Acked-by: Viacheslav Ovsiienko <[email protected]>
> -----Original Message-----
> From: Vincent Jardin <[email protected]>
> Sent: Sunday, March 22, 2026 3:46 PM
> To: [email protected]
> Cc: Raslan Darawsheh <[email protected]>; NBU-Contact-Thomas Monjalon
> (EXTERNAL) <[email protected]>; [email protected];
> Dariusz Sosnowski <[email protected]>; Slava Ovsiienko
> <[email protected]>; Bing Zhao <[email protected]>; Ori Kam
> <[email protected]>; Suanming Mou <[email protected]>; Matan Azrad
> <[email protected]>; [email protected];
> [email protected]; Vincent Jardin <[email protected]>
> Subject: [PATCH v4 10/10] net/mlx5: add rate table capacity query API
>
> Add rte_pmd_mlx5_pp_rate_table_query() to report the HW packet pacing
> rate table size and how many entries are used by this port.
>
> The total comes from the HCA QoS capability packet_pacing_rate_table_size.
> The port_used count is derived by collecting unique non-zero PP indices across
> this port's TX queues.
>
> The rate table is a global shared HW resource: firmware, kernel, other DPDK
> ports on the same device, and other application instances may all consume
> entries. The port_used count is therefore a lower bound of actual HW usage.
>
> With shared PP allocation (flags=0), the kernel mlx5 driver reuses a single
> rate
> table entry for all PP contexts with identical parameters (rate, burst, packet
> size). Multiple queues configured with the same rate share one pp_id, so
> port_used counts unique entries, not the number of queues with rate limiting
> enabled.
>
> Applications that need device-wide visibility should query all ports on the
> same
> physical device and aggregate the results, similar to how the kernel mlx5
> driver
> tracks usage internally.
>
> Signed-off-by: Vincent Jardin <[email protected]>
> ---
> drivers/net/mlx5/mlx5_tx.c | 64 +++++++++++++++++++++++++++++++++
> drivers/net/mlx5/rte_pmd_mlx5.h | 44 +++++++++++++++++++++++
> 2 files changed, 108 insertions(+)
>
> diff --git a/drivers/net/mlx5/mlx5_tx.c b/drivers/net/mlx5/mlx5_tx.c index
> 7d71782d33..615b792836 100644
> --- a/drivers/net/mlx5/mlx5_tx.c
> +++ b/drivers/net/mlx5/mlx5_tx.c
> @@ -19,6 +19,7 @@
>
> #include <mlx5_prm.h>
> #include <mlx5_common.h>
> +#include <mlx5_malloc.h>
>
> #include "mlx5_autoconf.h"
> #include "mlx5_defs.h"
> @@ -886,3 +887,66 @@ int rte_pmd_mlx5_txq_rate_limit_query(uint16_t
> port_id, uint16_t queue_id,
> packet_pacing_rate_limit_index);
> return 0;
> }
> +
> +RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_pmd_mlx5_pp_rate_table_query,
> 26.07)
> +int rte_pmd_mlx5_pp_rate_table_query(uint16_t port_id,
> + struct rte_pmd_mlx5_pp_rate_table_info
> *info) {
> + struct rte_eth_dev *dev;
> + struct mlx5_priv *priv;
> + uint16_t used = 0;
> + uint16_t *seen;
> + unsigned int i;
> +
> + if (info == NULL)
> + return -EINVAL;
> + if (!rte_eth_dev_is_valid_port(port_id))
> + return -ENODEV;
> + dev = &rte_eth_devices[port_id];
> + priv = dev->data->dev_private;
> + if (!priv->sh->cdev->config.hca_attr.qos.packet_pacing) {
> + rte_errno = ENOTSUP;
> + return -ENOTSUP;
> + }
> + info->total = priv->sh->cdev-
> >config.hca_attr.qos.packet_pacing_rate_table_size;
> + if (priv->txqs == NULL || priv->txqs_n == 0) {
> + info->port_used = 0;
> + return 0;
> + }
> + seen = mlx5_malloc(MLX5_MEM_SYS | MLX5_MEM_ZERO,
> + priv->txqs_n * sizeof(*seen), 0, SOCKET_ID_ANY);
> + if (seen == NULL)
> + return -ENOMEM;
> + /*
> + * Count unique non-zero PP indices across this port's TX queues.
