Message-ID: <20250619113721.60201-5-mbloch@nvidia.com>
Date: Thu, 19 Jun 2025 14:37:20 +0300
From: Mark Bloch <mbloch@...dia.com>
To: "David S. Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>,
	Paolo Abeni <pabeni@...hat.com>, Eric Dumazet <edumazet@...gle.com>, "Andrew
 Lunn" <andrew+netdev@...n.ch>, Simon Horman <horms@...nel.org>
CC: <saeedm@...dia.com>, <gal@...dia.com>, <leonro@...dia.com>,
	<tariqt@...dia.com>, Leon Romanovsky <leon@...nel.org>, Jonathan Corbet
	<corbet@....net>, <netdev@...r.kernel.org>, <linux-rdma@...r.kernel.org>,
	<linux-doc@...r.kernel.org>, <linux-kernel@...r.kernel.org>, Dragos Tatulea
	<dtatulea@...dia.com>, Mark Bloch <mbloch@...dia.com>
Subject: [PATCH net-next 4/5] net/mlx5e: Add device PCIe congestion ethtool stats

From: Dragos Tatulea <dtatulea@...dia.com>

Implement the PCIe Congestion Event notifier which triggers a work item
to query the PCIe Congestion Event object. The result of the congestion
state is reflected in the new ethtool stats:

* pci_bw_inbound_high: the device has crossed the high threshold for
  inbound PCIe traffic.
* pci_bw_inbound_low: the device has crossed the low threshold for
  inbound PCIe traffic
* pci_bw_outbound_high: the device has crossed the high threshold for
  outbound PCIe traffic.
* pci_bw_outbound_low: the device has crossed the low threshold for
  outbound PCIe traffic

The high and low thresholds are currently configured at 90% and 75%.
These are hysteresis thresholds which help to check if the
PCI bus on the device side is in a congested state.

If low + 1 = high then the device is in a congested state. If low == high
then the device is not in a congested state.

The counters are also documented.

A follow-up patch will make the thresholds configurable.

Signed-off-by: Dragos Tatulea <dtatulea@...dia.com>
Reviewed-by: Tariq Toukan <tariqt@...dia.com>
Signed-off-by: Mark Bloch <mbloch@...dia.com>
---
 .../ethernet/mellanox/mlx5/counters.rst       |  32 ++++
 .../mellanox/mlx5/core/en/pcie_cong_event.c   | 175 ++++++++++++++++++
 .../ethernet/mellanox/mlx5/core/en_stats.c    |   1 +
 .../ethernet/mellanox/mlx5/core/en_stats.h    |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/eq.c  |   4 +
 5 files changed, 213 insertions(+)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
index 43d72c8b713b..754c81436408 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
@@ -1341,3 +1341,35 @@ Device Counters
      - The number of times the device owned queue had not enough buffers
        allocated.
      - Error
+
+   * - `pci_bw_inbound_high`
+     - The number of times the device crossed the high inbound pcie bandwidth
+       threshold. To be compared to pci_bw_inbound_low to check if the device
+       is in a congested state.
+       If pci_bw_inbound_high == pci_bw_inbound_low then the device is not congested.
+       If pci_bw_inbound_high > pci_bw_inbound_low then the device is congested.
+     - Tnformative
+
+   * - `pci_bw_inbound_low`
+     - The number of times the device crossed the low inbound PCIe bandwidth
+       threshold. To be compared to pci_bw_inbound_high to check if the device
+       is in a congested state.
+       If pci_bw_inbound_high == pci_bw_inbound_low then the device is not congested.
+       If pci_bw_inbound_high > pci_bw_inbound_low then the device is congested.
+     - Informative
+
+   * - `pci_bw_outbound_high`
+     - The number of times the device crossed the high outbound pcie bandwidth
+       threshold. To be compared to pci_bw_outbound_low to check if the device
+       is in a congested state.
+       If pci_bw_outbound_high == pci_bw_outbound_low then the device is not congested.
+       If pci_bw_outbound_high > pci_bw_outbound_low then the device is congested.
+     - Informative
+
+   * - `pci_bw_outbound_low`
+     - The number of times the device crossed the low outbound PCIe bandwidth
+       threshold. To be compared to pci_bw_outbound_high to check if the device
+       is in a congested state.
+       If pci_bw_outbound_high == pci_bw_outbound_low then the device is not congested.
+       If pci_bw_outbound_high > pci_bw_outbound_low then the device is congested.
+     - Informative
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c
index 95a6db9d30b3..a24e5465ceeb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c
@@ -4,6 +4,13 @@
 #include "en.h"
 #include "pcie_cong_event.h"
 
