Merge branch 'mlx5-misx-fixes-2025-08-20'

Mark Bloch says: ==================== mlx5 misx fixes 2025-08-20 This patchset provides misc bug fixes from the team to the mlx5 core and Eth drivers. v1: https://lore.kernel.org/1755095476-414026-1-git-send-email-tariqt@nvidia.com ==================== Link: https://patch.msgid.link/20250820133209.389065-1-mbloch@nvidia.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-08-21 07:58:35 -07:00
parent 7ef353879f 8b0587a885
commit 1b78236a05
8 changed files with 140 additions and 105 deletions
@@ -26,7 +26,6 @@ struct mlx5e_dcbx {
 	u8                         cap;

 	/* Buffer configuration */
-	bool                       manual_buffer;
 	u32                        cable_len;
 	u32                        xoff;
 	u16                        port_buff_cell_sz;
@@ -272,8 +272,8 @@ static int port_update_shared_buffer(struct mlx5_core_dev *mdev,
 	/* Total shared buffer size is split in a ratio of 3:1 between
 	 * lossy and lossless pools respectively.
 	 */
-	lossy_epool_size = (shared_buffer_size / 4) * 3;
 	lossless_ipool_size = shared_buffer_size / 4;
+	lossy_epool_size    = shared_buffer_size - lossless_ipool_size;

 	mlx5e_port_set_sbpr(mdev, 0, MLX5_EGRESS_DIR, MLX5_LOSSY_POOL, 0,
 			    lossy_epool_size);
@@ -288,14 +288,12 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int sz = MLX5_ST_SZ_BYTES(pbmc_reg);
-	u32 new_headroom_size = 0;
-	u32 current_headroom_size;
+	u32 current_headroom_cells = 0;
+	u32 new_headroom_cells = 0;
 	void *in;
 	int err;
 	int i;

-	current_headroom_size = port_buffer->headroom_size;
-
 	in = kzalloc(sz, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -306,12 +304,14 @@ static int port_set_buffer(struct mlx5e_priv *priv,

 	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]);
+		current_headroom_cells += MLX5_GET(bufferx_reg, buffer, size);
+
 		u64 size = port_buffer->buffer[i].size;
 		u64 xoff = port_buffer->buffer[i].xoff;
 		u64 xon = port_buffer->buffer[i].xon;

-		new_headroom_size += size;
 		do_div(size, port_buff_cell_sz);
+		new_headroom_cells += size;
 		do_div(xoff, port_buff_cell_sz);
 		do_div(xon, port_buff_cell_sz);
 		MLX5_SET(bufferx_reg, buffer, size, size);
@@ -320,10 +320,8 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 		MLX5_SET(bufferx_reg, buffer, xon_threshold, xon);
 	}

-	new_headroom_size /= port_buff_cell_sz;
-	current_headroom_size /= port_buff_cell_sz;
-	err = port_update_shared_buffer(priv->mdev, current_headroom_size,
-					new_headroom_size);
+	err = port_update_shared_buffer(priv->mdev, current_headroom_cells,
+					new_headroom_cells);
 	if (err)
 		goto out;

@@ -362,6 +362,7 @@ static int mlx5e_dcbnl_ieee_getpfc(struct net_device *dev,
 static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
+	u8 buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN;
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 old_cable_len = priv->dcbx.cable_len;
@@ -389,7 +390,14 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,

 	if (MLX5_BUFFER_SUPPORTED(mdev)) {
 		pfc_new.pfc_en = (changed & MLX5E_PORT_BUFFER_PFC) ? pfc->pfc_en : curr_pfc_en;
-		if (priv->dcbx.manual_buffer)
+		ret = mlx5_query_port_buffer_ownership(mdev,
+						       &buffer_ownership);
+		if (ret)
+			netdev_err(dev,
+				   "%s, Failed to get buffer ownership: %d\n",
+				   __func__, ret);
+
+		if (buffer_ownership == MLX5_BUF_OWNERSHIP_SW_OWNED)
 			ret = mlx5e_port_manual_buffer_config(priv, changed,
 							      dev->mtu, &pfc_new,
 							      NULL, NULL);
@@ -982,7 +990,6 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev,
 	if (!changed)
 		return 0;

-	priv->dcbx.manual_buffer = true;
 	err = mlx5e_port_manual_buffer_config(priv, changed, dev->mtu, NULL,
 					      buffer_size, prio2buffer);
 	return err;
@@ -1252,7 +1259,6 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv)
 		priv->dcbx.cap |= DCB_CAP_DCBX_HOST;

 	priv->dcbx.port_buff_cell_sz = mlx5e_query_port_buffers_cell_size(priv);
-	priv->dcbx.manual_buffer = false;
 	priv->dcbx.cable_len = MLX5E_DEFAULT_CABLE_LEN;

 	mlx5e_ets_init(priv);
@@ -47,10 +47,12 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 		devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum,
 					      vport_num - 1, external);
 	}  else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) {
+		u16 base_vport = mlx5_core_ec_vf_vport_base(dev);
+
 		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
 		dl_port->attrs.switch_id.id_len = ppid.id_len;
 		devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum,
-					      vport_num - 1, false);
+					      vport_num - base_vport, false);
 	}
 }

