Merge branch 'mlx5-fixes'

Tariq Toukan says:

====================
mlx5 fixes

This patchset provides bug fixes to mlx5 core and Eth drivers.
====================

Link: https://lore.kernel.org/r/20240411115444.374475-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 39 insertions, 23 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 0ab9db31953025..22918b2ef7f128 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -108,7 +108,10 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 	mlx5e_reset_txqsq_cc_pc(sq);
 	sq->stats->recover++;
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
+	rtnl_lock();
 	mlx5e_activate_txqsq(sq);
+	rtnl_unlock();
+
 	if (sq->channel)
 		mlx5e_trigger_napi_icosq(sq->channel);
 	else
@@ -179,12 +182,16 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
 	carrier_ok = netif_carrier_ok(netdev);
 	netif_carrier_off(netdev);
 
+	rtnl_lock();
 	mlx5e_deactivate_priv_channels(priv);
+	rtnl_unlock();
 
 	mlx5e_ptp_close(chs->ptp);
 	err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp);
 
+	rtnl_lock();
 	mlx5e_activate_priv_channels(priv);
+	rtnl_unlock();
 
 	/* return carrier back if needed */
 	if (carrier_ok)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index c7f542d0b8f08c..93cf23278d93c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -46,6 +46,10 @@ struct arfs_table {
 	struct hlist_head	 rules_hash[ARFS_HASH_SIZE];
 };
 
+enum {
+	MLX5E_ARFS_STATE_ENABLED,
+};
+
 enum arfs_type {
 	ARFS_IPV4_TCP,
 	ARFS_IPV6_TCP,
@@ -60,6 +64,7 @@ struct mlx5e_arfs_tables {
 	spinlock_t                     arfs_lock;
 	int                            last_filter_id;
 	struct workqueue_struct        *wq;
+	unsigned long                  state;
 };
 
 struct arfs_tuple {
@@ -170,6 +175,8 @@ int mlx5e_arfs_enable(struct mlx5e_flow_steering *fs)
 			return err;
 		}
 	}
+	set_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state);
+
 	return 0;
 }
 
@@ -455,6 +462,8 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs)
 	int i;
 	int j;
 
+	clear_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state);
+
 	spin_lock_bh(&arfs->arfs_lock);
 	mlx5e_for_each_arfs_rule(rule, htmp, arfs->arfs_tables, i, j) {
 		hlist_del_init(&rule->hlist);
@@ -627,17 +636,8 @@ static void arfs_handle_work(struct work_struct *work)
 	struct mlx5_flow_handle *rule;
 
 	arfs = mlx5e_fs_get_arfs(priv->fs);
-	mutex_lock(&priv->state_lock);
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		spin_lock_bh(&arfs->arfs_lock);
-		hlist_del(&arfs_rule->hlist);
-		spin_unlock_bh(&arfs->arfs_lock);
-
-		mutex_unlock(&priv->state_lock);
-		kfree(arfs_rule);
-		goto out;
-	}
-	mutex_unlock(&priv->state_lock);
+	if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state))
+		return;
 
 	if (!arfs_rule->rule) {
 		rule = arfs_add_rule(priv, arfs_rule);
@@ -753,6 +753,11 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 		return -EPROTONOSUPPORT;
 
 	spin_lock_bh(&arfs->arfs_lock);
+	if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) {
+		spin_unlock_bh(&arfs->arfs_lock);
+		return -EPERM;
+	}
+
 	arfs_rule = arfs_find_rule(arfs_t, &fk);
 	if (arfs_rule) {
 		if (arfs_rule->rxq == rxq_index || work_busy(&arfs_rule->arfs_work)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 8f101181648c6a..67a29826bb5702 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -589,12 +589,12 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 static void
 mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	int tc;
 	int i;
 
 	for (i = 0; i < priv->channels.num; ++i) {
 		struct mlx5e_channel *c = priv->channels.c[i];
+		struct mlx5_core_dev *mdev = c->mdev;
 
