net/mlx5e: Support per-mdev queue counter

Each queue counter object counts some events (in hardware) for the RQs
that are attached to it, like events of packet drops due to no receive
WQE (rx_out_of_buffer).

Each RQ can be attached to a queue counter only within the same vhca. To
still cover all RQs with these counters, we create multiple instances,
one per vhca.

The result that's shown to the user is now the sum of all instances.
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -793,6 +793,7 @@ struct mlx5e_channel {
 	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;
@@ -916,7 +917,7 @@ 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;
@@ -1031,12 +1032,12 @@ 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;

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);
 }

drivers/net/ethernet/mellanox/mlx5/core/en/params.c

@@ -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;
 

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_param *param);
 void mlx5e_build_sq_param_common(struct mlx5_core_dev *mdev,
 				 struct mlx5e_sq_param *param);
@@ -149,7 +147,6 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 			     struct mlx5e_sq_param *param);
 int mlx5e_build_channel_param(struct mlx5_core_dev *mdev,
 			      struct mlx5e_params *params,
-			      u16 q_counter,
 			      struct mlx5e_channel_param *cparam);
 
 u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params);

drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c

@@ -646,7 +646,6 @@ static void mlx5e_ptp_build_sq_param(struct mlx5_core_dev *mdev,
 
 static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev,
 				     struct net_device *netdev,
-				     u16 q_counter,
 				     struct mlx5e_ptp_params *ptp_params)
 {
 	struct mlx5e_rq_param *rq_params = &ptp_params->rq_param;
@@ -655,7 +654,7 @@ static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev,
 	params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC;
 	mlx5e_init_rq_type_params(mdev, params);
 	params->sw_mtu = netdev->max_mtu;
-	mlx5e_build_rq_param(mdev, params, NULL, q_counter, rq_params);
+	mlx5e_build_rq_param(mdev, params, NULL, rq_params);
 }
 
 static void mlx5e_ptp_build_params(struct mlx5e_ptp *c,
@@ -681,7 +680,7 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c,
 	/* RQ */
 	if (test_bit(MLX5E_PTP_STATE_RX, c->state)) {
 		params->vlan_strip_disable = orig->vlan_strip_disable;
-		mlx5e_ptp_build_rq_param(c->mdev, c->netdev, c->priv->q_counter, cparams);
+		mlx5e_ptp_build_rq_param(c->mdev, c->netdev, cparams);
 	}
 }
 
@@ -714,13 +713,16 @@ static int mlx5e_ptp_open_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
 			     struct mlx5e_rq_param *rq_param)
 {
 	int node = dev_to_node(c->mdev->device);
-	int err;
+	int err, sd_ix;
+	u16 q_counter;
 
 	err = mlx5e_init_ptp_rq(c, params, &c->rq);
 	if (err)
 		return err;
 
-	return mlx5e_open_rq(params, rq_param, NULL, node, &c->rq);
+	sd_ix = mlx5_sd_ch_ix_get_dev_ix(c->mdev, MLX5E_PTP_CHANNEL_IX);
+	q_counter = c->priv->q_counter[sd_ix];
+	return mlx5e_open_rq(params, rq_param, NULL, node, q_counter, &c->rq);
 }
 
 static int mlx5e_ptp_open_queues(struct mlx5e_ptp *c,

drivers/net/ethernet/mellanox/mlx5/core/en/trap.c

@@ -63,10 +63,12 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t)
 	struct mlx5e_create_cq_param ccp = {};
 	struct dim_cq_moder trap_moder = {};
 	struct mlx5e_rq *rq = &t->rq;
+	u16 q_counter;
 	int node;
 	int err;
 
 	node = dev_to_node(mdev->device);
+	q_counter = priv->q_counter[0];
 
 	ccp.netdev   = priv->netdev;
 	ccp.wq       = priv->wq;
@@ -79,7 +81,7 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t)
 		return err;
 
 	mlx5e_init_trap_rq(t, &t->params, rq);
-	err = mlx5e_open_rq(&t->params, rq_param, NULL, node, rq);
+	err = mlx5e_open_rq(&t->params, rq_param, NULL, node, q_counter, rq);
 	if (err)
 		goto err_destroy_cq;
 
@@ -116,15 +118,14 @@ static int mlx5e_create_trap_direct_rq_tir(struct mlx5_core_dev *mdev, struct ml
 }
 
 static void mlx5e_build_trap_params(struct mlx5_core_dev *mdev,
-				    int max_mtu, u16 q_counter,
-				    struct mlx5e_trap *t)
+				    int max_mtu, struct mlx5e_trap *t)
 {
 	struct mlx5e_params *params = &t->params;
 
 	params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC;
 	mlx5e_init_rq_type_params(mdev, params);
 	params->sw_mtu = max_mtu;
-	mlx5e_build_rq_param(mdev, params, NULL, q_counter, &t->rq_param);
+	mlx5e_build_rq_param(mdev, params, NULL, &t->rq_param);
 }
 
 static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
@@ -138,7 +139,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 	if (!t)
 		return ERR_PTR(-ENOMEM);
 