+#define MLX5E_CONG_HIGH_STATE 0x7
+
+enum {
+	MLX5E_INBOUND_CONG  = BIT(0),
+	MLX5E_OUTBOUND_CONG = BIT(1),
+};
+
 struct mlx5e_pcie_cong_thresh {
 	u16 inbound_high;
 	u16 inbound_low;
@@ -11,10 +18,27 @@ struct mlx5e_pcie_cong_thresh {
 	u16 outbound_low;
 };
 
+struct mlx5e_pcie_cong_stats {
+	u32 pci_bw_inbound_high;
+	u32 pci_bw_inbound_low;
+	u32 pci_bw_outbound_high;
+	u32 pci_bw_outbound_low;
+};
+
 struct mlx5e_pcie_cong_event {
 	u64 obj_id;
 
 	struct mlx5e_priv *priv;
+
+	/* For event notifier and workqueue. */
+	struct work_struct work;
+	struct mlx5_nb nb;
+
+	/* Stores last read state. */
+	u8 state;
+
+	/* For ethtool stats group. */
+	struct mlx5e_pcie_cong_stats stats;
 };
 
 /* In units of 0.01 % */
@@ -25,6 +49,51 @@ static const struct mlx5e_pcie_cong_thresh default_thresh_config = {
 	.outbound_low = 7500,
 };
 
+static const struct counter_desc mlx5e_pcie_cong_stats_desc[] = {
+	{ MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats,
+			     pci_bw_inbound_high) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats,
+			     pci_bw_inbound_low) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats,
+			     pci_bw_outbound_high) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats,
+			     pci_bw_outbound_low) },
+};
+
+#define NUM_PCIE_CONG_COUNTERS ARRAY_SIZE(mlx5e_pcie_cong_stats_desc)
+
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(pcie_cong)
+{
+	return priv->cong_event ? NUM_PCIE_CONG_COUNTERS : 0;
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(pcie_cong) {}
+
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(pcie_cong)
+{
+	if (!priv->cong_event)
+		return;
+
+	for (int i = 0; i < NUM_PCIE_CONG_COUNTERS; i++)
+		ethtool_puts(data, mlx5e_pcie_cong_stats_desc[i].format);
+}
+
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pcie_cong)
+{
+	if (!priv->cong_event)
+		return;
+
+	for (int i = 0; i < NUM_PCIE_CONG_COUNTERS; i++) {
+		u32 ctr = MLX5E_READ_CTR32_CPU(&priv->cong_event->stats,
+					       mlx5e_pcie_cong_stats_desc,
+					       i);
+
+		mlx5e_ethtool_put_stat(data, ctr);
+	}
+}
+
+MLX5E_DEFINE_STATS_GRP(pcie_cong, 0);
+
 static int
 mlx5_cmd_pcie_cong_event_set(struct mlx5_core_dev *dev,
 			     const struct mlx5e_pcie_cong_thresh *config,
@@ -89,6 +158,97 @@ static int mlx5_cmd_pcie_cong_event_destroy(struct mlx5_core_dev *dev,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
+static int mlx5_cmd_pcie_cong_event_query(struct mlx5_core_dev *dev,
+					  u64 obj_id,
+					  u32 *state)
+{
+	u32 in[MLX5_ST_SZ_DW(pcie_cong_event_cmd_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(pcie_cong_event_cmd_out)];
+	void *obj;
+	void *hdr;
+	u8 cong;
+	int err;
+
+	hdr = MLX5_ADDR_OF(pcie_cong_event_cmd_in, in, hdr);
+
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, opcode,
+		 MLX5_CMD_OP_QUERY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_type,
+		 MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT);
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_id, obj_id);
+
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	obj = MLX5_ADDR_OF(pcie_cong_event_cmd_out, out, cong_obj);
+
+	if (state) {
+		cong = MLX5_GET(pcie_cong_event_obj, obj, inbound_cong_state);
+		if (cong == MLX5E_CONG_HIGH_STATE)
+			*state |= MLX5E_INBOUND_CONG;
+
+		cong = MLX5_GET(pcie_cong_event_obj, obj, outbound_cong_state);
+		if (cong == MLX5E_CONG_HIGH_STATE)
+			*state |= MLX5E_OUTBOUND_CONG;
+	}
+
+	return 0;
+}
+
+static void mlx5e_pcie_cong_event_work(struct work_struct *work)
+{
+	struct mlx5e_pcie_cong_event *cong_event;
+	struct mlx5_core_dev *dev;
+	struct mlx5e_priv *priv;
+	u32 new_cong_state = 0;
+	u32 changes;
+	int err;
+
+	cong_event = container_of(work, struct mlx5e_pcie_cong_event, work);
+	priv = cong_event->priv;
+	dev = priv->mdev;
+
+	err = mlx5_cmd_pcie_cong_event_query(dev, cong_event->obj_id,
+					     &new_cong_state);
+	if (err) {
+		mlx5_core_warn(dev, "Error %d when querying PCIe cong event object (obj_id=%llu).\n",
+			       err, cong_event->obj_id);
+		return;
+	}
+
+	changes = cong_event->state ^ new_cong_state;
+	if (!changes)
+		return;
+
+	cong_event->state = new_cong_state;
+
+	if (changes & MLX5E_INBOUND_CONG) {
+		if (new_cong_state & MLX5E_INBOUND_CONG)
+			cong_event->stats.pci_bw_inbound_high++;
+		else
+			cong_event->stats.pci_bw_inbound_low++;
+	}
+
+	if (changes & MLX5E_OUTBOUND_CONG) {
+		if (new_cong_state & MLX5E_OUTBOUND_CONG)
+			cong_event->stats.pci_bw_outbound_high++;
+		else
+			cong_event->stats.pci_bw_outbound_low++;
+	}
+}
+
+static int mlx5e_pcie_cong_event_handler(struct notifier_block *nb,
+					 unsigned long event, void *eqe)
+{
+	struct mlx5e_pcie_cong_event *cong_event;
+
+	cong_event = mlx5_nb_cof(nb, struct mlx5e_pcie_cong_event, nb);
+	queue_work(cong_event->priv->wq, &cong_event->work);
+
+	return NOTIFY_OK;
+}
+
 bool mlx5e_pcie_cong_event_supported(struct mlx5_core_dev *dev)
 {
 	u64 features = MLX5_CAP_GEN_2_64(dev, general_obj_types_127_64);
@@ -116,6 +276,10 @@ int mlx5e_pcie_cong_event_init(struct mlx5e_priv *priv)
 	if (!cong_event)
 		return -ENOMEM;
 
