[dpdk-dev] [PATCH v5 10/15] net/mlx5: add support for hairpin hrxq

[Ori Kam <orika@mellanox.com>]

Add support for rss on hairpin queues.

Signed-off-by: Ori Kam <orika@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
---
 drivers/net/mlx5/mlx5.h         |   3 ++
 drivers/net/mlx5/mlx5_ethdev.c  | 102 ++++++++++++++++++++++++++++++----------
 drivers/net/mlx5/mlx5_rss.c     |   1 +
 drivers/net/mlx5/mlx5_rxq.c     |  22 ++++++---
 drivers/net/mlx5/mlx5_trigger.c |   6 +++
 5 files changed, 104 insertions(+), 30 deletions(-)

diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index 33cfc5b..a36ba2d 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -716,6 +716,7 @@ struct mlx5_priv {
 	rte_spinlock_t uar_lock[MLX5_UAR_PAGE_NUM_MAX];
 	/* UAR same-page access control required in 32bit implementations. */
 #endif
+	uint8_t skip_default_rss_reta; /* Skip configuration of default reta. */
 };
 
 #define PORT_ID(priv) ((priv)->dev_data->port_id)
@@ -792,6 +793,8 @@ int mlx5_get_module_eeprom(struct rte_eth_dev *dev,
 			   struct rte_dev_eeprom_info *info);
 int mlx5_hairpin_cap_get(struct rte_eth_dev *dev,
 			 struct rte_eth_hairpin_cap *cap);
+int mlx5_dev_configure_rss_reta(struct rte_eth_dev *dev);
+
 /* mlx5_mac.c */
 
 int mlx5_get_mac(struct rte_eth_dev *dev, uint8_t (*mac)[RTE_ETHER_ADDR_LEN]);
diff --git a/drivers/net/mlx5/mlx5_ethdev.c b/drivers/net/mlx5/mlx5_ethdev.c
index fe1b4d4..c2bed2f 100644
--- a/drivers/net/mlx5/mlx5_ethdev.c
+++ b/drivers/net/mlx5/mlx5_ethdev.c
@@ -383,9 +383,6 @@ struct ethtool_link_settings {
 	struct mlx5_priv *priv = dev->data->dev_private;
 	unsigned int rxqs_n = dev->data->nb_rx_queues;
 	unsigned int txqs_n = dev->data->nb_tx_queues;
-	unsigned int i;
-	unsigned int j;
-	unsigned int reta_idx_n;
 	const uint8_t use_app_rss_key =
 		!!dev->data->dev_conf.rx_adv_conf.rss_conf.rss_key;
 	int ret = 0;
@@ -431,28 +428,8 @@ struct ethtool_link_settings {
 		DRV_LOG(INFO, "port %u Rx queues number update: %u -> %u",
 			dev->data->port_id, priv->rxqs_n, rxqs_n);
 		priv->rxqs_n = rxqs_n;
-		/*
-		 * If the requested number of RX queues is not a power of two,
-		 * use the maximum indirection table size for better balancing.
-		 * The result is always rounded to the next power of two.
-		 */
-		reta_idx_n = (1 << log2above((rxqs_n & (rxqs_n - 1)) ?
-					     priv->config.ind_table_max_size :
-					     rxqs_n));
-		ret = mlx5_rss_reta_index_resize(dev, reta_idx_n);
-		if (ret)
-			return ret;
-		/*
-		 * When the number of RX queues is not a power of two,
-		 * the remaining table entries are padded with reused WQs
-		 * and hashes are not spread uniformly.
-		 */
-		for (i = 0, j = 0; (i != reta_idx_n); ++i) {
-			(*priv->reta_idx)[i] = j;
-			if (++j == rxqs_n)
-				j = 0;
-		}
 	}
+	priv->skip_default_rss_reta = 0;
 	ret = mlx5_proc_priv_init(dev);
 	if (ret)
 		return ret;
@@ -460,6 +437,83 @@ struct ethtool_link_settings {
 }
 