-	mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, priv->q_counter, t);
+	mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, t);
 
 	t->priv     = priv;
 	t->mdev     = priv->mdev;

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c

@@ -49,10 +49,9 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
 static void mlx5e_build_xsk_cparam(struct mlx5_core_dev *mdev,
 				   struct mlx5e_params *params,
 				   struct mlx5e_xsk_param *xsk,
-				   u16 q_counter,
 				   struct mlx5e_channel_param *cparam)
 {
-	mlx5e_build_rq_param(mdev, params, xsk, q_counter, &cparam->rq);
+	mlx5e_build_rq_param(mdev, params, xsk, &cparam->rq);
 	mlx5e_build_xdpsq_param(mdev, params, xsk, &cparam->xdp_sq);
 }
 
@@ -93,6 +92,7 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 			     struct mlx5e_rq_param *rq_params, struct xsk_buff_pool *pool,
 			     struct mlx5e_xsk_param *xsk)
 {
+	u16 q_counter = c->priv->q_counter[c->sd_ix];
 	struct mlx5e_rq *xskrq = &c->xskrq;
 	int err;
 
@@ -100,7 +100,7 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 	if (err)
 		return err;
 
-	err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), xskrq);
+	err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), q_counter, xskrq);
 	if (err)
 		return err;
 
@@ -125,7 +125,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	if (!cparam)
 		return -ENOMEM;
 
-	mlx5e_build_xsk_cparam(priv->mdev, params, xsk, priv->q_counter, cparam);
+	mlx5e_build_xsk_cparam(priv->mdev, params, xsk, cparam);
 
 	err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp,
 			    &c->xskrq.cq);

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -1025,7 +1025,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 	mlx5_wq_destroy(&rq->wq_ctrl);
 }
 
-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)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;
 	u8 ts_format;
@@ -1052,6 +1052,7 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
 	MLX5_SET(rqc,  rqc, cqn,		rq->cq.mcq.cqn);
 	MLX5_SET(rqc,  rqc, state,		MLX5_RQC_STATE_RST);
 	MLX5_SET(rqc,  rqc, ts_format,		ts_format);
+	MLX5_SET(rqc,  rqc, counter_set_id,     q_counter);
 	MLX5_SET(wq,   wq,  log_wq_pg_sz,	rq->wq_ctrl.buf.page_shift -
 						MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq,  dbr_addr,		rq->wq_ctrl.db.dma);
@@ -1275,7 +1276,7 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 }
 
 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)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;
@@ -1288,7 +1289,7 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
 	if (err)
 		return err;
 
-	err = mlx5e_create_rq(rq, param);
+	err = mlx5e_create_rq(rq, param, q_counter);
 	if (err)
 		goto err_free_rq;
 
@@ -2334,13 +2335,14 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 static int mlx5e_open_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
 			     struct mlx5e_rq_param *rq_params)
 {
+	u16 q_counter = c->priv->q_counter[c->sd_ix];
 	int err;
 
 	err = mlx5e_init_rxq_rq(c, params, rq_params->xdp_frag_size, &c->rq);
 	if (err)
 		return err;
 
-	return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), &c->rq);
+	return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), q_counter, &c->rq);
 }
 
 static int mlx5e_open_queues(struct mlx5e_channel *c,
@@ -2557,6 +2559,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
 	c->vec_ix   = vec_ix;
+	c->sd_ix    = mlx5_sd_ch_ix_get_dev_ix(mdev, ix);
 	c->cpu      = cpu;
 	c->pdev     = mlx5_core_dma_dev(mdev);
 	c->netdev   = priv->netdev;
@@ -2655,7 +2658,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 	if (!chs->c || !cparam)
 		goto err_free;
 
-	err = mlx5e_build_channel_param(priv->mdev, &chs->params, priv->q_counter, cparam);
+	err = mlx5e_build_channel_param(priv->mdev, &chs->params, cparam);
 	if (err)
 		goto err_free;
 
@@ -3346,7 +3349,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
 	struct mlx5e_cq *cq = &drop_rq->cq;
 	int err;
 
-	mlx5e_build_drop_rq_param(mdev, priv->drop_rq_q_counter, &rq_param);
+	mlx5e_build_drop_rq_param(mdev, &rq_param);
 
 	err = mlx5e_alloc_drop_cq(priv, cq, &cq_param);
 	if (err)
@@ -3360,7 +3363,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
 	if (err)
 		goto err_destroy_cq;
 
