1 files changed, 140 insertions, 70 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 4ef3dc79f73c..dd7f338425eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -63,6 +63,7 @@
 #include "en/xsk/rx.h"
 #include "en/xsk/tx.h"
 #include "en/hv_vhca_stats.h"
+#include "en/devlink.h"
 #include "lib/mlx5.h"
 
 
@@ -1811,29 +1812,6 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 	return err;
 }
 
-static int mlx5e_alloc_xps_cpumask(struct mlx5e_channel *c,
-				   struct mlx5e_params *params)
-{
-	int num_comp_vectors = mlx5_comp_vectors_count(c->mdev);
-	int irq;
-
-	if (!zalloc_cpumask_var(&c->xps_cpumask, GFP_KERNEL))
-		return -ENOMEM;
-
-	for (irq = c->ix; irq < num_comp_vectors; irq += params->num_channels) {
-		int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(c->mdev, irq));
-
-		cpumask_set_cpu(cpu, c->xps_cpumask);
-	}
-
-	return 0;
-}
-
-static void mlx5e_free_xps_cpumask(struct mlx5e_channel *c)
-{
-	free_cpumask_var(c->xps_cpumask);
-}
-
 static int mlx5e_open_queues(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
@@ -1984,10 +1962,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->irq_desc = irq_to_desc(irq);
 	c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix);
 
-	err = mlx5e_alloc_xps_cpumask(c, params);
-	if (err)
-		goto err_free_channel;
-
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
 
 	err = mlx5e_open_queues(c, params, cparam);
@@ -2010,9 +1984,7 @@ err_close_queues:
 
 err_napi_del:
 	netif_napi_del(&c->napi);
-	mlx5e_free_xps_cpumask(c);
 
-err_free_channel:
 	kvfree(c);
 
 	return err;
@@ -2026,7 +1998,6 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 		mlx5e_activate_txqsq(&c->sq[tc]);
 	mlx5e_activate_icosq(&c->icosq);
 	mlx5e_activate_rq(&c->rq);
-	netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix);
 
 	if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
 		mlx5e_activate_xsk(c);
@@ -2051,7 +2022,6 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 		mlx5e_close_xsk(c);
 	mlx5e_close_queues(c);
 	netif_napi_del(&c->napi);
-	mlx5e_free_xps_cpumask(c);
 
 	kvfree(c);
 }
@@ -2801,6 +2771,8 @@ free_in:
 	return err;
 }
 
+static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro);
+
 static int mlx5e_set_mtu(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params, u16 mtu)
 {
@@ -2850,6 +2822,8 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 	return 0;
 }
 
+MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_set_dev_port_mtu);
+
 void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv)
 {
 	struct mlx5e_params *params = &priv->channels.params;
@@ -2886,6 +2860,54 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
+static void mlx5e_update_netdev_queues(struct mlx5e_priv *priv, u16 count)
+{
+	int num_txqs = count * priv->channels.params.num_tc;
+	int num_rxqs = count * priv->profile->rq_groups;
+	struct net_device *netdev = priv->netdev;
+
+	mlx5e_netdev_set_tcs(netdev);
+	netif_set_real_num_tx_queues(netdev, num_txqs);
+	netif_set_real_num_rx_queues(netdev, num_rxqs);
+}
+
+static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
+					   struct mlx5e_params *params)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int num_comp_vectors, ix, irq;
+
+	num_comp_vectors = mlx5_comp_vectors_count(mdev);
+
+	for (ix = 0; ix < params->num_channels; ix++) {
+		cpumask_clear(priv->scratchpad.cpumask);
+
+		for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) {
+			int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(mdev, irq));
+
+			cpumask_set_cpu(cpu, priv->scratchpad.cpumask);
+		}
+
+		netif_set_xps_queue(priv->netdev, priv->scratchpad.cpumask, ix);
+	}
+}
+
+int mlx5e_num_channels_changed(struct mlx5e_priv *priv)
+{
+	u16 count = priv->channels.params.num_channels;
+
+	mlx5e_update_netdev_queues(priv, count);
+	mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params);
+
+	if (!netif_is_rxfh_configured(priv->netdev))
+		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+					      MLX5E_INDIR_RQT_SIZE, count);
+
+	return 0;
+}
+
+MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_num_channels_changed);
+
 static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
 {
 	int i, ch;
@@ -2907,14 +2929,6 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
 
 void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 {
-	int num_txqs = priv->channels.num * priv->channels.params.num_tc;
-	int num_rxqs = priv->channels.num * priv->profile->rq_groups;
-	struct net_device *netdev = priv->netdev;
-
-	mlx5e_netdev_set_tcs(netdev);
-	netif_set_real_num_tx_queues(netdev, num_txqs);
-	netif_set_real_num_rx_queues(netdev, num_rxqs);
-
 	mlx5e_build_txq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
 	mlx5e_xdp_tx_enable(priv);
@@ -2947,42 +2961,52 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 	mlx5e_deactivate_channels(&priv->channels);
 }
 
