linux/net/bridge/br_vlan_tunnel.c
Ido Schimmel 29cfb2aaa4 bridge: Add backup nexthop ID support
Add a new bridge port attribute that allows attaching a nexthop object
ID to an skb that is redirected to a backup bridge port with VLAN
tunneling enabled.

Specifically, when redirecting a known unicast packet, read the backup
nexthop ID from the bridge port that lost its carrier and set it in the
bridge control block of the skb before forwarding it via the backup
port. Note that reading the ID from the bridge port should not result in
a cache miss as the ID is added next to the 'backup_port' field that was
already accessed. After this change, the 'state' field still stays on
the first cache line, together with other data path related fields such
as 'flags and 'vlgrp':

struct net_bridge_port {
        struct net_bridge *        br;                   /*     0     8 */
        struct net_device *        dev;                  /*     8     8 */
        netdevice_tracker          dev_tracker;          /*    16     0 */
        struct list_head           list;                 /*    16    16 */
        long unsigned int          flags;                /*    32     8 */
        struct net_bridge_vlan_group * vlgrp;            /*    40     8 */
        struct net_bridge_port *   backup_port;          /*    48     8 */
        u32                        backup_nhid;          /*    56     4 */
        u8                         priority;             /*    60     1 */
        u8                         state;                /*    61     1 */
        u16                        port_no;              /*    62     2 */
        /* --- cacheline 1 boundary (64 bytes) --- */
[...]
} __attribute__((__aligned__(8)));

When forwarding an skb via a bridge port that has VLAN tunneling
enabled, check if the backup nexthop ID stored in the bridge control
block is valid (i.e., not zero). If so, instead of attaching the
pre-allocated metadata (that only has the tunnel key set), allocate a
new metadata, set both the tunnel key and the nexthop object ID and
attach it to the skb.

By default, do not dump the new attribute to user space as a value of
zero is an invalid nexthop object ID.

The above is useful for EVPN multihoming. When one of the links
composing an Ethernet Segment (ES) fails, traffic needs to be redirected
towards the host via one of the other ES peers. For example, if a host
is multihomed to three different VTEPs, the backup port of each ES link
needs to be set to the VXLAN device and the backup nexthop ID needs to
point to an FDB nexthop group that includes the IP addresses of the
other two VTEPs. The VXLAN driver will extract the ID from the metadata
of the redirected skb, calculate its flow hash and forward it towards
one of the other VTEPs. If the ID does not exist, or represents an
invalid nexthop object, the VXLAN driver will drop the skb. This
relieves the bridge driver from the need to validate the ID.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2023-07-19 10:53:49 +01:00

