Wire rte_eth_set_queue_rate_limit() to the mlx5 PMD. The callback allocates a per-queue PP index with the requested data rate, then modifies the live SQ via modify_bitmask bit 0 to apply the new packet_pacing_rate_limit_index — no queue teardown required.
Setting tx_rate=0 clears the PP index on the SQ and frees it. Capability check uses hca_attr.qos.packet_pacing directly (not dev_cap.txpp_en which requires Clock Queue prerequisites). This allows per-queue rate limiting without the tx_pp devarg. The callback rejects hairpin queues and queues whose SQ is not yet created. testpmd usage (no testpmd changes needed): set port 0 queue 0 rate 1000 set port 0 queue 1 rate 5000 set port 0 queue 0 rate 0 # disable Supported hardware: - ConnectX-6 Dx: full support, per-SQ rate via HW rate table - ConnectX-7/8: full support, coexists with wait-on-time scheduling - BlueField-2/3: full support as DPU rep ports Not supported: - ConnectX-5: packet_pacing exists but dynamic SQ modify may not work on all firmware versions - ConnectX-4 Lx and earlier: no packet_pacing capability Signed-off-by: Vincent Jardin <[email protected]> --- drivers/net/mlx5/mlx5.c | 2 + drivers/net/mlx5/mlx5_tx.h | 2 + drivers/net/mlx5/mlx5_txq.c | 97 +++++++++++++++++++++++++++++++++++++ 3 files changed, 101 insertions(+) diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index 4d3bfddc36..c390406ac7 100644 --- a/drivers/net/mlx5/mlx5.c +++ b/drivers/net/mlx5/mlx5.c @@ -2690,6 +2690,7 @@ const struct eth_dev_ops mlx5_dev_ops = { .map_aggr_tx_affinity = mlx5_map_aggr_tx_affinity, .rx_metadata_negotiate = mlx5_flow_rx_metadata_negotiate, .get_restore_flags = mlx5_get_restore_flags, + .set_queue_rate_limit = mlx5_set_queue_rate_limit, }; /* Available operations from secondary process. */ @@ -2783,6 +2784,7 @@ const struct eth_dev_ops mlx5_dev_ops_isolate = { .count_aggr_ports = mlx5_count_aggr_ports, .map_aggr_tx_affinity = mlx5_map_aggr_tx_affinity, .get_restore_flags = mlx5_get_restore_flags, + .set_queue_rate_limit = mlx5_set_queue_rate_limit, }; /** diff --git a/drivers/net/mlx5/mlx5_tx.h b/drivers/net/mlx5/mlx5_tx.h index b1b3653247..3a37f5bb4d 100644 --- a/drivers/net/mlx5/mlx5_tx.h +++ b/drivers/net/mlx5/mlx5_tx.h @@ -222,6 +222,8 @@ struct mlx5_txq_ctrl *mlx5_txq_get(struct rte_eth_dev *dev, uint16_t idx); int mlx5_txq_release(struct rte_eth_dev *dev, uint16_t idx); int mlx5_txq_releasable(struct rte_eth_dev *dev, uint16_t idx); int mlx5_txq_verify(struct rte_eth_dev *dev); +int mlx5_set_queue_rate_limit(struct rte_eth_dev *dev, uint16_t queue_idx, + uint32_t tx_rate); int mlx5_txq_get_sqn(struct mlx5_txq_ctrl *txq); void mlx5_txq_alloc_elts(struct mlx5_txq_ctrl *txq_ctrl); void mlx5_txq_free_elts(struct mlx5_txq_ctrl *txq_ctrl); diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c index fa9bb48fd4..f2ed2454a0 100644 --- a/drivers/net/mlx5/mlx5_txq.c +++ b/drivers/net/mlx5/mlx5_txq.c @@ -1363,6 +1363,103 @@ mlx5_txq_release(struct rte_eth_dev *dev, uint16_t idx) return 0; } +/** + * Set per-queue packet pacing rate limit. + * + * @param dev + * Pointer to Ethernet device. + * @param queue_idx + * TX queue index. + * @param tx_rate + * TX rate in Mbps, 0 to disable rate limiting. