Merge branch 'net-ethernet-ti-am65-cpsw-add-multi-port-support-in-mac-only-mode'

Grygorii Strashko says:

====================
net: ethernet: ti: am65-cpsw: add multi port support in mac-only mode

This series adds multi-port support in mac-only mode (multi MAC mode) to TI
AM65x CPSW driver in preparation for enabling support for multi-port devices,
like Main CPSW0 on K3 J721E SoC or future CPSW3g on K3 AM64x SoC.

The multi MAC mode is implemented by configuring every enabled port in "mac-only"
mode (all ingress packets are sent only to the Host port and egress packets
directed to target Ext. Port) and creating separate net_device for
every enabled Ext. port.

This series does not affect on existing CPSW2g one Ext. Port devices and xmit
path changes are done only for multi-port devices by splitting xmit path for
one-port and multi-port devices.

Patches 1-3: Preparation patches to improve K3 CPSW configuration depending on DT
Patches 4-5: Fix VLAN offload for multi MAC mode
Patch 6: Fixes CPTS context lose issue during PM runtime transition
Patch 7: Fixes TX csum offload for multi MAC mode
Patches 8-9: add multi-port support to TI AM65x CPSW
Patch 10: handle deferred probe with new dev_err_probe() API

changes in v3:
 - rebased
 - added Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
 - added Patch 10 which is minor optimization

changes in v2:
- patch 8: xmit path split for one-port and multi-port devices to avoid
  performance losses
- patch 9: fixed the case when Port 1 is disabled
- Patch 7: added fix for TX csum offload

v2: https://lore.kernel.org/patchwork/cover/1321608/
v1: https://lore.kernel.org/patchwork/cover/1315766/
====================

Link: https://lore.kernel.org/r/20201030200707.24294-1-grygorii.strashko@ti.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/ti/am65-cpsw-nuss.c

@@ -241,8 +241,8 @@ static int am65_cpsw_nuss_ndo_slave_add_vid(struct net_device *ndev,
 	if (!vid)
 		unreg_mcast = port_mask;
 	dev_info(common->dev, "Adding vlan %d to vlan filter\n", vid);
-	ret = cpsw_ale_add_vlan(common->ale, vid, port_mask,
-				unreg_mcast, port_mask, 0);
+	ret = cpsw_ale_vlan_add_modify(common->ale, vid, port_mask,
+				       unreg_mcast, port_mask, 0);
 
 	pm_runtime_put(common->dev);
 	return ret;
@@ -252,6 +252,7 @@ static int am65_cpsw_nuss_ndo_slave_kill_vid(struct net_device *ndev,
 					     __be16 proto, u16 vid)
 {
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 	int ret;
 
 	if (!netif_running(ndev) || !vid)
@@ -264,14 +265,15 @@ static int am65_cpsw_nuss_ndo_slave_kill_vid(struct net_device *ndev,
 	}
 
 	dev_info(common->dev, "Removing vlan %d from vlan filter\n", vid);
-	ret = cpsw_ale_del_vlan(common->ale, vid, 0);
+	ret = cpsw_ale_del_vlan(common->ale, vid,
+				BIT(port->port_id) | ALE_PORT_HOST);
 
 	pm_runtime_put(common->dev);
 	return ret;
 }
 
-static void am65_cpsw_slave_set_promisc_2g(struct am65_cpsw_port *port,
-					   bool promisc)
+static void am65_cpsw_slave_set_promisc(struct am65_cpsw_port *port,
+					bool promisc)
 {
 	struct am65_cpsw_common *common = port->common;
 
@@ -296,7 +298,7 @@ static void am65_cpsw_nuss_ndo_slave_set_rx_mode(struct net_device *ndev)
 	bool promisc;
 
 	promisc = !!(ndev->flags & IFF_PROMISC);
-	am65_cpsw_slave_set_promisc_2g(port, promisc);
+	am65_cpsw_slave_set_promisc(port, promisc);
 
 	if (promisc)
 		return;
@@ -373,7 +375,7 @@ static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common,
 
 	cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT,
 			 AM65_CPSW_NAV_PS_DATA_SIZE);
-	cppi5_hdesc_attach_buf(desc_rx, 0, 0, buf_dma, skb_tailroom(skb));
+	cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb));
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
 	*((void **)swdata) = skb;
 
