From: Tariq Toukan <tariqt@nvidia.com>
To: Leon Romanovsky <leon@kernel.org>, Jason Gunthorpe <jgg@ziepe.ca>,
"Saeed Mahameed" <saeedm@nvidia.com>,
Tariq Toukan <tariqt@nvidia.com>
Cc: Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Mark Bloch <mbloch@nvidia.com>,
"Moshe Shemesh" <moshe@nvidia.com>,
Parav Pandit <parav@nvidia.com>, Shay Drori <shayd@nvidia.com>,
Kees Cook <kees@kernel.org>, Daniel Jurgens <danielj@nvidia.com>,
Or Har-Toov <ohartoov@nvidia.com>,
Simon Horman <horms@kernel.org>, Jiri Pirko <jiri@resnulli.us>,
Adithya Jayachandran <ajayachandra@nvidia.com>,
<linux-rdma@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<netdev@vger.kernel.org>, Gal Pressman <gal@nvidia.com>,
Dragos Tatulea <dtatulea@nvidia.com>
Subject: [PATCH mlx5-next 4/4] net/mlx5: Extend query_esw_functions output for multi-function support
Date: Tue, 28 Apr 2026 08:38:51 +0300 [thread overview]
Message-ID: <20260428053851.220089-5-tariqt@nvidia.com> (raw)
In-Reply-To: <20260428053851.220089-1-tariqt@nvidia.com>
From: Moshe Shemesh <moshe@nvidia.com>
Update the query_esw_functions command to support a new response layout
that can report data for multiple network functions. Setting bit 14 of
the op_mod field selects the v1 layout with network_function_params
entries instead of the legacy host_params_context.
The query_host_net_function_v1 read-only capability indicates firmware
support for layout version 1, and query_host_net_function_num_max
advertises the maximum number of network function entries.
Define a new network_function_params layout and a net_function_params
union that groups host_params_context and network_function_params.
Rework the query_esw_functions output to use a flexible array of this
union, and adjust existing driver callers to use it.
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/eswitch.c | 14 ++--
.../mellanox/mlx5/core/eswitch_offloads.c | 25 +++++---
.../mlx5/core/sf/mlx5_ifc_vhca_event.h | 8 ---
.../net/ethernet/mellanox/mlx5/core/sriov.c | 7 +-
include/linux/mlx5/mlx5_ifc.h | 64 +++++++++++++++++--
5 files changed, 91 insertions(+), 27 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 80ba360347e7..408f729d8914 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1045,6 +1045,7 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
static int mlx5_esw_host_functions_enabled_query(struct mlx5_eswitch *esw)
{
const u32 *query_host_out;
+ void *host_params;
if (!mlx5_core_is_ecpf_esw_manager(esw->dev))
return 0;
@@ -1053,9 +1054,11 @@ static int mlx5_esw_host_functions_enabled_query(struct mlx5_eswitch *esw)
if (IS_ERR(query_host_out))
return PTR_ERR(query_host_out);
+ host_params = MLX5_ADDR_OF(query_esw_functions_out,
+ query_host_out, net_function_params);
esw->esw_funcs.host_funcs_disabled =
- MLX5_GET(query_esw_functions_out, query_host_out,
- host_params_context.host_pf_not_exist);
+ MLX5_GET(host_params_context, host_params,
+ host_pf_not_exist);
kvfree(query_host_out);
return 0;
@@ -1475,6 +1478,7 @@ static void mlx5_eswitch_get_devlink_param(struct mlx5_eswitch *esw)
static void
mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, int num_vfs)
{
+ void *host_params;
const u32 *out;
if (num_vfs < 0)
@@ -1489,8 +1493,10 @@ mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, int num_vfs)
if (IS_ERR(out))
return;
- esw->esw_funcs.num_vfs = MLX5_GET(query_esw_functions_out, out,
- host_params_context.host_num_of_vfs);
+ host_params = MLX5_ADDR_OF(query_esw_functions_out, out,
+ net_function_params);
+ esw->esw_funcs.num_vfs = MLX5_GET(host_params_context, host_params,
+ host_num_of_vfs);
if (mlx5_core_ec_sriov_enabled(esw->dev))