 		for (tc = 0; tc < c->num_tc; tc++) {
 			mlx5_core_modify_cq_moderation(mdev,
@@ -608,11 +608,11 @@ mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coal
 static void
 mlx5e_set_priv_channels_rx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	int i;
 
 	for (i = 0; i < priv->channels.num; ++i) {
 		struct mlx5e_channel *c = priv->channels.c[i];
+		struct mlx5_core_dev *mdev = c->mdev;
 
 		mlx5_core_modify_cq_moderation(mdev, &c->rq.cq.mcq,
 					       coal->rx_coalesce_usecs,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b375ef268671ab..319930c04093ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -209,8 +209,8 @@ static int mlx5e_devcom_init_mpv(struct mlx5e_priv *priv, u64 *data)
 						      *data,
 						      mlx5e_devcom_event_mpv,
 						      priv);
-	if (IS_ERR_OR_NULL(priv->devcom))
-		return -EOPNOTSUPP;
+	if (IS_ERR(priv->devcom))
+		return PTR_ERR(priv->devcom);
 
 	if (mlx5_core_is_mp_master(priv->mdev)) {
 		mlx5_devcom_send_event(priv->devcom, MPV_DEVCOM_MASTER_UP,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 1f60954c12f725..844d3e3a65ddf0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3060,7 +3060,7 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key)
 						     key,
 						     mlx5_esw_offloads_devcom_event,
 						     esw);
-	if (IS_ERR_OR_NULL(esw->devcom))
+	if (IS_ERR(esw->devcom))
 		return;
 
 	mlx5_devcom_send_event(esw->devcom,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index d14459e5c04fc5..69d482f7c5a299 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -703,8 +703,10 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 		return err;
 	}
 
-	if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags))
+	if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) {
 		mlx5_lag_port_sel_destroy(ldev);
+		ldev->buckets = 1;
+	}
 	if (mlx5_lag_has_drop_rule(ldev))
 		mlx5_lag_drop_rule_cleanup(ldev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
index e7d59cfa8708e1..7b0766c89f4cf0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
@@ -220,7 +220,7 @@ mlx5_devcom_register_component(struct mlx5_devcom_dev *devc,
 	struct mlx5_devcom_comp *comp;
 
 	if (IS_ERR_OR_NULL(devc))
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	mutex_lock(&comp_list_lock);
 	comp = devcom_component_get(devc, id, key, handler);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
index 5b28084e8a03c7..dd5d186dc6148f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
@@ -213,8 +213,8 @@ static int sd_register(struct mlx5_core_dev *dev)
 	sd = mlx5_get_sd(dev);
 	devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP,
 						sd->group_id, NULL, dev);
-	if (!devcom)
-		return -ENOMEM;
+	if (IS_ERR(devcom))
+		return PTR_ERR(devcom);
 
 	sd->devcom = devcom;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 59806553889e90..331ce47f51a17a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -956,7 +956,7 @@ static void mlx5_register_hca_devcom_comp(struct mlx5_core_dev *dev)
 		mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_HCA_PORTS,
 					       mlx5_query_nic_system_image_guid(dev),
 					       NULL, dev);
-	if (IS_ERR_OR_NULL(dev->priv.hca_devcom_comp))
+	if (IS_ERR(dev->priv.hca_devcom_comp))
 		mlx5_core_err(dev, "Failed to register devcom HCA component\n");
 }
 
@@ -1699,12 +1699,15 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev)
 	err = mlx5_devlink_params_register(priv_to_devlink(dev));
 	if (err) {
 		mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err);
-		goto query_hca_caps_err;
+		goto params_reg_err;
 	}
 
 	devl_unlock(devlink);
 	return 0;
 
+params_reg_err:
+	devl_unregister(devlink);
+	devl_unlock(devlink);
 query_hca_caps_err:
 	devl_unregister(devlink);
 	devl_unlock(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
index e3bf8c7e4baa62..7ebe712808275a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -75,7 +75,6 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia
 		goto peer_devlink_set_err;
 	}
 
-	devlink_register(devlink);
 	return 0;
 
 peer_devlink_set_err: