linux-kernel - [PATCH V2 net 4/8] net/mlx5: Destroy vport QoS element when no configuration remains

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250820133209.389065-5-mbloch@nvidia.com>
Date: Wed, 20 Aug 2025 16:32:05 +0300
From: Mark Bloch <mbloch@...dia.com>
To: Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
	Paolo Abeni <pabeni@...hat.com>, Andrew Lunn <andrew+netdev@...n.ch>, "David
 S. Miller" <davem@...emloft.net>, <przemyslaw.kitszel@...el.com>
CC: Tariq Toukan <tariqt@...dia.com>, Leon Romanovsky <leon@...nel.org>,
	"Saeed Mahameed" <saeedm@...dia.com>, <netdev@...r.kernel.org>,
	<linux-rdma@...r.kernel.org>, <linux-kernel@...r.kernel.org>, Gal Pressman
	<gal@...dia.com>, Carolina Jubran <cjubran@...dia.com>, Cosmin Ratiu
	<cratiu@...dia.com>, Mark Bloch <mbloch@...dia.com>, Mohamad Haj Yahia
	<mohamad@...lanox.com>, Saeed Mahameed <saeedm@...lanox.com>
Subject: [PATCH V2 net 4/8] net/mlx5: Destroy vport QoS element when no configuration remains

From: Carolina Jubran <cjubran@...dia.com>

If a VF has been configured and the user later clears all QoS settings,
the vport element remains in the firmware QoS tree. This leads to
inconsistent behavior compared to VFs that were never configured, since
the FW assumes that unconfigured VFs are outside the QoS hierarchy.
As a result, the bandwidth share across VFs may differ, even though
none of them appear to have any configuration.

Align the driver behavior with the FW expectation by destroying the
vport QoS element when all configurations are removed.

Fixes: c9497c98901c ("net/mlx5: Add support for setting VF min rate")
Fixes: cf7e73770d1b ("net/mlx5: Manage TC arbiter nodes and implement full support for tc-bw")
Signed-off-by: Carolina Jubran <cjubran@...dia.com>
Reviewed-by: Cosmin Ratiu <cratiu@...dia.com>
Signed-off-by: Mark Bloch <mbloch@...dia.com>
---
 .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 57 ++++++++++++++++---
 1 file changed, 49 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 4ed5968f1638..452a948a3e6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -1127,6 +1127,19 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	return err;
 }
 
+static void mlx5_esw_qos_vport_disable_locked(struct mlx5_vport *vport)
+{
+	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
+
+	esw_assert_qos_lock_held(esw);
+	if (!vport->qos.sched_node)
+		return;
+
+	esw_qos_vport_disable(vport, NULL);
+	mlx5_esw_qos_vport_qos_free(vport);
+	esw_qos_put(esw);
+}
+
 void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport)
 {
 	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
@@ -1140,9 +1153,7 @@ void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport)
 	parent = vport->qos.sched_node->parent;
 	WARN(parent, "Disabling QoS on port before detaching it from node");
 
-	esw_qos_vport_disable(vport, NULL);
-	mlx5_esw_qos_vport_qos_free(vport);
-	esw_qos_put(esw);
+	mlx5_esw_qos_vport_disable_locked(vport);
 unlock:
 	esw_qos_unlock(esw);
 }
@@ -1642,6 +1653,21 @@ static bool esw_qos_tc_bw_disabled(u32 *tc_bw)
 	return true;
 }
 
+static void esw_vport_qos_prune_empty(struct mlx5_vport *vport)
+{
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+
+	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	if (!vport_node)
+		return;
+
+	if (vport_node->parent || vport_node->max_rate ||
+	    vport_node->min_rate || !esw_qos_tc_bw_disabled(vport_node->tc_bw))
+		return;
+
+	mlx5_esw_qos_vport_disable_locked(vport);
+}
+
 int mlx5_esw_qos_init(struct mlx5_eswitch *esw)
 {
 	if (esw->qos.domain)
@@ -1675,6 +1701,10 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void
 
 	esw_qos_lock(esw);
 	err = mlx5_esw_qos_set_vport_min_rate(vport, tx_share, extack);
+	if (err)
+		goto out;
+	esw_vport_qos_prune_empty(vport);
+out:
 	esw_qos_unlock(esw);
 	return err;
 }
@@ -1696,6 +1726,10 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *
 
 	esw_qos_lock(esw);
 	err = mlx5_esw_qos_set_vport_max_rate(vport, tx_max, extack);
+	if (err)
+		goto out;
+	esw_vport_qos_prune_empty(vport);
+out:
 	esw_qos_unlock(esw);
 	return err;
 }
@@ -1733,6 +1767,7 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf,
 		if (vport_node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 			err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_VPORT,
 						   vport_node->parent, extack);
+		esw_vport_qos_prune_empty(vport);
 		goto unlock;
 	}
 
@@ -1893,14 +1928,20 @@ int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
 					  void *priv, void *parent_priv,
 					  struct netlink_ext_ack *extack)
 {
-	struct mlx5_esw_sched_node *node;
+	struct mlx5_esw_sched_node *node = parent ? parent_priv : NULL;
 	struct mlx5_vport *vport = priv;
+	int err;
 
-	if (!parent)
-		return mlx5_esw_qos_vport_update_parent(vport, NULL, extack);
+	err = mlx5_esw_qos_vport_update_parent(vport, node, extack);
+	if (!err) {
+		struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
+
+		esw_qos_lock(esw);
+		esw_vport_qos_prune_empty(vport);
+		esw_qos_unlock(esw);
+	}
 
-	node = parent_priv;
-	return mlx5_esw_qos_vport_update_parent(vport, node, extack);
+	return err;
 }
 
 static bool esw_qos_is_node_empty(struct mlx5_esw_sched_node *node)
-- 
2.34.1