224 lines
5.2 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Bridge per vlan tunnel port dst_metadata handling code
*
* Authors:
* Roopa Prabhu <roopa@cumulusnetworks.com>
*/
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
#include <net/switchdev.h>
#include <net/dst_metadata.h>
#include "br_private.h"
#include "br_private_tunnel.h"
static inline int br_vlan_tunid_cmp(struct rhashtable_compare_arg *arg,
const void *ptr)
{
const struct net_bridge_vlan *vle = ptr;
__be64 tunid = *(__be64 *)arg->key;
return vle->tinfo.tunnel_id != tunid;
}
static const struct rhashtable_params br_vlan_tunnel_rht_params = {
.head_offset = offsetof(struct net_bridge_vlan, tnode),
.key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id),
.key_len = sizeof(__be64),
.nelem_hint = 3,
.obj_cmpfn = br_vlan_tunid_cmp,
.automatic_shrinking = true,
};
static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl,
__be64 tunnel_id)
{
return rhashtable_lookup_fast(tbl, &tunnel_id,
br_vlan_tunnel_rht_params);
}
static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan)
{
struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst);
WRITE_ONCE(vlan->tinfo.tunnel_id, 0);
RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL);
dst_release(&tdst->dst);
}
void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg,
struct net_bridge_vlan *vlan)
{
if (!rcu_access_pointer(vlan->tinfo.tunnel_dst))
return;
rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode,
br_vlan_tunnel_rht_params);
vlan_tunnel_info_release(vlan);
}
static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg,
struct net_bridge_vlan *vlan, u32 tun_id)
{
struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst);
__be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id));
int err;
if (metadata)
return -EEXIST;
metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY,
key, 0);
if (!metadata)
return -EINVAL;
metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE;
rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata);
WRITE_ONCE(vlan->tinfo.tunnel_id, key);
err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode,
br_vlan_tunnel_rht_params);
if (err)
goto out;
return 0;
out:
vlan_tunnel_info_release(vlan);
return err;
}
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
*/
int nbp_vlan_tunnel_info_add(const struct net_bridge_port *port, u16 vid,
u32 tun_id)
{
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *vlan;
ASSERT_RTNL();
vg = nbp_vlan_group(port);
vlan = br_vlan_find(vg, vid);
if (!vlan)
return -EINVAL;
return __vlan_tunnel_info_add(vg, vlan, tun_id);
}
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
*/
int nbp_vlan_tunnel_info_delete(const struct net_bridge_port *port, u16 vid)
{
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *v;
ASSERT_RTNL();
vg = nbp_vlan_group(port);
v = br_vlan_find(vg, vid);
if (!v)
return -ENOENT;
vlan_tunnel_info_del(vg, v);
return 0;
}
static void __vlan_tunnel_info_flush(struct net_bridge_vlan_group *vg)
{
struct net_bridge_vlan *vlan, *tmp;
list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist)
vlan_tunnel_info_del(vg, vlan);
}
void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port)
{
struct net_bridge_vlan_group *vg;
ASSERT_RTNL();
vg = nbp_vlan_group(port);
__vlan_tunnel_info_flush(vg);
}
int vlan_tunnel_init(struct net_bridge_vlan_group *vg)
{
return rhashtable_init(&vg->tunnel_hash, &br_vlan_tunnel_rht_params);
}
void vlan_tunnel_deinit(struct net_bridge_vlan_group *vg)
{
rhashtable_destroy(&vg->tunnel_hash);
}
void br_handle_ingress_vlan_tunnel(struct sk_buff *skb,
struct net_bridge_port *p,
struct net_bridge_vlan_group *vg)
{
struct ip_tunnel_info *tinfo = skb_tunnel_info(skb);
struct net_bridge_vlan *vlan;
if (!vg || !tinfo)
return;
/* if already tagged, ignore */
if (skb_vlan_tagged(skb))
return;
/* lookup vid, given tunnel id */
vlan = br_vlan_tunnel_lookup(&vg->tunnel_hash, tinfo->key.tun_id);
if (!vlan)
return;
skb_dst_drop(skb);
__vlan_hwaccel_put_tag(skb, p->br->vlan_proto, vlan->vid);
}
int br_handle_egress_vlan_tunnel(struct sk_buff *skb,
struct net_bridge_vlan *vlan)
{
struct metadata_dst *tunnel_dst;
__be64 tunnel_id;
int err;
if (!vlan)
return 0;
tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id);
if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb)))
return 0;
skb_dst_drop(skb);
err = skb_vlan_pop(skb);
if (err)
return err;
if (BR_INPUT_SKB_CB(skb)->backup_nhid) {
tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY,
tunnel_id, 0);
if (!tunnel_dst)
return -ENOMEM;
tunnel_dst->u.tun_info.mode |= IP_TUNNEL_INFO_TX |
IP_TUNNEL_INFO_BRIDGE;
tunnel_dst->u.tun_info.key.nhid =
BR_INPUT_SKB_CB(skb)->backup_nhid;
skb_dst_set(skb, &tunnel_dst->dst);
return 0;
}
tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst);
if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst))
skb_dst_set(skb, &tunnel_dst->dst);
return 0;
}