-	err = mlx5e_create_rq(drop_rq, &rq_param);
+	err = mlx5e_create_rq(drop_rq, &rq_param, priv->drop_rq_q_counter);
 	if (err)
 		goto err_free_rq;
 
@@ -5275,13 +5278,17 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv)
 	u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {};
 	struct mlx5_core_dev *mdev = priv->mdev;
-	int err;
+	struct mlx5_core_dev *pos;
+	int err, i;
 
 	MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER);
-	err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out);
-	if (!err)
-		priv->q_counter =
-			MLX5_GET(alloc_q_counter_out, out, counter_set_id);
+
+	mlx5_sd_for_each_dev(i, mdev, pos) {
+		err = mlx5_cmd_exec_inout(pos, alloc_q_counter, in, out);
+		if (!err)
+			priv->q_counter[i] =
+				MLX5_GET(alloc_q_counter_out, out, counter_set_id);
+	}
 
 	err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out);
 	if (!err)
@@ -5292,13 +5299,17 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv)
 void mlx5e_destroy_q_counters(struct mlx5e_priv *priv)
 {
 	u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {};
+	struct mlx5_core_dev *pos;
+	int i;
 
 	MLX5_SET(dealloc_q_counter_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_Q_COUNTER);
-	if (priv->q_counter) {
-		MLX5_SET(dealloc_q_counter_in, in, counter_set_id,
-			 priv->q_counter);
-		mlx5_cmd_exec_in(priv->mdev, dealloc_q_counter, in);
+	mlx5_sd_for_each_dev(i, priv->mdev, pos) {
+		if (priv->q_counter[i]) {
+			MLX5_SET(dealloc_q_counter_in, in, counter_set_id,
+				 priv->q_counter[i]);
+			mlx5_cmd_exec_in(pos, dealloc_q_counter, in);
+		}
 	}
 
 	if (priv->drop_rq_q_counter) {

drivers/net/ethernet/mellanox/mlx5/core/en_stats.c

@@ -561,11 +561,23 @@ static const struct counter_desc drop_rq_stats_desc[] = {
 #define NUM_Q_COUNTERS			ARRAY_SIZE(q_stats_desc)
 #define NUM_DROP_RQ_COUNTERS		ARRAY_SIZE(drop_rq_stats_desc)
 
+static bool q_counter_any(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *pos;
+	int i;
+
+	mlx5_sd_for_each_dev(i, priv->mdev, pos)
+		if (priv->q_counter[i++])
+			return true;
+
+	return false;
+}
+
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(qcnt)
 {
 	int num_stats = 0;
 
-	if (priv->q_counter)
+	if (q_counter_any(priv))
 		num_stats += NUM_Q_COUNTERS;
 
 	if (priv->drop_rq_q_counter)
@@ -578,7 +590,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(qcnt)
 {
 	int i;
 
-	for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++)
+	for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
 		       q_stats_desc[i].format);
 
@@ -593,7 +605,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qcnt)
 {
 	int i;
 
-	for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++)
+	for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++)
 		data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt,
 						   q_stats_desc, i);
 	for (i = 0; i < NUM_DROP_RQ_COUNTERS && priv->drop_rq_q_counter; i++)
@@ -607,18 +619,23 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(qcnt)
 	struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt;
 	u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {};
-	int ret;
+	struct mlx5_core_dev *pos;
+	u32 rx_out_of_buffer = 0;
+	int ret, i;
 
 	MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER);
 
-	if (priv->q_counter) {
-		MLX5_SET(query_q_counter_in, in, counter_set_id,
-			 priv->q_counter);
-		ret = mlx5_cmd_exec_inout(priv->mdev, query_q_counter, in, out);
-		if (!ret)
-			qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out,
-							  out, out_of_buffer);
+	mlx5_sd_for_each_dev(i, priv->mdev, pos) {
+		if (priv->q_counter[i]) {
+			MLX5_SET(query_q_counter_in, in, counter_set_id,
+				 priv->q_counter[i]);
+			ret = mlx5_cmd_exec_inout(pos, query_q_counter, in, out);
+			if (!ret)
+				rx_out_of_buffer += MLX5_GET(query_q_counter_out,
+							     out, out_of_buffer);
+		}
 	}
+	qcnt->rx_out_of_buffer = rx_out_of_buffer;
 
 	if (priv->drop_rq_q_counter) {
 		MLX5_SET(query_q_counter_in, in, counter_set_id,

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -1169,7 +1169,7 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 			MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz),
 			MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz));
 
-	params.q_counter = priv->q_counter;
+	params.q_counter = priv->q_counter[0];
 	err = devl_param_driverinit_value_get(
 		devlink, MLX5_DEVLINK_PARAM_ID_HAIRPIN_NUM_QUEUES, &val);
 	if (err) {