[PATCH v9 5/9] net/ice: support queue group bandwidth limit

[Wenjun Wu <wenjun1.wu@intel.com>]

To set up the exact queue group, we need to reconfigure topology by
delete and then recreate queue nodes.

This patch adds queue group configuration support and queue group
bandwidth limit support.

Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com>
---
 drivers/net/ice/ice_ethdev.h |   9 +-
 drivers/net/ice/ice_tm.c     | 239 ++++++++++++++++++++++++++++++++---
 2 files changed, 232 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ice/ice_ethdev.h b/drivers/net/ice/ice_ethdev.h
index 4359c61624..f9f4a1c71b 100644
--- a/drivers/net/ice/ice_ethdev.h
+++ b/drivers/net/ice/ice_ethdev.h
@@ -474,6 +474,7 @@ struct ice_tm_node {
 	uint32_t weight;
 	uint32_t reference_count;
 	struct ice_tm_node *parent;
+	struct ice_tm_node **children;
 	struct ice_tm_shaper_profile *shaper_profile;
 	struct rte_tm_node_params params;
 };
@@ -482,6 +483,8 @@ struct ice_tm_node {
 enum ice_tm_node_type {
 	ICE_TM_NODE_TYPE_PORT,
 	ICE_TM_NODE_TYPE_TC,
+	ICE_TM_NODE_TYPE_VSI,
+	ICE_TM_NODE_TYPE_QGROUP,
 	ICE_TM_NODE_TYPE_QUEUE,
 	ICE_TM_NODE_TYPE_MAX,
 };
@@ -489,10 +492,14 @@ enum ice_tm_node_type {
 /* Struct to store all the Traffic Manager configuration. */
 struct ice_tm_conf {
 	struct ice_shaper_profile_list shaper_profile_list;
-	struct ice_tm_node *root; /* root node - vf vsi */
+	struct ice_tm_node *root; /* root node - port */
 	struct ice_tm_node_list tc_list; /* node list for all the TCs */
+	struct ice_tm_node_list vsi_list; /* node list for all the VSIs */
+	struct ice_tm_node_list qgroup_list; /* node list for all the queue groups */
 	struct ice_tm_node_list queue_list; /* node list for all the queues */
 	uint32_t nb_tc_node;
+	uint32_t nb_vsi_node;
+	uint32_t nb_qgroup_node;
 	uint32_t nb_queue_node;
 	bool committed;
 };
diff --git a/drivers/net/ice/ice_tm.c b/drivers/net/ice/ice_tm.c
index 383af88981..d70d077286 100644
--- a/drivers/net/ice/ice_tm.c
+++ b/drivers/net/ice/ice_tm.c
@@ -44,8 +44,12 @@ ice_tm_conf_init(struct rte_eth_dev *dev)
 	TAILQ_INIT(&pf->tm_conf.shaper_profile_list);
 	pf->tm_conf.root = NULL;
 	TAILQ_INIT(&pf->tm_conf.tc_list);
+	TAILQ_INIT(&pf->tm_conf.vsi_list);
+	TAILQ_INIT(&pf->tm_conf.qgroup_list);
 	TAILQ_INIT(&pf->tm_conf.queue_list);
 	pf->tm_conf.nb_tc_node = 0;
+	pf->tm_conf.nb_vsi_node = 0;
+	pf->tm_conf.nb_qgroup_node = 0;
 	pf->tm_conf.nb_queue_node = 0;
 	pf->tm_conf.committed = false;
 }
@@ -62,6 +66,16 @@ ice_tm_conf_uninit(struct rte_eth_dev *dev)
 		rte_free(tm_node);
 	}
 	pf->tm_conf.nb_queue_node = 0;
+	while ((tm_node = TAILQ_FIRST(&pf->tm_conf.qgroup_list))) {
+		TAILQ_REMOVE(&pf->tm_conf.qgroup_list, tm_node, node);
+		rte_free(tm_node);
+	}
+	pf->tm_conf.nb_qgroup_node = 0;
+	while ((tm_node = TAILQ_FIRST(&pf->tm_conf.vsi_list))) {
+		TAILQ_REMOVE(&pf->tm_conf.vsi_list, tm_node, node);
+		rte_free(tm_node);
+	}
+	pf->tm_conf.nb_vsi_node = 0;
 	while ((tm_node = TAILQ_FIRST(&pf->tm_conf.tc_list))) {
 		TAILQ_REMOVE(&pf->tm_conf.tc_list, tm_node, node);
 		rte_free(tm_node);
@@ -79,6 +93,8 @@ ice_tm_node_search(struct rte_eth_dev *dev,
 {
 	struct ice_pf *pf = ICE_DEV_PRIVATE_TO_PF(dev->data->dev_private);
 	struct ice_tm_node_list *tc_list = &pf->tm_conf.tc_list;
+	struct ice_tm_node_list *vsi_list = &pf->tm_conf.vsi_list;
+	struct ice_tm_node_list *qgroup_list = &pf->tm_conf.qgroup_list;
 	struct ice_tm_node_list *queue_list = &pf->tm_conf.queue_list;
 	struct ice_tm_node *tm_node;
 
