[dpdk-dev] [PATCH v5 04/15] net/mlx5: support Rx hairpin queues

[Ori Kam <orika@mellanox.com>]

This commit adds the support for creating Rx hairpin queues.
Hairpin queue is a queue that is created using DevX and only used
by the HW. This results in that all the data part of the RQ is not being
used.

Signed-off-by: Ori Kam <orika@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
---
 drivers/net/mlx5/mlx5.c         |   2 +
 drivers/net/mlx5/mlx5_rxq.c     | 270 ++++++++++++++++++++++++++++++++++++----
 drivers/net/mlx5/mlx5_rxtx.h    |  15 +++
 drivers/net/mlx5/mlx5_trigger.c |   7 ++
 4 files changed, 270 insertions(+), 24 deletions(-)

diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index fac5105..6be423f 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -985,6 +985,7 @@ struct mlx5_dev_spawn_data {
 	.dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get,
 	.vlan_filter_set = mlx5_vlan_filter_set,
 	.rx_queue_setup = mlx5_rx_queue_setup,
+	.rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup,
 	.tx_queue_setup = mlx5_tx_queue_setup,
 	.rx_queue_release = mlx5_rx_queue_release,
 	.tx_queue_release = mlx5_tx_queue_release,
@@ -1051,6 +1052,7 @@ struct mlx5_dev_spawn_data {
 	.dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get,
 	.vlan_filter_set = mlx5_vlan_filter_set,
 	.rx_queue_setup = mlx5_rx_queue_setup,
+	.rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup,
 	.tx_queue_setup = mlx5_tx_queue_setup,
 	.rx_queue_release = mlx5_rx_queue_release,
 	.tx_queue_release = mlx5_tx_queue_release,
diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index f0ab843..c70e161 100644
--- a/drivers/net/mlx5/mlx5_rxq.c
+++ b/drivers/net/mlx5/mlx5_rxq.c
@@ -106,21 +106,25 @@
 	struct mlx5_priv *priv = dev->data->dev_private;
 	uint16_t i;
 	uint16_t n = 0;
+	uint16_t n_ibv = 0;
 
 	if (mlx5_check_mprq_support(dev) < 0)
 		return 0;
 	/* All the configured queues should be enabled. */
 	for (i = 0; i < priv->rxqs_n; ++i) {
 		struct mlx5_rxq_data *rxq = (*priv->rxqs)[i];
+		struct mlx5_rxq_ctrl *rxq_ctrl = container_of
+			(rxq, struct mlx5_rxq_ctrl, rxq);
 
-		if (!rxq)
+		if (rxq == NULL || rxq_ctrl->type != MLX5_RXQ_TYPE_STANDARD)
 			continue;
+		n_ibv++;
 		if (mlx5_rxq_mprq_enabled(rxq))
 			++n;
 	}
 	/* Multi-Packet RQ can't be partially configured. */
-	assert(n == 0 || n == priv->rxqs_n);
-	return n == priv->rxqs_n;
+	assert(n == 0 || n == n_ibv);
+	return n == n_ibv;
 }
 
 /**
@@ -427,6 +431,7 @@
 }
 
 /**
+ * Rx queue presetup checks.
  *
  * @param dev
  *   Pointer to Ethernet device structure.
@@ -434,25 +439,14 @@
  *   RX queue index.
  * @param desc
  *   Number of descriptors to configure in queue.
- * @param socket
- *   NUMA socket on which memory must be allocated.
- * @param[in] conf
- *   Thresholds parameters.
- * @param mp
- *   Memory pool for buffer allocations.
  *
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
-int
-mlx5_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
-		    unsigned int socket, const struct rte_eth_rxconf *conf,
-		    struct rte_mempool *mp)
+static int
+mlx5_rx_queue_pre_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc)
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
-	struct mlx5_rxq_data *rxq = (*priv->rxqs)[idx];
-	struct mlx5_rxq_ctrl *rxq_ctrl =
-		container_of(rxq, struct mlx5_rxq_ctrl, rxq);
 
 	if (!rte_is_power_of_2(desc)) {
 		desc = 1 << log2above(desc);
@@ -476,6 +470,41 @@
 		return -rte_errno;
 	}
 	mlx5_rxq_release(dev, idx);
+	return 0;
+}
+
+/**
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param idx
+ *   RX queue index.
+ * @param desc
+ *   Number of descriptors to configure in queue.
+ * @param socket
+ *   NUMA socket on which memory must be allocated.
+ * @param[in] conf
+ *   Thresholds parameters.
+ * @param mp
+ *   Memory pool for buffer allocations.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
+		    unsigned int socket, const struct rte_eth_rxconf *conf,
+		    struct rte_mempool *mp)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_rxq_data *rxq = (*priv->rxqs)[idx];
+	struct mlx5_rxq_ctrl *rxq_ctrl =
+		container_of(rxq, struct mlx5_rxq_ctrl, rxq);
+	int res;
+
+	res = mlx5_rx_queue_pre_setup(dev, idx, desc);
+	if (res)
+		return res;
 	rxq_ctrl = mlx5_rxq_new(dev, idx, desc, socket, conf, mp);
 	if (!rxq_ctrl) {
 		DRV_LOG(ERR, "port %u unable to allocate queue index %u",
@@ -490,6 +519,56 @@
 }
 