> + * Note: the count reflects only queues on this port; other ports
> + * sharing the same device may also consume rate table entries.
> + */
> + for (i = 0; i < priv->txqs_n; i++) {
> + struct mlx5_txq_data *txq_data;
> + struct mlx5_txq_ctrl *txq_ctrl;
> + uint16_t pp_id;
> + uint16_t j;
> + bool dup;
> +
> + if ((*priv->txqs)[i] == NULL)
> + continue;
> + txq_data = (*priv->txqs)[i];
> + txq_ctrl = container_of(txq_data, struct mlx5_txq_ctrl, txq);
> + pp_id = txq_ctrl->rate_limit.pp_id;
> + if (pp_id == 0)
> + continue;
> + dup = false;
> + for (j = 0; j < used; j++) {
> + if (seen[j] == pp_id) {
> + dup = true;
> + break;
> + }
> + }
> + if (!dup)
> + seen[used++] = pp_id;
> + }
> + mlx5_free(seen);
> + info->port_used = used;
> + return 0;
> +}
> diff --git a/drivers/net/mlx5/rte_pmd_mlx5.h
> b/drivers/net/mlx5/rte_pmd_mlx5.h index 698d7d2032..621d8c2b15 100644
> --- a/drivers/net/mlx5/rte_pmd_mlx5.h
> +++ b/drivers/net/mlx5/rte_pmd_mlx5.h
> @@ -450,6 +450,50 @@ int
> rte_pmd_mlx5_txq_rate_limit_query(uint16_t port_id, uint16_t queue_id,
> struct rte_pmd_mlx5_txq_rate_limit_info
> *info);
>
> +/**
> + * Packet pacing rate table capacity information.
> + */
> +struct rte_pmd_mlx5_pp_rate_table_info {
> + uint16_t total; /**< Total HW rate table entries. */
> + uint16_t port_used; /**< Entries used by this port's TX queues. */
> +};
> +
> +/**
> + * Query packet pacing rate table capacity.
> + *
> + * The ``port_used`` count reflects only unique PP indices allocated
> + * by the queried port's TX queues. It is a lower bound of actual HW
> + * usage because the rate table is a global shared resource:
> + * - Other DPDK ports on the same physical device may hold entries.
> + * - The kernel mlx5 driver and firmware may also consume entries.
> + * - Multiple DPDK application instances may share the device.
> + *
> + * When multiple queues on the same port are configured with identical
> + * rate parameters, the kernel shares a single rate table entry across
> + * them (with flags=0 allocation), so ``port_used`` counts unique
> + * entries, not the number of queues with rate limiting enabled.
> + *
> + * Applications that need device-wide visibility should query all
> + * ports on the same physical device and aggregate the results,
> + * similar to how the kernel mlx5 driver tracks usage internally.
> + *
> + * @param[in] port_id
> + * Port ID.
> + * @param[out] info
> + * Rate table capacity information.
> + *
> + * @return
> + * 0 on success, negative errno on failure:
> + * - -ENODEV: invalid port_id.
> + * - -EINVAL: info is NULL.
> + * - -ENOTSUP: packet pacing not supported.
> + * - -ENOMEM: allocation failure.
> + */
> +__rte_experimental
> +int
> +rte_pmd_mlx5_pp_rate_table_query(uint16_t port_id,
> + struct rte_pmd_mlx5_pp_rate_table_info
> *info);
> +
> /** Type of mlx5 driver event for which custom callback is called. */ enum
> rte_pmd_mlx5_driver_event_cb_type {
> /** Called after HW Rx queue is created. */
> --
> 2.43.0
