Commit 1274e1cc4226 ("vxlan: ecmp support for mac fdb entries") lets a
single inner MAC be reached through a group of remote VTEPs, with the
kernel flow-hashing across the group members. Each member carries its
own remote IP, but the UDP destination port is always taken from the
VXLAN device (vxlan->cfg.dst_port) and cannot be set per member.
Some deployments pack several receivers behind one underlay IP and tell
them apart by UDP port, so they need a per-nexthop destination port to
spread flows across (IP, port) tuples rather than IP alone.
Add a netlink attribute NHA_FDB_PORT (__be16, mirroring NDA_PORT) that
carries an optional UDP destination port on an fdb nexthop. It is only
accepted together with NHA_FDB and NHA_GATEWAY; it is stored in struct
nh_info and echoed back on dump. This patch is control-plane plumbing
only; the VXLAN datapath is wired up in a follow-up patch, so behaviour
is unchanged for now.
Signed-off-by: Jack Ma <[email protected]>
---
include/net/nexthop.h | 2 ++
include/uapi/linux/nexthop.h | 3 +++
net/ipv4/nexthop.c | 20 +++++++++++++++++++-
3 files changed, 24 insertions(+), 1 deletion(-)
diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index 572e69cda..9c8227996 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -28,6 +28,7 @@ struct nh_config {
u8 nh_protocol;
u8 nh_blackhole;
u8 nh_fdb;
+ __be16 nh_fdb_port;
u32 nh_flags;
int nh_ifindex;
@@ -63,6 +64,7 @@ struct nh_info {
u8 family;
bool reject_nh;
bool fdb_nh;
+ __be16 fdb_port;
union {
struct fib_nh_common fib_nhc;
diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h
index bc49baf4a..e587bbf3b 100644
--- a/include/uapi/linux/nexthop.h
+++ b/include/uapi/linux/nexthop.h
@@ -83,6 +83,9 @@ enum {
/* u32; read-only; whether any driver collects HW stats */
NHA_HW_STATS_USED,
+ /* be16; UDP destination port for an fdb nexthop (e.g. VXLAN) */
+ NHA_FDB_PORT,
+
__NHA_MAX,
};
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 6205bd57a..5b27cc9a9 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -39,6 +39,7 @@ static const struct nla_policy rtm_nh_policy_new[] = {
[NHA_ENCAP_TYPE] = { .type = NLA_U16 },
[NHA_ENCAP] = { .type = NLA_NESTED },
[NHA_FDB] = { .type = NLA_FLAG },
+ [NHA_FDB_PORT] = { .type = NLA_U16 },
[NHA_RES_GROUP] = { .type = NLA_NESTED },
[NHA_HW_STATS_ENABLE] = NLA_POLICY_MAX(NLA_U32, true),
};
@@ -956,6 +957,9 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop
*nh,
} else if (nhi->fdb_nh) {
if (nla_put_flag(skb, NHA_FDB))
goto nla_put_failure;
+ if (nhi->fdb_port &&
+ nla_put_be16(skb, NHA_FDB_PORT, nhi->fdb_port))
+ goto nla_put_failure;
} else {
const struct net_device *dev;
@@ -1055,6 +1059,9 @@ static size_t nh_nlmsg_size_single(struct nexthop *nh)
break;
}
+ if (nhi->fdb_nh)
+ sz += nla_total_size(2); /* NHA_FDB_PORT */
+
if (nhi->fib_nhc.nhc_lwtstate) {
sz += lwtunnel_get_encap_size(nhi->fib_nhc.nhc_lwtstate);
sz += nla_total_size(2); /* NHA_ENCAP_TYPE */
@@ -2956,8 +2963,10 @@ static struct nexthop *nexthop_create(struct net *net,
struct nh_config *cfg,
nhi->family = cfg->nh_family;
nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK;
- if (cfg->nh_fdb)
+ if (cfg->nh_fdb) {
nhi->fdb_nh = 1;
+ nhi->fdb_port = cfg->nh_fdb_port;
+ }
if (cfg->nh_blackhole) {
nhi->reject_nh = 1;
@@ -3147,6 +3156,15 @@ static int rtm_to_nh_config(struct net *net, struct
sk_buff *skb,
cfg->nh_fdb = nla_get_flag(tb[NHA_FDB]);
}
+ if (tb[NHA_FDB_PORT]) {
+ if (!tb[NHA_FDB] || !tb[NHA_GATEWAY]) {
+ NL_SET_ERR_MSG(extack,
+ "FDB port can only be set on fdb
nexthops that have a gateway");
+ goto out;
+ }
+ cfg->nh_fdb_port = nla_get_be16(tb[NHA_FDB_PORT]);
+ }
+
if (tb[NHA_GROUP]) {
if (nhm->nh_family != AF_UNSPEC) {
NL_SET_ERR_MSG(extack, "Invalid family for group");
--
2.43.0
