Merge tag 'mlx5-updates-2023-12-20' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2023-12-20

mlx5 Socket direct support and management PF profile.

Tariq Says:
===========
Support Socket-Direct multi-dev netdev

This series adds support for combining multiple devices (PFs) of the
same port under one netdev instance. Passing traffic through different
devices belonging to different NUMA sockets saves cross-numa traffic and
allows apps running on the same netdev from different numas to still
feel a sense of proximity to the device and achieve improved
performance.

We achieve this by grouping PFs together, and creating the netdev only
once all group members are probed. Symmetrically, we destroy the netdev
once any of the PFs is removed.

The channels are distributed between all devices, a proper configuration
would utilize the correct close numa when working on a certain app/cpu.

We pick one device to be a primary (leader), and it fills a special
role.  The other devices (secondaries) are disconnected from the network
in the chip level (set to silent mode). All RX/TX traffic is steered
through the primary to/from the secondaries.

Currently, we limit the support to PFs only, and up to two devices
(sockets).

===========

Armen Says:
===========
Management PF support and module integration

This patch rolls out comprehensive support for the Management Physical
Function (MGMT PF) within the mlx5 driver. It involves updating the
mlx5 interface header to introduce necessary definitions for MGMT PF
and adding a new management PF netdev profile, which will allow the host
side to communicate with the embedded linux on Blue-field devices.

===========
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

40 files changed, 1320 insertions, 192 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index c44870b175f9..f36232dead1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -29,7 +29,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \
 		en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \
 		en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o \
 		en/qos.o en/htb.o en/trap.o en/fs_tt_redirect.o en/selq.o \
-		lib/crypto.o
+		en/mgmt_pf.o lib/crypto.o lib/sd.o
 
 #
 # Netdev extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index cf0477f53dc4..aa1b471e13fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -190,6 +190,9 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev)
 	if (is_mp_supported(dev))
 		return false;
 
+	if (mlx5_core_is_mgmt_pf(dev))
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
index d000236ddbac..aa397e3ebe6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -75,6 +75,9 @@ int mlx5_ec_init(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return 0;
 
+	if (mlx5_core_is_mgmt_pf(dev))
+		return 0;
+
 	return mlx5_host_pf_init(dev);
 }
 
@@ -85,6 +88,9 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return;
 
+	if (mlx5_core_is_mgmt_pf(dev))
+		return;
+
 	mlx5_host_pf_cleanup(dev);
 
 	err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0bfe1ca8a364..922b63c25154 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -60,8 +60,10 @@
 #include "lib/clock.h"
 #include "en/rx_res.h"
 #include "en/selq.h"
+#include "lib/sd.h"
 
 extern const struct net_device_ops mlx5e_netdev_ops;
+extern const struct net_device_ops mlx5e_mgmt_netdev_ops;
 struct page_pool;
 
 #define MLX5E_METADATA_ETHER_TYPE (0x8CE4)
@@ -791,6 +793,8 @@ struct mlx5e_channel {
 	struct hwtstamp_config    *tstamp;
 	DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
 	int                        ix;
+	int                        vec_ix;
+	int                        sd_ix;
 	int                        cpu;
 	/* Sync between icosq recovery and XSK enable/disable. */
 	struct mutex               icosq_recovery_lock;
@@ -914,7 +918,7 @@ struct mlx5e_priv {
 	bool                       tx_ptp_opened;
 	bool                       rx_ptp_opened;
 	struct hwtstamp_config     tstamp;
-	u16                        q_counter;
+	u16                        q_counter[MLX5_SD_MAX_GROUP_SZ];
 	u16                        drop_rq_q_counter;
 	struct notifier_block      events_nb;
 	struct notifier_block      blocking_events_nb;
@@ -1029,12 +1033,12 @@ struct mlx5e_xsk_param;
 
 struct mlx5e_rq_param;
 int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
-		  struct mlx5e_xsk_param *xsk, int node,
+		  struct mlx5e_xsk_param *xsk, int node, u16 q_counter,
 		  struct mlx5e_rq *rq);
 #define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */
 int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time);
 void mlx5e_close_rq(struct mlx5e_rq *rq);
-int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param);
+int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter);
 void mlx5e_destroy_rq(struct mlx5e_rq *rq);
 
 struct mlx5e_sq_param;
@@ -1122,9 +1126,10 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 }
 
 extern const struct ethtool_ops mlx5e_ethtool_ops;
+extern const struct mlx5e_profile mlx5e_mgmt_pf_nic_profile;
 
 int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
 int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
 		       bool enable_mc_lb);
@@ -1227,6 +1232,8 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 				       struct net_device *netdev,
 				       netdev_features_t features);
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features);
+void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv);
+
 #ifdef CONFIG_MLX5_ESWITCH
 int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
 int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
index 48581ea3adcb..874a1016623c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
@@ -23,20 +23,26 @@ bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix)
 	return test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
 }
 
