[PATCH net-next 8/8] net/mlx5: Manage TC arbiter nodes and provide full support for tc-bw

[Tariq Toukan <tariqt@nvidia.com>]

From: Carolina Jubran <cjubran@nvidia.com>

Introduce support for managing Traffic Class (TC) arbiter nodes and
associated vports TC nodes within the E-Switch QoS hierarchy. This patch
adds support for the new scheduling node type,
`SCHED_NODE_TYPE_VPORTS_TC_TSAR`, and provides full support for setting
tc-bw on both vports and nodes.

Key changes include:

- New helper functions for creating and destroying vports TC nodes under
  the TC arbiter.

- Introduced the new scheduling node type,
  `SCHED_NODE_TYPE_VPORTS_TC_TSAR`, for managing vports within the TC
  arbiter node.

- Updated the minimum rate normalization function to skip nodes of type
  `SCHED_NODE_TYPE_VPORTS_TC_TSAR`. Vports TC TSARs have bandwidth
  shares configured on them but not minimum rates, so their `min_rate`
  cannot be normalized.

- Implementation of `esw_qos_tc_arbiter_scheduling_setup()` and
  `esw_qos_tc_arbiter_scheduling_teardown()` for initializing and
  cleaning up TC arbiter scheduling elements. These functions now fully
  support tc-bw configuration on TC arbiter nodes.

- Added `esw_qos_tc_arbiter_get_bw_shares()` and
  `esw_qos_set_tc_arbiter_bw_shares()` to handle the settings of
  bandwidth shares for vports traffic class TSARs.

- Enhanced `mlx5_esw_devlink_rate_node_tc_bw_set()` and
  `mlx5_esw_devlink_rate_leaf_tc_bw_set()` to fully support configuring
  tc-bw on devlink rate nodes and vports, respectively.

Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 185 +++++++++++++++++-
 1 file changed, 180 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index afb00deaae16..87c9789c2836 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -67,6 +67,7 @@ enum sched_node_type {
 	SCHED_NODE_TYPE_TC_ARBITER_TSAR,
 	SCHED_NODE_TYPE_RATE_LIMITER,
 	SCHED_NODE_TYPE_VPORT_TC,
+	SCHED_NODE_TYPE_VPORTS_TC_TSAR,
 };
 
 static const char * const sched_node_type_str[] = {
@@ -75,6 +76,7 @@ static const char * const sched_node_type_str[] = {
 	[SCHED_NODE_TYPE_TC_ARBITER_TSAR] = "TC Arbiter TSAR",
 	[SCHED_NODE_TYPE_RATE_LIMITER] = "Rate Limiter",
 	[SCHED_NODE_TYPE_VPORT_TC] = "vport TC",
+	[SCHED_NODE_TYPE_VPORTS_TC_TSAR] = "vports TC TSAR",
 };
 
 struct mlx5_esw_sched_node {
@@ -159,6 +161,11 @@ mlx5_esw_qos_vport_get_parent(const struct mlx5_vport *vport)
 static void esw_qos_sched_elem_warn(struct mlx5_esw_sched_node *node, int err, const char *op)
 {
 	switch (node->type) {
+	case SCHED_NODE_TYPE_VPORTS_TC_TSAR:
+		esw_warn(node->esw->dev,
+			 "E-Switch %s %s scheduling element failed (tc=%d,err=%d)\n",
+			 op, sched_node_type_str[node->type], node->tc, err);
+		break;
 	case SCHED_NODE_TYPE_VPORT_TC:
 		esw_warn(node->esw->dev,
 			 "E-Switch %s %s scheduling element failed (vport=%d,tc=%d,err=%d)\n",
@@ -344,7 +351,11 @@ static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw,
 		if (node->esw != esw || node->ix == esw->qos.root_tsar_ix)
 			continue;
 
-		esw_qos_update_sched_node_bw_share(node, divider, extack);
+		/* Vports TC TSARs don't have a minimum rate configured,
+		 * so there's no need to update the bw_share on them.
+		 */
+		if (node->type != SCHED_NODE_TYPE_VPORTS_TC_TSAR)
+			esw_qos_update_sched_node_bw_share(node, divider, extack);
 
 		if (list_empty(&node->children))
 			continue;
@@ -476,6 +487,129 @@ static void esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netlin
 	__esw_qos_free_node(node);
 }
 