@@ -94,6 +110,20 @@ ice_tm_node_search(struct rte_eth_dev *dev,
 		}
 	}
 
+	TAILQ_FOREACH(tm_node, vsi_list, node) {
+		if (tm_node->id == node_id) {
+			*node_type = ICE_TM_NODE_TYPE_VSI;
+			return tm_node;
+		}
+	}
+
+	TAILQ_FOREACH(tm_node, qgroup_list, node) {
+		if (tm_node->id == node_id) {
+			*node_type = ICE_TM_NODE_TYPE_QGROUP;
+			return tm_node;
+		}
+	}
+
 	TAILQ_FOREACH(tm_node, queue_list, node) {
 		if (tm_node->id == node_id) {
 			*node_type = ICE_TM_NODE_TYPE_QUEUE;
@@ -354,6 +384,7 @@ ice_tm_node_add(struct rte_eth_dev *dev, uint32_t node_id,
 	struct ice_tm_node *tm_node;
 	struct ice_tm_node *parent_node;
 	uint16_t tc_nb = 1;
+	uint16_t vsi_nb = 1;
 	int ret;
 
 	if (!params || !error)
@@ -415,6 +446,8 @@ ice_tm_node_add(struct rte_eth_dev *dev, uint32_t node_id,
 		tm_node->id = node_id;
 		tm_node->parent = NULL;
 		tm_node->reference_count = 0;
+		tm_node->children = (struct ice_tm_node **)
+			rte_calloc(NULL, 256, (sizeof(struct ice_tm_node *)), 0);
 		rte_memcpy(&tm_node->params, params,
 				 sizeof(struct rte_tm_node_params));
 		pf->tm_conf.root = tm_node;
@@ -431,9 +464,11 @@ ice_tm_node_add(struct rte_eth_dev *dev, uint32_t node_id,
 		return -EINVAL;
 	}
 	if (parent_node_type != ICE_TM_NODE_TYPE_PORT &&
-	    parent_node_type != ICE_TM_NODE_TYPE_TC) {
+	    parent_node_type != ICE_TM_NODE_TYPE_TC &&
+	    parent_node_type != ICE_TM_NODE_TYPE_VSI &&
+	    parent_node_type != ICE_TM_NODE_TYPE_QGROUP) {
 		error->type = RTE_TM_ERROR_TYPE_NODE_PARENT_NODE_ID;
-		error->message = "parent is not root or TC";
+		error->message = "parent is not valid";
 		return -EINVAL;
 	}
 	/* check level */
@@ -452,6 +487,20 @@ ice_tm_node_add(struct rte_eth_dev *dev, uint32_t node_id,
 			error->message = "too many TCs";
 			return -EINVAL;
 		}
+	} else if (parent_node_type == ICE_TM_NODE_TYPE_TC) {
+		/* check the VSI number */
+		if (pf->tm_conf.nb_vsi_node >= vsi_nb) {
+			error->type = RTE_TM_ERROR_TYPE_NODE_ID;
+			error->message = "too many VSIs";
+			return -EINVAL;
+		}
+	} else if (parent_node_type == ICE_TM_NODE_TYPE_VSI) {
+		/* check the queue group number */
+		if (parent_node->reference_count >= pf->dev_data->nb_tx_queues) {
+			error->type = RTE_TM_ERROR_TYPE_NODE_ID;
+			error->message = "too many queue groups";
+			return -EINVAL;
+		}
 	} else {
 		/* check the queue number */
 		if (parent_node->reference_count >= pf->dev_data->nb_tx_queues) {
@@ -466,7 +515,7 @@ ice_tm_node_add(struct rte_eth_dev *dev, uint32_t node_id,
 		}
 	}
 
