From: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
To: <dev@dpdk.org>
Cc: <rasland@nvidia.com>, <matan@nvidia.com>, <suanmingm@nvidia.com>,
<stable@dpdk.org>, Edwin Brossette <edwin.brossette@6wind.com>,
"Dariusz Sosnowski" <dsosnowski@nvidia.com>
Subject: [PATCH] net/mlx5: fix the maximal queue size query
Date: Tue, 29 Apr 2025 15:25:56 +0300 [thread overview]
Message-ID: <20250429122556.214279-1-viacheslavo@nvidia.com> (raw)
In-Reply-To: <CANDF9xANRqeTnkvAk61y=2TCd2fsWDQQ4YoTFdpL-RW8ksDDGQ@mail.gmail.com>
The mlx5 PMD manages the device using two modes: the Verbs API
and the DevX API. Each API offers its own method for querying
the maximum work queue size (in descriptors).
The corrected patch enhanced the rte_eth_dev_info_get() API
support in mlx5 PMD to return the true maximum number of descriptors.
It also implemented a limit check during queue creation, but this
was applied only to "DevX mode." Consequently, the "Verbs mode"
was overlooked, leading to malfunction on legacy NICs that do
not support DevX.
This patch adds support for Verbs mode, and all limit checks are
updated accordingly.
Fixes: 4c3d7961d900 ("net/mlx5: fix reported Rx/Tx descriptor limits")
Cc: stable@dpdk.org
Reported-by: Edwin Brossette <edwin.brossette@6wind.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
Acked-by: Dariusz Sosnowski <dsosnowski@nvidia.com>
---
drivers/common/mlx5/mlx5_prm.h | 1 +
drivers/net/mlx5/mlx5.h | 1 +
drivers/net/mlx5/mlx5_devx.c | 2 +-
drivers/net/mlx5/mlx5_ethdev.c | 39 +++++++++++++++++++++++++++++----
drivers/net/mlx5/mlx5_rxq.c | 2 +-
drivers/net/mlx5/mlx5_trigger.c | 4 ++--
drivers/net/mlx5/mlx5_txq.c | 12 +++++-----
7 files changed, 47 insertions(+), 14 deletions(-)
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 742c274a85..7accdeab87 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -41,6 +41,7 @@
/* Hardware index widths. */
#define MLX5_CQ_INDEX_WIDTH 24
#define MLX5_WQ_INDEX_WIDTH 16
+#define MLX5_WQ_INDEX_MAX (1u << (MLX5_WQ_INDEX_WIDTH - 1))
/* WQE Segment sizes in bytes. */
#define MLX5_WSEG_SIZE 16u
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index 0194887a8b..ff182996d3 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -2303,6 +2303,7 @@ int mlx5_representor_info_get(struct rte_eth_dev *dev,
(((repr_id) >> 12) & 3)
uint16_t mlx5_representor_id_encode(const struct mlx5_switch_info *info,
enum rte_eth_representor_type hpf_type);
+uint16_t mlx5_dev_get_max_wq_size(struct mlx5_dev_ctx_shared *sh);
int mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info);
int mlx5_fw_version_get(struct rte_eth_dev *dev, char *fw_ver, size_t fw_size);
const uint32_t *mlx5_dev_supported_ptypes_get(struct rte_eth_dev *dev,
diff --git a/drivers/net/mlx5/mlx5_devx.c b/drivers/net/mlx5/mlx5_devx.c
index a12891a983..9711746edb 100644
--- a/drivers/net/mlx5/mlx5_devx.c
+++ b/drivers/net/mlx5/mlx5_devx.c
@@ -1593,7 +1593,7 @@ mlx5_txq_devx_obj_new(struct rte_eth_dev *dev, uint16_t idx)
wqe_size = RTE_ALIGN(wqe_size, MLX5_WQE_SIZE) / MLX5_WQE_SIZE;
/* Create Send Queue object with DevX. */
wqe_n = RTE_MIN((1UL << txq_data->elts_n) * wqe_size,
- (uint32_t)priv->sh->dev_cap.max_qp_wr);
+ (uint32_t)mlx5_dev_get_max_wq_size(priv->sh));
log_desc_n = log2above(wqe_n);
ret = mlx5_txq_create_devx_sq_resources(dev, idx, log_desc_n);
if (ret) {
diff --git a/drivers/net/mlx5/mlx5_ethdev.c b/drivers/net/mlx5/mlx5_ethdev.c
index 7708a0b808..7f12194f30 100644
--- a/drivers/net/mlx5/mlx5_ethdev.c
+++ b/drivers/net/mlx5/mlx5_ethdev.c
@@ -314,6 +314,37 @@ mlx5_set_txlimit_params(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
info->tx_desc_lim.nb_mtu_seg_max = nb_max;
}
+/**
+ * Get maximal work queue size in WQEs
+ *
+ * @param sh
+ * Pointer to the device shared context.