@@ -426,9 +428,7 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common,
 	writel(common->rx_flow_id_base,
 	       host_p->port_base + AM65_CPSW_PORT0_REG_FLOW_ID_OFFSET);
 	/* en tx crc offload */
-	if (features & NETIF_F_HW_CSUM)
-		writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN,
-		       host_p->port_base + AM65_CPSW_P0_REG_CTL);
+	writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN, host_p->port_base + AM65_CPSW_P0_REG_CTL);
 
 	am65_cpsw_nuss_set_p0_ptype(common);
 
@@ -629,13 +629,13 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev)
 
 	am65_cpsw_port_set_sl_mac(port, ndev->dev_addr);
 
-	if (port->slave.mac_only)
+	if (port->slave.mac_only) {
 		/* enable mac-only mode on port */
 		cpsw_ale_control_set(common->ale, port->port_id,
 				     ALE_PORT_MACONLY, 1);
-	if (AM65_CPSW_IS_CPSW2G(common))
 		cpsw_ale_control_set(common->ale, port->port_id,
 				     ALE_PORT_NOLEARN, 1);
+	}
 
 	port_mask = BIT(port->port_id) | ALE_PORT_HOST;
 	cpsw_ale_add_ucast(common->ale, ndev->dev_addr,
@@ -767,7 +767,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 		return ret;
 	}
 
-	if (desc_dma & 0x1) {
+	if (cppi5_desc_is_tdcm(desc_dma)) {
 		dev_dbg(dev, "%s RX tdown flow: %u\n", __func__, flow_idx);
 		return 0;
 	}
@@ -911,10 +911,57 @@ static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma)
 	dev_kfree_skb_any(skb);
 }
 
+static struct sk_buff *
+am65_cpsw_nuss_tx_compl_packet(struct am65_cpsw_tx_chn *tx_chn,
+			       dma_addr_t desc_dma)
+{
+	struct am65_cpsw_ndev_priv *ndev_priv;
+	struct am65_cpsw_ndev_stats *stats;
+	struct cppi5_host_desc_t *desc_tx;
+	struct net_device *ndev;
+	struct sk_buff *skb;
+	void **swdata;
+
+	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
+					     desc_dma);
+	swdata = cppi5_hdesc_get_swdata(desc_tx);
+	skb = *(swdata);
+	am65_cpsw_nuss_xmit_free(tx_chn, tx_chn->common->dev, desc_tx);
+
+	ndev = skb->dev;
+
+	am65_cpts_tx_timestamp(tx_chn->common->cpts, skb);
+
+	ndev_priv = netdev_priv(ndev);
+	stats = this_cpu_ptr(ndev_priv->stats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->tx_packets++;
+	stats->tx_bytes += skb->len;
+	u64_stats_update_end(&stats->syncp);
+
+	return skb;
+}
+
+static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_device *ndev,
+				   struct netdev_queue *netif_txq)
+{
+	if (netif_tx_queue_stopped(netif_txq)) {
+		/* Check whether the queue is stopped due to stalled
+		 * tx dma, if the queue is stopped then wake the queue
+		 * as we have free desc for tx
+		 */
+		__netif_tx_lock(netif_txq, smp_processor_id());
+		if (netif_running(ndev) &&
+		    (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >= MAX_SKB_FRAGS))
+			netif_tx_wake_queue(netif_txq);
+
+		__netif_tx_unlock(netif_txq);
+	}
+}
+
 static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 					   int chn, unsigned int budget)
 {
-	struct cppi5_host_desc_t *desc_tx;
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
 	struct netdev_queue *netif_txq;
@@ -923,41 +970,68 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 	struct sk_buff *skb;
 	dma_addr_t desc_dma;
 	int res, num_tx = 0;
-	void **swdata;
 
 	tx_chn = &common->tx_chns[chn];
 
 	while (true) {
-		struct am65_cpsw_ndev_priv *ndev_priv;
-		struct am65_cpsw_ndev_stats *stats;
-
+		spin_lock(&tx_chn->lock);
 		res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
+		spin_unlock(&tx_chn->lock);
 		if (res == -ENODATA)
 			break;
 
