net: ethernet: ti: introduce cpsw switchdev based driver part 1 - dual-emac

Part 1:
 Introduce basic CPSW dual_mac driver (cpsw_new.c) which is operating in
dual-emac mode by default, thus working as 2 individual network interfaces.
Main differences from legacy CPSW driver are:

 - optimized promiscuous mode: The P0_UNI_FLOOD (both ports) is enabled in
addition to ALLMULTI (current port) instead of ALE_BYPASS. So, Ports in
promiscuous mode will keep possibility of mcast and vlan filtering, which
is provides significant benefits when ports are joined to the same bridge,
but without enabling "switch" mode, or to different bridges.
 - learning disabled on ports as it make not too much sense for
   segregated ports - no forwarding in HW.
 - enabled basic support for devlink.

	devlink dev show
		platform/48484000.switch

	devlink dev param show
	 platform/48484000.switch:
	name ale_bypass type driver-specific
	 values:
		cmode runtime value false

 - "ale_bypass" devlink driver parameter allows to enable
ALE_CONTROL(4).BYPASS mode for debug purposes.
 - updated DT bindings.

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 1710 insertions, 5 deletions

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 137632b09c72..9170572346b5 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -59,9 +59,24 @@ config TI_CPSW
 	  To compile this driver as a module, choose M here: the module
 	  will be called cpsw.
 
+config TI_CPSW_SWITCHDEV
+	tristate "TI CPSW Switch Support with switchdev"
+	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
+	select NET_SWITCHDEV
+	select TI_DAVINCI_MDIO
+	select MFD_SYSCON
+	select REGMAP
+	select NET_DEVLINK
+	imply PHY_TI_GMII_SEL
+	help
+	  This driver supports TI's CPSW Ethernet Switch.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called cpsw_new.
+
 config TI_CPTS
 	bool "TI Common Platform Time Sync (CPTS) Support"
-	depends on TI_CPSW || TI_KEYSTONE_NETCP || COMPILE_TEST
+	depends on TI_CPSW || TI_KEYSTONE_NETCP || TI_CPSW_SWITCHDEV || COMPILE_TEST
 	depends on COMMON_CLK
 	depends on POSIX_TIMERS
 	---help---
@@ -73,7 +88,7 @@ config TI_CPTS
 config TI_CPTS_MOD
 	tristate
 	depends on TI_CPTS
-	default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y
+	default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y || TI_CPSW_SWITCHDEV=y
 	select NET_PTP_CLASSIFY
 	imply PTP_1588_CLOCK
 	default m
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index ed12e1e5df2f..c59670956ed3 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -15,6 +15,8 @@ obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o
 obj-$(CONFIG_TI_CPTS_MOD) += cpts.o
 obj-$(CONFIG_TI_CPSW) += ti_cpsw.o
 ti_cpsw-y := cpsw.o davinci_cpdma.o cpsw_ale.o cpsw_priv.o cpsw_sl.o cpsw_ethtool.o
+obj-$(CONFIG_TI_CPSW_SWITCHDEV) += ti_cpsw_new.o
+ti_cpsw_new-y := cpsw_new.o davinci_cpdma.o cpsw_ale.o cpsw_sl.o cpsw_priv.o cpsw_ethtool.o
 
 obj-$(CONFIG_TI_KEYSTONE_NETCP) += keystone_netcp.o
 keystone_netcp-y := netcp_core.o cpsw_ale.o
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
new file mode 100644
index 000000000000..25e59d328342
--- /dev/null
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -0,0 +1,1673 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Texas Instruments Ethernet Switch Driver
+ *
+ * Copyright (C) 2019 Texas Instruments
+ */
+
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/timer.h>
+#include <linux/module.h>
+#include <linux/irqreturn.h>
+#include <linux/interrupt.h>
+#include <linux/if_ether.h>
+#include <linux/etherdevice.h>
+#include <linux/net_tstamp.h>
+#include <linux/phy.h>
+#include <linux/phy/phy.h>
+#include <linux/delay.h>
+#include <linux/pm_runtime.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_device.h>
+#include <linux/if_vlan.h>
+#include <linux/kmemleak.h>
+#include <linux/sys_soc.h>
+
+#include <net/page_pool.h>
+#include <net/pkt_cls.h>
+#include <net/devlink.h>
+
+#include "cpsw.h"
+#include "cpsw_ale.h"
+#include "cpsw_priv.h"
+#include "cpsw_sl.h"
+#include "cpts.h"
+#include "davinci_cpdma.h"
+
+#include <net/pkt_sched.h>
+
+static int debug_level;
+static int ale_ageout = CPSW_ALE_AGEOUT_DEFAULT;
+static int rx_packet_max = CPSW_MAX_PACKET_SIZE;
+static int descs_pool_size = CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT;
+
+struct cpsw_devlink {
+	struct cpsw_common *cpsw;
+};
+
+enum cpsw_devlink_param_id {
+	CPSW_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	CPSW_DL_PARAM_ALE_BYPASS,
+};
+
+/* struct cpsw_common is not needed, kept here for compatibility
+ * reasons witrh the old driver
+ */
+static int cpsw_slave_index_priv(struct cpsw_common *cpsw,
+				 struct cpsw_priv *priv)
+{
+	if (priv->emac_port == HOST_PORT_NUM)
+		return -1;
+
+	return priv->emac_port - 1;
+}
+
+static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	bool enable_uni = false;
+	int i;
+
+	/* Enabling promiscuous mode for one interface will be
+	 * common for both the interface as the interface shares
+	 * the same hardware resource.