-static void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
-				       struct mlx5e_channels *new_chs,
-				       mlx5e_fp_hw_modify hw_modify)
+static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				      struct mlx5e_channels *new_chs,
+				      mlx5e_fp_preactivate preactivate,
+				      void *context)
 {
 	struct net_device *netdev = priv->netdev;
-	int new_num_txqs;
+	struct mlx5e_channels old_chs;
 	int carrier_ok;
-
-	new_num_txqs = new_chs->num * new_chs->params.num_tc;
+	int err = 0;
 
 	carrier_ok = netif_carrier_ok(netdev);
 	netif_carrier_off(netdev);
 
-	if (new_num_txqs < netdev->real_num_tx_queues)
-		netif_set_real_num_tx_queues(netdev, new_num_txqs);
-
 	mlx5e_deactivate_priv_channels(priv);
-	mlx5e_close_channels(&priv->channels);
 
+	old_chs = priv->channels;
 	priv->channels = *new_chs;
 
-	/* New channels are ready to roll, modify HW settings if needed */
-	if (hw_modify)
-		hw_modify(priv);
+	/* New channels are ready to roll, call the preactivate hook if needed
+	 * to modify HW settings or update kernel parameters.
+	 */
+	if (preactivate) {
+		err = preactivate(priv, context);
+		if (err) {
+			priv->channels = old_chs;
+			goto out;
+		}
+	}
 
+	mlx5e_close_channels(&old_chs);
 	priv->profile->update_rx(priv);
+
+out:
 	mlx5e_activate_priv_channels(priv);
 
 	/* return carrier back if needed */
 	if (carrier_ok)
 		netif_carrier_on(netdev);
+
+	return err;
 }
 
 int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
 			       struct mlx5e_channels *new_chs,
-			       mlx5e_fp_hw_modify hw_modify)
+			       mlx5e_fp_preactivate preactivate,
+			       void *context)
 {
 	int err;
 
@@ -2990,8 +3014,16 @@ int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
 	if (err)
 		return err;
 
-	mlx5e_switch_priv_channels(priv, new_chs, hw_modify);
+	err = mlx5e_switch_priv_channels(priv, new_chs, preactivate, context);
+	if (err)
+		goto err_close;
+
 	return 0;
+
+err_close:
+	mlx5e_close_channels(new_chs);
+
+	return err;
 }
 
 int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
@@ -2999,7 +3031,7 @@ int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
 	struct mlx5e_channels new_channels = {};
 
 	new_channels.params = priv->channels.params;
-	return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL);
 }
 
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
@@ -3448,7 +3480,8 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+	err = mlx5e_safe_switch_channels(priv, &new_channels,
+					 mlx5e_num_channels_changed_ctx, NULL);
 	if (err)
 		goto out;
 
@@ -3661,7 +3694,8 @@ static int set_feature_lro(struct net_device *netdev, bool enable)
 		goto out;
 	}
 
-	err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_modify_tirs_lro);
+	err = mlx5e_safe_switch_channels(priv, &new_channels,
+					 mlx5e_modify_tirs_lro_ctx, NULL);
 out:
 	mutex_unlock(&priv->state_lock);
 	return err;
@@ -3880,7 +3914,7 @@ static bool mlx5e_xsk_validate_mtu(struct net_device *netdev,
 }
 
 int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
-		     change_hw_mtu_cb set_mtu_cb)
+		     mlx5e_fp_preactivate preactivate)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_channels new_channels = {};
@@ -3929,13 +3963,13 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 
 	if (!reset) {
 		params->sw_mtu = new_mtu;
-		if (set_mtu_cb)
-			set_mtu_cb(priv);
+		if (preactivate)
+			preactivate(priv, NULL);
 		netdev->mtu = params->sw_mtu;
 		goto out;
 	}
 
-	err = mlx5e_safe_switch_channels(priv, &new_channels, set_mtu_cb);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, preactivate, NULL);
 	if (err)
 		goto out;
 