@@ -102,6 +102,8 @@ struct mlx5_esw_sched_node {
 	u8 level;
 	/* Valid only when this node represents a traffic class. */
 	u8 tc;
+	/* Valid only for a TC arbiter node or vport TC arbiter. */
+	u32 tc_bw[DEVLINK_RATE_TCS_MAX];
 };

 static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node)
@@ -462,6 +464,7 @@ static int
 esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node,
 				   struct netlink_ext_ack *extack)
 {
+	struct mlx5_esw_sched_node *parent = vport_node->parent;
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
 	struct mlx5_core_dev *dev = vport_node->esw->dev;
 	void *attr;
@@ -477,7 +480,7 @@ esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node,
 	attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes);
 	MLX5_SET(vport_element, attr, vport_number, vport_node->vport->vport);
 	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
-		 vport_node->parent->ix);
+		 parent ? parent->ix : vport_node->esw->qos.root_tsar_ix);
 	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
 		 vport_node->max_rate);

@@ -608,10 +611,7 @@ static void
 esw_qos_tc_arbiter_get_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node,
 				 u32 *tc_bw)
 {
-	struct mlx5_esw_sched_node *vports_tc_node;
-
-	list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry)
-		tc_bw[vports_tc_node->tc] = vports_tc_node->bw_share;
+	memcpy(tc_bw, tc_arbiter_node->tc_bw, sizeof(tc_arbiter_node->tc_bw));
 }

 static void
@@ -628,6 +628,7 @@ esw_qos_set_tc_arbiter_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node,
 		u8 tc = vports_tc_node->tc;
 		u32 bw_share;

+		tc_arbiter_node->tc_bw[tc] = tc_bw[tc];
 		bw_share = tc_bw[tc] * fw_max_bw_share;
 		bw_share = esw_qos_calc_bw_share(bw_share, divider,
 						 fw_max_bw_share);
@@ -786,48 +787,15 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta
 		return err;
 	}

-	if (MLX5_CAP_QOS(dev, log_esw_max_sched_depth)) {
-		esw->qos.node0 = __esw_qos_create_vports_sched_node(esw, NULL, extack);
-	} else {
-		/* The eswitch doesn't support scheduling nodes.
-		 * Create a software-only node0 using the root TSAR to attach vport QoS to.
-		 */
-		if (!__esw_qos_alloc_node(esw,
-					  esw->qos.root_tsar_ix,
-					  SCHED_NODE_TYPE_VPORTS_TSAR,
-					  NULL))
-			esw->qos.node0 = ERR_PTR(-ENOMEM);
-		else
-			list_add_tail(&esw->qos.node0->entry,
-				      &esw->qos.domain->nodes);
-	}
-	if (IS_ERR(esw->qos.node0)) {
-		err = PTR_ERR(esw->qos.node0);
-		esw_warn(dev, "E-Switch create rate node 0 failed (%d)\n", err);
-		goto err_node0;
-	}
 	refcount_set(&esw->qos.refcnt, 1);

 	return 0;
-
-err_node0:
-	if (mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH,
-						esw->qos.root_tsar_ix))
-		esw_warn(esw->dev, "E-Switch destroy root TSAR failed.\n");
-
-	return err;
 }

 static void esw_qos_destroy(struct mlx5_eswitch *esw)
 {
 	int err;

-	if (esw->qos.node0->ix != esw->qos.root_tsar_ix)
-		__esw_qos_destroy_node(esw->qos.node0, NULL);
-	else
-		__esw_qos_free_node(esw->qos.node0);
-	esw->qos.node0 = NULL;
-
 	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
 						  SCHEDULING_HIERARCHY_E_SWITCH,
 						  esw->qos.root_tsar_ix);
@@ -990,13 +958,16 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type,
 			struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
-	int err, new_level, max_level;
+	struct mlx5_esw_sched_node *parent = vport_node->parent;
+	int err;