esw->esw_funcs.num_ec_vfs = num_vfs;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index c32335df6b64..b859aa5062ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3664,6 +3664,7 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, int work_gen,
{
struct devlink *devlink;
bool host_pf_disabled;
+ void *host_params;
u16 new_num_vfs;
devlink = priv_to_devlink(esw->dev);
@@ -3673,10 +3674,12 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, int work_gen,
if (work_gen != atomic_read(&esw->esw_funcs.generation))
goto unlock;
- new_num_vfs = MLX5_GET(query_esw_functions_out, out,
- host_params_context.host_num_of_vfs);
- host_pf_disabled = MLX5_GET(query_esw_functions_out, out,
- host_params_context.host_pf_disabled);
+ host_params = MLX5_ADDR_OF(query_esw_functions_out, out,
+ net_function_params);
+ new_num_vfs = MLX5_GET(host_params_context, host_params,
+ host_num_of_vfs);
+ host_pf_disabled = MLX5_GET(host_params_context, host_params,
+ host_pf_disabled);
if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled)
goto unlock;
@@ -3743,6 +3746,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type
static int mlx5_esw_host_number_init(struct mlx5_eswitch *esw)
{
const u32 *query_host_out;
+ void *host_params;
if (!mlx5_core_is_ecpf_esw_manager(esw->dev))
return 0;
@@ -3752,8 +3756,10 @@ static int mlx5_esw_host_number_init(struct mlx5_eswitch *esw)
return PTR_ERR(query_host_out);
/* Mark non local controller with non zero controller number. */
- esw->offloads.host_number = MLX5_GET(query_esw_functions_out, query_host_out,
- host_params_context.host_number);
+ host_params = MLX5_ADDR_OF(query_esw_functions_out,
+ query_host_out, net_function_params);
+ esw->offloads.host_number = MLX5_GET(host_params_context,
+ host_params, host_number);
kvfree(query_host_out);
return 0;
}
@@ -4792,6 +4798,7 @@ int mlx5_devlink_pf_port_fn_state_get(struct devlink_port *port,
{
struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
const u32 *query_out;
+ void *host_params;
bool pf_disabled;
if (vport->vport != MLX5_VPORT_HOST_PF) {
@@ -4806,8 +4813,10 @@ int mlx5_devlink_pf_port_fn_state_get(struct devlink_port *port,
if (IS_ERR(query_out))
return PTR_ERR(query_out);
- pf_disabled = MLX5_GET(query_esw_functions_out, query_out,
- host_params_context.host_pf_disabled);
+ host_params = MLX5_ADDR_OF(query_esw_functions_out, query_out,
+ net_function_params);
+ pf_disabled = MLX5_GET(host_params_context, host_params,
+ host_pf_disabled);
*opstate = pf_disabled ? DEVLINK_PORT_FN_OPSTATE_DETACHED :
DEVLINK_PORT_FN_OPSTATE_ATTACHED;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
index 4fc870140d71..487c94b56203 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
@@ -4,14 +4,6 @@
#ifndef __MLX5_IFC_VHCA_EVENT_H__
#define __MLX5_IFC_VHCA_EVENT_H__
-enum mlx5_ifc_vhca_state {
- MLX5_VHCA_STATE_INVALID = 0x0,
- MLX5_VHCA_STATE_ALLOCATED = 0x1,
- MLX5_VHCA_STATE_ACTIVE = 0x2,
- MLX5_VHCA_STATE_IN_USE = 0x3,
- MLX5_VHCA_STATE_TEARDOWN_REQUEST = 0x4,
-};
-
struct mlx5_ifc_vhca_state_context_bits {
u8 arm_change_event[0x1];
u8 reserved_at_1[0xb];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index bf6f631cf2ce..6eb6026eadd6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -274,6 +274,7 @@ void mlx5_sriov_detach(struct mlx5_core_dev *dev)
static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev)
{
u16 host_total_vfs;
+ void *host_params;
const u32 *out;
if (mlx5_core_is_ecpf_esw_manager(dev)) {
@@ -284,8 +285,10 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev)
*/
if (IS_ERR(out))
goto done;
- host_total_vfs = MLX5_GET(query_esw_functions_out, out,
- host_params_context.host_total_vfs);
+ host_params = MLX5_ADDR_OF(query_esw_functions_out, out,
+ net_function_params);
+ host_total_vfs = MLX5_GET(host_params_context, host_params,
