net/mlx5: Bridge, support LAG

Allow adding bond net devices to mlx5 bridge with following changes:

- Modify bridge representor code to obtain uplink represetor that belongs
to eswitch that is registered for notification. Require representor to be
in shared FDB mode. If representor is the lag master, then consider its
port as local, otherwise treat it as peer.

- Use devcom to match on paired eswitch metadata in peer FDB entries. This
is necessary for shared FDB LAG to function since packets are always
received on active eswitch instance as opposed to parent eswitch of port.

- Support for deleting peer flows when receiving
SWITCHDEV_FDB_DEL_TO_BRIDGE notification was implemented in one of previous
patches in series. Now also implement support for handling
SWITCHDEV_FDB_ADD_TO_BRIDGE which can be generated on peer by bridge update
workqueue task in LAG configuration. Refresh the flow 'lastuse' timestamp
to current jiffies when receiving such notification on eswitch that manages
the local FDB entry. This allows peer entries to prevent ageing of the FDB.

Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

2 files changed, 72 insertions, 10 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index 20d44b0ae337..7e221038df8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -5,6 +5,7 @@
 #include <linux/notifier.h>
 #include <net/netevent.h>
 #include <net/switchdev.h>
+#include "lib/devcom.h"
 #include "bridge.h"
 #include "eswitch.h"
 #include "bridge_priv.h"
@@ -408,9 +409,10 @@ mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge)
 }
 
 static struct mlx5_flow_handle *
-mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
-				    struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
-				    struct mlx5_esw_bridge *bridge)
+mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char *addr,
+					     struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+					     struct mlx5_esw_bridge *bridge,
+					     struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads;
 	struct mlx5_flow_act flow_act = {
@@ -438,7 +440,7 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
 	MLX5_SET(fte_match_param, rule_spec->match_criteria,
 		 misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask());
 	MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0,
-		 mlx5_eswitch_get_vport_metadata_for_match(br_offloads->esw, vport_num));
+		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num));
 
 	if (vlan && vlan->pkt_reformat_push) {
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
@@ -467,6 +469,35 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
 }
 
 static struct mlx5_flow_handle *
+mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
+				    struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+				    struct mlx5_esw_bridge *bridge)
+{
+	return mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id,
+							    bridge, bridge->br_offloads->esw);
+}
+
+static struct mlx5_flow_handle *
+mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, const unsigned char *addr,
+					 struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+					 struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_devcom *devcom = bridge->br_offloads->esw->dev->priv.devcom;
+	static struct mlx5_flow_handle *handle;
+	struct mlx5_eswitch *peer_esw;
+
+	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (!peer_esw)
+		return ERR_PTR(-ENODEV);
+
+	handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id,
+							      bridge, peer_esw);
+
+	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	return handle;
+}
+
+static struct mlx5_flow_handle *
 mlx5_esw_bridge_ingress_filter_flow_create(u16 vport_num, const unsigned char *addr,
 					   struct mlx5_esw_bridge *bridge)
 {
@@ -679,12 +710,10 @@ static void mlx5_esw_bridge_port_erase(struct mlx5_esw_bridge_port *port,
 	xa_erase(&br_offloads->ports, mlx5_esw_bridge_port_key(port));
 }
 
-static void mlx5_esw_bridge_fdb_entry_refresh(unsigned long lastuse,
-					      struct mlx5_esw_bridge_fdb_entry *entry)
+static void mlx5_esw_bridge_fdb_entry_refresh(struct mlx5_esw_bridge_fdb_entry *entry)
 {
 	trace_mlx5_esw_bridge_fdb_entry_refresh(entry);
 
-	entry->lastuse = lastuse;
 	mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
 					   entry->key.vid,
 					   SWITCHDEV_FDB_ADD_TO_BRIDGE);
@@ -959,8 +988,11 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_ow
 	}
 	entry->ingress_counter = counter;
 
-	handle = mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, mlx5_fc_id(counter),
-						     bridge);
+	handle = peer ?
+		mlx5_esw_bridge_ingress_flow_peer_create(vport_num, addr, vlan,
+							 mlx5_fc_id(counter), bridge) :
+		mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan,
+						    mlx5_fc_id(counter), bridge);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
 		esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d)\n",
@@ -1228,6 +1260,33 @@ void mlx5_esw_bridge_port_vlan_del(u16 vport_num, u16 esw_owner_vhca_id, u16 vid
 	mlx5_esw_bridge_vlan_cleanup(port, vlan, port->bridge);
 }
 
+void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				     struct mlx5_esw_bridge_offloads *br_offloads,
+				     struct switchdev_notifier_fdb_info *fdb_info)
+{
+	struct mlx5_esw_bridge_fdb_entry *entry;
+	struct mlx5_esw_bridge_fdb_key key;
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge *bridge;
+
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port || port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER)
+		return;
+
+	bridge = port->bridge;
+	ether_addr_copy(key.addr, fdb_info->addr);
+	key.vid = fdb_info->vid;
+	entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params);
+	if (!entry) {
+		esw_debug(br_offloads->esw->dev,
+			  "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n",
+			  key.addr, key.vid, vport_num);
+		return;
+	}
+
+	entry->lastuse = jiffies;
+}
+
 void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
 				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info)
@@ -1300,7 +1359,7 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
 				continue;
 
 			if (time_after(lastuse, entry->lastuse)) {
-				mlx5_esw_bridge_fdb_entry_refresh(lastuse, entry);
+				mlx5_esw_bridge_fdb_entry_refresh(entry);
 			} else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER) &&
 				   time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) {
 				mlx5_esw_bridge_fdb_del_notify(entry);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
index a4f04f3f5b11..efc39975226e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
@@ -46,6 +46,9 @@ int mlx5_esw_bridge_vport_peer_link(int ifindex, u16 vport_num, u16 esw_owner_vh
 int mlx5_esw_bridge_vport_peer_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
 				      struct mlx5_esw_bridge_offloads *br_offloads,
 				      struct netlink_ext_ack *extack);
+void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				     struct mlx5_esw_bridge_offloads *br_offloads,
+				     struct switchdev_notifier_fdb_info *fdb_info);
 void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
 				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info);