-void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn)
+void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn,
+				    u32 *vhca_id)
 {
 	struct mlx5e_channel *c = mlx5e_channels_get(chs, ix);
 
 	*rqn = c->rq.rqn;
+	if (vhca_id)
+		*vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id);
 }
 
-void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn)
+void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn,
+				u32 *vhca_id)
 {
 	struct mlx5e_channel *c = mlx5e_channels_get(chs, ix);
 
 	WARN_ON_ONCE(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state));
 
 	*rqn = c->xskrq.rqn;
+	if (vhca_id)
+		*vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id);
 }
 
 bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
index 637ca90daaa8..6715aa9383b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
@@ -10,8 +10,10 @@ struct mlx5e_channels;
 
 unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs);
 bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix);
-void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn);
-void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn);
+void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn,
+				    u32 *vhca_id);
+void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn,
+				u32 *vhca_id);
 bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn);
 
 #endif /* __MLX5_EN_CHANNELS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c
new file mode 100644
index 000000000000..77b5805895b9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c
@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+#include <linux/kernel.h>
+#include "en/params.h"
+#include "en/health.h"
+#include "lib/eq.h"
+#include "en/dcbnl.h"
+#include "en_accel/ipsec.h"
+#include "en_accel/en_accel.h"
+#include "en/trap.h"
+#include "en/monitor_stats.h"
+#include "en/hv_vhca_stats.h"
+#include "en_rep.h"
+#include "en.h"
+
+static int mgmt_pf_async_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
+	struct mlx5_eqe   *eqe = data;
+
+	if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
+		return NOTIFY_DONE;
+
+	switch (eqe->sub_type) {
+	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+		queue_work(priv->wq, &priv->update_carrier_work);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static void mlx5e_mgmt_pf_enable_async_events(struct mlx5e_priv *priv)
+{
+	priv->events_nb.notifier_call = mgmt_pf_async_event;
+	mlx5_notifier_register(priv->mdev, &priv->events_nb);
+}
+
+static void mlx5e_disable_mgmt_pf_async_events(struct mlx5e_priv *priv)
+{
+	mlx5_notifier_unregister(priv->mdev, &priv->events_nb);
+}
+
+static void mlx5e_modify_mgmt_pf_admin_state(struct mlx5_core_dev *mdev,
+					     enum mlx5_port_status state)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int vport_admin_state;
+
+	mlx5_set_port_admin_status(mdev, state);
+
+	if (state == MLX5_PORT_UP)
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+	else
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN;
+
+	mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state);
+}
+
+static void mlx5e_build_mgmt_pf_nic_params(struct mlx5e_priv *priv, u16 mtu)
+{
+	struct mlx5e_params *params = &priv->channels.params;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u8 rx_cq_period_mode;
+
+	params->sw_mtu = mtu;
+	params->hard_mtu = MLX5E_ETH_HARD_MTU;
+	params->num_channels = 1;
+
+	/* SQ */
+	params->log_sq_size = is_kdump_kernel() ?
+		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
+		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE, mlx5e_tx_mpwqe_supported(mdev));
+
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE, false);
+
+	/* RQ */
+	mlx5e_build_rq_params(mdev, params);
+
+	/* CQ moderation params */
+	rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
+			MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
+			MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode);
+	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
+
+	/* TX inline */
+	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
+}
+
+static int mlx5e_mgmt_pf_init(struct mlx5_core_dev *mdev,
+			      struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_flow_steering *fs;
+	int err;
+
+	mlx5e_build_mgmt_pf_nic_params(priv, netdev->mtu);
+
+	mlx5e_timestamp_init(priv);
+
+	fs = mlx5e_fs_init(priv->profile, mdev,
+			   !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
