[PATCH AUTOSEL 6.5 25/52] net/mlx5: Bridge, fix peer entry ageing in LAG mode

From: Sasha Levin
Date: Sun Oct 29 2023 - 19:33:25 EST


From: Vlad Buslov <vladbu@xxxxxxxxxx>

[ Upstream commit 7a3ce8074878a68a75ceacec93d9ae05906eec86 ]

With current implementation in single FDB LAG mode all packets are
processed by eswitch 0 rules. As such, 'peer' FDB entries receive the
packets for rules of other eswitches and are responsible for updating the
main entry by sending SWITCHDEV_FDB_ADD_TO_BRIDGE notification from their
background update wq task. However, this introduces a race condition when
non-zero eswitch instance decides to delete a FDB entry, sends
SWITCHDEV_FDB_DEL_TO_BRIDGE notification, but another eswitch's update task
refreshes the same entry concurrently while its async delete work is still
pending on the workque. In such case another SWITCHDEV_FDB_ADD_TO_BRIDGE
event may be generated and entry will remain stuck in FDB marked as
'offloaded' since no more SWITCHDEV_FDB_DEL_TO_BRIDGE notifications are
sent for deleting the peer entries.

Fix the issue by synchronously marking deleted entries with
MLX5_ESW_BRIDGE_FLAG_DELETED flag and skipping them in background update
job.

Signed-off-by: Vlad Buslov <vladbu@xxxxxxxxxx>
Reviewed-by: Jianbo Liu <jianbol@xxxxxxxxxx>
Signed-off-by: Saeed Mahameed <saeedm@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
.../mellanox/mlx5/core/en/rep/bridge.c | 11 ++++++++
.../ethernet/mellanox/mlx5/core/esw/bridge.c | 25 ++++++++++++++++++-
.../ethernet/mellanox/mlx5/core/esw/bridge.h | 3 +++
.../mellanox/mlx5/core/esw/bridge_priv.h | 1 +
4 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
index 5608002465734..285c13edc09f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -463,6 +463,17 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
/* only handle the event on peers */
if (mlx5_esw_bridge_is_local(dev, rep, esw))
break;
+
+ fdb_info = container_of(info,
+ struct switchdev_notifier_fdb_info,
+ info);
+ /* Mark for deletion to prevent the update wq task from
+ * spuriously refreshing the entry which would mark it again as
+ * offloaded in SW bridge. After this fallthrough to regular
+ * async delete code.
+ */
+ mlx5_esw_bridge_fdb_mark_deleted(dev, vport_num, esw_owner_vhca_id, br_offloads,
+ fdb_info);
fallthrough;
case SWITCHDEV_FDB_ADD_TO_DEVICE:
case SWITCHDEV_FDB_DEL_TO_DEVICE:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index f4fe1daa4afd5..de1ed59239da8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -1748,6 +1748,28 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16
entry->lastuse = jiffies;
}

+void mlx5_esw_bridge_fdb_mark_deleted(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 *bridge;
+
+ bridge = mlx5_esw_bridge_from_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+ if (!bridge)
+ return;
+
+ entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid);
+ if (!entry) {
+ esw_debug(br_offloads->esw->dev,
+ "FDB mark deleted entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n",
+ fdb_info->addr, fdb_info->vid, vport_num);
+ return;
+ }
+
+ entry->flags |= MLX5_ESW_BRIDGE_FLAG_DELETED;
+}
+
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)
@@ -1810,7 +1832,8 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
unsigned long lastuse =
(unsigned long)mlx5_fc_query_lastuse(entry->ingress_counter);

- if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)
+ if (entry->flags & (MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER |
+ MLX5_ESW_BRIDGE_FLAG_DELETED))
continue;

if (time_after(lastuse, entry->lastuse))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
index c2c7c70d99eb7..d6f5391619930 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
@@ -62,6 +62,9 @@ int mlx5_esw_bridge_vport_peer_unlink(struct net_device *br_netdev, u16 vport_nu
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_mark_deleted(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);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
index 4911cc32161b4..7c251af566c6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
@@ -133,6 +133,7 @@ struct mlx5_esw_bridge_mdb_key {
enum {
MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER = BIT(0),
MLX5_ESW_BRIDGE_FLAG_PEER = BIT(1),
+ MLX5_ESW_BRIDGE_FLAG_DELETED = BIT(2),
};

enum {
--
2.42.0