Files
laptops-kernel/include/uapi/linux/nexthop.h
Jack MaandJakub Kicinski 53531e6a64 net: nexthop: add NHA_DST_PORT for fdb nexthops
Commit 1274e1cc42 ("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_DST_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.  The attribute is named generically
rather than fdb-specific so it can be reused should another nexthop type
ever need a destination port.  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 <jack4it@gmail.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260724-b4-vxlan-fdb-port-v5-1-cd1c6aeee058@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-07-30 16:09:22 -07:00

161 lines
4.1 KiB
C

/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI_LINUX_NEXTHOP_H
#define _UAPI_LINUX_NEXTHOP_H
#include <linux/types.h>
struct nhmsg {
unsigned char nh_family;
unsigned char nh_scope; /* return only */
unsigned char nh_protocol; /* Routing protocol that installed nh */
unsigned char resvd;
unsigned int nh_flags; /* RTNH_F flags */
};
/* entry in a nexthop group */
struct nexthop_grp {
__u32 id; /* nexthop id - must exist */
__u8 weight; /* weight of this nexthop */
__u8 weight_high; /* high order bits of weight */
__u16 resvd2;
};
static inline __u16 nexthop_grp_weight(const struct nexthop_grp *entry)
{
return ((entry->weight_high << 8) | entry->weight) + 1;
}
enum {
NEXTHOP_GRP_TYPE_MPATH, /* hash-threshold nexthop group
* default type if not specified
*/
NEXTHOP_GRP_TYPE_RES, /* resilient nexthop group */
__NEXTHOP_GRP_TYPE_MAX,
};
#define NEXTHOP_GRP_TYPE_MAX (__NEXTHOP_GRP_TYPE_MAX - 1)
#define NHA_OP_FLAG_DUMP_STATS BIT(0)
#define NHA_OP_FLAG_DUMP_HW_STATS BIT(1)
/* Response OP_FLAGS. */
#define NHA_OP_FLAG_RESP_GRP_RESVD_0 BIT(31) /* Dump clears resvd fields. */
enum {
NHA_UNSPEC,
NHA_ID, /* u32; id for nexthop. id == 0 means auto-assign */
NHA_GROUP, /* array of nexthop_grp */
NHA_GROUP_TYPE, /* u16 one of NEXTHOP_GRP_TYPE */
/* if NHA_GROUP attribute is added, no other attributes can be set */
NHA_BLACKHOLE, /* flag; nexthop used to blackhole packets */
/* if NHA_BLACKHOLE is added, OIF, GATEWAY, ENCAP can not be set */
NHA_OIF, /* u32; nexthop device */
NHA_GATEWAY, /* be32 (IPv4) or in6_addr (IPv6) gw address */
NHA_ENCAP_TYPE, /* u16; lwt encap type */
NHA_ENCAP, /* lwt encap data */
/* NHA_OIF can be appended to dump request to return only
* nexthops using given device
*/
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 */
/* nested; resilient nexthop group attributes */
NHA_RES_GROUP,
/* nested; nexthop bucket attributes */
NHA_RES_BUCKET,
/* u32; operation-specific flags */
NHA_OP_FLAGS,
/* nested; nexthop group stats */
NHA_GROUP_STATS,
/* u32; nexthop hardware stats enable */
NHA_HW_STATS_ENABLE,
/* 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_DST_PORT,
__NHA_MAX,
};
#define NHA_MAX (__NHA_MAX - 1)
enum {
NHA_RES_GROUP_UNSPEC,
/* Pad attribute for 64-bit alignment. */
NHA_RES_GROUP_PAD = NHA_RES_GROUP_UNSPEC,
/* u16; number of nexthop buckets in a resilient nexthop group */
NHA_RES_GROUP_BUCKETS,
/* clock_t as u32; nexthop bucket idle timer (per-group) */
NHA_RES_GROUP_IDLE_TIMER,
/* clock_t as u32; nexthop unbalanced timer */
NHA_RES_GROUP_UNBALANCED_TIMER,
/* clock_t as u64; nexthop unbalanced time */
NHA_RES_GROUP_UNBALANCED_TIME,
__NHA_RES_GROUP_MAX,
};
#define NHA_RES_GROUP_MAX (__NHA_RES_GROUP_MAX - 1)
enum {
NHA_RES_BUCKET_UNSPEC,
/* Pad attribute for 64-bit alignment. */
NHA_RES_BUCKET_PAD = NHA_RES_BUCKET_UNSPEC,
/* u16; nexthop bucket index */
NHA_RES_BUCKET_INDEX,
/* clock_t as u64; nexthop bucket idle time */
NHA_RES_BUCKET_IDLE_TIME,
/* u32; nexthop id assigned to the nexthop bucket */
NHA_RES_BUCKET_NH_ID,
__NHA_RES_BUCKET_MAX,
};
#define NHA_RES_BUCKET_MAX (__NHA_RES_BUCKET_MAX - 1)
enum {
NHA_GROUP_STATS_UNSPEC,
/* nested; nexthop group entry stats */
NHA_GROUP_STATS_ENTRY,
__NHA_GROUP_STATS_MAX,
};
#define NHA_GROUP_STATS_MAX (__NHA_GROUP_STATS_MAX - 1)
enum {
NHA_GROUP_STATS_ENTRY_UNSPEC,
/* u32; nexthop id of the nexthop group entry */
NHA_GROUP_STATS_ENTRY_ID,
/* uint; number of packets forwarded via the nexthop group entry */
NHA_GROUP_STATS_ENTRY_PACKETS,
/* uint; number of packets forwarded via the nexthop group entry in
* hardware
*/
NHA_GROUP_STATS_ENTRY_PACKETS_HW,
__NHA_GROUP_STATS_ENTRY_MAX,
};
#define NHA_GROUP_STATS_ENTRY_MAX (__NHA_GROUP_STATS_ENTRY_MAX - 1)
#endif