[PATCH 2/4] net/mlx5: configure Tx queue with send on time offload

[Viacheslav Ovsiienko <viacheslavo@nvidia.com>]

The wait on time configuration flag is copied to the Tx queue
structure due to performance considerations. Timestamp
mask is preparted and stored in queue structure as well.

Signed-off-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
---
 drivers/net/mlx5/linux/mlx5_verbs.c |  2 ++
 drivers/net/mlx5/mlx5.h             |  3 +++
 drivers/net/mlx5/mlx5_devx.c        |  2 ++
 drivers/net/mlx5/mlx5_tx.h          |  3 +++
 drivers/net/mlx5/mlx5_txq.c         | 11 ++++++++++-
 5 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/net/mlx5/linux/mlx5_verbs.c b/drivers/net/mlx5/linux/mlx5_verbs.c
index 2b6eef44a7..80dd0bb6c1 100644
--- a/drivers/net/mlx5/linux/mlx5_verbs.c
+++ b/drivers/net/mlx5/linux/mlx5_verbs.c
@@ -1036,6 +1036,8 @@ mlx5_txq_ibv_obj_new(struct rte_eth_dev *dev, uint16_t idx)
 	txq_data->wqe_pi = 0;
 	txq_data->wqe_comp = 0;
 	txq_data->wqe_thres = txq_data->wqe_s / MLX5_TX_COMP_THRESH_INLINE_DIV;
+	txq_data->wait_on_time = !!(!priv->config.tx_pp &&
+				     priv->config.hca_attr.wait_on_time);
 #ifdef HAVE_IBV_FLOW_DV_SUPPORT
 	/*
 	 * If using DevX need to query and store TIS transport domain value.
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index 737ad6895c..3983d3aa50 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -341,6 +341,9 @@ struct mlx5_lb_ctx {
 #define MLX5_CNT_ARRAY_IDX(pool, cnt) \
 	((int)(((uint8_t *)(cnt) - (uint8_t *)((pool) + 1)) / \
 	MLX5_CNT_LEN(pool)))
+#define MLX5_TS_MASK_SECS 8ull
+/* timestamp wrapping in seconds, must be  power of 2. */
+
 /*
  * The pool index and offset of counter in the pool array makes up the
  * counter index. In case the counter is from pool 0 and offset 0, it
diff --git a/drivers/net/mlx5/mlx5_devx.c b/drivers/net/mlx5/mlx5_devx.c
index 91243f684f..c6994e4a75 100644
--- a/drivers/net/mlx5/mlx5_devx.c
+++ b/drivers/net/mlx5/mlx5_devx.c
@@ -1327,6 +1327,8 @@ mlx5_txq_devx_obj_new(struct rte_eth_dev *dev, uint16_t idx)
 	txq_data->qp_num_8s = txq_obj->sq_obj.sq->id << 8;
 	txq_data->db_heu = sh->cdev->config.dbnc == MLX5_TXDB_HEURISTIC;
 	txq_data->db_nc = sh->tx_uar.dbnc;
+	txq_data->wait_on_time = !!(!priv->config.tx_pp &&
+				     priv->config.hca_attr.wait_on_time);
 	/* Change Send Queue state to Ready-to-Send. */
 	ret = mlx5_txq_devx_modify(txq_obj, MLX5_TXQ_MOD_RST2RDY, 0);
 	if (ret) {
diff --git a/drivers/net/mlx5/mlx5_tx.h b/drivers/net/mlx5/mlx5_tx.h
index c4b8271f6f..b50deb8b67 100644
--- a/drivers/net/mlx5/mlx5_tx.h
+++ b/drivers/net/mlx5/mlx5_tx.h
@@ -138,6 +138,8 @@ struct mlx5_txq_data {
 	uint16_t vlan_en:1; /* VLAN insertion in WQE is supported. */
 	uint16_t db_nc:1; /* Doorbell mapped to non-cached region. */
 	uint16_t db_heu:1; /* Doorbell heuristic write barrier. */
+	uint16_t rt_timestamp:1; /* Realtime timestamp format. */
+	uint16_t wait_on_time:1; /* WQE with timestamp is supported. */
 	uint16_t fast_free:1; /* mbuf fast free on Tx is enabled. */
 	uint16_t inlen_send; /* Ordinary send data inline size. */
 	uint16_t inlen_empw; /* eMPW max packet size to inline. */
@@ -157,6 +159,7 @@ struct mlx5_txq_data {
 	volatile uint32_t *cq_db; /* Completion queue doorbell. */
 	uint16_t port_id; /* Port ID of device. */
 	uint16_t idx; /* Queue index. */
+	uint64_t rt_timemask; /* Scheduling timestamp mask. */
 	uint64_t ts_mask; /* Timestamp flag dynamic mask. */
 	int32_t ts_offset; /* Timestamp field dynamic offset. */
 	struct mlx5_dev_ctx_shared *sh; /* Shared context. */
diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c
index 4e0bf7af9c..3585546628 100644
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_txq.c
@@ -108,7 +108,7 @@ mlx5_get_tx_port_offloads(struct rte_eth_dev *dev)
 			     RTE_ETH_TX_OFFLOAD_TCP_CKSUM);
 	if (config->tso)
 		offloads |= RTE_ETH_TX_OFFLOAD_TCP_TSO;
-	if (config->tx_pp)
+	if (config->tx_pp || config->hca_attr.wait_on_time)
 		offloads |= RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP;
 	if (config->swp) {
 		if (config->swp & MLX5_SW_PARSING_CSUM_CAP)
@@ -1290,7 +1290,14 @@ mlx5_txq_dynf_timestamp_set(struct rte_eth_dev *dev)
 	int off, nbit;
 	unsigned int i;
 	uint64_t mask = 0;
+	uint64_t ts_mask;
 
+	if (priv->config.rt_timestamp || !priv->config.hca_attr.dev_freq_khz)
+		ts_mask = MLX5_TS_MASK_SECS << 32;
+	else
+		ts_mask = rte_align64pow2(MLX5_TS_MASK_SECS * 1000ull *
+					  priv->config.hca_attr.dev_freq_khz);
+	ts_mask = rte_cpu_to_be_64(ts_mask - 1ull);
 	nbit = rte_mbuf_dynflag_lookup
 				(RTE_MBUF_DYNFLAG_TX_TIMESTAMP_NAME, NULL);
 	off = rte_mbuf_dynfield_lookup
@@ -1304,5 +1311,7 @@ mlx5_txq_dynf_timestamp_set(struct rte_eth_dev *dev)
 		data->sh = sh;
 		data->ts_mask = mask;
 		data->ts_offset = off;
+		data->rt_timestamp = priv->config.rt_timestamp;
+		data->rt_timemask = ts_mask;
 	}
 }
-- 
2.18.1