 /**
+ *
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param idx
+ *   RX queue index.
+ * @param desc
+ *   Number of descriptors to configure in queue.
+ * @param hairpin_conf
+ *   Hairpin configuration parameters.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_rx_hairpin_queue_setup(struct rte_eth_dev *dev, uint16_t idx,
+			    uint16_t desc,
+			    const struct rte_eth_hairpin_conf *hairpin_conf)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_rxq_data *rxq = (*priv->rxqs)[idx];
+	struct mlx5_rxq_ctrl *rxq_ctrl =
+		container_of(rxq, struct mlx5_rxq_ctrl, rxq);
+	int res;
+
+	res = mlx5_rx_queue_pre_setup(dev, idx, desc);
+	if (res)
+		return res;
+	if (hairpin_conf->peer_count != 1 ||
+	    hairpin_conf->peers[0].port != dev->data->port_id ||
+	    hairpin_conf->peers[0].queue >= priv->txqs_n) {
+		DRV_LOG(ERR, "port %u unable to setup hairpin queue index %u "
+			" invalid hairpind configuration", dev->data->port_id,
+			idx);
+		rte_errno = EINVAL;
+		return -rte_errno;
+	}
+	rxq_ctrl = mlx5_rxq_hairpin_new(dev, idx, desc, hairpin_conf);
+	if (!rxq_ctrl) {
+		DRV_LOG(ERR, "port %u unable to allocate queue index %u",
+			dev->data->port_id, idx);
+		rte_errno = ENOMEM;
+		return -rte_errno;
+	}
+	DRV_LOG(DEBUG, "port %u adding Rx queue %u to list",
+		dev->data->port_id, idx);
+	(*priv->rxqs)[idx] = &rxq_ctrl->rxq;
+	return 0;
+}
+
+/**
  * DPDK callback to release a RX queue.
  *
  * @param dpdk_rxq
@@ -561,6 +640,24 @@
 }
 
 /**
+ * Release an Rx hairpin related resources.
+ *
+ * @param rxq_obj
+ *   Hairpin Rx queue object.
+ */
+static void
+rxq_obj_hairpin_release(struct mlx5_rxq_obj *rxq_obj)
+{
+	struct mlx5_devx_modify_rq_attr rq_attr = { 0 };
+
+	assert(rxq_obj);
+	rq_attr.state = MLX5_RQC_STATE_RST;
+	rq_attr.rq_state = MLX5_RQC_STATE_RDY;
+	mlx5_devx_cmd_modify_rq(rxq_obj->rq, &rq_attr);
+	claim_zero(mlx5_devx_cmd_destroy(rxq_obj->rq));
+}
+
+/**
  * Release an Rx verbs/DevX queue object.
  *
  * @param rxq_obj
@@ -577,14 +674,22 @@
 		assert(rxq_obj->wq);
 	assert(rxq_obj->cq);
 	if (rte_atomic32_dec_and_test(&rxq_obj->refcnt)) {
-		rxq_free_elts(rxq_obj->rxq_ctrl);
-		if (rxq_obj->type == MLX5_RXQ_OBJ_TYPE_IBV) {
+		switch (rxq_obj->type) {
+		case MLX5_RXQ_OBJ_TYPE_IBV:
+			rxq_free_elts(rxq_obj->rxq_ctrl);
 			claim_zero(mlx5_glue->destroy_wq(rxq_obj->wq));
-		} else if (rxq_obj->type == MLX5_RXQ_OBJ_TYPE_DEVX_RQ) {
+			claim_zero(mlx5_glue->destroy_cq(rxq_obj->cq));
+			break;
+		case MLX5_RXQ_OBJ_TYPE_DEVX_RQ:
+			rxq_free_elts(rxq_obj->rxq_ctrl);
 			claim_zero(mlx5_devx_cmd_destroy(rxq_obj->rq));
 			rxq_release_rq_resources(rxq_obj->rxq_ctrl);
+			claim_zero(mlx5_glue->destroy_cq(rxq_obj->cq));
+			break;
+		case MLX5_RXQ_OBJ_TYPE_DEVX_HAIRPIN:
+			rxq_obj_hairpin_release(rxq_obj);
+			break;
 		}
-		claim_zero(mlx5_glue->destroy_cq(rxq_obj->cq));
 		if (rxq_obj->channel)
 			claim_zero(mlx5_glue->destroy_comp_channel
 				   (rxq_obj->channel));
@@ -1132,6 +1237,70 @@
 }
 