+	 */
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev &&
+		    (cpsw->slaves[i].ndev->flags & IFF_PROMISC))
+			enable_uni = true;
+
+	if (!enable && enable_uni) {
+		enable = enable_uni;
+		dev_dbg(cpsw->dev, "promiscuity not disabled as the other interface is still in promiscuity mode\n");
+	}
+
+	if (enable) {
+		/* Enable unknown unicast, reg/unreg mcast */
+		cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM,
+				     ALE_P0_UNI_FLOOD, 1);
+
+		dev_dbg(cpsw->dev, "promiscuity enabled\n");
+	} else {
+		/* Disable unknown unicast */
+		cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM,
+				     ALE_P0_UNI_FLOOD, 0);
+		dev_dbg(cpsw->dev, "promiscuity disabled\n");
+	}
+}
+
+/**
+ * cpsw_set_mc - adds multicast entry to the table if it's not added or deletes
+ * if it's not deleted
+ * @ndev: device to sync
+ * @addr: address to be added or deleted
+ * @vid: vlan id, if vid < 0 set/unset address for real device
+ * @add: add address if the flag is set or remove otherwise
+ */
+static int cpsw_set_mc(struct net_device *ndev, const u8 *addr,
+		       int vid, int add)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int mask, flags, ret, slave_no;
+
+	slave_no = cpsw_slave_index(cpsw, priv);
+	if (vid < 0)
+		vid = cpsw->slaves[slave_no].port_vlan;
+
+	mask =  ALE_PORT_HOST;
+	flags = vid ? ALE_VLAN : 0;
+
+	if (add)
+		ret = cpsw_ale_add_mcast(cpsw->ale, addr, mask, flags, vid, 0);
+	else
+		ret = cpsw_ale_del_mcast(cpsw->ale, addr, 0, flags, vid);
+
+	return ret;
+}
+
+static int cpsw_update_vlan_mc(struct net_device *vdev, int vid, void *ctx)
+{
+	struct addr_sync_ctx *sync_ctx = ctx;
+	struct netdev_hw_addr *ha;
+	int found = 0, ret = 0;
+
+	if (!vdev || !(vdev->flags & IFF_UP))
+		return 0;
+
+	/* vlan address is relevant if its sync_cnt != 0 */
+	netdev_for_each_mc_addr(ha, vdev) {
+		if (ether_addr_equal(ha->addr, sync_ctx->addr)) {
+			found = ha->sync_cnt;
+			break;
+		}
+	}
+
+	if (found)
+		sync_ctx->consumed++;
+
+	if (sync_ctx->flush) {
+		if (!found)
+			cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 0);
+		return 0;
+	}
+
+	if (found)
+		ret = cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 1);
+
+	return ret;
+}
+
+static int cpsw_add_mc_addr(struct net_device *ndev, const u8 *addr, int num)
+{
+	struct addr_sync_ctx sync_ctx;
+	int ret;
+
+	sync_ctx.consumed = 0;
+	sync_ctx.addr = addr;
+	sync_ctx.ndev = ndev;
+	sync_ctx.flush = 0;
+
+	ret = vlan_for_each(ndev, cpsw_update_vlan_mc, &sync_ctx);
+	if (sync_ctx.consumed < num && !ret)
+		ret = cpsw_set_mc(ndev, addr, -1, 1);
+
+	return ret;
+}
+
+static int cpsw_del_mc_addr(struct net_device *ndev, const u8 *addr, int num)
+{
+	struct addr_sync_ctx sync_ctx;
+
+	sync_ctx.consumed = 0;
+	sync_ctx.addr = addr;
+	sync_ctx.ndev = ndev;
+	sync_ctx.flush = 1;
+
+	vlan_for_each(ndev, cpsw_update_vlan_mc, &sync_ctx);
+	if (sync_ctx.consumed == num)
+		cpsw_set_mc(ndev, addr, -1, 0);
+
+	return 0;
+}
+
+static int cpsw_purge_vlan_mc(struct net_device *vdev, int vid, void *ctx)
+{
+	struct addr_sync_ctx *sync_ctx = ctx;
+	struct netdev_hw_addr *ha;
+	int found = 0;
+
+	if (!vdev || !(vdev->flags & IFF_UP))
+		return 0;
+
+	/* vlan address is relevant if its sync_cnt != 0 */
+	netdev_for_each_mc_addr(ha, vdev) {
+		if (ether_addr_equal(ha->addr, sync_ctx->addr)) {
+			found = ha->sync_cnt;
+			break;
+		}
+	}
+
+	if (!found)
+		return 0;
+
+	sync_ctx->consumed++;
+	cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 0);
+	return 0;
+}
+
+static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num)
+{
+	struct addr_sync_ctx sync_ctx;
+
+	sync_ctx.addr = addr;
+	sync_ctx.ndev = ndev;
+	sync_ctx.consumed = 0;
+