 	if (type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
+		int new_level, max_level;
+
 		/* Increase the parent's level by 2 to account for both the
 		 * TC arbiter and the vports TC scheduling element.
 		 */
-		new_level = vport_node->parent->level + 2;
+		new_level = (parent ? parent->level : 2) + 2;
 		max_level = 1 << MLX5_CAP_QOS(vport_node->esw->dev,
 					      log_esw_max_sched_depth);
 		if (new_level > max_level) {
@@ -1033,9 +1004,7 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type,
 err_sched_nodes:
 	if (type == SCHED_NODE_TYPE_RATE_LIMITER) {
 		esw_qos_node_destroy_sched_element(vport_node, NULL);
-		list_add_tail(&vport_node->entry,
-			      &vport_node->parent->children);
-		vport_node->level = vport_node->parent->level + 1;
+		esw_qos_node_attach_to_parent(vport_node);
 	} else {
 		esw_qos_tc_arbiter_scheduling_teardown(vport_node, NULL);
 	}
@@ -1083,7 +1052,6 @@ err_out:
 static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
-	struct mlx5_esw_sched_node *parent = vport_node->parent;
 	enum sched_node_type curr_type = vport_node->type;

 	if (curr_type == SCHED_NODE_TYPE_VPORT)
@@ -1092,8 +1060,9 @@ static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_a
 		esw_qos_vport_tc_disable(vport, extack);

 	vport_node->bw_share = 0;
+	memset(vport_node->tc_bw, 0, sizeof(vport_node->tc_bw));
 	list_del_init(&vport_node->entry);
-	esw_qos_normalize_min_rate(parent->esw, parent, extack);
+	esw_qos_normalize_min_rate(vport_node->esw, vport_node->parent, extack);

 	trace_mlx5_esw_vport_qos_destroy(vport_node->esw->dev, vport);
 }
@@ -1103,25 +1072,23 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport,
 				struct mlx5_esw_sched_node *parent,
 				struct netlink_ext_ack *extack)
 {
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
 	int err;

 	esw_assert_qos_lock_held(vport->dev->priv.eswitch);

-	esw_qos_node_set_parent(vport->qos.sched_node, parent);
-	if (type == SCHED_NODE_TYPE_VPORT) {
-		err = esw_qos_vport_create_sched_element(vport->qos.sched_node,
-							 extack);
-	} else {
+	esw_qos_node_set_parent(vport_node, parent);
+	if (type == SCHED_NODE_TYPE_VPORT)
+		err = esw_qos_vport_create_sched_element(vport_node, extack);
+	else
 		err = esw_qos_vport_tc_enable(vport, type, extack);
-	}
 	if (err)
 		return err;

-	vport->qos.sched_node->type = type;
-	esw_qos_normalize_min_rate(parent->esw, parent, extack);
-	trace_mlx5_esw_vport_qos_create(vport->dev, vport,
-					vport->qos.sched_node->max_rate,
-					vport->qos.sched_node->bw_share);
+	vport_node->type = type;
+	esw_qos_normalize_min_rate(vport_node->esw, parent, extack);
+	trace_mlx5_esw_vport_qos_create(vport->dev, vport, vport_node->max_rate,
+					vport_node->bw_share);

 	return 0;
 }
@@ -1132,6 +1099,7 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 {
 	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
 	struct mlx5_esw_sched_node *sched_node;
+	struct mlx5_eswitch *parent_esw;
 	int err;

 	esw_assert_qos_lock_held(esw);
@@ -1139,10 +1107,14 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	if (err)
 		return err;

-	parent = parent ?: esw->qos.node0;
-	sched_node = __esw_qos_alloc_node(parent->esw, 0, type, parent);
-	if (!sched_node)
+	parent_esw = parent ? parent->esw : esw;
+	sched_node = __esw_qos_alloc_node(parent_esw, 0, type, parent);
+	if (!sched_node) {
+		esw_qos_put(esw);
 		return -ENOMEM;
+	}
+	if (!parent)
+		list_add_tail(&sched_node->entry, &esw->qos.domain->nodes);

 	sched_node->max_rate = max_rate;
 	sched_node->min_rate = min_rate;
@@ -1150,6 +1122,7 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	vport->qos.sched_node = sched_node;
 	err = esw_qos_vport_enable(vport, type, parent, extack);
 	if (err) {
+		__esw_qos_free_node(sched_node);
 		esw_qos_put(esw);
 		vport->qos.sched_node = NULL;
 	}
@@ -1157,6 +1130,19 @@ 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;
@@ -1168,11 +1154,9 @@ void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport)
 		goto unlock;

 	parent = vport->qos.sched_node->parent;
-	WARN(parent != esw->qos.node0, "Disabling QoS on port before detaching it from node");
+	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);
 }
@@ -1262,13 +1246,13 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 				struct mlx5_esw_sched_node *parent,
 				struct netlink_ext_ack *extack)
 {
-	struct mlx5_esw_sched_node *curr_parent = vport->qos.sched_node->parent;
-	enum sched_node_type curr_type = vport->qos.sched_node->type;
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+	struct mlx5_esw_sched_node *curr_parent = vport_node->parent;
+	enum sched_node_type curr_type = vport_node->type;
 	u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0};
 	int err;

 	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
-	parent = parent ?: curr_parent;
 	if (curr_type == type && curr_parent == parent)
 		return 0;