+	INIT_WORK(&cong_event->work, mlx5e_pcie_cong_event_work);
+	MLX5_NB_INIT(&cong_event->nb, mlx5e_pcie_cong_event_handler,
+		     OBJECT_CHANGE);
+
 	cong_event->priv = priv;
 
 	err = mlx5_cmd_pcie_cong_event_set(mdev, &default_thresh_config,
@@ -125,10 +289,18 @@ int mlx5e_pcie_cong_event_init(struct mlx5e_priv *priv)
 		goto err_free;
 	}
 
+	err = mlx5_eq_notifier_register(mdev, &cong_event->nb);
+	if (err) {
+		mlx5_core_warn(mdev, "Error registering notifier for the PCIe congestion event\n");
+		goto err_obj_destroy;
+	}
+
 	priv->cong_event = cong_event;
 
 	return 0;
 
+err_obj_destroy:
+	mlx5_cmd_pcie_cong_event_destroy(mdev, cong_event->obj_id);
 err_free:
 	kvfree(cong_event);
 
@@ -145,6 +317,9 @@ void mlx5e_pcie_cong_event_cleanup(struct mlx5e_priv *priv)
 
 	priv->cong_event = NULL;
 
+	mlx5_eq_notifier_unregister(mdev, &cong_event->nb);
+	cancel_work_sync(&cong_event->work);
+
 	if (mlx5_cmd_pcie_cong_event_destroy(mdev, cong_event->obj_id))
 		mlx5_core_warn(mdev, "Error destroying PCIe congestion event (obj_id=%llu)\n",
 			       cong_event->obj_id);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 19664fa7f217..87536f158d07 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -2612,6 +2612,7 @@ mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = {
 #ifdef CONFIG_MLX5_MACSEC
 	&MLX5E_STATS_GRP(macsec_hw),
 #endif
+	&MLX5E_STATS_GRP(pcie_cong),
 };
 
 unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index def5dea1463d..72dbcc1928ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -535,5 +535,6 @@ extern MLX5E_DECLARE_STATS_GRP(ipsec_hw);
 extern MLX5E_DECLARE_STATS_GRP(ipsec_sw);
 extern MLX5E_DECLARE_STATS_GRP(ptp);
 extern MLX5E_DECLARE_STATS_GRP(macsec_hw);
+extern MLX5E_DECLARE_STATS_GRP(pcie_cong);
 
 #endif /* __MLX5_EN_STATS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index dfb079e59d85..db54f6d26591 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -21,6 +21,7 @@
 #include "pci_irq.h"
 #include "devlink.h"
 #include "en_accel/ipsec.h"
+#include "en/pcie_cong_event.h"
 
 enum {
 	MLX5_EQE_OWNER_INIT_VAL	= 0x1,
@@ -585,6 +586,9 @@ static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4])
 		async_event_mask |=
 			(1ull << MLX5_EVENT_TYPE_OBJECT_CHANGE);
 
+	if (mlx5e_pcie_cong_event_supported(dev))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_OBJECT_CHANGE);
+
 	mask[0] = async_event_mask;
 
 	if (MLX5_CAP_GEN(dev, event_cap))
-- 
2.34.1

Powered by blists - more mailing lists