 /**
+ * Configure default RSS reta.
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_dev_configure_rss_reta(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	unsigned int rxqs_n = dev->data->nb_rx_queues;
+	unsigned int i;
+	unsigned int j;
+	unsigned int reta_idx_n;
+	int ret = 0;
+	unsigned int *rss_queue_arr = NULL;
+	unsigned int rss_queue_n = 0;
+
+	if (priv->skip_default_rss_reta)
+		return ret;
+	rss_queue_arr = rte_malloc("", rxqs_n * sizeof(unsigned int), 0);
+	if (!rss_queue_arr) {
+		DRV_LOG(ERR, "port %u cannot allocate RSS queue list (%u)",
+			dev->data->port_id, rxqs_n);
+		rte_errno = ENOMEM;
+		return -rte_errno;
+	}
+	for (i = 0, j = 0; i < rxqs_n; i++) {
+		struct mlx5_rxq_data *rxq_data;
+		struct mlx5_rxq_ctrl *rxq_ctrl;
+
+		rxq_data = (*priv->rxqs)[i];
+		rxq_ctrl = container_of(rxq_data, struct mlx5_rxq_ctrl, rxq);
+		if (rxq_ctrl->type == MLX5_RXQ_TYPE_STANDARD)
+			rss_queue_arr[j++] = i;
+	}
+	rss_queue_n = j;
+	if (rss_queue_n > priv->config.ind_table_max_size) {
+		DRV_LOG(ERR, "port %u cannot handle this many Rx queues (%u)",
+			dev->data->port_id, rss_queue_n);
+		rte_errno = EINVAL;
+		rte_free(rss_queue_arr);
+		return -rte_errno;
+	}
+	DRV_LOG(INFO, "port %u Rx queues number update: %u -> %u",
+		dev->data->port_id, priv->rxqs_n, rxqs_n);
+	priv->rxqs_n = rxqs_n;
+	/*
+	 * If the requested number of RX queues is not a power of two,
+	 * use the maximum indirection table size for better balancing.
+	 * The result is always rounded to the next power of two.
+	 */
+	reta_idx_n = (1 << log2above((rss_queue_n & (rss_queue_n - 1)) ?
+				priv->config.ind_table_max_size :
+				rss_queue_n));
+	ret = mlx5_rss_reta_index_resize(dev, reta_idx_n);
+	if (ret) {
+		rte_free(rss_queue_arr);
+		return ret;
+	}
+	/*
+	 * When the number of RX queues is not a power of two,
+	 * the remaining table entries are padded with reused WQs
+	 * and hashes are not spread uniformly.
+	 */
+	for (i = 0, j = 0; (i != reta_idx_n); ++i) {
+		(*priv->reta_idx)[i] = rss_queue_arr[j];
+		if (++j == rss_queue_n)
+			j = 0;
+	}
+	rte_free(rss_queue_arr);
+	return ret;
+}
+
+/**
  * Sets default tuning parameters.
  *
  * @param dev
diff --git a/drivers/net/mlx5/mlx5_rss.c b/drivers/net/mlx5/mlx5_rss.c
index 891d764..1028264 100644
--- a/drivers/net/mlx5/mlx5_rss.c
+++ b/drivers/net/mlx5/mlx5_rss.c
@@ -223,6 +223,7 @@
 	}
 	if (dev->data->dev_started) {
 		mlx5_dev_stop(dev);
+		priv->skip_default_rss_reta = 1;
 		return mlx5_dev_start(dev);
 	}
 	return 0;
diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index c70e161..2c3d5eb 100644
--- a/drivers/net/mlx5/mlx5_rxq.c
+++ b/drivers/net/mlx5/mlx5_rxq.c
@@ -2156,9 +2156,13 @@ struct mlx5_rxq_ctrl *
 		}
 	} else { /* ind_tbl->type == MLX5_IND_TBL_TYPE_DEVX */
 		struct mlx5_devx_rqt_attr *rqt_attr = NULL;
+		const unsigned int rqt_n =
+			1 << (rte_is_power_of_2(queues_n) ?
+			      log2above(queues_n) :
+			      log2above(priv->config.ind_table_max_size));
 