-	/* add the TC or queue node */
+	/* add the TC or VSI or queue group or queue node */
 	tm_node = rte_zmalloc("ice_tm_node",
 			      sizeof(struct ice_tm_node),
 			      0);
@@ -478,6 +527,10 @@ ice_tm_node_add(struct rte_eth_dev *dev, uint32_t node_id,
 	tm_node->reference_count = 0;
 	tm_node->parent = parent_node;
 	tm_node->shaper_profile = shaper_profile;
+	tm_node->children = (struct ice_tm_node **)
+			rte_calloc(NULL, 256, (sizeof(struct ice_tm_node *)), 0);
+	tm_node->parent->children[tm_node->parent->reference_count] = tm_node;
+
 	rte_memcpy(&tm_node->params, params,
 			 sizeof(struct rte_tm_node_params));
 	if (parent_node_type == ICE_TM_NODE_TYPE_PORT) {
@@ -485,10 +538,20 @@ ice_tm_node_add(struct rte_eth_dev *dev, uint32_t node_id,
 				  tm_node, node);
 		tm_node->tc = pf->tm_conf.nb_tc_node;
 		pf->tm_conf.nb_tc_node++;
+	} else if (parent_node_type == ICE_TM_NODE_TYPE_TC) {
+		TAILQ_INSERT_TAIL(&pf->tm_conf.vsi_list,
+				  tm_node, node);
+		tm_node->tc = parent_node->tc;
+		pf->tm_conf.nb_vsi_node++;
+	} else if (parent_node_type == ICE_TM_NODE_TYPE_VSI) {
+		TAILQ_INSERT_TAIL(&pf->tm_conf.qgroup_list,
+				  tm_node, node);
+		tm_node->tc = parent_node->parent->tc;
+		pf->tm_conf.nb_qgroup_node++;
 	} else {
 		TAILQ_INSERT_TAIL(&pf->tm_conf.queue_list,
 				  tm_node, node);
-		tm_node->tc = parent_node->tc;
+		tm_node->tc = parent_node->parent->parent->tc;
 		pf->tm_conf.nb_queue_node++;
 	}
 	tm_node->parent->reference_count++;
@@ -543,11 +606,17 @@ ice_tm_node_delete(struct rte_eth_dev *dev, uint32_t node_id,
 		return 0;
 	}
 
-	/* TC or queue node */
+	/* TC or VSI or queue group or queue node */
 	tm_node->parent->reference_count--;
 	if (node_type == ICE_TM_NODE_TYPE_TC) {
 		TAILQ_REMOVE(&pf->tm_conf.tc_list, tm_node, node);
 		pf->tm_conf.nb_tc_node--;
+	} else if (node_type == ICE_TM_NODE_TYPE_VSI) {
+		TAILQ_REMOVE(&pf->tm_conf.vsi_list, tm_node, node);
+		pf->tm_conf.nb_vsi_node--;
+	} else if (node_type == ICE_TM_NODE_TYPE_QGROUP) {
+		TAILQ_REMOVE(&pf->tm_conf.qgroup_list, tm_node, node);
+		pf->tm_conf.nb_qgroup_node--;
 	} else {
 		TAILQ_REMOVE(&pf->tm_conf.queue_list, tm_node, node);
 		pf->tm_conf.nb_queue_node--;
@@ -557,36 +626,176 @@ ice_tm_node_delete(struct rte_eth_dev *dev, uint32_t node_id,
 	return 0;
 }
 