+	vlan_for_each(ndev, cpsw_purge_vlan_mc, &sync_ctx);
+	if (sync_ctx.consumed < num)
+		cpsw_set_mc(ndev, addr, -1, 0);
+
+	return 0;
+}
+
+static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	if (ndev->flags & IFF_PROMISC) {
+		/* Enable promiscuous mode */
+		cpsw_set_promiscious(ndev, true);
+		cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI, priv->emac_port);
+		return;
+	}
+
+	/* Disable promiscuous mode */
+	cpsw_set_promiscious(ndev, false);
+
+	/* Restore allmulti on vlans if necessary */
+	cpsw_ale_set_allmulti(cpsw->ale,
+			      ndev->flags & IFF_ALLMULTI, priv->emac_port);
+
+	/* add/remove mcast address either for real netdev or for vlan */
+	__hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr,
+			       cpsw_del_mc_addr);
+}
+
+static unsigned int cpsw_rxbuf_total_len(unsigned int len)
+{
+	len += CPSW_HEADROOM;
+	len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	return SKB_DATA_ALIGN(len);
+}
+
+static void cpsw_rx_handler(void *token, int len, int status)
+{
+	struct page *new_page, *page = token;
+	void *pa = page_address(page);
+	int headroom = CPSW_HEADROOM;
+	struct cpsw_meta_xdp *xmeta;
+	struct cpsw_common *cpsw;
+	struct net_device *ndev;
+	int port, ch, pkt_size;
+	struct cpsw_priv *priv;
+	struct page_pool *pool;
+	struct sk_buff *skb;
+	struct xdp_buff xdp;
+	int ret = 0;
+	dma_addr_t dma;
+
+	xmeta = pa + CPSW_XMETA_OFFSET;
+	cpsw = ndev_to_cpsw(xmeta->ndev);
+	ndev = xmeta->ndev;
+	pkt_size = cpsw->rx_packet_max;
+	ch = xmeta->ch;
+
+	if (status >= 0) {
+		port = CPDMA_RX_SOURCE_PORT(status);
+		if (port)
+			ndev = cpsw->slaves[--port].ndev;
+	}
+
+	priv = netdev_priv(ndev);
+	pool = cpsw->page_pool[ch];
+
+	if (unlikely(status < 0) || unlikely(!netif_running(ndev))) {
+		/* In dual emac mode check for all interfaces */
+		if (cpsw->usage_count && status >= 0) {
+			/* The packet received is for the interface which
+			 * is already down and the other interface is up
+			 * and running, instead of freeing which results
+			 * in reducing of the number of rx descriptor in
+			 * DMA engine, requeue page back to cpdma.
+			 */
+			new_page = page;
+			goto requeue;
+		}
+
+		/* the interface is going down, pages are purged */
+		page_pool_recycle_direct(pool, page);
+		return;
+	}
+
+	new_page = page_pool_dev_alloc_pages(pool);
+	if (unlikely(!new_page)) {
+		new_page = page;
+		ndev->stats.rx_dropped++;
+		goto requeue;
+	}
+
+	if (priv->xdp_prog) {
+		if (status & CPDMA_RX_VLAN_ENCAP) {
+			xdp.data = pa + CPSW_HEADROOM +
+				   CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+			xdp.data_end = xdp.data + len -
+				       CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+		} else {
+			xdp.data = pa + CPSW_HEADROOM;
+			xdp.data_end = xdp.data + len;
+		}
+
+		xdp_set_data_meta_invalid(&xdp);
+
+		xdp.data_hard_start = pa;
+		xdp.rxq = &priv->xdp_rxq[ch];
+
+		ret = cpsw_run_xdp(priv, ch, &xdp, page, priv->emac_port);
+		if (ret != CPSW_XDP_PASS)
+			goto requeue;
+
+		/* XDP prog might have changed packet data and boundaries */
+		len = xdp.data_end - xdp.data;
+		headroom = xdp.data - xdp.data_hard_start;
+
+		/* XDP prog can modify vlan tag, so can't use encap header */
+		status &= ~CPDMA_RX_VLAN_ENCAP;
+	}
+
+	/* pass skb to netstack if no XDP prog or returned XDP_PASS */
+	skb = build_skb(pa, cpsw_rxbuf_total_len(pkt_size));
+	if (!skb) {
+		ndev->stats.rx_dropped++;
+		page_pool_recycle_direct(pool, page);
+		goto requeue;
+	}
+
+	skb_reserve(skb, headroom);
+	skb_put(skb, len);
+	skb->dev = ndev;
+	if (status & CPDMA_RX_VLAN_ENCAP)
+		cpsw_rx_vlan_encap(skb);
+	if (priv->rx_ts_enabled)
+		cpts_rx_timestamp(cpsw->cpts, skb);