-		if (desc_dma & 0x1) {
+		if (cppi5_desc_is_tdcm(desc_dma)) {
 			if (atomic_dec_and_test(&common->tdown_cnt))
 				complete(&common->tdown_complete);
 			break;
 		}
 
-		desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
-						     desc_dma);
-		swdata = cppi5_hdesc_get_swdata(desc_tx);
-		skb = *(swdata);
-		am65_cpsw_nuss_xmit_free(tx_chn, dev, desc_tx);
-
+		skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma);
+		total_bytes = skb->len;
 		ndev = skb->dev;
+		napi_consume_skb(skb, budget);
+		num_tx++;
 
-		am65_cpts_tx_timestamp(common->cpts, skb);
+		netif_txq = netdev_get_tx_queue(ndev, chn);
 
-		ndev_priv = netdev_priv(ndev);
-		stats = this_cpu_ptr(ndev_priv->stats);
-		u64_stats_update_begin(&stats->syncp);
-		stats->tx_packets++;
-		stats->tx_bytes += skb->len;
-		u64_stats_update_end(&stats->syncp);
+		netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
 
+		am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
+	}
+
+	dev_dbg(dev, "%s:%u pkt:%d\n", __func__, chn, num_tx);
+
+	return num_tx;
+}
+
+static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common,
+					      int chn, unsigned int budget)
+{
+	struct device *dev = common->dev;
+	struct am65_cpsw_tx_chn *tx_chn;
+	struct netdev_queue *netif_txq;
+	unsigned int total_bytes = 0;
+	struct net_device *ndev;
+	struct sk_buff *skb;
+	dma_addr_t desc_dma;
+	int res, num_tx = 0;
+
+	tx_chn = &common->tx_chns[chn];
+
+	while (true) {
+		res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
+		if (res == -ENODATA)
+			break;
+
+		if (cppi5_desc_is_tdcm(desc_dma)) {
+			if (atomic_dec_and_test(&common->tdown_cnt))
+				complete(&common->tdown_complete);
+			break;
+		}
+
+		skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma);
+
+		ndev = skb->dev;
 		total_bytes += skb->len;
 		napi_consume_skb(skb, budget);
 		num_tx++;
@@ -970,19 +1044,8 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 
 	netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
 
-	if (netif_tx_queue_stopped(netif_txq)) {
-		/* Check whether the queue is stopped due to stalled tx dma,
-		 * if the queue is stopped then wake the queue as
-		 * we have free desc for tx
-		 */
-		__netif_tx_lock(netif_txq, smp_processor_id());
-		if (netif_running(ndev) &&
-		    (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >=
-		     MAX_SKB_FRAGS))
-			netif_tx_wake_queue(netif_txq);
+	am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
 
-		__netif_tx_unlock(netif_txq);
-	}
 	dev_dbg(dev, "%s:%u pkt:%d\n", __func__, chn, num_tx);
 
 	return num_tx;
@@ -993,8 +1056,11 @@ static int am65_cpsw_nuss_tx_poll(struct napi_struct *napi_tx, int budget)
 	struct am65_cpsw_tx_chn *tx_chn = am65_cpsw_napi_to_tx_chn(napi_tx);
 	int num_tx;
 
-	num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, tx_chn->id,
-						 budget);
+	if (AM65_CPSW_IS_CPSW2G(tx_chn->common))
+		num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id, budget);
+	else
+		num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, tx_chn->id, budget);
+
 	num_tx = min(num_tx, budget);
 	if (num_tx < budget) {
 		napi_complete(napi_tx);
@@ -1139,7 +1205,13 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 
 	cppi5_hdesc_set_pktlen(first_desc, pkt_len);
 	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
-	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+	if (AM65_CPSW_IS_CPSW2G(common)) {
+		ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+	} else {
+		spin_lock_bh(&tx_chn->lock);
+		ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+		spin_unlock_bh(&tx_chn->lock);
+	}
 	if (ret) {
 		dev_err(dev, "can't push desc %d\n", ret);
 		/* inform bql */
@@ -1369,32 +1441,7 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev,
 	stats->tx_dropped	= dev->stats.tx_dropped;
 }
 
