list;    /* v4 entries using nh */
 	struct list_head	f6i_list;   /* v6 entries using nh */
+	struct list_head        fdb_list;   /* fdb entries using this nh */
 	struct list_head	grp_list;   /* nh group entries using this nh */
 	struct net		*net;
 
@@ -88,6 +91,7 @@ struct nexthop {
 	u8			protocol;   /* app managing this nh */
 	u8			nh_flags;
 	bool			is_group;
+	bool			is_fdb_nh;
 
 	refcount_t		refcnt;
 	struct rcu_head		rcu;
@@ -304,4 +308,32 @@ static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash)
 int nexthop_for_each_fib6_nh(struct nexthop *nh,
 			     int (*cb)(struct fib6_nh *nh, void *arg),
 			     void *arg);
+
+static inline int nexthop_get_family(struct nexthop *nh)
+{
+	struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info);
+
+	return nhi->family;
+}
+
+static inline
+struct fib_nh_common *nexthop_fdb_nhc(struct nexthop *nh)
+{
+	struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info);
+
+	return &nhi->fib_nhc;
+}
+
+static inline struct fib_nh_common *nexthop_path_fdb_result(struct nexthop *nh,
+							    int hash)
+{
+	struct nh_info *nhi;
+	struct nexthop *nhp;
+
+	nhp = nexthop_select_path(nh, hash);
+	if (unlikely(!nhp))
+		return NULL;
+	nhi = rcu_dereference(nhp->nh_info);
+	return &nhi->fib_nhc;
+}
 #endif
diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h
index 7b61867e9848..2d4a1e784cf0 100644
--- a/include/uapi/linux/nexthop.h
+++ b/include/uapi/linux/nexthop.h
@@ -49,6 +49,9 @@ enum {
 	NHA_GROUPS,	/* flag; only return nexthop groups in dump */
 	NHA_MASTER,	/* u32;  only return nexthops with given master dev */
 
+	NHA_FDB,	/* flag; nexthop belongs to a bridge fdb */
+	/* if NHA_FDB is added, OIF, BLACKHOLE, ENCAP cannot be set */
+
 	__NHA_MAX,
 };