net/mlx5e: Update neighbour 'used' state using HW flow rules counters

When IP tunnel encapsulation rules are offloaded, the kernel can't see
the traffic of the offloaded flow. The neighbour for the IP tunnel
destination of the offloaded flow can mistakenly become STALE and
deleted by the kernel since its 'used' value wasn't changed.

To make sure that a neighbour which is used by the HW won't become
STALE, we proactively update the neighbour 'used' value every
DELAY_PROBE_TIME period, when packets were matched and counted by the HW
for one of the tunnel encap flows related to this neighbour.

The periodic task that updates the used neighbours is scheduled when a
tunnel encap rule is successfully offloaded into HW and keeps re-scheduling
itself as long as the representor's neighbours list isn't empty.

Add, remove, lookup and status change operations done over the
representor's neighbours list or the neighbour hash entry encaps list
are all serialized by RTNL lock.

Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

1 files changed, 58 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 624dbfe31a0e..11c27e4fadf6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -44,6 +44,7 @@
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_pedit.h>
 #include <net/vxlan.h>
+#include <net/arp.h>
 #include "en.h"
 #include "en_rep.h"
 #include "en_tc.h"
@@ -278,6 +279,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 		return;
 	}
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(priv);
 
 	list_for_each_entry(flow, &e->flows, encap) {
 		flow->esw_attr->encap_id = e->encap_id;
@@ -315,6 +317,58 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 	}
 }
 
+void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
+{
+	struct mlx5e_neigh *m_neigh = &nhe->m_neigh;
+	u64 bytes, packets, lastuse = 0;
+	struct mlx5e_tc_flow *flow;
+	struct mlx5e_encap_entry *e;
+	struct mlx5_fc *counter;
+	struct neigh_table *tbl;
+	bool neigh_used = false;
+	struct neighbour *n;
+
+	if (m_neigh->family == AF_INET)
+		tbl = &arp_tbl;
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (m_neigh->family == AF_INET6)
+		tbl = ipv6_stub->nd_tbl;
+#endif
+	else
+		return;
+
+	list_for_each_entry(e, &nhe->encap_list, encap_list) {
+		if (!(e->flags & MLX5_ENCAP_ENTRY_VALID))
+			continue;
+		list_for_each_entry(flow, &e->flows, encap) {
+			if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
+				counter = mlx5_flow_rule_counter(flow->rule);
+				mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+				if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) {
+					neigh_used = true;
+					break;
+				}
+			}
+		}
+	}
+
+	if (neigh_used) {
+		nhe->reported_lastuse = jiffies;
+
+		/* find the relevant neigh according to the cached device and
+		 * dst ip pair
+		 */
+		n = neigh_lookup(tbl, &m_neigh->dst_ip, m_neigh->dev);
+		if (!n) {
+			WARN(1, "The neighbour already freed\n");
+			return;
+		}
+
+		neigh_event_send(n, NULL);
+		neigh_release(n);
+	}
+}
+
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 			       struct mlx5e_tc_flow *flow)
 {
@@ -1315,6 +1369,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	 * entry in the neigh hash table when a user deletes a rule
 	 */
 	e->m_neigh.dev = n->dev;
+	e->m_neigh.family = n->ops->family;
 	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
 	e->out_dev = out_dev;
 
@@ -1359,6 +1414,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 		goto destroy_neigh_entry;
 
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
 	neigh_release(n);
 	return err;
 
@@ -1418,6 +1474,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	 * entry in the neigh hash table when a user deletes a rule
 	 */
 	e->m_neigh.dev = n->dev;
+	e->m_neigh.family = n->ops->family;
 	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
 	e->out_dev = out_dev;
 
@@ -1463,6 +1520,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 		goto destroy_neigh_entry;
 
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
 	neigh_release(n);
 	return err;