-static int am65_cpsw_nuss_ndo_slave_set_features(struct net_device *ndev,
-						 netdev_features_t features)
-{
-	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
-	netdev_features_t changes = features ^ ndev->features;
-	struct am65_cpsw_host *host_p;
-
-	host_p = am65_common_get_host(common);
-
-	if (changes & NETIF_F_HW_CSUM) {
-		bool enable = !!(features & NETIF_F_HW_CSUM);
-
-		dev_info(common->dev, "Turn %s tx-checksum-ip-generic\n",
-			 enable ? "ON" : "OFF");
-		if (enable)
-			writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN,
-			       host_p->port_base + AM65_CPSW_P0_REG_CTL);
-		else
-			writel(0,
-			       host_p->port_base + AM65_CPSW_P0_REG_CTL);
-	}
-
-	return 0;
-}
-
-static const struct net_device_ops am65_cpsw_nuss_netdev_ops_2g = {
+static const struct net_device_ops am65_cpsw_nuss_netdev_ops = {
 	.ndo_open		= am65_cpsw_nuss_ndo_slave_open,
 	.ndo_stop		= am65_cpsw_nuss_ndo_slave_stop,
 	.ndo_start_xmit		= am65_cpsw_nuss_ndo_slave_xmit,
@@ -1406,7 +1453,6 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops_2g = {
 	.ndo_vlan_rx_add_vid	= am65_cpsw_nuss_ndo_slave_add_vid,
 	.ndo_vlan_rx_kill_vid	= am65_cpsw_nuss_ndo_slave_kill_vid,
 	.ndo_do_ioctl		= am65_cpsw_nuss_ndo_slave_ioctl,
-	.ndo_set_features	= am65_cpsw_nuss_ndo_slave_set_features,
 	.ndo_setup_tc           = am65_cpsw_qos_ndo_setup_tc,
 };
 
@@ -1417,7 +1463,6 @@ static void am65_cpsw_nuss_slave_disable_unused(struct am65_cpsw_port *port)
 	if (!port->disabled)
 		return;
 
-	common->disabled_ports_mask |= BIT(port->port_id);
 	cpsw_ale_control_set(common->ale, port->port_id,
 			     ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
 
@@ -1496,6 +1541,7 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common)
 		snprintf(tx_chn->tx_chn_name,
 			 sizeof(tx_chn->tx_chn_name), "tx%d", i);
 
+		spin_lock_init(&tx_chn->lock);
 		tx_chn->common = common;
 		tx_chn->id = i;
 		tx_chn->descs_num = max_desc_num;
@@ -1515,9 +1561,8 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common)
 						    tx_chn->tx_chn_name,
 						    &tx_cfg);
 		if (IS_ERR(tx_chn->tx_chn)) {
-			ret = PTR_ERR(tx_chn->tx_chn);
-			dev_err(dev, "Failed to request tx dma channel %d\n",
-				ret);
+			ret = dev_err_probe(dev, PTR_ERR(tx_chn->tx_chn),
+					    "Failed to request tx dma channel\n");
 			goto err;
 		}
 
@@ -1588,8 +1633,8 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 
 	rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, "rx", &rx_cfg);
 	if (IS_ERR(rx_chn->rx_chn)) {
-		ret = PTR_ERR(rx_chn->rx_chn);
-		dev_err(dev, "Failed to request rx dma channel %d\n", ret);
+		ret = dev_err_probe(dev, PTR_ERR(rx_chn->rx_chn),
+				    "Failed to request rx dma channel\n");
 		goto err;
 	}
 
