rpms/kernel
9
4
Fork 6
Code Issues Pull Requests Releases Activity
26248cc311
kernel/SOURCES/1529-net-mlx5-implement-devlink-enable-sriov-parameter.patch

309 lines
9.8 KiB
Diff
Raw Blame History

From 9392c0b3d4463777bea3276ddbd9ef0dded68854 Mon Sep 17 00:00:00 2001
From: Kamal Heib <kheib@redhat.com>
Date: Sun, 19 Apr 2026 18:20:57 -0400
Subject: [PATCH] net/mlx5: Implement devlink enable_sriov parameter
JIRA: https://redhat.atlassian.net/browse/RHEL-169055
commit 95a0af146dff5437acb4ea27eacc05aa22c7bb54
Author: Vlad Dumitrescu <vdumitrescu@nvidia.com>
Date: Sat Sep 6 18:29:45 2025 -0700
net/mlx5: Implement devlink enable_sriov parameter
Example usage:
devlink dev param set pci/0000:01:00.0 name enable_sriov value {true, false} cmode permanent
devlink dev reload pci/0000:01:00.0 action fw_activate
echo 1 >/sys/bus/pci/devices/0000:01:00.0/remove
echo 1 >/sys/bus/pci/rescan
grep ^ /sys/bus/pci/devices/0000:01:00.0/sriov_*
Signed-off-by: Vlad Dumitrescu <vdumitrescu@nvidia.com>
Tested-by: Kamal Heib <kheib@redhat.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250907012953.301746-4-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Kamal Heib <kheib@redhat.com>
diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 2edc842b620d..c3610f7c1d4b 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -15,23 +15,31 @@ Parameters
* - Name
- Mode
- Validation
+ - Notes
* - ``enable_roce``
- driverinit
- - Type: Boolean
-
- If the device supports RoCE disablement, RoCE enablement state controls
+ - Boolean
+ - If the device supports RoCE disablement, RoCE enablement state controls
device support for RoCE capability. Otherwise, the control occurs in the
driver stack. When RoCE is disabled at the driver level, only raw
ethernet QPs are supported.
* - ``io_eq_size``
- driverinit
- The range is between 64 and 4096.
+ -
* - ``event_eq_size``
- driverinit
- The range is between 64 and 4096.
+ -
* - ``max_macs``
- driverinit
- The range is between 1 and 2^31. Only power of 2 values are supported.
+ -
+ * - ``enable_sriov``
+ - permanent
+ - Boolean
+ - Applies to each physical function (PF) independently, if the device
+ supports it. Otherwise, it applies symmetrically to all PFs.
The ``mlx5`` driver also implements the following driver-specific
parameters.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c
index 20a39483be04..ed2129843ec7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c
@@ -5,7 +5,11 @@
#include "mlx5_core.h"
enum {
+ MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CONF = 0x80,
+ MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CAP = 0x81,
MLX5_CLASS_0_CTRL_ID_NV_SW_OFFLOAD_CONFIG = 0x10a,
+
+ MLX5_CLASS_3_CTRL_ID_NV_PF_PCI_CONF = 0x80,
};
struct mlx5_ifc_configuration_item_type_class_global_bits {
@@ -13,9 +17,18 @@ struct mlx5_ifc_configuration_item_type_class_global_bits {
u8 parameter_index[0x18];
};
+struct mlx5_ifc_configuration_item_type_class_per_host_pf_bits {
+ u8 type_class[0x8];
+ u8 pf_index[0x6];
+ u8 pci_bus_index[0x8];
+ u8 parameter_index[0xa];
+};
+
union mlx5_ifc_config_item_type_auto_bits {
struct mlx5_ifc_configuration_item_type_class_global_bits
configuration_item_type_class_global;
+ struct mlx5_ifc_configuration_item_type_class_per_host_pf_bits
+ configuration_item_type_class_per_host_pf;
u8 reserved_at_0[0x20];
};
@@ -45,6 +58,45 @@ struct mlx5_ifc_mnvda_reg_bits {
u8 configuration_item_data[64][0x20];
};
+struct mlx5_ifc_nv_global_pci_conf_bits {
+ u8 sriov_valid[0x1];
+ u8 reserved_at_1[0x10];
+ u8 per_pf_total_vf[0x1];
+ u8 reserved_at_12[0xe];
+
+ u8 sriov_en[0x1];
+ u8 reserved_at_21[0xf];
+ u8 total_vfs[0x10];
+
+ u8 reserved_at_40[0x20];
+};
+
+struct mlx5_ifc_nv_global_pci_cap_bits {
+ u8 max_vfs_per_pf_valid[0x1];
+ u8 reserved_at_1[0x13];
+ u8 per_pf_total_vf_supported[0x1];
+ u8 reserved_at_15[0xb];
+
+ u8 sriov_support[0x1];
+ u8 reserved_at_21[0xf];
+ u8 max_vfs_per_pf[0x10];
+
+ u8 reserved_at_40[0x60];
+};
+
+struct mlx5_ifc_nv_pf_pci_conf_bits {
+ u8 reserved_at_0[0x9];
+ u8 pf_total_vf_en[0x1];
+ u8 reserved_at_a[0x16];
+
+ u8 reserved_at_20[0x20];
+
+ u8 reserved_at_40[0x10];
+ u8 total_vf[0x10];
+
+ u8 reserved_at_60[0x20];
+};
+
struct mlx5_ifc_nv_sw_offload_conf_bits {
u8 ip_over_vxlan_port[0x10];
u8 tunnel_ecn_copy_offload_disable[0x1];
@@ -216,7 +268,154 @@ mlx5_nv_param_devlink_cqe_compress_set(struct devlink *devlink, u32 id,
return mlx5_nv_param_write(dev, mnvda, sizeof(mnvda));
}
+static int mlx5_nv_param_read_global_pci_conf(struct mlx5_core_dev *dev,
