Commit 25c800b2 authored by David S. Miller's avatar David S. Miller

Merge branch 'bridge-neigh-suppression'

Ido Schimmel says:

====================
bridge: Add per-{Port, VLAN} neighbor suppression

Background
==========

In order to minimize the flooding of ARP and ND messages in the VXLAN
network, EVPN includes provisions [1] that allow participating VTEPs to
suppress such messages in case they know the MAC-IP binding and can
reply on behalf of the remote host. In Linux, the above is implemented
in the bridge driver using a per-port option called "neigh_suppress"
that was added in kernel version 4.15 [2].

Motivation
==========

Some applications use ARP messages as keepalives between the application
nodes in the network. This works perfectly well when two nodes are
connected to the same VTEP. When a node goes down it will stop
responding to ARP requests and the other node will notice it
immediately.

However, when the two nodes are connected to different VTEPs and
neighbor suppression is enabled, the local VTEP will reply to ARP
requests even after the remote node went down, until certain timers
expire and the EVPN control plane decides to withdraw the MAC/IP
Advertisement route for the address. Therefore, some users would like to
be able to disable neighbor suppression on VLANs where such applications
reside and keep it enabled on the rest.

Implementation
==============

The proposed solution is to allow user space to control neighbor
suppression on a per-{Port, VLAN} basis, in a similar fashion to other
per-port options that gained per-{Port, VLAN} counterparts such as
"mcast_router". This allows users to benefit from the operational
simplicity and scalability associated with shared VXLAN devices (i.e.,
external / collect-metadata mode), while still allowing for per-VLAN/VNI
neighbor suppression control.

The user interface is extended with a new "neigh_vlan_suppress" bridge
port option that allows user space to enable per-{Port, VLAN} neighbor
suppression on the bridge port. When enabled, the existing
"neigh_suppress" option has no effect and neighbor suppression is
controlled using a new "neigh_suppress" VLAN option. Example usage:

 # bridge link set dev vxlan0 neigh_vlan_suppress on
 # bridge vlan add vid 10 dev vxlan0
 # bridge vlan set vid 10 dev vxlan0 neigh_suppress on

Testing
=======

Tested using existing bridge selftests. Added a dedicated selftest in
the last patch.

Patchset overview
=================

Patches #1-#5 are preparations.

Patch #6 adds per-{Port, VLAN} neighbor suppression support to the
bridge's data path.

Patches #7-#8 add the required netlink attributes to enable the feature.

Patch #9 adds a selftest.

iproute2 patches can be found here [3].

Changelog
=========

Since RFC [4]:

No changes.