+			   priv->dfs_root);
+	if (!fs) {
+		err = -ENOMEM;
+		mlx5_core_err(mdev, "FS initialization failed, %d\n", err);
+		return err;
+	}
+	priv->fs = fs;
+
+	mlx5e_health_create_reporters(priv);
+
+	return 0;
+}
+
+static void mlx5e_mgmt_pf_cleanup(struct mlx5e_priv *priv)
+{
+	mlx5e_health_destroy_reporters(priv);
+	mlx5e_fs_cleanup(priv->fs);
+	priv->fs = NULL;
+}
+
+static int mlx5e_mgmt_pf_init_rx(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int err;
+
+	priv->rx_res = mlx5e_rx_res_create(mdev, 0, priv->max_nch, priv->drop_rq.rqn,
+					   &priv->channels.params.packet_merge,
+					   priv->channels.params.num_channels);
+	if (!priv->rx_res)
+		return -ENOMEM;
+
+	mlx5e_create_q_counters(priv);
+
+	err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
+	if (err) {
+		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
+		goto err_destroy_q_counters;
+	}
+
+	err = mlx5e_create_flow_steering(priv->fs, priv->rx_res, priv->profile,
+					 priv->netdev);
+	if (err) {
+		mlx5_core_warn(mdev, "create flow steering failed, %d\n", err);
+		goto err_destroy_rx_res;
+	}
+
+	return 0;
+
+err_destroy_rx_res:
+	mlx5e_rx_res_destroy(priv->rx_res);
+	priv->rx_res = NULL;
+	mlx5e_close_drop_rq(&priv->drop_rq);
+err_destroy_q_counters:
+	mlx5e_destroy_q_counters(priv);
+	return err;
+}
+
+static void mlx5e_mgmt_pf_cleanup_rx(struct mlx5e_priv *priv)
+{
+	mlx5e_destroy_flow_steering(priv->fs, !!(priv->netdev->hw_features & NETIF_F_NTUPLE),
+				    priv->profile);
+	mlx5e_rx_res_destroy(priv->rx_res);
+	priv->rx_res = NULL;
+	mlx5e_close_drop_rq(&priv->drop_rq);
+	mlx5e_destroy_q_counters(priv);
+}
+
+static int mlx5e_mgmt_pf_init_tx(struct mlx5e_priv *priv)
+{
+	return 0;
+}
+
+static void mlx5e_mgmt_pf_cleanup_tx(struct mlx5e_priv *priv)
+{
+}
+
+static void mlx5e_mgmt_pf_enable(struct mlx5e_priv *priv)
+{
+	struct net_device *netdev = priv->netdev;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	mlx5e_fs_init_l2_addr(priv->fs, netdev);
+
+	/* Marking the link as currently not needed by the Driver */
+	if (!netif_running(netdev))
+		mlx5e_modify_mgmt_pf_admin_state(mdev, MLX5_PORT_DOWN);
+
+	mlx5e_set_netdev_mtu_boundaries(priv);
+	mlx5e_set_dev_port_mtu(priv);
+
+	mlx5e_mgmt_pf_enable_async_events(priv);
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_init(priv);
+
+	mlx5e_hv_vhca_stats_create(priv);
+	if (netdev->reg_state != NETREG_REGISTERED)
+		return;
+	mlx5e_dcbnl_init_app(priv);
+
+	mlx5e_nic_set_rx_mode(priv);
+
+	rtnl_lock();
+	if (netif_running(netdev))
+		mlx5e_open(netdev);
+	udp_tunnel_nic_reset_ntf(priv->netdev);
+	netif_device_attach(netdev);
+	rtnl_unlock();
+}
+
+static void mlx5e_mgmt_pf_disable(struct mlx5e_priv *priv)
+{
+	if (priv->netdev->reg_state == NETREG_REGISTERED)
+		mlx5e_dcbnl_delete_app(priv);
+
+	rtnl_lock();
+	if (netif_running(priv->netdev))
+		mlx5e_close(priv->netdev);
+	netif_device_detach(priv->netdev);
+	rtnl_unlock();
+
+	mlx5e_nic_set_rx_mode(priv);
+
+	mlx5e_hv_vhca_stats_destroy(priv);
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_cleanup(priv);
+
+	mlx5e_disable_mgmt_pf_async_events(priv);
+	mlx5e_ipsec_cleanup(priv);
+}
+
+static int mlx5e_mgmt_pf_update_rx(struct mlx5e_priv *priv)
+{
+	return mlx5e_refresh_tirs(priv, false, false);
+}
+
+static int mlx5e_mgmt_pf_max_nch_limit(struct mlx5_core_dev *mdev)
+{
+	return 1;
+}
+
+const struct mlx5e_profile mlx5e_mgmt_pf_nic_profile = {
+	.init		   = mlx5e_mgmt_pf_init,
+	.cleanup	   = mlx5e_mgmt_pf_cleanup,
+	.init_rx	   = mlx5e_mgmt_pf_init_rx,
+	.cleanup_rx	   = mlx5e_mgmt_pf_cleanup_rx,
+	.init_tx	   = mlx5e_mgmt_pf_init_tx,
+	.cleanup_tx	   = mlx5e_mgmt_pf_cleanup_tx,
+	.enable		   = mlx5e_mgmt_pf_enable,
+	.disable	   = mlx5e_mgmt_pf_disable,
+	.update_rx	   = mlx5e_mgmt_pf_update_rx,
+	.update_stats	   = mlx5e_stats_update_ndo_stats,
+	.update_carrier	   = mlx5e_update_carrier,
+	.rx_handlers       = &mlx5e_rx_handlers_nic,
+	.max_tc		   = 1,
+	.max_nch_limit	   = mlx5e_mgmt_pf_max_nch_limit,
+	.stats_grps	   = mlx5e_nic_stats_grps,
+	.stats_grps_num	   = mlx5e_nic_stats_grps_num
+};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
index 40c8df111754..e2d8d2754be0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -20,10 +20,8 @@
 #define NUM_REQ_PPCNT_COUNTER_S1 MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1
 #define NUM_REQ_Q_COUNTERS_S1    MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1
 