+static int ice_move_recfg_lan_txq(struct rte_eth_dev *dev,
+				  struct ice_sched_node *queue_sched_node,
+				  struct ice_sched_node *dst_node,
+				  uint16_t queue_id)
+{
+	struct ice_hw *hw = ICE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+	struct ice_aqc_move_txqs_data *buf;
+	struct ice_sched_node *queue_parent_node;
+	uint8_t txqs_moved;
+	int ret = ICE_SUCCESS;
+	uint16_t buf_size = ice_struct_size(buf, txqs, 1);
+
+	buf = (struct ice_aqc_move_txqs_data *)ice_malloc(hw, sizeof(*buf));
+
+	queue_parent_node = queue_sched_node->parent;
+	buf->src_teid = queue_parent_node->info.node_teid;
+	buf->dest_teid = dst_node->info.node_teid;
+	buf->txqs[0].q_teid = queue_sched_node->info.node_teid;
+	buf->txqs[0].txq_id = queue_id;
+
+	ret = ice_aq_move_recfg_lan_txq(hw, 1, true, false, false, false, 50,
+					NULL, buf, buf_size, &txqs_moved, NULL);
+	if (ret || txqs_moved == 0) {
+		PMD_DRV_LOG(ERR, "move lan queue %u failed", queue_id);
+		return ICE_ERR_PARAM;
+	}
+
+	if (queue_parent_node->num_children > 0) {
+		queue_parent_node->num_children--;
+		queue_parent_node->children[queue_parent_node->num_children] = NULL;
+	} else {
+		PMD_DRV_LOG(ERR, "invalid children number %d for queue %u",
+			    queue_parent_node->num_children, queue_id);
+		return ICE_ERR_PARAM;
+	}
+	dst_node->children[dst_node->num_children++] = queue_sched_node;
+	queue_sched_node->parent = dst_node;
+	ice_sched_query_elem(hw, queue_sched_node->info.node_teid, &queue_sched_node->info);
+
+	return ret;
+}
+
 static int ice_hierarchy_commit(struct rte_eth_dev *dev,
 				 int clear_on_fail,
 				 __rte_unused struct rte_tm_error *error)
 {
 	struct ice_pf *pf = ICE_DEV_PRIVATE_TO_PF(dev->data->dev_private);
 	struct ice_hw *hw = ICE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+	struct ice_tm_node_list *qgroup_list = &pf->tm_conf.qgroup_list;
 	struct ice_tm_node_list *queue_list = &pf->tm_conf.queue_list;
 	struct ice_tm_node *tm_node;
+	struct ice_sched_node *node;
+	struct ice_sched_node *vsi_node;
+	struct ice_sched_node *queue_node;
 	struct ice_tx_queue *txq;
 	struct ice_vsi *vsi;
 	int ret_val = ICE_SUCCESS;
 	uint64_t peak = 0;
+	uint32_t i;
+	uint32_t idx_vsi_child;
+	uint32_t idx_qg;
+	uint32_t nb_vsi_child;
+	uint32_t nb_qg;
+	uint32_t qid;
+	uint32_t q_teid;
+	uint32_t vsi_layer;
+
+	for (i = 0; i < dev->data->nb_tx_queues; i++) {
+		ret_val = ice_tx_queue_stop(dev, i);
+		if (ret_val) {
+			error->type = RTE_TM_ERROR_TYPE_UNSPECIFIED;
+			PMD_DRV_LOG(ERR, "stop queue %u failed", i);
+			goto fail_clear;
+		}
+	}
 