+ * @return
+ * Maximal number of WQEs in queue
+ */
+uint16_t
+mlx5_dev_get_max_wq_size(struct mlx5_dev_ctx_shared *sh)
+{
+ uint16_t max_wqe = MLX5_WQ_INDEX_MAX;
+
+ if (sh->cdev->config.devx) {
+ /* use HCA properties for DevX config */
+ MLX5_ASSERT(sh->cdev->config.hca_attr.log_max_wq_sz != 0);
+ MLX5_ASSERT(sh->cdev->config.hca_attr.log_max_wq_sz < MLX5_WQ_INDEX_WIDTH);
+ if (sh->cdev->config.hca_attr.log_max_wq_sz != 0 &&
+ sh->cdev->config.hca_attr.log_max_wq_sz < MLX5_WQ_INDEX_WIDTH)
+ max_wqe = 1u << sh->cdev->config.hca_attr.log_max_wq_sz;
+ } else {
+ /* use IB device capabilities */
+ MLX5_ASSERT(sh->dev_cap.max_qp_wr > 0);
+ MLX5_ASSERT(sh->dev_cap.max_qp_wr <= MLX5_WQ_INDEX_MAX);
+ if (sh->dev_cap.max_qp_wr > 0 &&
+ (uint32_t)sh->dev_cap.max_qp_wr <= MLX5_WQ_INDEX_MAX)
+ max_wqe = (uint16_t)sh->dev_cap.max_qp_wr;
+ }
+ return max_wqe;
+}
+
/**
* DPDK callback to get information about the device.
*
@@ -327,6 +358,7 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
{
struct mlx5_priv *priv = dev->data->dev_private;
unsigned int max;
+ uint16_t max_wqe;
/* FIXME: we should ask the device for these values. */
info->min_rx_bufsize = 32;
@@ -359,10 +391,9 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
info->flow_type_rss_offloads = ~MLX5_RSS_HF_MASK;
mlx5_set_default_params(dev, info);
mlx5_set_txlimit_params(dev, info);
- info->rx_desc_lim.nb_max =
- 1 << priv->sh->cdev->config.hca_attr.log_max_wq_sz;
- info->tx_desc_lim.nb_max =
- 1 << priv->sh->cdev->config.hca_attr.log_max_wq_sz;
+ max_wqe = mlx5_dev_get_max_wq_size(priv->sh);
+ info->rx_desc_lim.nb_max = max_wqe;
+ info->tx_desc_lim.nb_max = max_wqe;
if (priv->sh->cdev->config.hca_attr.mem_rq_rmp &&
priv->obj_ops.rxq_obj_new == devx_obj_ops.rxq_obj_new)
info->dev_capa |= RTE_ETH_DEV_CAPA_RXQ_SHARE;
diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index 5cf7d4971b..a8aaab13c8 100644
--- a/drivers/net/mlx5/mlx5_rxq.c
+++ b/drivers/net/mlx5/mlx5_rxq.c
@@ -655,7 +655,7 @@ mlx5_rx_queue_pre_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t *desc,
struct mlx5_rxq_priv *rxq;
bool empty;
- if (*desc > 1 << priv->sh->cdev->config.hca_attr.log_max_wq_sz) {
+ if (*desc > mlx5_dev_get_max_wq_size(priv->sh)) {
DRV_LOG(ERR,
"port %u number of descriptors requested for Rx queue"
" %u is more than supported",
diff --git a/drivers/net/mlx5/mlx5_trigger.c b/drivers/net/mlx5/mlx5_trigger.c
index 4ee44e9165..8145ad4233 100644
--- a/drivers/net/mlx5/mlx5_trigger.c
+++ b/drivers/net/mlx5/mlx5_trigger.c
@@ -217,8 +217,8 @@ mlx5_rxq_start(struct rte_eth_dev *dev)
/* Should not release Rx queues but return immediately. */