-int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv)
+static int mlx5e_monitor_counter_cap(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
-
 	if (!MLX5_CAP_GEN(mdev, max_num_of_monitor_counters))
 		return false;
 	if (MLX5_CAP_PCAM_REG(mdev, ppcnt) &&
@@ -36,24 +34,38 @@ int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv)
 	return true;
 }
 
-static void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv)
+int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *pos;
+	int i;
+
+	mlx5_sd_for_each_dev(i, priv->mdev, pos)
+		if (!mlx5e_monitor_counter_cap(pos))
+			return false;
+	return true;
+}
+
+static void mlx5e_monitor_counter_arm(struct mlx5_core_dev *mdev)
 {
 	u32 in[MLX5_ST_SZ_DW(arm_monitor_counter_in)] = {};
 
 	MLX5_SET(arm_monitor_counter_in, in, opcode,
 		 MLX5_CMD_OP_ARM_MONITOR_COUNTER);
-	mlx5_cmd_exec_in(priv->mdev, arm_monitor_counter, in);
+	mlx5_cmd_exec_in(mdev, arm_monitor_counter, in);
 }
 
 static void mlx5e_monitor_counters_work(struct work_struct *work)
 {
 	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
 					       monitor_counters_work);
+	struct mlx5_core_dev *pos;
+	int i;
 
 	mutex_lock(&priv->state_lock);
 	mlx5e_stats_update_ndo_stats(priv);
 	mutex_unlock(&priv->state_lock);
-	mlx5e_monitor_counter_arm(priv);
+	mlx5_sd_for_each_dev(i, priv->mdev, pos)
+		mlx5e_monitor_counter_arm(pos);
 }
 
 static int mlx5e_monitor_event_handler(struct notifier_block *nb,
@@ -97,15 +109,13 @@ static int fill_monitor_counter_q_counter_set1(int cnt, int q_counter, u32 *in)
 }
 