@@ -1606,7 +1651,6 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 		};
 		struct k3_ring_cfg fdqring_cfg = {
 			.elm_size = K3_RINGACC_RING_ELSIZE_8,
-			.mode = K3_RINGACC_RING_MODE_MESSAGE,
 			.flags = K3_RINGACC_RING_SHARED,
 		};
 		struct k3_udma_glue_rx_flow_cfg rx_flow_cfg = {
@@ -1620,6 +1664,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 		rx_flow_cfg.ring_rxfdq0_id = fdqring_id;
 		rx_flow_cfg.rx_cfg.size = max_desc_num;
 		rx_flow_cfg.rxfdq_cfg.size = max_desc_num;
+		rx_flow_cfg.rxfdq_cfg.mode = common->pdata.fdqring_mode;
 
 		ret = k3_udma_glue_rx_flow_init(rx_chn->rx_chn,
 						i, &rx_flow_cfg);
@@ -1725,6 +1770,13 @@ static int am65_cpsw_init_cpts(struct am65_cpsw_common *common)
 		return ret;
 	}
 	common->cpts = cpts;
+	/* Forbid PM runtime if CPTS is running.
+	 * K3 CPSWxG modules may completely lose context during ON->OFF
+	 * transitions depending on integration.
+	 * AM65x/J721E MCU CPSW2G: false
+	 * J721E MAIN_CPSW9G: true
+	 */
+	pm_runtime_forbid(dev);
 
 	return 0;
 }
@@ -1778,8 +1830,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 			return PTR_ERR(port->slave.mac_sl);
 
 		port->disabled = !of_device_is_available(port_np);
-		if (port->disabled)
+		if (port->disabled) {
+			common->disabled_ports_mask |= BIT(port->port_id);
 			continue;
+		}
 
 		port->slave.ifphy = devm_of_phy_get(dev, port_np, NULL);
 		if (IS_ERR(port->slave.ifphy)) {
@@ -1795,12 +1849,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 		/* get phy/link info */
 		if (of_phy_is_fixed_link(port_np)) {
 			ret = of_phy_register_fixed_link(port_np);
-			if (ret) {
-				if (ret != -EPROBE_DEFER)
-					dev_err(dev, "%pOF failed to register fixed-link phy: %d\n",
-						port_np, ret);
-				return ret;
-			}
+			if (ret)
+				return dev_err_probe(dev, ret,
+						     "failed to register fixed-link phy %pOF\n",
+						     port_np);
 			port->slave.phy_node = of_node_get(port_np);
 		} else {
 			port->slave.phy_node =
@@ -1833,6 +1885,12 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 	}
 	of_node_put(node);
 
+	/* is there at least one ext.port */
+	if (!(~common->disabled_ports_mask & GENMASK(common->port_num, 1))) {
+		dev_err(dev, "No Ext. port are available\n");
+		return -ENODEV;
+	}
+
 	return 0;
 }
 
@@ -1843,14 +1901,18 @@ static void am65_cpsw_pcpu_stats_free(void *data)
 	free_percpu(stats);
 }
 
-static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common)
+static int
+am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 {
 	struct am65_cpsw_ndev_priv *ndev_priv;
 	struct device *dev = common->dev;
 	struct am65_cpsw_port *port;
 	int ret;
 
-	port = am65_common_get_port(common, 1);
+	port = &common->ports[port_idx];
+
+	if (port->disabled)
+		return 0;
 
 	/* alloc netdev */
 	port->ndev = devm_alloc_etherdev_mqs(common->dev,
@@ -1879,7 +1941,7 @@ static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common)
 	port->ndev->features = port->ndev->hw_features |
 			       NETIF_F_HW_VLAN_CTAG_FILTER;
 	port->ndev->vlan_features |=  NETIF_F_SG;
-	port->ndev->netdev_ops = &am65_cpsw_nuss_netdev_ops_2g;
+	port->ndev->netdev_ops = &am65_cpsw_nuss_netdev_ops;
 	port->ndev->ethtool_ops = &am65_cpsw_ethtool_ops_slave;
 
 	/* Disable TX checksum offload by default due to HW bug */
@@ -1892,29 +1954,41 @@ static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common)
 
 	ret = devm_add_action_or_reset(dev, am65_cpsw_pcpu_stats_free,
 				       ndev_priv->stats);
-	if (ret) {
-		dev_err(dev, "Failed to add percpu stat free action %d\n", ret);
-		return ret;
+	if (ret)
+		dev_err(dev, "failed to add percpu stat free action %d\n", ret);
+
+	if (!common->dma_ndev)
+		common->dma_ndev = port->ndev;
+
+	return ret;
+}
+
+static int am65_cpsw_nuss_init_ndevs(struct am65_cpsw_common *common)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < common->port_num; i++) {
+		ret = am65_cpsw_nuss_init_port_ndev(common, i);
+		if (ret)
+			return ret;
 	}
 
