patch 'net/mlx5: fix maximal queue size query' has been queued to stable release 23.11.5
Xueming Li
xuemingl at nvidia.com
Thu Jun 26 14:00:46 CEST 2025
Hi,
FYI, your patch has been queued to stable release 23.11.5
Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 06/28/25. So please
shout if anyone has objections.
Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.
Queued patches are on a temporary branch at:
https://git.dpdk.org/dpdk-stable/log/?h=23.11-staging
This queued commit can be viewed at:
https://git.dpdk.org/dpdk-stable/commit/?h=23.11-staging&id=101a72d85868860c46e834db4c91a1a6f7d42749
Thanks.
Xueming Li <xuemingl at nvidia.com>
---
>From 101a72d85868860c46e834db4c91a1a6f7d42749 Mon Sep 17 00:00:00 2001
From: Viacheslav Ovsiienko <viacheslavo at nvidia.com>
Date: Wed, 14 May 2025 10:55:30 +0300
Subject: [PATCH] net/mlx5: fix maximal queue size query
Cc: Xueming Li <xuemingl at nvidia.com>
[ upstream commit 9de8acd30d5adfc5b9703d15a3e1babc7d4ddacc ]
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")
Reported-by: Edwin Brossette <edwin.brossette at 6wind.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo at nvidia.com>
Acked-by: Dariusz Sosnowski <dsosnowski at 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 79533ff35a..d9e216b635 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 a9129bf61b..75b822785b 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -2122,6 +2122,7 @@ 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 4f08ddf899..3f8fb9512b 100644
--- a/drivers/net/mlx5/mlx5_devx.c
+++ b/drivers/net/mlx5/mlx5_devx.c
@@ -1527,7 +1527,7 @@ 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 8f29e58cda..4218aef032 100644
--- a/drivers/net/mlx5/mlx5_ethdev.c
+++ b/drivers/net/mlx5/mlx5_ethdev.c
@@ -306,6 +306,37 @@ 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((unsigned int)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.
*
@@ -319,6 +350,7 @@ 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;
@@ -351,10 +383,9 @@ 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 7b377974d3..aa8e9316af 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 a4887a8d20..a61128ec21 100644
--- a/drivers/net/mlx5/mlx5_trigger.c
+++ b/drivers/net/mlx5/mlx5_trigger.c
@@ -215,8 +215,8 @@ 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 52a39ae073..0905570f1a 100644
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_txq.c
@@ -332,7 +332,7 @@ 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",
@@ -726,7 +726,7 @@ 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;
/*
@@ -1081,6 +1081,7 @@ 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);
@@ -1106,13 +1107,12 @@ 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
---
Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- - 2025-06-26 19:59:18.980412677 +0800
+++ 0026-net-mlx5-fix-maximal-queue-size-query.patch 2025-06-26 19:59:17.302418047 +0800
@@ -1 +1 @@
-From 9de8acd30d5adfc5b9703d15a3e1babc7d4ddacc Mon Sep 17 00:00:00 2001
+From 101a72d85868860c46e834db4c91a1a6f7d42749 Mon Sep 17 00:00:00 2001
@@ -4,0 +5,3 @@
+Cc: Xueming Li <xuemingl at nvidia.com>
+
+[ upstream commit 9de8acd30d5adfc5b9703d15a3e1babc7d4ddacc ]
@@ -21 +23,0 @@
-Cc: stable at dpdk.org
@@ -37 +39 @@
-index 742c274a85..7accdeab87 100644
+index 79533ff35a..d9e216b635 100644
@@ -49 +51 @@
-index 36f11b9c51..5695d0f54a 100644
+index a9129bf61b..75b822785b 100644
@@ -52 +54 @@
-@@ -2303,6 +2303,7 @@ int mlx5_representor_info_get(struct rte_eth_dev *dev,
+@@ -2122,6 +2122,7 @@ int mlx5_representor_info_get(struct rte_eth_dev *dev,
@@ -59 +61 @@
- const uint32_t *mlx5_dev_supported_ptypes_get(struct rte_eth_dev *dev,
+ const uint32_t *mlx5_dev_supported_ptypes_get(struct rte_eth_dev *dev);
@@ -61 +63 @@
-index a12891a983..9711746edb 100644
+index 4f08ddf899..3f8fb9512b 100644
@@ -64 +66 @@
-@@ -1593,7 +1593,7 @@ mlx5_txq_devx_obj_new(struct rte_eth_dev *dev, uint16_t idx)
+@@ -1527,7 +1527,7 @@ mlx5_txq_devx_obj_new(struct rte_eth_dev *dev, uint16_t idx)
@@ -74 +76 @@
-index 7708a0b808..a50320075c 100644
+index 8f29e58cda..4218aef032 100644
@@ -77 +79 @@
-@@ -314,6 +314,37 @@ mlx5_set_txlimit_params(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
+@@ -306,6 +306,37 @@ mlx5_set_txlimit_params(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
@@ -115 +117 @@
-@@ -327,6 +358,7 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
+@@ -319,6 +350,7 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
@@ -123 +125 @@
-@@ -359,10 +391,9 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
+@@ -351,10 +383,9 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
@@ -138 +140 @@
-index ab29b43875..b676e5394b 100644
+index 7b377974d3..aa8e9316af 100644
@@ -141 +143 @@
-@@ -656,7 +656,7 @@ mlx5_rx_queue_pre_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t *desc,
+@@ -655,7 +655,7 @@ mlx5_rx_queue_pre_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t *desc,
@@ -151 +153 @@
-index 4ee44e9165..8145ad4233 100644
+index a4887a8d20..a61128ec21 100644
@@ -154 +156 @@
-@@ -217,8 +217,8 @@ mlx5_rxq_start(struct rte_eth_dev *dev)
+@@ -215,8 +215,8 @@ mlx5_rxq_start(struct rte_eth_dev *dev)
@@ -166 +168 @@
-index ddd3a66282..5fee5bc4e8 100644
+index 52a39ae073..0905570f1a 100644
@@ -169 +171 @@
-@@ -334,7 +334,7 @@ mlx5_tx_queue_pre_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t *desc)
+@@ -332,7 +332,7 @@ mlx5_tx_queue_pre_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t *desc)
@@ -178 +180 @@
-@@ -728,7 +728,7 @@ txq_calc_inline_max(struct mlx5_txq_ctrl *txq_ctrl)
+@@ -726,7 +726,7 @@ txq_calc_inline_max(struct mlx5_txq_ctrl *txq_ctrl)
@@ -187 +189 @@
-@@ -1054,6 +1054,7 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
+@@ -1081,6 +1081,7 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
@@ -195,2 +197 @@
-@@ -1078,13 +1079,12 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
- tmpl->txq.idx = idx;
+@@ -1106,13 +1107,12 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
@@ -198 +199,2 @@
- txq_adjust_params(tmpl);
+ if (txq_adjust_params(tmpl))
+ goto error;
More information about the stable
mailing list