+	skb->protocol = eth_type_trans(skb, ndev);
+
+	/* unmap page as no netstack skb page recycling */
+	page_pool_release_page(pool, page);
+	netif_receive_skb(skb);
+
+	ndev->stats.rx_bytes += len;
+	ndev->stats.rx_packets++;
+
+requeue:
+	xmeta = page_address(new_page) + CPSW_XMETA_OFFSET;
+	xmeta->ndev = ndev;
+	xmeta->ch = ch;
+
+	dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM;
+	ret = cpdma_chan_submit_mapped(cpsw->rxv[ch].ch, new_page, dma,
+				       pkt_size, 0);
+	if (ret < 0) {
+		WARN_ON(ret == -ENOMEM);
+		page_pool_recycle_direct(pool, new_page);
+	}
+}
+
+static inline int cpsw_add_vlan_ale_entry(struct cpsw_priv *priv,
+					  unsigned short vid)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	int unreg_mcast_mask = 0;
+	int mcast_mask;
+	u32 port_mask;
+	int ret;
+
+	port_mask = (1 << priv->emac_port) | ALE_PORT_HOST;
+
+	mcast_mask = ALE_PORT_HOST;
+	if (priv->ndev->flags & IFF_ALLMULTI)
+		unreg_mcast_mask = mcast_mask;
+
+	ret = cpsw_ale_add_vlan(cpsw->ale, vid, port_mask, 0, port_mask,
+				unreg_mcast_mask);
+	if (ret != 0)
+		return ret;
+
+	ret = cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
+				 HOST_PORT_NUM, ALE_VLAN, vid);
+	if (ret != 0)
+		goto clean_vid;
+
+	ret = cpsw_ale_add_mcast(cpsw->ale, priv->ndev->broadcast,
+				 mcast_mask, ALE_VLAN, vid, 0);
+	if (ret != 0)
+		goto clean_vlan_ucast;
+	return 0;
+
+clean_vlan_ucast:
+	cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
+			   HOST_PORT_NUM, ALE_VLAN, vid);
+clean_vid:
+	cpsw_ale_del_vlan(cpsw->ale, vid, 0);
+	return ret;
+}
+
+static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
+				    __be16 proto, u16 vid)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int ret, i;
+
+	if (vid == cpsw->data.default_vlan)
+		return 0;
+
+	ret = pm_runtime_get_sync(cpsw->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(cpsw->dev);
+		return ret;
+	}
+
+	/* In dual EMAC, reserved VLAN id should not be used for
+	 * creating VLAN interfaces as this can break the dual
+	 * EMAC port separation
+	 */
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		if (cpsw->slaves[i].ndev &&
+		    vid == cpsw->slaves[i].port_vlan) {
+			ret = -EINVAL;
+			goto err;
+		}
+	}
+
+	dev_dbg(priv->dev, "Adding vlanid %d to vlan filter\n", vid);
+	ret = cpsw_add_vlan_ale_entry(priv, vid);
+err:
+	pm_runtime_put(cpsw->dev);
+	return ret;
+}
+
+static int cpsw_restore_vlans(struct net_device *vdev, int vid, void *arg)
+{
+	struct cpsw_priv *priv = arg;
+
+	if (!vdev || !vid)
+		return 0;
+
+	cpsw_ndo_vlan_rx_add_vid(priv->ndev, 0, vid);
+	return 0;
+}
+
+/* restore resources after port reset */
+static void cpsw_restore(struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	/* restore vlan configurations */
+	vlan_for_each(priv->ndev, cpsw_restore_vlans, priv);
+
+	/* restore MQPRIO offload */
+	cpsw_mqprio_resume(&cpsw->slaves[priv->emac_port - 1], priv);
+
+	/* restore CBS offload */
+	cpsw_cbs_resume(&cpsw->slaves[priv->emac_port - 1], priv);
+}
+
+static void cpsw_init_host_port_dual_mac(struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	int vlan = cpsw->data.default_vlan;
+
+	writel(CPSW_FIFO_DUAL_MAC_MODE, &cpsw->host_port_regs->tx_in_ctl);
+
+	cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_P0_UNI_FLOOD, 0);
+	dev_dbg(cpsw->dev, "unset P0_UNI_FLOOD\n");
+
+	writel(vlan, &cpsw->host_port_regs->port_vlan);
+
+	cpsw_ale_add_vlan(cpsw->ale, vlan, ALE_ALL_PORTS, ALE_ALL_PORTS, 0, 0);
+	/* learning make no sense in dual_mac mode */
+	cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_PORT_NOLEARN, 1);
+}
+
+static void cpsw_init_host_port(struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	u32 control_reg;