-	netif_napi_add(port->ndev, &common->napi_rx,
+	netif_napi_add(common->dma_ndev, &common->napi_rx,
 		       am65_cpsw_nuss_rx_poll, NAPI_POLL_WEIGHT);
 
 	return ret;
 }
 
-static int am65_cpsw_nuss_ndev_add_napi_2g(struct am65_cpsw_common *common)
+static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
 {
 	struct device *dev = common->dev;
-	struct am65_cpsw_port *port;
 	int i, ret = 0;
 
-	port = am65_common_get_port(common, 1);
-
 	for (i = 0; i < common->tx_ch_num; i++) {
 		struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i];
 
-		netif_tx_napi_add(port->ndev, &tx_chn->napi_tx,
+		netif_tx_napi_add(common->dma_ndev, &tx_chn->napi_tx,
 				  am65_cpsw_nuss_tx_poll, NAPI_POLL_WEIGHT);
 
 		ret = devm_request_irq(dev, tx_chn->irq,
@@ -1932,16 +2006,27 @@ static int am65_cpsw_nuss_ndev_add_napi_2g(struct am65_cpsw_common *common)
 	return ret;
 }
 
-static int am65_cpsw_nuss_ndev_reg_2g(struct am65_cpsw_common *common)
+static void am65_cpsw_nuss_cleanup_ndev(struct am65_cpsw_common *common)
+{
+	struct am65_cpsw_port *port;
+	int i;
+
+	for (i = 0; i < common->port_num; i++) {
+		port = &common->ports[i];
+		if (port->ndev)
+			unregister_netdev(port->ndev);
+	}
+}
+
+static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 {
 	struct device *dev = common->dev;
 	struct am65_cpsw_port *port;
-	int ret = 0;
+	int ret = 0, i;
 
-	port = am65_common_get_port(common, 1);
-	ret = am65_cpsw_nuss_ndev_add_napi_2g(common);
+	ret = am65_cpsw_nuss_ndev_add_tx_napi(common);
 	if (ret)
-		goto err;
+		return ret;
 
 	ret = devm_request_irq(dev, common->rx_chns.irq,
 			       am65_cpsw_nuss_rx_irq,
@@ -1949,17 +2034,31 @@ static int am65_cpsw_nuss_ndev_reg_2g(struct am65_cpsw_common *common)
 	if (ret) {
 		dev_err(dev, "failure requesting rx irq %u, %d\n",
 			common->rx_chns.irq, ret);
-		goto err;
+		return ret;
+	}
+
+	for (i = 0; i < common->port_num; i++) {
+		port = &common->ports[i];
+
+		if (!port->ndev)
+			continue;
+
+		ret = register_netdev(port->ndev);
+		if (ret) {
+			dev_err(dev, "error registering slave net device%i %d\n",
+				i, ret);
+			goto err_cleanup_ndev;
+		}
 	}
 
-	ret = register_netdev(port->ndev);
-	if (ret)
-		dev_err(dev, "error registering slave net device %d\n", ret);
 
 	/* can't auto unregister ndev using devm_add_action() due to
 	 * devres release sequence in DD core for DMA
 	 */
-err:
+	return 0;
+
+err_cleanup_ndev:
+	am65_cpsw_nuss_cleanup_ndev(common);
 	return ret;
 }
 
@@ -1972,19 +2071,7 @@ int am65_cpsw_nuss_update_tx_chns(struct am65_cpsw_common *common, int num_tx)
 	if (ret)
 		return ret;
 