@@ -3948,7 +3982,7 @@ out:
 
 static int mlx5e_change_nic_mtu(struct net_device *netdev, int new_mtu)
 {
-	return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu);
+	return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu_ctx);
 }
 
 int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
@@ -4409,7 +4443,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 		mlx5e_set_rq_type(priv->mdev, &new_channels.params);
 		old_prog = priv->channels.params.xdp_prog;
 
-		err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+		err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL);
 		if (err)
 			goto unlock;
 	} else {
@@ -4589,6 +4623,7 @@ const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
 #endif
+	.ndo_get_devlink_port    = mlx5e_get_devlink_port,
 };
 
 static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
@@ -4787,9 +4822,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv,
 	mlx5e_build_rq_params(mdev, params);
 
 	/* HW LRO */
-
-	/* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */
-	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+	if (MLX5_CAP_ETH(mdev, lro_cap) &&
+	    params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		/* No XSK params: checking the availability of striding RQ in general. */
 		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
 			params->lro_en = !slow_pci_heuristic(mdev);
@@ -5230,6 +5264,9 @@ int mlx5e_netdev_init(struct net_device *netdev,
 	priv->max_nch     = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1);
 	priv->max_opened_tc = 1;
 
+	if (!alloc_cpumask_var(&priv->scratchpad.cpumask, GFP_KERNEL))
+		return -ENOMEM;
+
 	mutex_init(&priv->state_lock);
 	INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
 	INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
@@ -5238,7 +5275,7 @@ int mlx5e_netdev_init(struct net_device *netdev,
 
 	priv->wq = create_singlethread_workqueue("mlx5e");
 	if (!priv->wq)
-		return -ENOMEM;
+		goto err_free_cpumask;
 
 	/* netdev init */
 	netif_carrier_off(netdev);
@@ -5248,11 +5285,17 @@ int mlx5e_netdev_init(struct net_device *netdev,
 #endif
 
 	return 0;
+
+err_free_cpumask:
+	free_cpumask_var(priv->scratchpad.cpumask);
+
+	return -ENOMEM;
 }
 
 void mlx5e_netdev_cleanup(struct net_device *netdev, struct mlx5e_priv *priv)
 {
 	destroy_workqueue(priv->wq);
+	free_cpumask_var(priv->scratchpad.cpumask);
 }
 
 struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
@@ -5287,6 +5330,7 @@ err_free_netdev:
 
 int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 {
+	const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED;
 	const struct mlx5e_profile *profile;
 	int max_nch;
 	int err;
@@ -5298,10 +5342,25 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	max_nch = mlx5e_get_max_num_channels(priv->mdev);
 	if (priv->channels.params.num_channels > max_nch) {
 		mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
+		/* Reducing the number of channels - RXFH has to be reset, and
+		 * mlx5e_num_channels_changed below will build the RQT.
+		 */
+		priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED;
 		priv->channels.params.num_channels = max_nch;
-		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
-					      MLX5E_INDIR_RQT_SIZE, max_nch);
 	}
+	/* 1. Set the real number of queues in the kernel the first time.
+	 * 2. Set our default XPS cpumask.
+	 * 3. Build the RQT.
+	 *
+	 * rtnl_lock is required by netif_set_real_num_*_queues in case the
+	 * netdev has been registered by this point (if this function was called
+	 * in the reload or resume flow).
+	 */
+	if (take_rtnl)
+		rtnl_lock();
+	mlx5e_num_channels_changed(priv);
+	if (take_rtnl)
+		rtnl_unlock();
 
 	err = profile->init_tx(priv);
 	if (err)
@@ -5425,17 +5484,27 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 		goto err_destroy_netdev;
 	}
 
+	err = mlx5e_devlink_port_register(priv);
+	if (err) {
+		mlx5_core_err(mdev, "mlx5e_devlink_port_register failed, %d\n", err);
+		goto err_detach;
+	}
+
 	err = register_netdev(netdev);
 	if (err) {
 		mlx5_core_err(mdev, "register_netdev failed, %d\n", err);
-		goto err_detach;
+		goto err_devlink_port_unregister;
 	}
 
+	mlx5e_devlink_port_type_eth_set(priv);
+
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_init_app(priv);
 #endif
 	return priv;
 
+err_devlink_port_unregister:
+	mlx5e_devlink_port_unregister(priv);
 err_detach:
 	mlx5e_detach(mdev, priv);
 err_destroy_netdev:
@@ -5457,6 +5526,7 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_delete_app(priv);
 #endif
+	mlx5e_devlink_port_unregister(priv);
 	unregister_netdev(priv->netdev);
 	mlx5e_detach(mdev, vpriv);
 	mlx5e_destroy_netdev(priv);