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +int +mlx5_set_queue_rate_limit(struct rte_eth_dev *dev, uint16_t queue_idx, + uint32_t tx_rate) +{ + struct mlx5_priv *priv = dev->data->dev_private; + struct mlx5_dev_ctx_shared *sh = priv->sh; + struct mlx5_txq_ctrl *txq_ctrl; + struct mlx5_devx_modify_sq_attr sq_attr = { 0 }; + int ret; + + if (!sh->cdev->config.hca_attr.qos.packet_pacing) { + DRV_LOG(ERR, "Port %u packet pacing not supported.", + dev->data->port_id); + rte_errno = ENOTSUP; + return -rte_errno; + } + if (priv->txqs == NULL || (*priv->txqs)[queue_idx] == NULL) { + DRV_LOG(ERR, "Port %u Tx queue %u not configured.", + dev->data->port_id, queue_idx); + rte_errno = EINVAL; + return -rte_errno; + } + txq_ctrl = container_of((*priv->txqs)[queue_idx], + struct mlx5_txq_ctrl, txq); + if (txq_ctrl->is_hairpin) { + DRV_LOG(ERR, "Port %u Tx queue %u is hairpin.", + dev->data->port_id, queue_idx); + rte_errno = EINVAL; + return -rte_errno; + } + if (txq_ctrl->obj == NULL || txq_ctrl->obj->sq == NULL) { + DRV_LOG(ERR, "Port %u Tx queue %u SQ not ready.", + dev->data->port_id, queue_idx); + rte_errno = EINVAL; + return -rte_errno; + } + if (tx_rate == 0) { + /* Disable rate limiting. */ + if (txq_ctrl->rl.pp_id == 0) + return 0; /* Already disabled. */ + sq_attr.sq_state = MLX5_SQC_STATE_RDY; + sq_attr.state = MLX5_SQC_STATE_RDY; + sq_attr.rl_update = 1; + sq_attr.packet_pacing_rate_limit_index = 0; + ret = mlx5_devx_cmd_modify_sq(txq_ctrl->obj->sq, &sq_attr); + if (ret) { + DRV_LOG(ERR, + "Port %u Tx queue %u failed to clear rate.", + dev->data->port_id, queue_idx); + rte_errno = -ret; + return ret; + } + mlx5_txq_free_pp_rate_limit(&txq_ctrl->rl); + DRV_LOG(DEBUG, "Port %u Tx queue %u rate limit disabled.", + dev->data->port_id, queue_idx); + return 0; + } + /* Allocate a new PP index for the requested rate into a temp. */ + struct mlx5_txq_rate_limit new_rl = { 0 }; + + ret = mlx5_txq_alloc_pp_rate_limit(sh, &new_rl, tx_rate); + if (ret) + return ret; + /* Modify live SQ to use the new PP index. */ + sq_attr.sq_state = MLX5_SQC_STATE_RDY; + sq_attr.state = MLX5_SQC_STATE_RDY; + sq_attr.rl_update = 1; + sq_attr.packet_pacing_rate_limit_index = new_rl.pp_id; + ret = mlx5_devx_cmd_modify_sq(txq_ctrl->obj->sq, &sq_attr); + if (ret) { + DRV_LOG(ERR, "Port %u Tx queue %u failed to set rate %u Mbps.", + dev->data->port_id, queue_idx, tx_rate); + mlx5_txq_free_pp_rate_limit(&new_rl); + rte_errno = -ret; + return ret; + } + /* SQ updated — release old PP context, install new one. */ + mlx5_txq_free_pp_rate_limit(&txq_ctrl->rl); + txq_ctrl->rl = new_rl; + DRV_LOG(DEBUG, "Port %u Tx queue %u rate set to %u Mbps (PP idx %u).", + dev->data->port_id, queue_idx, tx_rate, txq_ctrl->rl.pp_id); + return 0; +} + /** * Verify if the queue can be released. * -- 2.43.0