+static int esw_qos_create_vports_tc_node(struct mlx5_esw_sched_node *parent, u8 tc,
+					 struct netlink_ext_ack *extack)
+{
+	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_core_dev *dev = parent->esw->dev;
+	struct mlx5_esw_sched_node *vports_tc_node;
+	void *attr;
+	int err;
+
+	if (!mlx5_qos_element_type_supported(dev,
+					     SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR,
+					     SCHEDULING_HIERARCHY_E_SWITCH) ||
+	    !mlx5_qos_tsar_type_supported(dev,
+					  TSAR_ELEMENT_TSAR_TYPE_DWRR,
+					  SCHEDULING_HIERARCHY_E_SWITCH))
+		return -EOPNOTSUPP;
+
+	vports_tc_node = __esw_qos_alloc_node(parent->esw, 0, SCHED_NODE_TYPE_VPORTS_TC_TSAR,
+					      parent);
+	if (!vports_tc_node) {
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch alloc node failed");
+		esw_warn(dev, "Failed to alloc vports TC node (tc=%d)\n", tc);
+		return -ENOMEM;
+	}
+
+	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
+	MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_DWRR);
+	MLX5_SET(tsar_element, attr, traffic_class, tc);
+	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, parent->ix);
+	MLX5_SET(scheduling_context, tsar_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+
+	err = esw_qos_node_create_sched_element(vports_tc_node, tsar_ctx, extack);
+	if (err)
+		goto err_create_sched_element;
+
+	vports_tc_node->tc = tc;
+
+	return 0;
+
+err_create_sched_element:
+	__esw_qos_free_node(vports_tc_node);
+	return err;
+}
+
+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;
+}
+
+static void esw_qos_set_tc_arbiter_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node,
+					     u32 *tc_bw, struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vports_tc_node;
+
+	list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) {
+		u32 bw_share;
+		u8 tc;
+
+		tc = vports_tc_node->tc;
+		bw_share = tc_bw[tc] ?: MLX5_MIN_BW_SHARE;
+		esw_qos_sched_elem_config(vports_tc_node, 0, bw_share, extack);
+	}
+}
+
+static void esw_qos_destroy_vports_tc_nodes(struct mlx5_esw_sched_node *tc_arbiter_node,
+					    struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *vports_tc_node, *tmp;
+
+	list_for_each_entry_safe(vports_tc_node, tmp, &tc_arbiter_node->children, entry)
+		esw_qos_destroy_node(vports_tc_node, extack);
+}
+
+static int esw_qos_create_vports_tc_nodes(struct mlx5_esw_sched_node *tc_arbiter_node,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw = tc_arbiter_node->esw;
+	int err, i, num_tcs = esw_qos_num_tcs(esw->dev);
+
+	for (i = 0; i < num_tcs; i++) {
+		err = esw_qos_create_vports_tc_node(tc_arbiter_node, i, extack);
+		if (err)
+			goto err_tc_node_create;
+	}
+
+	return 0;
+
+err_tc_node_create:
+	esw_qos_destroy_vports_tc_nodes(tc_arbiter_node, NULL);
+	return err;
+}
+
+static int esw_qos_create_tc_arbiter_sched_elem(struct mlx5_esw_sched_node *tc_arbiter_node,
+						struct netlink_ext_ack *extack)
+{
+	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	u32 tsar_parent_ix;
+	void *attr;
+
+	if (!mlx5_qos_tsar_type_supported(tc_arbiter_node->esw->dev,
+					  TSAR_ELEMENT_TSAR_TYPE_TC_ARB,
+					  SCHEDULING_HIERARCHY_E_SWITCH)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "E-Switch TC Arbiter scheduling element is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
+	MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_TC_ARB);
+	tsar_parent_ix = tc_arbiter_node->parent ? tc_arbiter_node->parent->ix :
+			 tc_arbiter_node->esw->qos.root_tsar_ix;
+	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id, tsar_parent_ix);
+	MLX5_SET(scheduling_context, tsar_ctx, element_type, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+	MLX5_SET(scheduling_context, tsar_ctx, max_average_bw, tc_arbiter_node->max_rate);
+	MLX5_SET(scheduling_context, tsar_ctx, bw_share, tc_arbiter_node->bw_share);
+
+	return esw_qos_node_create_sched_element(tc_arbiter_node, tsar_ctx, extack);
+}
+
 static struct mlx5_esw_sched_node *
 __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sched_node *parent,
 				   struct netlink_ext_ack *extack)
@@ -539,6 +673,9 @@ static void __esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netl
 {
 	struct mlx5_eswitch *esw = node->esw;
 
