diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index a9166cd85013..ceebfc20f65e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -303,6 +303,7 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 	int ret = 0, i;
 
 	mutex_lock(&mlx5_intf_mutex);
+	priv->flags &= ~MLX5_PRIV_FLAGS_DETACH;
 	for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) {
 		if (!priv->adev[i]) {
 			bool is_supported = false;
@@ -320,6 +321,16 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 			}
 		} else {
 			adev = &priv->adev[i]->adev;
+
+			/* Pay attention that this is not PCI driver that
+			 * mlx5_core_dev is connected, but auxiliary driver.
+			 *
+			 * Here we can race of module unload with devlink
+			 * reload, but we don't need to take extra lock because
+			 * we are holding global mlx5_intf_mutex.
+			 */
+			if (!adev->dev.driver)
+				continue;
 			adrv = to_auxiliary_drv(adev->dev.driver);
 
 			if (adrv->resume)
@@ -350,6 +361,10 @@ void mlx5_detach_device(struct mlx5_core_dev *dev)
 			continue;
 
 		adev = &priv->adev[i]->adev;
+		/* Auxiliary driver was unbind manually through sysfs */
+		if (!adev->dev.driver)
+			goto skip_suspend;
+
 		adrv = to_auxiliary_drv(adev->dev.driver);
 
 		if (adrv->suspend) {
@@ -357,9 +372,11 @@ void mlx5_detach_device(struct mlx5_core_dev *dev)
 			continue;
 		}
 
+skip_suspend:
 		del_adev(&priv->adev[i]->adev);
 		priv->adev[i] = NULL;
 	}
+	priv->flags |= MLX5_PRIV_FLAGS_DETACH;
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
@@ -448,6 +465,8 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev)
 	struct mlx5_priv *priv = &dev->priv;
 
 	lockdep_assert_held(&mlx5_intf_mutex);
+	if (priv->flags & MLX5_PRIV_FLAGS_DETACH)
+		return 0;
 
 	delete_drivers(dev);
 	if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index b88705a3a1a8..97e6cb6f13c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1054,6 +1054,12 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num,
 			goto err_vhca_mapping;
 	}
 
+	/* External controller host PF has factory programmed MAC.
+	 * Read it from the device.
+	 */
+	if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF)
+		mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac);
+
 	esw_vport_change_handle_locked(vport);
 
 	esw->enabled_vports++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a1d67bd7fb43..0d0f63a27aba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1161,7 +1161,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 	err = mlx5_core_set_hca_defaults(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to set hca defaults\n");
-		goto err_sriov;
+		goto err_set_hca;
 	}
 
 	mlx5_vhca_event_start(dev);
@@ -1194,6 +1194,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 	mlx5_sf_hw_table_destroy(dev);
 err_vhca:
 	mlx5_vhca_event_stop(dev);
+err_set_hca:
 	mlx5_cleanup_fs(dev);
 err_fs:
 	mlx5_accel_tls_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 50af84e76fb6..174f71ed5280 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -54,7 +54,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 	mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
 	mkey->iova = MLX5_GET64(mkc, mkc, start_addr);
 	mkey->size = MLX5_GET64(mkc, mkc, len);
-	mkey->key |= mlx5_idx_to_mkey(mkey_index);
+	mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index);
 	mkey->pd = MLX5_GET(mkc, mkc, pd);
 	init_waitqueue_head(&mkey->wait);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 6a0c6f965ad1..fa0288afc0dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -163,6 +163,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_
 	sf_index = event->function_id - base_id;
 	sf_dev = xa_load(&table->devices, sf_index);
 	switch (event->new_vhca_state) {
+	case MLX5_VHCA_STATE_INVALID:
 	case MLX5_VHCA_STATE_ALLOCATED:
 		if (sf_dev)
 			mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
index 054c2e2b6554..7466f016375c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
@@ -694,7 +694,11 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data,
 	if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM)
 		return -EINVAL;
 
-	memcpy(padded_data, data, data_sz);
+	inline_data_sz =
+		MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data);
+
+	/* Add an alignment padding  */
+	memcpy(padded_data + data_sz % inline_data_sz, data, data_sz);
 
 	/* Remove L2L3 outer headers */
 	MLX5_SET(ste_single_action_remove_header_v1, hw_action, action_id,
@@ -706,32 +710,34 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data,
 	hw_action += DR_STE_ACTION_DOUBLE_SZ;
 	used_actions++; /* Remove and NOP are a single double action */
 
-	inline_data_sz =
-		MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data);
+	/* Point to the last dword of the header */
+	data_ptr += (data_sz / inline_data_sz) * inline_data_sz;
 
-	/* Add the new header inline + 2 extra bytes */
+	/* Add the new header using inline action 4Byte at a time, the header
+	 * is added in reversed order to the beginning of the packet to avoid
+	 * incorrect parsing by the HW. Since header is 14B or 18B an extra
+	 * two bytes are padded and later removed.
+	 */
 	for (i = 0; i < data_sz / inline_data_sz + 1; i++) {
 		void *addr_inline;
 
 		MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, action_id,
 			 DR_STE_V1_ACTION_ID_INSERT_INLINE);
 		/* The hardware expects here offset to words (2 bytes) */
-		MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset,
-			 i * 2);
+		MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, 0);
 
 		/* Copy bytes one by one to avoid endianness problem */
 		addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v1,
 					   hw_action, inline_data);
-		memcpy(addr_inline, data_ptr, inline_data_sz);
+		memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz);
 		hw_action += DR_STE_ACTION_DOUBLE_SZ;
-		data_ptr += inline_data_sz;
 		used_actions++;
 	}
 
-	/* Remove 2 extra bytes */
+	/* Remove first 2 extra bytes */
 	MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, action_id,
 		 DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
-	MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, data_sz / 2);
+	MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, 0);
 	/* The hardware expects here size in words (2 bytes) */
 	MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, remove_size, 1);
 	used_actions++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 457ad42eaa2a..4c1440a95ad7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -465,8 +465,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 	void *in;
 	int err;
 
-	if (!vport)
-		return -EINVAL;
 	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
 		return -EACCES;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 020a8f7fdbdd..f8902bcd91e2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -542,6 +542,10 @@ struct mlx5_core_roce {
 enum {
 	MLX5_PRIV_FLAGS_DISABLE_IB_ADEV = 1 << 0,
 	MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV = 1 << 1,
+	/* Set during device detach to block any further devices
+	 * creation/deletion on drivers rescan. Unset during device attach.
+	 */
+	MLX5_PRIV_FLAGS_DETACH = 1 << 2,
 };
 
 struct mlx5_adev {