From d47230a3480a5f6df98c5870ba26843850a600d5 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 2 Feb 2023 18:59:24 +0100 Subject: net: bridge: Add a tracepoint for MDB overflows The following patch will add two more maximum MDB allowances to the global one, mcast_hash_max, that exists today. In all these cases, attempts to add MDB entries above the configured maximums through netlink, fail noisily and obviously. Such visibility is missing when adding entries through the control plane traffic, by IGMP or MLD packets. To improve visibility in those cases, add a trace point that reports the violation, including the relevant netdevice (be it a slave or the bridge itself), and the MDB entry parameters: # perf record -e bridge:br_mdb_full & # [...] # perf script | cut -d: -f4- dev v2 af 2 src ::ffff:0.0.0.0 grp ::ffff:239.1.1.112/00:00:00:00:00:00 vid 0 dev v2 af 10 src :: grp ff0e::112/00:00:00:00:00:00 vid 0 dev v2 af 2 src ::ffff:0.0.0.0 grp ::ffff:239.1.1.112/00:00:00:00:00:00 vid 10 dev v2 af 10 src 2001:db8:1::1 grp ff0e::1/00:00:00:00:00:00 vid 10 dev v2 af 2 src ::ffff:192.0.2.1 grp ::ffff:239.1.1.1/00:00:00:00:00:00 vid 10 CC: Steven Rostedt CC: linux-trace-kernel@vger.kernel.org Signed-off-by: Petr Machata Reviewed-by: Steven Rostedt (Google) Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/trace/events/bridge.h | 58 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include') diff --git a/include/trace/events/bridge.h b/include/trace/events/bridge.h index 6b200059c2c5..a6b3a4e409f0 100644 --- a/include/trace/events/bridge.h +++ b/include/trace/events/bridge.h @@ -122,6 +122,64 @@ TRACE_EVENT(br_fdb_update, __entry->flags) ); +TRACE_EVENT(br_mdb_full, + + TP_PROTO(const struct net_device *dev, + const struct br_ip *group), + + TP_ARGS(dev, group), + + TP_STRUCT__entry( + __string(dev, dev->name) + __field(int, af) + __field(u16, vid) + __array(__u8, src, 16) + __array(__u8, grp, 16) + __array(__u8, grpmac, ETH_ALEN) /* For af == 0. */ + ), + + TP_fast_assign( + struct in6_addr *in6; + + __assign_str(dev, dev->name); + __entry->vid = group->vid; + + if (!group->proto) { + __entry->af = 0; + + memset(__entry->src, 0, sizeof(__entry->src)); + memset(__entry->grp, 0, sizeof(__entry->grp)); + memcpy(__entry->grpmac, group->dst.mac_addr, ETH_ALEN); + } else if (group->proto == htons(ETH_P_IP)) { + __entry->af = AF_INET; + + in6 = (struct in6_addr *)__entry->src; + ipv6_addr_set_v4mapped(group->src.ip4, in6); + + in6 = (struct in6_addr *)__entry->grp; + ipv6_addr_set_v4mapped(group->dst.ip4, in6); + + memset(__entry->grpmac, 0, ETH_ALEN); + +#if IS_ENABLED(CONFIG_IPV6) + } else { + __entry->af = AF_INET6; + + in6 = (struct in6_addr *)__entry->src; + *in6 = group->src.ip6; + + in6 = (struct in6_addr *)__entry->grp; + *in6 = group->dst.ip6; + + memset(__entry->grpmac, 0, ETH_ALEN); +#endif + } + ), + + TP_printk("dev %s af %u src %pI6c grp %pI6c/%pM vid %u", + __get_str(dev), __entry->af, __entry->src, __entry->grp, + __entry->grpmac, __entry->vid) +); #endif /* _TRACE_BRIDGE_H */ -- cgit v1.2.3 From a1aee20d5db29dc73331067b6a338eb650f0b5f1 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 2 Feb 2023 18:59:26 +0100 Subject: net: bridge: Add netlink knobs for number / maximum MDB entries The previous patch added accounting for number of MDB entries per port and per port-VLAN, and the logic to verify that these values stay within configured bounds. However it didn't provide means to actually configure those bounds or read the occupancy. This patch does that. Two new netlink attributes are added for the MDB occupancy: IFLA_BRPORT_MCAST_N_GROUPS for the per-port occupancy and BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS for the per-port-VLAN occupancy. And another two for the maximum number of MDB entries: IFLA_BRPORT_MCAST_MAX_GROUPS for the per-port maximum, and BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS for the per-port-VLAN one. Note that the two new IFLA_BRPORT_ attributes prompt bumping of RTNL_SLAVE_MAX_TYPE to size the slave attribute tables large enough. The new attributes are used like this: # ip link add name br up type bridge vlan_filtering 1 mcast_snooping 1 \ mcast_vlan_snooping 1 mcast_querier 1 # ip link set dev v1 master br # bridge vlan add dev v1 vid 2 # bridge vlan set dev v1 vid 1 mcast_max_groups 1 # bridge mdb add dev br port v1 grp 230.1.2.3 temp vid 1 # bridge mdb add dev br port v1 grp 230.1.2.4 temp vid 1 Error: bridge: Port-VLAN is already in 1 groups, and mcast_max_groups=1. # bridge link set dev v1 mcast_max_groups 1 # bridge mdb add dev br port v1 grp 230.1.2.3 temp vid 2 Error: bridge: Port is already in 1 groups, and mcast_max_groups=1. # bridge -d link show 5: v1@v2: mtu 1500 master br [...] [...] mcast_n_groups 1 mcast_max_groups 1 # bridge -d vlan show port vlan-id br 1 PVID Egress Untagged state forwarding mcast_router 1 v1 1 PVID Egress Untagged [...] mcast_n_groups 1 mcast_max_groups 1 2 [...] mcast_n_groups 0 mcast_max_groups 0 Signed-off-by: Petr Machata Acked-by: Nikolay Aleksandrov Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 2 ++ include/uapi/linux/if_link.h | 2 ++ net/bridge/br_multicast.c | 15 +++++++++++++++ net/bridge/br_netlink.c | 17 ++++++++++++++++- net/bridge/br_private.h | 6 +++++- net/bridge/br_vlan.c | 11 +++++++---- net/bridge/br_vlan_options.c | 27 ++++++++++++++++++++++++++- net/core/rtnetlink.c | 2 +- 8 files changed, 74 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index d9de241d90f9..d60c456710b3 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -523,6 +523,8 @@ enum { BRIDGE_VLANDB_ENTRY_TUNNEL_INFO, BRIDGE_VLANDB_ENTRY_STATS, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, + BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, + BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, __BRIDGE_VLANDB_ENTRY_MAX, }; #define BRIDGE_VLANDB_ENTRY_MAX (__BRIDGE_VLANDB_ENTRY_MAX - 1) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 02b87e4c65be..57ceb788250f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -567,6 +567,8 @@ enum { IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, IFLA_BRPORT_LOCKED, IFLA_BRPORT_MAB, + IFLA_BRPORT_MCAST_N_GROUPS, + IFLA_BRPORT_MCAST_MAX_GROUPS, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index b6aa0bad5817..96d1fc78dd39 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -772,6 +772,21 @@ static void br_multicast_port_ngroups_dec(struct net_bridge_port *port, u16 vid) br_multicast_port_ngroups_dec_one(&port->multicast_ctx); } +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_n_entries); +} + +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max) +{ + WRITE_ONCE(pmctx->mdb_max_entries, max); +} + +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_max_entries); +} + static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc) { struct net_bridge_port_group *pg; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a6133d469885..9173e52b89e2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -202,6 +202,8 @@ static inline size_t br_port_info_size(void) + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ @@ -298,7 +300,11 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, - p->multicast_eht_hosts_cnt)) + p->multicast_eht_hosts_cnt) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS, + br_multicast_ngroups_get(&p->multicast_ctx)) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&p->multicast_ctx))) return -EMSGSIZE; #endif @@ -883,6 +889,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [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 }, }; /* Change the state of the port and notify spanning tree */ @@ -1017,6 +1025,13 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], if (err) return err; } + + if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) { + u32 max_groups; + + max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups); + } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 49f411a0a1f1..cef5f6ea850c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -978,6 +978,9 @@ void br_multicast_uninit_stats(struct net_bridge *br); void br_multicast_get_stats(const struct net_bridge *br, const struct net_bridge_port *p, struct br_mcast_stats *dest); +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx); +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max); +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx); void br_mdb_init(void); void br_mdb_uninit(void); void br_multicast_host_join(const struct net_bridge_mcast *brmctx, @@ -1761,7 +1764,8 @@ static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid) #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end); -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v); +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, + const struct net_bridge_port *p); size_t br_vlan_opts_nl_size(void); int br_vlan_process_options(const struct net_bridge *br, const struct net_bridge_port *p, diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index bc75fa1e4666..8a3dbc09ba38 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1816,6 +1816,7 @@ out_err: /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, + const struct net_bridge_port *p, u16 flags, bool dump_stats) { @@ -1842,7 +1843,7 @@ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, goto out_err; if (v_opts) { - if (!br_vlan_opts_fill(skb, v_opts)) + if (!br_vlan_opts_fill(skb, v_opts, p)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) @@ -1925,7 +1926,7 @@ void br_vlan_notify(const struct net_bridge *br, goto out_kfree; } - if (!br_vlan_fill_vids(skb, vid, vid_range, v, flags, false)) + if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false)) goto out_err; nlmsg_end(skb, nlh); @@ -2030,7 +2031,7 @@ static int br_vlan_dump_dev(const struct net_device *dev, if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - vlan_flags, dump_stats)) { + p, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } @@ -2056,7 +2057,7 @@ update_end: else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - br_vlan_flags(range_start, pvid), + p, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } @@ -2131,6 +2132,8 @@ static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [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 }, }; static int br_vlan_rtm_process_one(struct net_device *dev, diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index a2724d03278c..e378c2f3a9e2 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -48,7 +48,8 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, curr_mc_rtr == range_mc_rtr; } -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) +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)) @@ -58,6 +59,12 @@ bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, br_vlan_multicast_router(v))) return false; + if (p && !br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx) && + (nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, + br_multicast_ngroups_get(&v->port_mcast_ctx)) || + nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&v->port_mcast_ctx)))) + return false; #endif return true; @@ -70,6 +77,8 @@ size_t br_vlan_opts_nl_size(void) + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_TINFO_ID */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_ENTRY_MCAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS */ #endif + 0; } @@ -212,6 +221,22 @@ static int br_vlan_process_one_opts(const struct net_bridge *br, return err; *changed = true; } + if (tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]) { + u32 val; + + if (!p) { + NL_SET_ERR_MSG_MOD(extack, "Can't set mcast_max_groups for non-port vlans"); + return -EINVAL; + } + if (br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx)) { + NL_SET_ERR_MSG_MOD(extack, "Multicast snooping disabled on this VLAN"); + return -EINVAL; + } + + val = nla_get_u32(tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&v->port_mcast_ctx, val); + *changed = true; + } #endif return 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b9f584955b77..5d8eb57867a9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -58,7 +58,7 @@ #include "dev.h" #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 40 +#define RTNL_SLAVE_MAX_TYPE 42 struct rtnl_link { rtnl_doit_func doit; -- cgit v1.2.3