netdev - [PATCH net-next 10/15] net/mlx5: Expose ICM consumption per function

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250209101716.112774-11-tariqt@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:11 +0200
From: Tariq Toukan <tariqt@...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>
CC: <netdev@...r.kernel.org>, Saeed Mahameed <saeedm@...dia.com>, Gal Pressman
	<gal@...dia.com>, Leon Romanovsky <leonro@...dia.com>, Simon Horman
	<horms@...nel.org>, Donald Hunter <donald.hunter@...il.com>, Jiri Pirko
	<jiri@...nulli.us>, Jonathan Corbet <corbet@....net>, Leon Romanovsky
	<leon@...nel.org>, Tariq Toukan <tariqt@...dia.com>, Alexei Starovoitov
	<ast@...nel.org>, Daniel Borkmann <daniel@...earbox.net>, "Jesper Dangaard
 Brouer" <hawk@...nel.org>, John Fastabend <john.fastabend@...il.com>,
	"Richard Cochran" <richardcochran@...il.com>, <linux-kernel@...r.kernel.org>,
	<linux-doc@...r.kernel.org>, <linux-rdma@...r.kernel.org>,
	<bpf@...r.kernel.org>, Akiva Goldberger <agoldberger@...dia.com>, "Moshe
 Shemesh" <moshe@...dia.com>
Subject: [PATCH net-next 10/15] net/mlx5: Expose ICM consumption per function

From: Akiva Goldberger <agoldberger@...dia.com>

ICM is a portion of the host's memory assigned to a function by the OS
through requests made by the NIC's firmware.

PF ICM consumption can be accessed directly, while VF/SF ICM consumption
can be accessed through their representors in switchdev mode.

The value is exposed to the user in granularity of 4KB through the vnic
health reporter as follows:

$ devlink health diagnose pci/0000:08:00.0 reporter vnic
 vNIC env counters:
     total_error_queues: 0 send_queue_priority_update_flow: 0
     comp_eq_overrun: 0 async_eq_overrun: 0 cq_overrun: 0
     invalid_command: 0 quota_exceeded_command: 0
     nic_receive_steering_discard: 0 icm_consumption: 1032

Signed-off-by: Akiva Goldberger <agoldberger@...dia.com>
Reviewed-by: Moshe Shemesh <moshe@...dia.com>
Signed-off-by: Tariq Toukan <tariqt@...dia.com>
---
 Documentation/networking/devlink/mlx5.rst     |  4 ++
 .../mellanox/mlx5/core/diag/reporter_vnic.c   | 46 +++++++++++++++++++
 2 files changed, 50 insertions(+)

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 41618538fc70..7febe0aecd53 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -280,6 +280,10 @@ Description of the vnic counters:
 	number of packets handled by the VNIC experiencing unexpected steering
 	failure (at any point in steering flow owned by the VNIC, including the FDB
 	for the eswitch owner).
+- icm_consumption
+        amount of Interconnect Host Memory (ICM) consumed by the vnic in
+        granularity of 4KB. ICM is host memory allocated by SW upon HCA request
+        and is used for storing data structures that control HCA operation.
 
 User commands examples:
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
index c7216e84ef8c..86253a89c24c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
@@ -13,6 +13,50 @@ struct mlx5_vnic_diag_stats {
 	__be64 query_vnic_env_out[MLX5_ST_SZ_QW(query_vnic_env_out)];
 };
 
+static void mlx5_reporter_vnic_diagnose_counter_icm(struct mlx5_core_dev *dev,
+						    struct devlink_fmsg *fmsg,
+						    u16 vport_num, bool other_vport)
+{
+	u32 out_icm_reg[MLX5_ST_SZ_DW(vhca_icm_ctrl_reg)] = {};
+	u32 in_icm_reg[MLX5_ST_SZ_DW(vhca_icm_ctrl_reg)] = {};
+	u32 out_reg[MLX5_ST_SZ_DW(nic_cap_reg)] = {};
+	u32 in_reg[MLX5_ST_SZ_DW(nic_cap_reg)] = {};
+	u32 cur_alloc_icm;
+	int vhca_icm_ctrl;
+	u16 vhca_id;
+	int err;
+
+	err = mlx5_core_access_reg(dev, in_reg, sizeof(in_reg), out_reg,
+				   sizeof(out_reg), MLX5_REG_NIC_CAP, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "Reading nic_cap_reg failed. err = %d\n", err);
+		return;
+	}
+	vhca_icm_ctrl = MLX5_GET(nic_cap_reg, out_reg, vhca_icm_ctrl);
+	if (!vhca_icm_ctrl)
+		return;
+
+	MLX5_SET(vhca_icm_ctrl_reg, in_icm_reg, vhca_id_valid, other_vport);
+	if (other_vport) {
+		err = mlx5_vport_get_vhca_id(dev, vport_num, &vhca_id);
+		if (err) {
+			mlx5_core_warn(dev, "vport to vhca_id failed. vport_num = %d, err = %d\n",
+				       vport_num, err);
+			return;
+		}
+		MLX5_SET(vhca_icm_ctrl_reg, in_icm_reg, vhca_id, vhca_id);
+	}
+	err = mlx5_core_access_reg(dev, in_icm_reg, sizeof(in_icm_reg),
+				   out_icm_reg, sizeof(out_icm_reg),
+				   MLX5_REG_VHCA_ICM_CTRL, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "Reading vhca_icm_ctrl failed. err = %d\n", err);
+		return;
+	}
+	cur_alloc_icm = MLX5_GET(vhca_icm_ctrl_reg, out_icm_reg, cur_alloc_icm);
+	devlink_fmsg_u32_pair_put(fmsg, "icm_consumption", cur_alloc_icm);
+}
+
 void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 					  struct devlink_fmsg *fmsg,
 					  u16 vport_num, bool other_vport)
@@ -59,6 +103,8 @@ void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 		devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail",
 					  VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail));
 	}
+	if (MLX5_CAP_GEN(dev, nic_cap_reg))
+		mlx5_reporter_vnic_diagnose_counter_icm(dev, fmsg, vport_num, other_vport);
 
 	devlink_fmsg_obj_nest_end(fmsg);
 	devlink_fmsg_pair_nest_end(fmsg);
-- 
2.45.0