+ void *mnvda, size_t len)
+{
+ MLX5_SET_CFG_ITEM_TYPE(global, mnvda, type_class, 0);
+ MLX5_SET_CFG_ITEM_TYPE(global, mnvda, parameter_index,
+ MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CONF);
+ MLX5_SET_CFG_HDR_LEN(mnvda, nv_global_pci_conf);
+
+ return mlx5_nv_param_read(dev, mnvda, len);
+}
+
+static int mlx5_nv_param_read_global_pci_cap(struct mlx5_core_dev *dev,
+ void *mnvda, size_t len)
+{
+ MLX5_SET_CFG_ITEM_TYPE(global, mnvda, type_class, 0);
+ MLX5_SET_CFG_ITEM_TYPE(global, mnvda, parameter_index,
+ MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CAP);
+ MLX5_SET_CFG_HDR_LEN(mnvda, nv_global_pci_cap);
+
+ return mlx5_nv_param_read(dev, mnvda, len);
+}
+
+static int mlx5_nv_param_read_per_host_pf_conf(struct mlx5_core_dev *dev,
+ void *mnvda, size_t len)
+{
+ MLX5_SET_CFG_ITEM_TYPE(per_host_pf, mnvda, type_class, 3);
+ MLX5_SET_CFG_ITEM_TYPE(per_host_pf, mnvda, parameter_index,
+ MLX5_CLASS_3_CTRL_ID_NV_PF_PCI_CONF);
+ MLX5_SET_CFG_HDR_LEN(mnvda, nv_pf_pci_conf);
+
+ return mlx5_nv_param_read(dev, mnvda, len);
+}
+
+static int mlx5_devlink_enable_sriov_get(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+ bool sriov_en = false;
+ void *data;
+ int err;
+
+ err = mlx5_nv_param_read_global_pci_cap(dev, mnvda, sizeof(mnvda));
+ if (err)
+ return err;
+
+ data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+ if (!MLX5_GET(nv_global_pci_cap, data, sriov_support)) {
+ ctx->val.vbool = false;
+ return 0;
+ }
+
+ memset(mnvda, 0, sizeof(mnvda));
+ err = mlx5_nv_param_read_global_pci_conf(dev, mnvda, sizeof(mnvda));
+ if (err)
+ return err;
+
+ data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+ sriov_en = MLX5_GET(nv_global_pci_conf, data, sriov_en);
+ if (!MLX5_GET(nv_global_pci_conf, data, per_pf_total_vf)) {
+ ctx->val.vbool = sriov_en;
+ return 0;
+ }
+
+ /* SRIOV is per PF */
+ memset(mnvda, 0, sizeof(mnvda));
+ err = mlx5_nv_param_read_per_host_pf_conf(dev, mnvda, sizeof(mnvda));
+ if (err)
+ return err;
+
+ data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+ ctx->val.vbool = sriov_en &&
+ MLX5_GET(nv_pf_pci_conf, data, pf_total_vf_en);
+ return 0;
+}
+
+static int mlx5_devlink_enable_sriov_set(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {};
+ bool per_pf_support;
+ void *cap, *data;
+ int err;
+
+ err = mlx5_nv_param_read_global_pci_cap(dev, mnvda, sizeof(mnvda));
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Failed to read global PCI capability");
+ return err;
+ }
+
+ cap = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+ per_pf_support = MLX5_GET(nv_global_pci_cap, cap,
+ per_pf_total_vf_supported);
+
+ if (!MLX5_GET(nv_global_pci_cap, cap, sriov_support)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "SRIOV is not supported on this device");
+ return -EOPNOTSUPP;
+ }
+
+ if (!per_pf_support) {
+ /* We don't allow global SRIOV setting on per PF devlink */
+ NL_SET_ERR_MSG_MOD(extack,
+ "SRIOV is not per PF on this device");
+ return -EOPNOTSUPP;
+ }
+
+ memset(mnvda, 0, sizeof(mnvda));
+ err = mlx5_nv_param_read_global_pci_conf(dev, mnvda, sizeof(mnvda));
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Unable to read global PCI configuration");
+ return err;
+ }
+
+ data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data);
+
+ /* setup per PF sriov mode */
+ MLX5_SET(nv_global_pci_conf, data, sriov_valid, 1);
+ MLX5_SET(nv_global_pci_conf, data, sriov_en, 1);
+ MLX5_SET(nv_global_pci_conf, data, per_pf_total_vf, 1);
+
+ err = mlx5_nv_param_write(dev, mnvda, sizeof(mnvda));
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Unable to write global PCI configuration");
+ return err;
+ }
+
+ /* enable/disable sriov on this PF */
+ memset(mnvda, 0, sizeof(mnvda));
+ err = mlx5_nv_param_read_per_host_pf_conf(dev, mnvda, sizeof(mnvda));
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Unable to read per host PF configuration");
+ return err;
+ }
+ MLX5_SET(nv_pf_pci_conf, data, pf_total_vf_en, ctx->val.vbool);
+ return mlx5_nv_param_write(dev, mnvda, sizeof(mnvda));
+}
+
static const struct devlink_param mlx5_nv_param_devlink_params[] = {
+ DEVLINK_PARAM_GENERIC(ENABLE_SRIOV, BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+ mlx5_devlink_enable_sriov_get,
+ mlx5_devlink_enable_sriov_set, NULL),
DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_CQE_COMPRESSION_TYPE,
"cqe_compress_type", DEVLINK_PARAM_TYPE_STRING,
BIT(DEVLINK_PARAM_CMODE_PERMANENT),
--
2.50.1 (Apple Git-155)
Reference in New Issue View Git Blame Copy Permalink