+
+	/* soft reset the controller and initialize ale */
+	soft_reset("cpsw", &cpsw->regs->soft_reset);
+	cpsw_ale_start(cpsw->ale);
+
+	/* switch to vlan unaware mode */
+	cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_VLAN_AWARE,
+			     CPSW_ALE_VLAN_AWARE);
+	control_reg = readl(&cpsw->regs->control);
+	control_reg |= CPSW_VLAN_AWARE | CPSW_RX_VLAN_ENCAP;
+	writel(control_reg, &cpsw->regs->control);
+
+	/* setup host port priority mapping */
+	writel_relaxed(CPDMA_TX_PRIORITY_MAP,
+		       &cpsw->host_port_regs->cpdma_tx_pri_map);
+	writel_relaxed(0, &cpsw->host_port_regs->cpdma_rx_chan_map);
+
+	/* disable priority elevation */
+	writel_relaxed(0, &cpsw->regs->ptype);
+
+	/* enable statistics collection only on all ports */
+	writel_relaxed(0x7, &cpsw->regs->stat_port_en);
+
+	/* Enable internal fifo flow control */
+	writel(0x7, &cpsw->regs->flow_control);
+
+	cpsw_init_host_port_dual_mac(priv);
+
+	cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM,
+			     ALE_PORT_STATE, ALE_PORT_STATE_FORWARD);
+}
+
+static void cpsw_port_add_dual_emac_def_ale_entries(struct cpsw_priv *priv,
+						    struct cpsw_slave *slave)
+{
+	u32 port_mask = 1 << priv->emac_port | ALE_PORT_HOST;
+	struct cpsw_common *cpsw = priv->cpsw;
+	u32 reg;
+
+	reg = (cpsw->version == CPSW_VERSION_1) ? CPSW1_PORT_VLAN :
+	       CPSW2_PORT_VLAN;
+	slave_write(slave, slave->port_vlan, reg);
+
+	cpsw_ale_add_vlan(cpsw->ale, slave->port_vlan, port_mask,
+			  port_mask, port_mask, 0);
+	cpsw_ale_add_mcast(cpsw->ale, priv->ndev->broadcast,
+			   ALE_PORT_HOST, ALE_VLAN, slave->port_vlan,
+			   ALE_MCAST_FWD);
+	cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
+			   HOST_PORT_NUM, ALE_VLAN |
+			   ALE_SECURE, slave->port_vlan);
+	cpsw_ale_control_set(cpsw->ale, priv->emac_port,
+			     ALE_PORT_DROP_UNKNOWN_VLAN, 1);
+	/* learning make no sense in dual_mac mode */
+	cpsw_ale_control_set(cpsw->ale, priv->emac_port,
+			     ALE_PORT_NOLEARN, 1);
+}
+
+static void cpsw_adjust_link(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	struct phy_device *phy;
+	u32 mac_control = 0;
+
+	slave = &cpsw->slaves[priv->emac_port - 1];
+	phy = slave->phy;
+
+	if (!phy)
+		return;
+
+	if (phy->link) {
+		mac_control = CPSW_SL_CTL_GMII_EN;
+
+		if (phy->speed == 1000)
+			mac_control |= CPSW_SL_CTL_GIG;
+		if (phy->duplex)
+			mac_control |= CPSW_SL_CTL_FULLDUPLEX;
+
+		/* set speed_in input in case RMII mode is used in 100Mbps */
+		if (phy->speed == 100)
+			mac_control |= CPSW_SL_CTL_IFCTL_A;
+		/* in band mode only works in 10Mbps RGMII mode */
+		else if ((phy->speed == 10) && phy_interface_is_rgmii(phy))
+			mac_control |= CPSW_SL_CTL_EXT_EN; /* In Band mode */
+
+		if (priv->rx_pause)
+			mac_control |= CPSW_SL_CTL_RX_FLOW_EN;
+
+		if (priv->tx_pause)
+			mac_control |= CPSW_SL_CTL_TX_FLOW_EN;
+
+		if (mac_control != slave->mac_control)
+			cpsw_sl_ctl_set(slave->mac_sl, mac_control);
+
+		/* enable forwarding */
+		cpsw_ale_control_set(cpsw->ale, priv->emac_port,
+				     ALE_PORT_STATE, ALE_PORT_STATE_FORWARD);
+
+		netif_tx_wake_all_queues(ndev);
+
+		if (priv->shp_cfg_speed &&
+		    priv->shp_cfg_speed != slave->phy->speed &&
+		    !cpsw_shp_is_off(priv))
+			dev_warn(priv->dev, "Speed was changed, CBS shaper speeds are changed!");
+	} else {
+		netif_tx_stop_all_queues(ndev);
+
+		mac_control = 0;
+		/* disable forwarding */
+		cpsw_ale_control_set(cpsw->ale, priv->emac_port,
+				     ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
+
+		cpsw_sl_wait_for_idle(slave->mac_sl, 100);
+
+		cpsw_sl_ctl_reset(slave->mac_sl);
+	}
+
+	if (mac_control != slave->mac_control)
+		phy_print_status(phy);
+
+	slave->mac_control = mac_control;