 /**
+ * Create the Rx hairpin queue object.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param idx
+ *   Queue index in DPDK Rx queue array
+ *
+ * @return
+ *   The hairpin DevX object initialised, NULL otherwise and rte_errno is set.
+ */
+static struct mlx5_rxq_obj *
+mlx5_rxq_obj_hairpin_new(struct rte_eth_dev *dev, uint16_t idx)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_rxq_data *rxq_data = (*priv->rxqs)[idx];
+	struct mlx5_rxq_ctrl *rxq_ctrl =
+		container_of(rxq_data, struct mlx5_rxq_ctrl, rxq);
+	struct mlx5_devx_create_rq_attr attr = { 0 };
+	struct mlx5_rxq_obj *tmpl = NULL;
+	int ret = 0;
+
+	assert(rxq_data);
+	assert(!rxq_ctrl->obj);
+	tmpl = rte_calloc_socket(__func__, 1, sizeof(*tmpl), 0,
+				 rxq_ctrl->socket);
+	if (!tmpl) {
+		DRV_LOG(ERR,
+			"port %u Rx queue %u cannot allocate verbs resources",
+			dev->data->port_id, rxq_data->idx);
+		rte_errno = ENOMEM;
+		goto error;
+	}
+	tmpl->type = MLX5_RXQ_OBJ_TYPE_DEVX_HAIRPIN;
+	tmpl->rxq_ctrl = rxq_ctrl;
+	attr.hairpin = 1;
+	/* Workaround for hairpin startup */
+	attr.wq_attr.log_hairpin_num_packets = log2above(32);
+	/* Workaround for packets larger than 1KB */
+	attr.wq_attr.log_hairpin_data_sz =
+			priv->config.hca_attr.log_max_hairpin_wq_data_sz;
+	tmpl->rq = mlx5_devx_cmd_create_rq(priv->sh->ctx, &attr,
+					   rxq_ctrl->socket);
+	if (!tmpl->rq) {
+		DRV_LOG(ERR,
+			"port %u Rx hairpin queue %u can't create rq object",
+			dev->data->port_id, idx);
+		rte_errno = errno;
+		goto error;
+	}
+	DRV_LOG(DEBUG, "port %u rxq %u updated with %p", dev->data->port_id,
+		idx, (void *)&tmpl);
+	rte_atomic32_inc(&tmpl->refcnt);
+	LIST_INSERT_HEAD(&priv->rxqsobj, tmpl, next);
+	priv->verbs_alloc_ctx.type = MLX5_VERBS_ALLOC_TYPE_NONE;
+	return tmpl;
+error:
+	ret = rte_errno; /* Save rte_errno before cleanup. */
+	if (tmpl->rq)
+		mlx5_devx_cmd_destroy(tmpl->rq);
+	rte_errno = ret; /* Restore rte_errno. */
+	return NULL;
+}
+
+/**
  * Create the Rx queue Verbs/DevX object.
  *
  * @param dev
@@ -1163,6 +1332,8 @@ struct mlx5_rxq_obj *
 
 	assert(rxq_data);
 	assert(!rxq_ctrl->obj);
+	if (type == MLX5_RXQ_OBJ_TYPE_DEVX_HAIRPIN)
+		return mlx5_rxq_obj_hairpin_new(dev, idx);
 	priv->verbs_alloc_ctx.type = MLX5_VERBS_ALLOC_TYPE_RX_QUEUE;
 	priv->verbs_alloc_ctx.obj = rxq_ctrl;
 	tmpl = rte_calloc_socket(__func__, 1, sizeof(*tmpl), 0,
@@ -1433,15 +1604,19 @@ struct mlx5_rxq_obj *
 	unsigned int strd_num_n = 0;
 	unsigned int strd_sz_n = 0;
 	unsigned int i;
+	unsigned int n_ibv = 0;
 
 	if (!mlx5_mprq_enabled(dev))
 		return 0;
 	/* Count the total number of descriptors configured. */
 	for (i = 0; i != priv->rxqs_n; ++i) {
 		struct mlx5_rxq_data *rxq = (*priv->rxqs)[i];
+		struct mlx5_rxq_ctrl *rxq_ctrl = container_of
+			(rxq, struct mlx5_rxq_ctrl, rxq);
 