[1] https://www.rfc-editor.org/rfc/rfc7432#section-10
[2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=a42317785c898c0ed46db45a33b0cc71b671bf29
[3] https://github.com/idosch/iproute2/tree/submit/neigh_suppress_v1
[4] https://lore.kernel.org/netdev/20230413095830.2182382-1-idosch@nvidia.com/
====================
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 1cf3fe1c 7648ac72
......@@ -60,6 +60,7 @@ struct br_ip_list {
#define BR_TX_FWD_OFFLOAD BIT(20)
#define BR_PORT_LOCKED BIT(21)
#define BR_PORT_MAB BIT(22)
#define BR_NEIGH_VLAN_SUPPRESS BIT(23)
#define BR_DEFAULT_AGEING_TIME (300 * HZ)
......
......@@ -525,6 +525,7 @@ enum {
BRIDGE_VLANDB_ENTRY_MCAST_ROUTER,
BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS,
BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS,
BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS,
__BRIDGE_VLANDB_ENTRY_MAX,
};
#define BRIDGE_VLANDB_ENTRY_MAX (__BRIDGE_VLANDB_ENTRY_MAX - 1)
......
......@@ -569,6 +569,7 @@ enum {
IFLA_BRPORT_MAB,
IFLA_BRPORT_MCAST_N_GROUPS,
IFLA_BRPORT_MCAST_MAX_GROUPS,
IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
......
......@@ -30,7 +30,7 @@ void br_recalculate_neigh_suppress_enabled(struct net_bridge *br)
bool neigh_suppress = false;
list_for_each_entry(p, &br->port_list, list) {
if (p->flags & BR_NEIGH_SUPPRESS) {
if (p->flags & (BR_NEIGH_SUPPRESS | BR_NEIGH_VLAN_SUPPRESS)) {
neigh_suppress = true;
break;
}
......@@ -158,7 +158,7 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
return;
if (br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) {
if (p && (p->flags & BR_NEIGH_SUPPRESS))
if (br_is_neigh_suppress_enabled(p, vid))
return;
if (parp->ar_op != htons(ARPOP_RREQUEST) &&
parp->ar_op != htons(ARPOP_RREPLY) &&
......@@ -202,8 +202,8 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
bool replied = false;
if ((p && (p->flags & BR_PROXYARP)) ||
(f->dst && (f->dst->flags & (BR_PROXYARP_WIFI |
BR_NEIGH_SUPPRESS)))) {
(f->dst && (f->dst->flags & BR_PROXYARP_WIFI)) ||
br_is_neigh_suppress_enabled(f->dst, vid)) {
if (!vid)
br_arp_send(br, p, skb->dev, sip, tip,
sha, n->ha, sha, 0, 0);
......@@ -407,7 +407,7 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
BR_INPUT_SKB_CB(skb)->proxyarp_replied = 0;
if (p && (p->flags & BR_NEIGH_SUPPRESS))
if (br_is_neigh_suppress_enabled(p, vid))
return;
if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT &&
......@@ -461,7 +461,7 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
if (f) {
bool replied = false;
if (f->dst && (f->dst->flags & BR_NEIGH_SUPPRESS)) {
if (br_is_neigh_suppress_enabled(f->dst, vid)) {
if (vid != 0)
br_nd_send(br, p, skb, n,
skb->vlan_proto,
......@@ -483,3 +483,24 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
}
}
#endif
bool br_is_neigh_suppress_enabled(const struct net_bridge_port *p, u16 vid)
{
if (!p)
return false;
if (!vid)
return !!(p->flags & BR_NEIGH_SUPPRESS);
if (p->flags & BR_NEIGH_VLAN_SUPPRESS) {
struct net_bridge_vlan_group *vg = nbp_vlan_group_rcu(p);
struct net_bridge_vlan *v;
v = br_vlan_find(vg, vid);
if (!v)
return false;
return !!(v->priv_flags & BR_VLFLAG_NEIGH_SUPPRESS_ENABLED);
} else {
return !!(p->flags & BR_NEIGH_SUPPRESS);
}
}
......@@ -80,10 +80,10 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
dest = eth_hdr(skb)->h_dest;
if (is_broadcast_ether_addr(dest)) {
br_flood(br, skb, BR_PKT_BROADCAST, false, true);
br_flood(br, skb, BR_PKT_BROADCAST, false, true, vid);
} else if (is_multicast_ether_addr(dest)) {
if (unlikely(netpoll_tx_running(dev))) {
br_flood(br, skb, BR_PKT_MULTICAST, false, true);
br_flood(br, skb, BR_PKT_MULTICAST, false, true, vid);
goto out;
}
if (br_multicast_rcv(&brmctx, &pmctx_null, vlan, skb, vid)) {
......@@ -96,11 +96,11 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst))
br_multicast_flood(mdst, skb, brmctx, false, true);
else
br_flood(br, skb, BR_PKT_MULTICAST, false, true);
br_flood(br, skb, BR_PKT_MULTICAST, false, true, vid);
} else if ((dst = br_fdb_find_rcu(br, dest, vid)) != NULL) {
br_forward(dst->dst, skb, false, true);
} else {
br_flood(br, skb, BR_PKT_UNICAST, false, true);
br_flood(br, skb, BR_PKT_UNICAST, false, true, vid);
}
out:
rcu_read_unlock();
......
......@@ -197,7 +197,8 @@ static struct net_bridge_port *maybe_deliver(
/* called under rcu_read_lock */
void br_flood(struct net_bridge *br, struct sk_buff *skb,
enum br_pkt_type pkt_type, bool local_rcv, bool local_orig)
enum br_pkt_type pkt_type, bool local_rcv, bool local_orig,
u16 vid)
{
struct net_bridge_port *prev = NULL;
struct net_bridge_port *p;
......@@ -224,8 +225,9 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
/* Do not flood to ports that enable proxy ARP */
if (p->flags & BR_PROXYARP)
continue;
if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) &&
BR_INPUT_SKB_CB(skb)->proxyarp_replied)
if (BR_INPUT_SKB_CB(skb)->proxyarp_replied &&
((p->flags & BR_PROXYARP_WIFI) ||
br_is_neigh_suppress_enabled(p, vid)))
continue;
prev = maybe_deliver(prev, p, skb, local_orig);
......
......@@ -759,7 +759,7 @@ void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
if (mask & BR_AUTO_MASK)
nbp_update_port_count(br);
if (mask & BR_NEIGH_SUPPRESS)
if (mask & (BR_NEIGH_SUPPRESS | BR_NEIGH_VLAN_SUPPRESS))