 /* check if mlx5e_monitor_counter_supported before calling this function*/
-static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv)
+static void mlx5e_set_monitor_counter(struct mlx5_core_dev *mdev, int q_counter)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	int max_num_of_counters = MLX5_CAP_GEN(mdev, max_num_of_monitor_counters);
 	int num_q_counters      = MLX5_CAP_GEN(mdev, num_q_monitor_counters);
 	int num_ppcnt_counters  = !MLX5_CAP_PCAM_REG(mdev, ppcnt) ? 0 :
 				  MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters);
 	u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {};
-	int q_counter = priv->q_counter;
 	int cnt	= 0;
 
 	if (num_ppcnt_counters  >=  NUM_REQ_PPCNT_COUNTER_S1 &&
@@ -127,13 +137,17 @@ static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv)
 /* check if mlx5e_monitor_counter_supported before calling this function*/
 void mlx5e_monitor_counter_init(struct mlx5e_priv *priv)
 {
+	struct mlx5_core_dev *pos;
+	int i;
+
 	INIT_WORK(&priv->monitor_counters_work, mlx5e_monitor_counters_work);
 	MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler,
 		     MONITOR_COUNTER);
-	mlx5_eq_notifier_register(priv->mdev, &priv->monitor_counters_nb);
-
-	mlx5e_set_monitor_counter(priv);
-	mlx5e_monitor_counter_arm(priv);
+	mlx5_sd_for_each_dev(i, priv->mdev, pos) {
+		mlx5_eq_notifier_register(pos, &priv->monitor_counters_nb);
+		mlx5e_set_monitor_counter(pos, priv->q_counter[i]);
+		mlx5e_monitor_counter_arm(pos);
+	}
 	queue_work(priv->wq, &priv->update_stats_work);
 }
 
@@ -141,11 +155,15 @@ void mlx5e_monitor_counter_init(struct mlx5e_priv *priv)
 void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv)
 {
 	u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {};
+	struct mlx5_core_dev *pos;
+	int i;
 
 	MLX5_SET(set_monitor_counter_in, in, opcode,
 		 MLX5_CMD_OP_SET_MONITOR_COUNTER);
 
-	mlx5_cmd_exec_in(priv->mdev, set_monitor_counter, in);
-	mlx5_eq_notifier_unregister(priv->mdev, &priv->monitor_counters_nb);
+	mlx5_sd_for_each_dev(i, priv->mdev, pos) {
+		mlx5_cmd_exec_in(pos, set_monitor_counter, in);
+		mlx5_eq_notifier_unregister(pos, &priv->monitor_counters_nb);
+	}
 	cancel_work_sync(&priv->monitor_counters_work);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 284253b79266..fb10bb166fbb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -674,7 +674,7 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e
 		.napi = &c->napi,
 		.ch_stats = c->stats,
 		.node = cpu_to_node(c->cpu),
-		.ix = c->ix,
+		.ix = c->vec_ix,
 	};
 }
 
@@ -945,7 +945,6 @@ static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *param
 int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params,
 			 struct mlx5e_xsk_param *xsk,
-			 u16 q_counter,
 			 struct mlx5e_rq_param *param)
 {
 	void *rqc = param->rqc;
@@ -1007,7 +1006,6 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 	MLX5_SET(wq, wq, log_wq_stride,
 		 mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs));
 	MLX5_SET(wq, wq, pd,               mdev->mlx5e_res.hw_objs.pdn);
-	MLX5_SET(rqc, rqc, counter_set_id, q_counter);
 	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
 	MLX5_SET(rqc, rqc, scatter_fcs,    params->scatter_fcs_en);
 
@@ -1018,7 +1016,6 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 }
 
 void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
-			       u16 q_counter,
 			       struct mlx5e_rq_param *param)
 {
 	void *rqc = param->rqc;
@@ -1027,7 +1024,6 @@ void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
 	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
 	MLX5_SET(wq, wq, log_wq_stride,
 		 mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1));
-	MLX5_SET(rqc, rqc, counter_set_id, q_counter);
 
 	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
 }
@@ -1292,13 +1288,12 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 
 int mlx5e_build_channel_param(struct mlx5_core_dev *mdev,
 			      struct mlx5e_params *params,
-			      u16 q_counter,
 			      struct mlx5e_channel_param *cparam)
 {
 	u8 icosq_log_wq_sz, async_icosq_log_wq_sz;
 	int err;
 
-	err = mlx5e_build_rq_param(mdev, params, NULL, q_counter, &cparam->rq);
+	err = mlx5e_build_rq_param(mdev, params, NULL, &cparam->rq);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 6800949dafbc..9a781f18b57f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -130,10 +130,8 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e
 int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params,
 			 struct mlx5e_xsk_param *xsk,
-			 u16 q_counter,
 			 struct mlx5e_rq_param *param);
 void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
-			       u16 q_counter,
 			       struct mlx5e_rq_p