-		if (rxq == NULL)
+		if (rxq == NULL || rxq_ctrl->type != MLX5_RXQ_TYPE_STANDARD)
 			continue;
+		n_ibv++;
 		desc += 1 << rxq->elts_n;
 		/* Get the max number of strides. */
 		if (strd_num_n < rxq->strd_num_n)
@@ -1466,7 +1641,7 @@ struct mlx5_rxq_obj *
 	 * this Mempool gets available again.
 	 */
 	desc *= 4;
-	obj_num = desc + MLX5_MPRQ_MP_CACHE_SZ * priv->rxqs_n;
+	obj_num = desc + MLX5_MPRQ_MP_CACHE_SZ * n_ibv;
 	/*
 	 * rte_mempool_create_empty() has sanity check to refuse large cache
 	 * size compared to the number of elements.
@@ -1514,8 +1689,10 @@ struct mlx5_rxq_obj *
 	/* Set mempool for each Rx queue. */
 	for (i = 0; i != priv->rxqs_n; ++i) {
 		struct mlx5_rxq_data *rxq = (*priv->rxqs)[i];
+		struct mlx5_rxq_ctrl *rxq_ctrl = container_of
+			(rxq, struct mlx5_rxq_ctrl, rxq);
 
-		if (rxq == NULL)
+		if (rxq == NULL || rxq_ctrl->type != MLX5_RXQ_TYPE_STANDARD)
 			continue;
 		rxq->mprq_mp = mp;
 	}
@@ -1620,6 +1797,7 @@ struct mlx5_rxq_ctrl *
 		rte_errno = ENOMEM;
 		return NULL;
 	}
+	tmpl->type = MLX5_RXQ_TYPE_STANDARD;
 	if (mlx5_mr_btree_init(&tmpl->rxq.mr_ctrl.cache_bh,
 			       MLX5_MR_BTREE_CACHE_N, socket)) {
 		/* rte_errno is already set. */
@@ -1788,6 +1966,49 @@ struct mlx5_rxq_ctrl *
 }
 
 /**
+ * Create a DPDK Rx hairpin queue.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param idx
+ *   RX queue index.
+ * @param desc
+ *   Number of descriptors to configure in queue.
+ * @param hairpin_conf
+ *   The hairpin binding configuration.
+ *
+ * @return
+ *   A DPDK queue object on success, NULL otherwise and rte_errno is set.
+ */
+struct mlx5_rxq_ctrl *
+mlx5_rxq_hairpin_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
+		     const struct rte_eth_hairpin_conf *hairpin_conf)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_rxq_ctrl *tmpl;
+
+	tmpl = rte_calloc_socket("RXQ", 1, sizeof(*tmpl), 0, SOCKET_ID_ANY);
+	if (!tmpl) {
+		rte_errno = ENOMEM;
+		return NULL;
+	}
+	tmpl->type = MLX5_RXQ_TYPE_HAIRPIN;
+	tmpl->socket = SOCKET_ID_ANY;
+	tmpl->rxq.rss_hash = 0;
+	tmpl->rxq.port_id = dev->data->port_id;
+	tmpl->priv = priv;
+	tmpl->rxq.mp = NULL;
+	tmpl->rxq.elts_n = log2above(desc);
+	tmpl->rxq.elts = NULL;
+	tmpl->rxq.mr_ctrl.cache_bh = (struct mlx5_mr_btree) { 0 };
+	tmpl->hairpin_conf = *hairpin_conf;
+	tmpl->rxq.idx = idx;
+	rte_atomic32_inc(&tmpl->refcnt);
+	LIST_INSERT_HEAD(&priv->rxqsctrl, tmpl, next);
+	return tmpl;
+}
+
+/**
  * Get a Rx queue.
  *
  * @param dev
@@ -1841,7 +2062,8 @@ struct mlx5_rxq_ctrl *
 		if (rxq_ctrl->dbr_umem_id_valid)
 			claim_zero(mlx5_release_dbr(dev, rxq_ctrl->dbr_umem_id,
 						    rxq_ctrl->dbr_offset));
-		mlx5_mr_btree_free(&rxq_ctrl->rxq.mr_ctrl.cache_bh);
+		if (rxq_ctrl->type == MLX5_RXQ_TYPE_STANDARD)
+			mlx5_mr_btree_free(&rxq_ctrl->rxq.mr_ctrl.cache_bh);
 		LIST_REMOVE(rxq_ctrl, next);
 		rte_free(rxq_ctrl);
 		(*priv->rxqs)[idx] = NULL;
diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h
index 4bb28a4..13fdc38 100644
--- a/drivers/net/mlx5/mlx5_rxtx.h
+++ b/drivers/net/mlx5/mlx5_rxtx.h
@@ -159,6 +159,13 @@ struct mlx5_rxq_data {
 enum mlx5_rxq_obj_type {
 	MLX5_RXQ_OBJ_TYPE_IBV,		/* mlx5_rxq_obj with ibv_wq. */
 	MLX5_RXQ_OBJ_TYPE_DEVX_RQ,	/* mlx5_rxq_obj with mlx5_devx_rq. */
+	MLX5_RXQ_OBJ_TYPE_DEVX_HAIRPIN,
+	/* mlx5_rxq_obj with mlx5_devx_rq and hairpin support. */
+};
+
+enum mlx5_rxq_type {
+	MLX5_RXQ_TYPE_STANDARD, /* Standard Rx queue. */
+	MLX5_RXQ_TYPE_HAIRPIN, /* Hairpin Rx queue. */
 };
 