+	if (node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+		esw_qos_destroy_vports_tc_nodes(node, extack);
+
 	trace_mlx5_esw_node_qos_destroy(esw->dev, node, node->ix);
 	esw_qos_destroy_node(node, extack);
 	esw_qos_normalize_min_rate(esw, NULL, extack);
@@ -628,13 +765,38 @@ static void esw_qos_put(struct mlx5_eswitch *esw)
 
 static void esw_qos_tc_arbiter_scheduling_teardown(struct mlx5_esw_sched_node *node,
 						   struct netlink_ext_ack *extack)
-{}
+{
+	/* Clean up all Vports TC nodes within the TC arbiter node. */
+	esw_qos_destroy_vports_tc_nodes(node, extack);
+	/* Destroy the scheduling element for the TC arbiter node itself. */
+	esw_qos_node_destroy_sched_element(node, extack);
+}
 
 static int esw_qos_tc_arbiter_scheduling_setup(struct mlx5_esw_sched_node *node,
 					       struct netlink_ext_ack *extack)
 {
-	NL_SET_ERR_MSG_MOD(extack, "TC arbiter elements are not supported.");
-	return -EOPNOTSUPP;
+	u32 curr_ix = node->ix;
+	int err;
+
+	err = esw_qos_create_tc_arbiter_sched_elem(node, extack);
+	if (err)
+		return err;
+	/* Initialize the vports TC nodes within created TC arbiter TSAR. */
+	err = esw_qos_create_vports_tc_nodes(node, extack);
+	if (err)
+		goto err_vports_tc_nodes;
+
+	node->type = SCHED_NODE_TYPE_TC_ARBITER_TSAR;
+
+	return 0;
+
+err_vports_tc_nodes:
+	/* If initialization fails, clean up the scheduling element
+	 * for the TC arbiter node.
+	 */
+	esw_qos_node_destroy_sched_element(node, NULL);
+	node->ix = curr_ix;
+	return err;
 }
 
 static int esw_qos_create_vport_tc_sched_node(struct mlx5_vport *vport,
@@ -965,6 +1127,7 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, enum sched_node_type t
 {
 	struct mlx5_esw_sched_node *curr_parent = vport->qos.sched_node->parent;
 	enum sched_node_type curr_type = vport->qos.sched_node->type;
+	u32 curr_tc_bw[IEEE_8021QAZ_MAX_TCS] = {0};
 	int err;
 
 	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
@@ -976,11 +1139,19 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, enum sched_node_type t
 	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);
+
 	esw_qos_vport_disable(vport, extack);
 
 	err = esw_qos_vport_enable(vport, type, parent, extack);
-	if (err)
+	if (err) {
 		esw_qos_vport_enable(vport, curr_type, curr_parent, NULL);
+		extack = NULL;
+	}
+
+	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);
 
 	return err;
 }
@@ -1415,6 +1586,8 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf, void *p
 	} else {
 		err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_TC_ARBITER_TSAR, NULL, extack);
 	}
+	if (!err)
+		esw_qos_set_tc_arbiter_bw_shares(vport_node, tc_bw, extack);
 unlock:
 	esw_qos_unlock(esw);
 	return err;
@@ -1441,6 +1614,8 @@ int mlx5_esw_devlink_rate_node_tc_bw_set(struct devlink_rate *rate_node, void *p
 	}
 
 	err = esw_qos_node_enable_tc_arbitration(node, extack);
+	if (!err)
+		esw_qos_set_tc_arbiter_bw_shares(node, tc_bw, extack);
 unlock:
 	esw_qos_unlock(esw);
 	return err;
-- 
2.44.0