-	return am65_cpsw_nuss_ndev_add_napi_2g(common);
-}
-
-static void am65_cpsw_nuss_cleanup_ndev(struct am65_cpsw_common *common)
-{
-	struct am65_cpsw_port *port;
-	int i;
-
-	for (i = 0; i < common->port_num; i++) {
-		port = &common->ports[i];
-		if (port->ndev)
-			unregister_netdev(port->ndev);
-	}
+	return am65_cpsw_nuss_ndev_add_tx_napi(common);
 }
 
 struct am65_cpsw_soc_pdata {
@@ -2005,10 +2092,14 @@ static const struct soc_device_attribute am65_cpsw_socinfo[] = {
 
 static const struct am65_cpsw_pdata am65x_sr1_0 = {
 	.quirks = AM65_CPSW_QUIRK_I2027_NO_TX_CSUM,
+	.ale_dev_id = "am65x-cpsw2g",
+	.fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
 };
 
 static const struct am65_cpsw_pdata j721e_pdata = {
 	.quirks = 0,
+	.ale_dev_id = "am65x-cpsw2g",
+	.fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
 };
 
 static const struct of_device_id am65_cpsw_nuss_of_mtable[] = {
@@ -2068,9 +2159,6 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 		return -ENOENT;
 	of_node_put(node);
 
-	if (common->port_num != 1)
-		return -EOPNOTSUPP;
-
 	common->rx_flow_id_base = -1;
 	init_completion(&common->tdown_complete);
 	common->tx_ch_num = 1;
@@ -2089,13 +2177,8 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	clk = devm_clk_get(dev, "fck");
-	if (IS_ERR(clk)) {
-		ret = PTR_ERR(clk);
-
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "error getting fck clock %d\n", ret);
-		return ret;
-	}
+	if (IS_ERR(clk))
+		return dev_err_probe(dev, PTR_ERR(clk), "getting fck clock\n");
 	common->bus_freq = clk_get_rate(clk);
 
 	pm_runtime_enable(dev);
@@ -2145,7 +2228,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	ale_params.ale_ageout = AM65_CPSW_ALE_AGEOUT_DEFAULT;
 	ale_params.ale_ports = common->port_num + 1;
 	ale_params.ale_regs = common->cpsw_base + AM65_CPSW_NU_ALE_BASE;
-	ale_params.dev_id = "am65x-cpsw2g";
+	ale_params.dev_id = common->pdata.ale_dev_id;
 	ale_params.bus_freq = common->bus_freq;
 
 	common->ale = cpsw_ale_create(&ale_params);
@@ -2165,11 +2248,11 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 
 	dev_set_drvdata(dev, common);
 
-	ret = am65_cpsw_nuss_init_ndev_2g(common);
+	ret = am65_cpsw_nuss_init_ndevs(common);
 	if (ret)
 		goto err_of_clear;
 
-	ret = am65_cpsw_nuss_ndev_reg_2g(common);
+	ret = am65_cpsw_nuss_register_ndevs(common);
 	if (ret)
 		goto err_of_clear;
 

drivers/net/ethernet/ti/am65-cpsw-nuss.h

@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
+#include <linux/soc/ti/k3-ringacc.h>
 #include "am65-cpsw-qos.h"
 
 struct am65_cpts;
@@ -59,6 +60,7 @@ struct am65_cpsw_tx_chn {
 	struct am65_cpsw_common	*common;
 	struct k3_cppi_desc_pool *desc_pool;
 	struct k3_udma_glue_tx_channel *tx_chn;
+	spinlock_t lock; /* protect TX rings in multi-port mode */
 	int irq;
 	u32 id;
 	u32 descs_num;
@@ -77,6 +79,8 @@ struct am65_cpsw_rx_chn {
 
 struct am65_cpsw_pdata {
 	u32	quirks;
+	enum k3_ring_mode fdqring_mode;
+	const char	*ale_dev_id;
 };
 
 struct am65_cpsw_common {
@@ -91,6 +95,7 @@ struct am65_cpsw_common {
 	struct am65_cpsw_host   host;
 	struct am65_cpsw_port	*ports;
 	u32			disabled_ports_mask;
+	struct net_device	*dma_ndev;
 
 	int			usage_count; /* number of opened ports */
 	struct cpsw_ale		*ale;

drivers/net/ethernet/ti/cpsw_ale.c

@@ -634,8 +634,8 @@ int cpsw_ale_add_vlan(struct cpsw_ale *ale, u16 vid, int port_mask, int untag,
 	return 0;
 }
 