+
+	if (phy->link && cpsw_need_resplit(cpsw))
+		cpsw_split_res(cpsw);
+}
+
+static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct phy_device *phy;
+
+	cpsw_sl_reset(slave->mac_sl, 100);
+	cpsw_sl_ctl_reset(slave->mac_sl);
+
+	/* setup priority mapping */
+	cpsw_sl_reg_write(slave->mac_sl, CPSW_SL_RX_PRI_MAP,
+			  RX_PRIORITY_MAPPING);
+
+	switch (cpsw->version) {
+	case CPSW_VERSION_1:
+		slave_write(slave, TX_PRIORITY_MAPPING, CPSW1_TX_PRI_MAP);
+		/* Increase RX FIFO size to 5 for supporting fullduplex
+		 * flow control mode
+		 */
+		slave_write(slave,
+			    (CPSW_MAX_BLKS_TX << CPSW_MAX_BLKS_TX_SHIFT) |
+			    CPSW_MAX_BLKS_RX, CPSW1_MAX_BLKS);
+		break;
+	case CPSW_VERSION_2:
+	case CPSW_VERSION_3:
+	case CPSW_VERSION_4:
+		slave_write(slave, TX_PRIORITY_MAPPING, CPSW2_TX_PRI_MAP);
+		/* Increase RX FIFO size to 5 for supporting fullduplex
+		 * flow control mode
+		 */
+		slave_write(slave,
+			    (CPSW_MAX_BLKS_TX << CPSW_MAX_BLKS_TX_SHIFT) |
+			    CPSW_MAX_BLKS_RX, CPSW2_MAX_BLKS);
+		break;
+	}
+
+	/* setup max packet size, and mac address */
+	cpsw_sl_reg_write(slave->mac_sl, CPSW_SL_RX_MAXLEN,
+			  cpsw->rx_packet_max);
+	cpsw_set_slave_mac(slave, priv);
+
+	slave->mac_control = 0;	/* no link yet */
+
+	cpsw_port_add_dual_emac_def_ale_entries(priv, slave);
+
+	if (!slave->data->phy_node)
+		dev_err(priv->dev, "no phy found on slave %d\n",
+			slave->slave_num);
+	phy = of_phy_connect(priv->ndev, slave->data->phy_node,
+			     &cpsw_adjust_link, 0, slave->data->phy_if);
+	if (!phy) {
+		dev_err(priv->dev, "phy \"%pOF\" not found on slave %d\n",
+			slave->data->phy_node,
+			slave->slave_num);
+		return;
+	}
+	slave->phy = phy;
+
+	phy_attached_info(slave->phy);
+
+	phy_start(slave->phy);
+
+	/* Configure GMII_SEL register */
+	phy_set_mode_ext(slave->data->ifphy, PHY_MODE_ETHERNET,
+			 slave->data->phy_if);
+}
+
+static int cpsw_ndo_stop(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+
+	cpsw_info(priv, ifdown, "shutting down ndev\n");
+	slave = &cpsw->slaves[priv->emac_port - 1];
+	if (slave->phy)
+		phy_stop(slave->phy);
+
+	netif_tx_stop_all_queues(priv->ndev);
+
+	if (slave->phy) {
+		phy_disconnect(slave->phy);
+		slave->phy = NULL;
+	}
+
+	__hw_addr_ref_unsync_dev(&ndev->mc, ndev, cpsw_purge_all_mc);
+
+	if (cpsw->usage_count <= 1) {
+		napi_disable(&cpsw->napi_rx);
+		napi_disable(&cpsw->napi_tx);
+		cpts_unregister(cpsw->cpts);
+		cpsw_intr_disable(cpsw);
+		cpdma_ctlr_stop(cpsw->dma);
+		cpsw_ale_stop(cpsw->ale);
+		cpsw_destroy_xdp_rxqs(cpsw);
+	}
+
+	if (cpsw_need_resplit(cpsw))
+		cpsw_split_res(cpsw);
+
+	cpsw->usage_count--;
+	pm_runtime_put_sync(cpsw->dev);
+	return 0;
+}
+
+static int cpsw_ndo_open(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int ret;
+
+	cpsw_info(priv, ifdown, "starting ndev\n");
+	ret = pm_runtime_get_sync(cpsw->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(cpsw->dev);
+		return ret;
+	}
+
+	/* Notify the stack of the actual queue counts. */
+	ret = netif_set_real_num_tx_queues(ndev, cpsw->tx_ch_num);
+	if (ret) {
+		dev_err(priv->dev, "cannot set real number of tx queues\n");
+		goto pm_cleanup;
+	}
+
+	ret = netif_set_real_num_rx_queues(ndev, cpsw->rx_ch_num);
+	if (ret) {
+		dev_err(priv->dev, "cannot set real number of rx queues\n");
+		goto pm_cleanup;
+	}
+
+	/* Initialize host and slave ports */
+	if (!cpsw->usage_count)
+		cpsw_init_host_port(priv);
+	cpsw_slave_open(&cpsw->slaves[priv->emac_port - 1], priv);
+
+	/* initialize shared resources for every ndev */
+	if (!cpsw->usage_count) {
+		/* create rxqs for both infs in dual mac as they use same pool
+		 * and must be destroyed together when no users.