-	TAILQ_FOREACH(tm_node, queue_list, node) {
-		txq = dev->data->tx_queues[tm_node->id];
-		vsi = txq->vsi;
-		if (tm_node->shaper_profile)
+	node = hw->port_info->root;
+	vsi_layer = hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET;
+	for (i = 0; i < vsi_layer; i++)
+		node = node->children[0];
+	vsi_node = node;
+	nb_vsi_child = vsi_node->num_children;
+	nb_qg = vsi_node->children[0]->num_children;
+
+	idx_vsi_child = 0;
+	idx_qg = 0;
+
+	TAILQ_FOREACH(tm_node, qgroup_list, node) {
+		struct ice_tm_node *tm_child_node;
+		struct ice_sched_node *qgroup_sched_node =
+			vsi_node->children[idx_vsi_child]->children[idx_qg];
+
+		for (i = 0; i < tm_node->reference_count; i++) {
+			tm_child_node = tm_node->children[i];
+			qid = tm_child_node->id;
+			ret_val = ice_tx_queue_start(dev, qid);
+			if (ret_val) {
+				error->type = RTE_TM_ERROR_TYPE_UNSPECIFIED;
+				PMD_DRV_LOG(ERR, "start queue %u failed", qid);
+				goto fail_clear;
+			}
+			txq = dev->data->tx_queues[qid];
+			q_teid = txq->q_teid;
+			queue_node = ice_sched_get_node(hw->port_info, q_teid);
+			if (queue_node == NULL) {
+				error->type = RTE_TM_ERROR_TYPE_UNSPECIFIED;
+				PMD_DRV_LOG(ERR, "get queue %u node failed", qid);
+				goto fail_clear;
+			}
+			if (queue_node->info.parent_teid == qgroup_sched_node->info.node_teid)
+				continue;
+			ret_val = ice_move_recfg_lan_txq(dev, queue_node, qgroup_sched_node, qid);
+			if (ret_val) {
+				error->type = RTE_TM_ERROR_TYPE_UNSPECIFIED;
+				PMD_DRV_LOG(ERR, "move queue %u failed", qid);
+				goto fail_clear;
+			}
+		}
+		if (tm_node->reference_count != 0 && tm_node->shaper_profile) {
+			uint32_t node_teid = qgroup_sched_node->info.node_teid;
 			/* Transfer from Byte per seconds to Kbps */
 			peak = tm_node->shaper_profile->profile.peak.rate;
-
-		peak = peak / 1000 * BITS_PER_BYTE;
-		ret_val = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx,
-				 tm_node->tc, tm_node->id, ICE_MAX_BW, (u32)peak);
-		if (ret_val) {
+			peak = peak / 1000 * BITS_PER_BYTE;
+			ret_val = ice_sched_set_node_bw_lmt_per_tc(hw->port_info,
+								   node_teid,
+								   ICE_AGG_TYPE_Q,
+								   tm_node->tc,
+								   ICE_MAX_BW,
+								   (u32)peak);
+			if (ret_val) {
+				error->type = RTE_TM_ERROR_TYPE_UNSPECIFIED;
+				PMD_DRV_LOG(ERR,
+					    "configure queue group %u bandwidth failed",
+					    tm_node->id);
+				goto fail_clear;
+			}
+		}
+		idx_qg++;
+		if (idx_qg >= nb_qg) {
+			idx_qg = 0;
+			idx_vsi_child++;
+		}
+		if (idx_vsi_child >= nb_vsi_child) {
 			error->type = RTE_TM_ERROR_TYPE_UNSPECIFIED;
-			PMD_DRV_LOG(ERR, "configure queue %u bandwidth failed", tm_node->id);
+			PMD_DRV_LOG(ERR, "too many queues");
 			goto fail_clear;
 		}
 	}
 
+	TAILQ_FOREACH(tm_node, queue_list, node) {
+		qid = tm_node->id;
+		txq = dev->data->tx_queues[qid];
+		vsi = txq->vsi;
+		if (tm_node->shaper_profile) {
+			/* Transfer from Byte per seconds to Kbps */
+			peak = tm_node->shaper_profile->profile.peak.rate;
+			peak = peak / 1000 * BITS_PER_BYTE;
+			ret_val = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx,
+						   tm_node->tc, tm_node->id,
+						   ICE_MAX_BW, (u32)peak);
+			if (ret_val) {
+				error->type = RTE_TM_ERROR_TYPE_UNSPECIFIED;
+				PMD_DRV_LOG(ERR,
+					    "configure queue %u bandwidth failed",
+					    tm_node->id);
+				goto fail_clear;
+			}
+		}
+	}
+
 	return ret_val;
 
 fail_clear:
-- 
2.25.1