[PATCH net-next mlxsw v2 06/16] net: bridge: Add a tracepoint for MDB overflows

[PATCH net-next mlxsw v2 06/16] net: bridge: Add a tracepoint for MDB overflows

[Petr Machata]

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 <rostedt@goodmis.org>
CC: linux-trace-kernel@vger.kernel.org
Signed-off-by: Petr Machata <petrm@nvidia.com>
---

Notes:
    v2:
    - Report IPv4 as an IPv6-mapped address through the IPv6 buffer
      as well, to save ring buffer space.

 include/trace/events/bridge.h | 58 +++++++++++++++++++++++++++++++++++
 net/core/net-traces.c         |  1 +
 2 files changed, 59 insertions(+)

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 */
 
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index c40cd8dd75c7..c6820ad2183f 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -41,6 +41,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_add);
 EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_external_learn_add);
 EXPORT_TRACEPOINT_SYMBOL_GPL(fdb_delete);
 EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update);
+EXPORT_TRACEPOINT_SYMBOL_GPL(br_mdb_full);
 #endif
 
 #if IS_ENABLED(CONFIG_PAGE_POOL)
-- 
2.39.0

Re: [PATCH net-next mlxsw v2 06/16] net: bridge: Add a tracepoint for MDB overflows

[Steven Rostedt]

On Wed, 1 Feb 2023 18:28:39 +0100
Petr Machata <petrm@nvidia.com> wrote:

> 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 <rostedt@goodmis.org>
> CC: linux-trace-kernel@vger.kernel.org
> Signed-off-by: Petr Machata <petrm@nvidia.com>
> ---
> 
> Notes:
>     v2:
>     - Report IPv4 as an IPv6-mapped address through the IPv6 buffer
>       as well, to save ring buffer space.
> 
>  include/trace/events/bridge.h | 58 +++++++++++++++++++++++++++++++++++
>  net/core/net-traces.c         |  1 +
>  2 files changed, 59 insertions(+)
> 

From the tracing point of view:

Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>

-- Steve