+		 */
+		ret = cpsw_create_xdp_rxqs(cpsw);
+		if (ret < 0)
+			goto err_cleanup;
+
+		ret = cpsw_fill_rx_channels(priv);
+		if (ret < 0)
+			goto err_cleanup;
+
+		if (cpts_register(cpsw->cpts))
+			dev_err(priv->dev, "error registering cpts device\n");
+
+		napi_enable(&cpsw->napi_rx);
+		napi_enable(&cpsw->napi_tx);
+
+		if (cpsw->tx_irq_disabled) {
+			cpsw->tx_irq_disabled = false;
+			enable_irq(cpsw->irqs_table[1]);
+		}
+
+		if (cpsw->rx_irq_disabled) {
+			cpsw->rx_irq_disabled = false;
+			enable_irq(cpsw->irqs_table[0]);
+		}
+	}
+
+	cpsw_restore(priv);
+
+	/* Enable Interrupt pacing if configured */
+	if (cpsw->coal_intvl != 0) {
+		struct ethtool_coalesce coal;
+
+		coal.rx_coalesce_usecs = cpsw->coal_intvl;
+		cpsw_set_coalesce(ndev, &coal);
+	}
+
+	cpdma_ctlr_start(cpsw->dma);
+	cpsw_intr_enable(cpsw);
+	cpsw->usage_count++;
+
+	return 0;
+
+err_cleanup:
+	cpsw_ndo_stop(ndev);
+
+pm_cleanup:
+	pm_runtime_put_sync(cpsw->dev);
+	return ret;
+}
+
+static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
+				       struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpts *cpts = cpsw->cpts;
+	struct netdev_queue *txq;
+	struct cpdma_chan *txch;
+	int ret, q_idx;
+
+	if (skb_padto(skb, CPSW_MIN_PACKET_SIZE)) {
+		cpsw_err(priv, tx_err, "packet pad failed\n");
+		ndev->stats.tx_dropped++;
+		return NET_XMIT_DROP;
+	}
+
+	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
+	    priv->tx_ts_enabled && cpts_can_timestamp(cpts, skb))
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+	q_idx = skb_get_queue_mapping(skb);
+	if (q_idx >= cpsw->tx_ch_num)
+		q_idx = q_idx % cpsw->tx_ch_num;
+
+	txch = cpsw->txv[q_idx].ch;
+	txq = netdev_get_tx_queue(ndev, q_idx);
+	skb_tx_timestamp(skb);
+	ret = cpdma_chan_submit(txch, skb, skb->data, skb->len,
+				priv->emac_port);
+	if (unlikely(ret != 0)) {
+		cpsw_err(priv, tx_err, "desc submit failed\n");
+		goto fail;
+	}
+
+	/* If there is no more tx desc left free then we need to
+	 * tell the kernel to stop sending us tx frames.