return -rte_errno;
}
- DRV_LOG(DEBUG, "Port %u dev_cap.max_qp_wr is %d.",
- dev->data->port_id, priv->sh->dev_cap.max_qp_wr);
+ DRV_LOG(DEBUG, "Port %u max work queue size is %d.",
+ dev->data->port_id, mlx5_dev_get_max_wq_size(priv->sh));
DRV_LOG(DEBUG, "Port %u dev_cap.max_sge is %d.",
dev->data->port_id, priv->sh->dev_cap.max_sge);
for (i = 0; i != priv->rxqs_n; ++i) {
diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c
index 3e93517323..b14a1a4379 100644
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_txq.c
@@ -333,7 +333,7 @@ mlx5_tx_queue_pre_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t *desc)
{
struct mlx5_priv *priv = dev->data->dev_private;
- if (*desc > 1 << priv->sh->cdev->config.hca_attr.log_max_wq_sz) {
+ if (*desc > mlx5_dev_get_max_wq_size(priv->sh)) {
DRV_LOG(ERR,
"port %u number of descriptors requested for Tx queue"
" %u is more than supported",
@@ -727,7 +727,7 @@ txq_calc_inline_max(struct mlx5_txq_ctrl *txq_ctrl)
struct mlx5_priv *priv = txq_ctrl->priv;
unsigned int wqe_size;
- wqe_size = priv->sh->dev_cap.max_qp_wr / desc;
+ wqe_size = mlx5_dev_get_max_wq_size(priv->sh) / desc;
if (!wqe_size)
return 0;
/*
@@ -1082,6 +1082,7 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
{
struct mlx5_priv *priv = dev->data->dev_private;
struct mlx5_txq_ctrl *tmpl;
+ uint16_t max_wqe;
tmpl = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO, sizeof(*tmpl) +
desc * sizeof(struct rte_mbuf *), 0, socket);
@@ -1107,13 +1108,12 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
txq_set_params(tmpl);
if (txq_adjust_params(tmpl))
goto error;
- if (txq_calc_wqebb_cnt(tmpl) >
- priv->sh->dev_cap.max_qp_wr) {
+ max_wqe = mlx5_dev_get_max_wq_size(priv->sh);
+ if (txq_calc_wqebb_cnt(tmpl) > max_wqe) {
DRV_LOG(ERR,
"port %u Tx WQEBB count (%d) exceeds the limit (%d),"
" try smaller queue size",
- dev->data->port_id, txq_calc_wqebb_cnt(tmpl),
- priv->sh->dev_cap.max_qp_wr);
+ dev->data->port_id, txq_calc_wqebb_cnt(tmpl), max_wqe);
rte_errno = ENOMEM;
goto error;
}
--
2.34.1
parent reply other threads:[~2025-04-29 12:26 UTC|newest]
Thread overview: expand[flat|nested] mbox.gz Atom feed
[parent not found: <CANDF9xANRqeTnkvAk61y=2TCd2fsWDQQ4YoTFdpL-RW8ksDDGQ@mail.gmail.com>]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250429122556.214279-1-viacheslavo@nvidia.com \
--to=viacheslavo@nvidia.com \
--cc=dev@dpdk.org \
--cc=dsosnowski@nvidia.com \
--cc=edwin.brossette@6wind.com \
--cc=matan@nvidia.com \
--cc=rasland@nvidia.com \
--cc=stable@dpdk.org \
--cc=suanmingm@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).