@@ -1276,10 +1260,8 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 	if (err)
 		return err;

-	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) {
-		esw_qos_tc_arbiter_get_bw_shares(vport->qos.sched_node,
-						 curr_tc_bw);
-	}
+	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type)
+		esw_qos_tc_arbiter_get_bw_shares(vport_node, curr_tc_bw);

 	esw_qos_vport_disable(vport, extack);

@@ -1290,8 +1272,8 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 	}

 	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) {
-		esw_qos_set_tc_arbiter_bw_shares(vport->qos.sched_node,
-						 curr_tc_bw, extack);
+		esw_qos_set_tc_arbiter_bw_shares(vport_node, curr_tc_bw,
+						 extack);
 	}

 	return err;
@@ -1306,16 +1288,16 @@ static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw

 	esw_assert_qos_lock_held(esw);
 	curr_parent = vport->qos.sched_node->parent;
-	parent = parent ?: esw->qos.node0;
 	if (curr_parent == parent)
 		return 0;

 	/* Set vport QoS type based on parent node type if different from
 	 * default QoS; otherwise, use the vport's current QoS type.
 	 */
-	if (parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+	if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 		type = SCHED_NODE_TYPE_RATE_LIMITER;
-	else if (curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+	else if (curr_parent &&
+		 curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 		type = SCHED_NODE_TYPE_VPORT;
 	else
 		type = vport->qos.sched_node->type;
@@ -1654,9 +1636,10 @@ static bool esw_qos_validate_unsupported_tc_bw(struct mlx5_eswitch *esw,
 static bool esw_qos_vport_validate_unsupported_tc_bw(struct mlx5_vport *vport,
 						     u32 *tc_bw)
 {
-	struct mlx5_eswitch *esw = vport->qos.sched_node ?
-				   vport->qos.sched_node->parent->esw :
-				   vport->dev->priv.eswitch;
+	struct mlx5_esw_sched_node *node = vport->qos.sched_node;
+	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
+
+	esw = (node && node->parent) ? node->parent->esw : esw;

 	return esw_qos_validate_unsupported_tc_bw(esw, tc_bw);
 }
@@ -1673,6 +1656,21 @@ 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)
@@ -1706,6 +1704,10 @@ 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;
 }
@@ -1727,6 +1729,10 @@ 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;
 }
@@ -1763,7 +1769,8 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf,
 	if (disable) {
 		if (vport_node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 			err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_VPORT,
-						   NULL, extack);
+						   vport_node->parent, extack);
+		esw_vport_qos_prune_empty(vport);
 		goto unlock;
 	}

@@ -1775,7 +1782,7 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf,
 	} else {
 		err = esw_qos_vport_update(vport,
 					   SCHED_NODE_TYPE_TC_ARBITER_TSAR,
-					   NULL, extack);
+					   vport_node->parent, extack);
 	}
 	if (!err)
 		esw_qos_set_tc_arbiter_bw_shares(vport_node, tc_bw, extack);
@@ -1924,14 +1931,20 @@ 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;

-	node = parent_priv;
-	return mlx5_esw_qos_vport_update_parent(vport, node, extack);
+		esw_qos_lock(esw);
+		esw_vport_qos_prune_empty(vport);
+		esw_qos_unlock(esw);
+	}
+
+	return err;
 }

 static bool esw_qos_is_node_empty(struct mlx5_esw_sched_node *node)
@@ -373,11 +373,6 @@ struct mlx5_eswitch {
 		refcount_t refcnt;
 		u32 root_tsar_ix;
 		struct mlx5_qos_domain *domain;
-		/* Contains all vports with QoS enabled but no explicit node.
-		 * Cannot be NULL if QoS is enabled, but may be a fake node
-		 * referencing the root TSAR if the esw doesn't support nodes.
-		 */
-		struct mlx5_esw_sched_node *node0;
 	} qos;

 	struct mlx5_esw_bridge_offloads *br_offloads;
@@ -367,6 +367,8 @@ int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
 int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
 int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
 int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
+int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev,
+				     u8 *buffer_ownership);
 int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
 int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);

@@ -968,6 +968,26 @@ int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state)
 	return err;
 }

+int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev,
+				     u8 *buffer_ownership)
+{
+	u32 out[MLX5_ST_SZ_DW(pfcc_reg)] = {};
+	int err;
+
+	if (!MLX5_CAP_PCAM_FEATURE(mdev, buffer_ownership)) {
+		*buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN;
+		return 0;
+	}
+
+	err = mlx5_query_pfcc_reg(mdev, out, sizeof(out));
+	if (err)
+		return err;
+
+	*buffer_ownership = MLX5_GET(pfcc_reg, out, buf_ownership);
+
+	return 0;
+}
+
 int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio)
 {
 	int sz = MLX5_ST_SZ_BYTES(qpdpm_reg);