-static void cpsw_ale_del_vlan_modify(struct cpsw_ale *ale, u32 *ale_entry,
-				     u16 vid, int port_mask)
+static void cpsw_ale_vlan_del_modify_int(struct cpsw_ale *ale,  u32 *ale_entry,
+					 u16 vid, int port_mask)
 {
 	int reg_mcast, unreg_mcast;
 	int members, untag;
@@ -644,6 +644,7 @@ static void cpsw_ale_del_vlan_modify(struct cpsw_ale *ale, u32 *ale_entry,
 					ALE_ENT_VID_MEMBER_LIST);
 	members &= ~port_mask;
 	if (!members) {
+		cpsw_ale_set_vlan_untag(ale, ale_entry, vid, 0);
 		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
 		return;
 	}
@@ -673,7 +674,7 @@ static void cpsw_ale_del_vlan_modify(struct cpsw_ale *ale, u32 *ale_entry,
 			      ALE_ENT_VID_MEMBER_LIST, members);
 }
 
-int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask)
+int cpsw_ale_vlan_del_modify(struct cpsw_ale *ale, u16 vid, int port_mask)
 {
 	u32 ale_entry[ALE_ENTRY_WORDS] = {0, 0, 0};
 	int idx;
@@ -684,11 +685,39 @@ int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask)
 
 	cpsw_ale_read(ale, idx, ale_entry);
 
-	if (port_mask) {
-		cpsw_ale_del_vlan_modify(ale, ale_entry, vid, port_mask);
-	} else {
+	cpsw_ale_vlan_del_modify_int(ale, ale_entry, vid, port_mask);
+	cpsw_ale_write(ale, idx, ale_entry);
+
+	return 0;
+}
+
+int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask)
+{
+	u32 ale_entry[ALE_ENTRY_WORDS] = {0, 0, 0};
+	int members, idx;
+
+	idx = cpsw_ale_match_vlan(ale, vid);
+	if (idx < 0)
+		return -ENOENT;
+
+	cpsw_ale_read(ale, idx, ale_entry);
+
+	/* if !port_mask - force remove VLAN (legacy).
+	 * Check if there are other VLAN members ports
+	 * if no - remove VLAN.
+	 * if yes it means same VLAN was added to >1 port in multi port mode, so
+	 * remove port_mask ports from VLAN ALE entry excluding Host port.
+	 */
+	members = cpsw_ale_vlan_get_fld(ale, ale_entry, ALE_ENT_VID_MEMBER_LIST);
+	members &= ~port_mask;
+
+	if (!port_mask || !members) {
+		/* last port or force remove - remove VLAN */
 		cpsw_ale_set_vlan_untag(ale, ale_entry, vid, 0);
 		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
+	} else {
+		port_mask &= ~ALE_PORT_HOST;
+		cpsw_ale_vlan_del_modify_int(ale, ale_entry, vid, port_mask);
 	}
 
 	cpsw_ale_write(ale, idx, ale_entry);

drivers/net/ethernet/ti/cpsw_ale.h

@@ -134,6 +134,7 @@ static inline int cpsw_ale_get_vlan_p0_untag(struct cpsw_ale *ale, u16 vid)
 
 int cpsw_ale_vlan_add_modify(struct cpsw_ale *ale, u16 vid, int port_mask,
 			     int untag_mask, int reg_mcast, int unreg_mcast);
+int cpsw_ale_vlan_del_modify(struct cpsw_ale *ale, u16 vid, int port_mask);
 void cpsw_ale_set_unreg_mcast(struct cpsw_ale *ale, int unreg_mcast_mask,
 			      bool add);
 

drivers/net/ethernet/ti/cpsw_switchdev.c

@@ -227,7 +227,7 @@ static int cpsw_port_vlan_del(struct cpsw_priv *priv, u16 vid,
 	else
 		port_mask = BIT(priv->emac_port);
 
-	ret = cpsw_ale_del_vlan(cpsw->ale, vid, port_mask);
+	ret = cpsw_ale_vlan_del_modify(cpsw->ale, vid, port_mask);
 	if (ret != 0)
 		return ret;