+	 */
+	if (unlikely(!cpdma_check_free_tx_desc(txch))) {
+		netif_tx_stop_queue(txq);
+
+		/* Barrier, so that stop_queue visible to other cpus */
+		smp_mb__after_atomic();
+
+		if (cpdma_check_free_tx_desc(txch))
+			netif_tx_wake_queue(txq);
+	}
+
+	return NETDEV_TX_OK;
+fail:
+	ndev->stats.tx_dropped++;
+	netif_tx_stop_queue(txq);
+
+	/* Barrier, so that stop_queue visible to other cpus */
+	smp_mb__after_atomic();
+
+	if (cpdma_check_free_tx_desc(txch))
+		netif_tx_wake_queue(txq);
+
+	return NETDEV_TX_BUSY;
+}
+
+static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p)
+{
+	struct sockaddr *addr = (struct sockaddr *)p;
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int ret, slave_no;
+	int flags = 0;
+	u16 vid = 0;
+
+	slave_no = cpsw_slave_index(cpsw, priv);
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	ret = pm_runtime_get_sync(cpsw->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(cpsw->dev);
+		return ret;
+	}
+
+	vid = cpsw->slaves[slave_no].port_vlan;
+	flags = ALE_VLAN | ALE_SECURE;
+
+	cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, HOST_PORT_NUM,
+			   flags, vid);
+	cpsw_ale_add_ucast(cpsw->ale, addr->sa_data, HOST_PORT_NUM,
+			   flags, vid);
+
+	ether_addr_copy(priv->mac_addr, addr->sa_data);
+	ether_addr_copy(ndev->dev_addr, priv->mac_addr);
+	cpsw_set_slave_mac(&cpsw->slaves[slave_no], priv);
+
+	pm_runtime_put(cpsw->dev);
+
+	return 0;
+}
+
+static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
+				     __be16 proto, u16 vid)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int ret;
+	int i;
+
+	if (vid == cpsw->data.default_vlan)
+		return 0;
+
+	ret = pm_runtime_get_sync(cpsw->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(cpsw->dev);
+		return ret;
+	}
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		if (cpsw->slaves[i].ndev &&
+		    vid == cpsw->slaves[i].port_vlan)
+			goto err;
+	}
+
+	dev_dbg(priv->dev, "removing vlanid %d from vlan filter\n", vid);
+	cpsw_ale_del_vlan(cpsw->ale, vid, 0);
+	cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
+			   HOST_PORT_NUM, ALE_VLAN, vid);
+	cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
+			   0, ALE_VLAN, vid);
+	cpsw_ale_flush_multicast(cpsw->ale, 0, vid);
+err:
+	pm_runtime_put(cpsw->dev);
+	return ret;
+}
+
+static int cpsw_ndo_get_phys_port_name(struct net_device *ndev, char *name,
+				       size_t len)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	int err;
+
+	err = snprintf(name, len, "p%d", priv->emac_port);
+
+	if (err >= len)
+		return -EINVAL;
+
+	return 0;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void cpsw_ndo_poll_controller(struct net_device *ndev)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	cpsw_intr_disable(cpsw);
+	cpsw_rx_interrupt(cpsw->irqs_table[0], cpsw);
+	cpsw_tx_interrupt(cpsw->irqs_table[1], cpsw);
+	cpsw_intr_enable(cpsw);
+}
+#endif
+
+static int cpsw_ndo_xdp_xmit(struct net_device *ndev, int n,
+			     struct xdp_frame **frames, u32 flags)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct xdp_frame *xdpf;
+	int i, drops = 0;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	for (i = 0; i < n; i++) {
+		xdpf = frames[i];
+		if (xdpf->len < CPSW_MIN_PACKET_SIZE) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+			continue;
+		}
+
+		if (cpsw_xdp_tx_frame(priv, xdpf, NULL, priv->emac_port))
+			drops++;
+	}
+
+	return n - drops;
+}
+
+static const struct net_device_ops cpsw_netdev_ops = {
+	.ndo_open		= cpsw_ndo_open,
+	.ndo_stop		= cpsw_ndo_stop,
+	.ndo_start_xmit		= cpsw_ndo_start_xmit,
+	.ndo_set_mac_address	= cpsw_ndo_set_mac_address,
+	.ndo_do_ioctl		= cpsw_ndo_ioctl,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_tx_timeout		= cpsw_ndo_tx_timeout,
+	.ndo_set_rx_mode	= cpsw_ndo_set_rx_mode,
+	.ndo_set_tx_maxrate	= cpsw_ndo_set_tx_maxrate,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= cpsw_ndo_poll_controller,
+#endif
+	.ndo_vlan_rx_add_vid	= cpsw_ndo_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= cpsw_ndo_vlan_rx_kill_vid,
+	.ndo_setup_tc           = cpsw_ndo_setup_tc,
+	.ndo_get_phys_port_name = cpsw_ndo_get_phys_port_name,
+	.ndo_bpf		= cpsw_ndo_bpf,
+	.ndo_xdp_xmit		= cpsw_ndo_xdp_xmit,
+};
+
+static void cpsw_get_drvinfo(struct net_device *ndev,
+			     struct ethtool_drvinfo *info)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct platform_device *pdev;
+
+	pdev = to_platform_device(cpsw->dev);
+	strlcpy(info->driver, "cpsw-switch", sizeof(info->driver));
+	strlcpy(info->version, "2.0", sizeof(info->version));
+	strlcpy(info->bus_info, pdev->name, sizeof(info->bus_info));
+}
+
+static int cpsw_set_pauseparam(struct net_device *ndev,
+			       struct ethtool_pauseparam *pause)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	int slave_no;
+
+	slave_no = cpsw_slave_index(cpsw, priv);
+	if (!cpsw->slaves[slave_no].phy)
+		return -EINVAL;
+
+	if (!phy_validate_pause(cpsw->slaves[slave_no].phy, pause))
+		return -EINVAL;
+
+	priv->rx_pause = pause->rx_pause ? true : false;
+	priv->tx_pause = pause->tx_pause ? true : false;
+
+	phy_set_asym_pause(cpsw->slaves[slave_no].phy,
+			   priv->rx_pause, priv->tx_pause);
+