 /* Verbs/DevX Rx queue elements. */
@@ -183,6 +190,7 @@ struct mlx5_rxq_ctrl {
 	rte_atomic32_t refcnt; /* Reference counter. */
 	struct mlx5_rxq_obj *obj; /* Verbs/DevX elements. */
 	struct mlx5_priv *priv; /* Back pointer to private data. */
+	enum mlx5_rxq_type type; /* Rxq type. */
 	unsigned int socket; /* CPU socket ID for allocations. */
 	unsigned int irq:1; /* Whether IRQ is enabled. */
 	unsigned int dbr_umem_id_valid:1; /* dbr_umem_id holds a valid value. */
@@ -193,6 +201,7 @@ struct mlx5_rxq_ctrl {
 	uint32_t dbr_umem_id; /* Storing door-bell information, */
 	uint64_t dbr_offset;  /* needed when freeing door-bell. */
 	struct mlx5dv_devx_umem *wq_umem; /* WQ buffer registration info. */
+	struct rte_eth_hairpin_conf hairpin_conf; /* Hairpin configuration. */
 };
 
 enum mlx5_ind_tbl_type {
@@ -339,6 +348,9 @@ struct mlx5_txq_ctrl {
 int mlx5_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
 			unsigned int socket, const struct rte_eth_rxconf *conf,
 			struct rte_mempool *mp);
+int mlx5_rx_hairpin_queue_setup
+	(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
+	 const struct rte_eth_hairpin_conf *hairpin_conf);
 void mlx5_rx_queue_release(void *dpdk_rxq);
 int mlx5_rx_intr_vec_enable(struct rte_eth_dev *dev);
 void mlx5_rx_intr_vec_disable(struct rte_eth_dev *dev);
@@ -351,6 +363,9 @@ struct mlx5_rxq_ctrl *mlx5_rxq_new(struct rte_eth_dev *dev, uint16_t idx,
 				   uint16_t desc, unsigned int socket,
 				   const struct rte_eth_rxconf *conf,
 				   struct rte_mempool *mp);
+struct mlx5_rxq_ctrl *mlx5_rxq_hairpin_new
+	(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
+	 const struct rte_eth_hairpin_conf *hairpin_conf);
 struct mlx5_rxq_ctrl *mlx5_rxq_get(struct rte_eth_dev *dev, uint16_t idx);
 int mlx5_rxq_release(struct rte_eth_dev *dev, uint16_t idx);
 int mlx5_rxq_verify(struct rte_eth_dev *dev);
diff --git a/drivers/net/mlx5/mlx5_trigger.c b/drivers/net/mlx5/mlx5_trigger.c
index 122f31c..cb31ae2 100644
--- a/drivers/net/mlx5/mlx5_trigger.c
+++ b/drivers/net/mlx5/mlx5_trigger.c
@@ -118,6 +118,13 @@
 
 		if (!rxq_ctrl)
 			continue;
+		if (rxq_ctrl->type == MLX5_RXQ_TYPE_HAIRPIN) {
+			rxq_ctrl->obj = mlx5_rxq_obj_new
+				(dev, i, MLX5_RXQ_OBJ_TYPE_DEVX_HAIRPIN);
+			if (!rxq_ctrl->obj)
+				goto error;
+			continue;
+		}
 		/* Pre-register Rx mempool. */
 		mp = mlx5_rxq_mprq_enabled(&rxq_ctrl->rxq) ?
 		     rxq_ctrl->rxq.mprq_mp : rxq_ctrl->rxq.mp;
-- 
1.8.3.1