 		rqt_attr = rte_calloc(__func__, 1, sizeof(*rqt_attr) +
-				      queues_n * sizeof(uint32_t), 0);
+				      rqt_n * sizeof(uint32_t), 0);
 		if (!rqt_attr) {
 			DRV_LOG(ERR, "port %u cannot allocate RQT resources",
 				dev->data->port_id);
@@ -2166,7 +2170,7 @@ struct mlx5_rxq_ctrl *
 			goto error;
 		}
 		rqt_attr->rqt_max_size = priv->config.ind_table_max_size;
-		rqt_attr->rqt_actual_size = queues_n;
+		rqt_attr->rqt_actual_size = rqt_n;
 		for (i = 0; i != queues_n; ++i) {
 			struct mlx5_rxq_ctrl *rxq = mlx5_rxq_get(dev,
 								 queues[i]);
@@ -2175,6 +2179,9 @@ struct mlx5_rxq_ctrl *
 			rqt_attr->rq_list[i] = rxq->obj->rq->id;
 			ind_tbl->queues[i] = queues[i];
 		}
+		k = i; /* Retain value of i for use in error case. */
+		for (j = 0; k != rqt_n; ++k, ++j)
+			rqt_attr->rq_list[k] = rqt_attr->rq_list[j];
 		ind_tbl->rqt = mlx5_devx_cmd_create_rqt(priv->sh->ctx,
 							rqt_attr);
 		rte_free(rqt_attr);
@@ -2328,13 +2335,13 @@ struct mlx5_hrxq *
 	struct mlx5_ind_table_obj *ind_tbl;
 	int err;
 	struct mlx5_devx_obj *tir = NULL;
+	struct mlx5_rxq_data *rxq_data = (*priv->rxqs)[queues[0]];
+	struct mlx5_rxq_ctrl *rxq_ctrl =
+		container_of(rxq_data, struct mlx5_rxq_ctrl, rxq);
 
 	queues_n = hash_fields ? queues_n : 1;
 	ind_tbl = mlx5_ind_table_obj_get(dev, queues, queues_n);
 	if (!ind_tbl) {
-		struct mlx5_rxq_data *rxq_data = (*priv->rxqs)[queues[0]];
-		struct mlx5_rxq_ctrl *rxq_ctrl =
-			container_of(rxq_data, struct mlx5_rxq_ctrl, rxq);
 		enum mlx5_ind_tbl_type type;
 
 		type = rxq_ctrl->obj->type == MLX5_RXQ_OBJ_TYPE_IBV ?
@@ -2430,7 +2437,10 @@ struct mlx5_hrxq *
 		tir_attr.rx_hash_fn = MLX5_RX_HASH_FN_TOEPLITZ;
 		memcpy(&tir_attr.rx_hash_field_selector_outer, &hash_fields,
 		       sizeof(uint64_t));
-		tir_attr.transport_domain = priv->sh->tdn;
+		if (rxq_ctrl->obj->type == MLX5_RXQ_OBJ_TYPE_DEVX_HAIRPIN)
+			tir_attr.transport_domain = priv->sh->td->id;
+		else
+			tir_attr.transport_domain = priv->sh->tdn;
 		memcpy(tir_attr.rx_hash_toeplitz_key, rss_key, rss_key_len);
 		tir_attr.indirect_table = ind_tbl->rqt->id;
 		if (dev->data->dev_conf.lpbk_mode)
diff --git a/drivers/net/mlx5/mlx5_trigger.c b/drivers/net/mlx5/mlx5_trigger.c
index a4fcdb3..f66b6ee 100644
--- a/drivers/net/mlx5/mlx5_trigger.c
+++ b/drivers/net/mlx5/mlx5_trigger.c
@@ -269,6 +269,12 @@
 	int ret;
 
 	DRV_LOG(DEBUG, "port %u starting device", dev->data->port_id);
+	ret = mlx5_dev_configure_rss_reta(dev);
+	if (ret) {
+		DRV_LOG(ERR, "port %u reta config failed: %s",
+			dev->data->port_id, strerror(rte_errno));
+		return -rte_errno;
+	}
 	ret = mlx5_txq_start(dev);
 	if (ret) {
 		DRV_LOG(ERR, "port %u Tx queue allocation failed: %s",
-- 
1.8.3.1