+ host_total_vfs);
kvfree(out);
return host_total_vfs;
}
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 02b57b2286da..6a675f918c40 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1935,7 +1935,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 max_flow_counter_31_16[0x10];
u8 max_wqe_sz_sq_dc[0x10];
- u8 reserved_at_2e0[0x7];
+ u8 query_host_net_function_num_max[0x5];
+ u8 reserved_at_2e5[0x2];
u8 max_qp_mcg[0x19];
u8 reserved_at_300[0x10];
@@ -2027,7 +2028,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 log_max_current_mc_list[0x5];
u8 reserved_at_3f8[0x1];
u8 silent_mode_query[0x1];
- u8 reserved_at_3fa[0x1];
+ u8 query_host_net_function_v1[0x1];
u8 log_max_current_uc_list[0x5];
u8 general_obj_types[0x40];
@@ -12704,6 +12705,54 @@ struct mlx5_ifc_host_params_context_bits {
u8 reserved_at_80[0x180];
};
+enum mlx5_ifc_vhca_state {
+ MLX5_VHCA_STATE_INVALID = 0x0,
+ MLX5_VHCA_STATE_ALLOCATED = 0x1,
+ MLX5_VHCA_STATE_ACTIVE = 0x2,
+ MLX5_VHCA_STATE_IN_USE = 0x3,
+ MLX5_VHCA_STATE_TEARDOWN_REQUEST = 0x4,
+};
+
+enum {
+ MLX5_PCI_PF_TYPE_EXTERNAL_HOST_PF = 0x0,
+ MLX5_PCI_PF_TYPE_SATELLITE_PF = 0x1,
+};
+
+struct mlx5_ifc_network_function_params_bits {
+ u8 host_number[0x8];
+ u8 pci_pf_type[0x4];
+ u8 reserved_at_c[0x4];
+ u8 pci_num_vfs[0x10];
+
+ u8 pci_total_vfs[0x10];
+ u8 pci_bus[0x8];
+ u8 pci_device_function[0x8];
+
+ u8 vhca_id[0x10];
+ u8 vhca_state[0x4];
+ u8 reserved_at_54[0xc];
+
+ u8 reserved_at_60[0xa];
+ u8 esw_vport_manual[0x1];
+ u8 pci_bus_assigned[0x1];
+ u8 pci_vf_info_valid[0x1];
+ u8 reserved_at_6d[0x13];
+
+ u8 pci_vf_stride[0x10];
+ u8 pci_first_vf_offset[0x10];
+
+ u8 reserved_at_a0[0x160];
+};
+
+union mlx5_ifc_net_function_params_bits {
+ struct mlx5_ifc_host_params_context_bits host_params_context;
+ struct mlx5_ifc_network_function_params_bits network_function_params;
+};
+
+enum {
+ MLX5_QUERY_ESW_FUNC_OP_MOD_LAYOUT_V1 = BIT(14),
+};
+
struct mlx5_ifc_query_esw_functions_in_bits {
u8 opcode[0x10];
u8 reserved_at_10[0x10];
@@ -12720,11 +12769,16 @@ struct mlx5_ifc_query_esw_functions_out_bits {
u8 syndrome[0x20];
- u8 reserved_at_40[0x40];
+ u8 reserved_at_40[0x20];
- struct mlx5_ifc_host_params_context_bits host_params_context;
+ u8 net_function_num[0x8];
+ u8 reserved_at_68[0x18];
- u8 reserved_at_280[0x180];
+ union {
+ u8 reserved_at_80[0x380];
+ DECLARE_FLEX_ARRAY(union mlx5_ifc_net_function_params_bits,
+ net_function_params);
+ };
};
struct mlx5_ifc_sf_partition_bits {
--
2.44.0
prev parent reply other threads:[~2026-04-28 5:40 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-28 5:38 [PATCH mlx5-next 0/4] mlx5-next updates 2026-04-28 Tariq Toukan
2026-04-28 5:38 ` [PATCH mlx5-next 1/4] mlx5: Rename the vport number enums for host PF and VF Tariq Toukan
2026-04-28 5:38 ` [PATCH mlx5-next 2/4] net/mlx5: Add function_id_type for enable/disable_hca cmds Tariq Toukan
2026-04-28 5:38 ` [PATCH mlx5-next 3/4] net/mlx5: Remove unused host_sf_enable field Tariq Toukan
2026-04-28 5:38 ` Tariq Toukan [this message]
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=20260428053851.220089-5-tariqt@nvidia.com \
--to=tariqt@nvidia.com \
--cc=ajayachandra@nvidia.com \
--cc=andrew+netdev@lunn.ch \
--cc=danielj@nvidia.com \
--cc=davem@davemloft.net \
--cc=dtatulea@nvidia.com \
--cc=edumazet@google.com \
--cc=gal@nvidia.com \
--cc=horms@kernel.org \
--cc=jgg@ziepe.ca \
--cc=jiri@resnulli.us \
--cc=kees@kernel.org \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mbloch@nvidia.com \
--cc=moshe@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=ohartoov@nvidia.com \
--cc=pabeni@redhat.com \
--cc=parav@nvidia.com \
--cc=saeedm@nvidia.com \
--cc=shayd@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