[PATCH net-next 07/13] net/mlx5e: TC, anchor peer-flow reverse index on the duplicated flow

[Tariq Toukan <tariqt@nvidia.com>]

From: Shay Drory <shayd@nvidia.com>

A TC eswitch flow offloaded to a shared FDB is duplicated onto every
peer eswitch. Besides the forward list of duplicates on the origin flow
(mlx5e_tc_flow.peer_flows), the eswitch keeps a reverse index,
esw->offloads.peer_flows[], an array of per-peer list heads keyed by the
peer's LAG sequence number, used to tear down a peer's duplicates when
it is removed.

That reverse index was anchored on the origin: since one origin can have
a duplicate on every peer, the origin carried per-peer storage sized to
the max port count - a peer[MLX5_MAX_PORTS] array of list nodes plus a
peer_used bitmap - and each duplicate stored its peer_index.

Anchor it on the duplicate instead, which belongs to a single peer. Give
each flow one list node, mlx5e_tc_flow.peer, and place the duplicate -
not the origin - on its peer's list through it; add a peer_orig back-ref
so del can reach the origin from the duplicate. One node then replaces
the origin's per-peer array, and del unlinks the duplicate directly, so
peer[], peer_used and peer_index are dropped.

The per-peer list heads remain the fixed esw->offloads.peer_flows[]
array keyed by the LAG sequence number - that array is replaced in the
next patch.  No functional change.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Akiva Goldberger <agoldberger@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en/tc_priv.h  | 14 ++---
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 59 ++++++++-----------
 2 files changed, 29 insertions(+), 44 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
index 7bfe7cdc5770..1ceebab4ce08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -97,18 +97,14 @@ struct mlx5e_tc_flow {
 	struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */
 	struct list_head hairpin; /* flows sharing the same hairpin */
-	struct list_head peer[MLX5_MAX_PORTS];    /* flows with peer flow */
-	DECLARE_BITMAP(peer_used, MLX5_MAX_PORTS); /* tracks populated peer
-						    * slots
-						    */
+	struct list_head peer; /* dup: node in origin esw's peer_flows */
 	struct list_head unready; /* flows not ready to be offloaded (e.g
 				   * due to missing route)
 				   */
-	struct list_head peer_flows; /* flows on peer */
-	int peer_index; /* peer-flow index pinned at add time, used at del
-			 * time so removal is independent of LAG state
-			 * changes between add and del.
-			 */
+
+	/* origin: its dups; dup: node on that list */
+	struct list_head peer_flows;
+	struct mlx5e_tc_flow *peer_orig; /* dup: back-ref to origin flow */
 	struct net_device *orig_dev; /* netdev adding flow first */
 	int tmp_entry_index;
 	struct list_head tmp_list; /* temporary flow list used by neigh update */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b290beb4369a..fae4f8625da4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2116,43 +2116,35 @@ void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list)
 		mlx5e_flow_put(priv, flow);
 }
 
-static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow,
-				       int peer_index)
+static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *peer_flow)
 {
-	struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch;
-	struct mlx5e_tc_flow *peer_flow;
-	struct mlx5e_tc_flow *tmp;
-
-	if (!flow_flag_test(flow, ESWITCH) ||
-	    !flow_flag_test(flow, DUP))
-		return;
+	struct mlx5e_tc_flow *flow = peer_flow->peer_orig;
+	struct mlx5_eswitch *esw;
 
+	esw = flow->priv->mdev->priv.eswitch;
 	mutex_lock(&esw->offloads.peer_mutex);
-	list_del(&flow->peer[peer_index]);
-	clear_bit(peer_index, flow->peer_used);
+	list_del(&peer_flow->peer);
 	mutex_unlock(&esw->offloads.peer_mutex);
 
-	list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows) {
-		if (peer_index != peer_flow->peer_index)
-			continue;
-
-		list_del(&peer_flow->peer_flows);
-		if (refcount_dec_and_test(&peer_flow->refcnt)) {
-			mlx5e_tc_del_fdb_flow(peer_flow->priv, peer_flow);
-			kfree(peer_flow);
-		}
-	}
-
+	list_del(&peer_flow->peer_flows);
 	if (list_empty(&flow->peer_flows))
 		flow_flag_clear(flow, DUP);
+
+	if (refcount_dec_and_test(&peer_flow->refcnt)) {
+		mlx5e_tc_del_fdb_flow(peer_flow->priv, peer_flow);
+		kfree(peer_flow);
+	}
 }
 
 static void mlx5e_tc_del_fdb_peers_flow(struct mlx5e_tc_flow *flow)
 {
-	int i;
+	struct mlx5e_tc_flow *peer_flow, *tmp;
 
-	for_each_set_bit(i, flow->peer_used, MLX5_MAX_PORTS)
-		mlx5e_tc_del_fdb_peer_flow(flow, i);
+	if (!flow_flag_test(flow, ESWITCH) || !flow_flag_test(flow, DUP))
+		return;
+
+	list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows)
+		mlx5e_tc_del_fdb_peer_flow(peer_flow);
 }
 
 static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
@@ -4639,12 +4631,11 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f,
 		goto out;
 	}
 
-	peer_flow->peer_index = i;
+	peer_flow->peer_orig = flow;
 	list_add_tail(&peer_flow->peer_flows, &flow->peer_flows);
 	flow_flag_set(flow, DUP);
 	mutex_lock(&esw->offloads.peer_mutex);
-	list_add_tail(&flow->peer[i], &esw->offloads.peer_flows[i]);
-	set_bit(i, flow->peer_used);
+	list_add_tail(&peer_flow->peer, &esw->offloads.peer_flows[i]);
 	mutex_unlock(&esw->offloads.peer_mutex);
 
 out:
@@ -5539,21 +5530,19 @@ int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags)
 
 void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw)
 {
-	struct mlx5_devcom_comp_dev *devcom;
-	struct mlx5_devcom_comp_dev *pos;
-	struct mlx5e_tc_flow *flow, *tmp;
+	struct mlx5_devcom_comp_dev *devcom = esw->devcom, *pos;
+	struct mlx5e_tc_flow *peer_flow, *tmp_peer_flow;
 	struct mlx5_eswitch *peer_esw;
 	int i;
 
-	devcom = esw->devcom;
-
 	mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) {
 		i = mlx5_lag_get_dev_seq(peer_esw->dev);
 		if (i < 0)
 			continue;
 
-		list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows[i], peer[i])
-			mlx5e_tc_del_fdb_peers_flow(flow);
+		list_for_each_entry_safe(peer_flow, tmp_peer_flow,
+					 &esw->offloads.peer_flows[i], peer)
+			mlx5e_tc_del_fdb_peer_flow(peer_flow);
 	}
 }
 
-- 
2.44.0