br_recalculate_neigh_suppress_enabled(br);
}
......
......@@ -207,7 +207,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
br_forward(dst->dst, skb, local_rcv, false);
} else {
if (!mcast_hit)
br_flood(br, skb, pkt_type, local_rcv, false);
br_flood(br, skb, pkt_type, local_rcv, false, vid);
else
br_multicast_flood(mdst, skb, brmctx, local_rcv, false);
}
......
......@@ -189,6 +189,7 @@ static inline size_t br_port_info_size(void)
+ nla_total_size(1) /* IFLA_BRPORT_ISOLATED */
+ nla_total_size(1) /* IFLA_BRPORT_LOCKED */
+ nla_total_size(1) /* IFLA_BRPORT_MAB */
+ nla_total_size(1) /* IFLA_BRPORT_NEIGH_VLAN_SUPPRESS */
+ nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */
+ nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */
+ nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */
......@@ -278,7 +279,9 @@ static int br_port_fill_attrs(struct sk_buff *skb,
!!(p->flags & BR_MRP_LOST_IN_CONT)) ||
nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)) ||
nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED)) ||
nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB)))
nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB)) ||
nla_put_u8(skb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
!!(p->flags & BR_NEIGH_VLAN_SUPPRESS)))
return -EMSGSIZE;
timerval = br_timer_value(&p->message_age_timer);
......@@ -891,6 +894,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 },
[IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT },
[IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 },
[IFLA_BRPORT_NEIGH_VLAN_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1),
};
/* Change the state of the port and notify spanning tree */
......@@ -957,6 +961,8 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[],
br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED);
br_set_port_flag(p, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED);
br_set_port_flag(p, tb, IFLA_BRPORT_MAB, BR_PORT_MAB);
br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
BR_NEIGH_VLAN_SUPPRESS);
if ((p->flags & BR_PORT_MAB) &&
(!(p->flags & BR_PORT_LOCKED) || !(p->flags & BR_LEARNING))) {
......
......@@ -178,6 +178,7 @@ enum {
BR_VLFLAG_ADDED_BY_SWITCHDEV = BIT(1),
BR_VLFLAG_MCAST_ENABLED = BIT(2),
BR_VLFLAG_GLOBAL_MCAST_ENABLED = BIT(3),
BR_VLFLAG_NEIGH_SUPPRESS_ENABLED = BIT(4),
};
/**
......@@ -849,7 +850,8 @@ void br_forward(const struct net_bridge_port *to, struct sk_buff *skb,
bool local_rcv, bool local_orig);
int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
void br_flood(struct net_bridge *br, struct sk_buff *skb,
enum br_pkt_type pkt_type, bool local_rcv, bool local_orig);
enum br_pkt_type pkt_type, bool local_rcv, bool local_orig,
u16 vid);
/* return true if both source port and dest port are isolated */
static inline bool br_skb_isolated(const struct net_bridge_port *to,
......@@ -2218,4 +2220,5 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
u16 vid, struct net_bridge_port *p, struct nd_msg *msg);
struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *m);
bool br_is_neigh_suppress_enabled(const struct net_bridge_port *p, u16 vid);
#endif
......@@ -2134,6 +2134,7 @@ static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] =
[BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 },
[BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT },
[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 },
[BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1),
};
static int br_vlan_rtm_process_one(struct net_device *dev,
......
......@@ -52,7 +52,9 @@ bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v,
const struct net_bridge_port *p)
{
if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE, br_vlan_get_state(v)) ||
!__vlan_tun_put(skb, v))
!__vlan_tun_put(skb, v) ||
nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS,
!!(v->priv_flags & BR_VLFLAG_NEIGH_SUPPRESS_ENABLED)))
return false;
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
......@@ -80,6 +82,7 @@ size_t br_vlan_opts_nl_size(void)
+ nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS */
+ nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS */
#endif
+ nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS */
+ 0;
}
......@@ -239,6 +242,21 @@ static int br_vlan_process_one_opts(const struct net_bridge *br,
}
#endif
if (tb[BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS]) {
bool enabled = v->priv_flags & BR_VLFLAG_NEIGH_SUPPRESS_ENABLED;
bool val = nla_get_u8(tb[BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS]);
if (!p) {
NL_SET_ERR_MSG_MOD(extack, "Can't set neigh_suppress for non-port vlans");
return -EINVAL;
}
if (val != enabled) {
v->priv_flags ^= BR_VLFLAG_NEIGH_SUPPRESS_ENABLED;
*changed = true;
}
}
return 0;
}
......
......@@ -61,7 +61,7 @@
#include "dev.h"
#define RTNL_MAX_TYPE 50
#define RTNL_SLAVE_MAX_TYPE 42
#define RTNL_SLAVE_MAX_TYPE 43
struct rtnl_link {
rtnl_doit_func doit;
......
......@@ -83,6 +83,7 @@ TEST_GEN_FILES += nat6to4.o
TEST_GEN_FILES += ip_local_port_range
TEST_GEN_FILES += bind_wildcard
TEST_PROGS += test_vxlan_mdb.sh
TEST_PROGS += test_bridge_neigh_suppress.sh
TEST_FILES := settings
......
This diff is collapsed.
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment