Merge tag 'v4.15-rc1' into next-seccomp

Linux 4.15-rc1

42 files changed, 4911 insertions, 909 deletions

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 96413808c726..af75156919ed 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -61,10 +61,12 @@ config BCM63XX_ENET
 
 config BCMGENET
 	tristate "Broadcom GENET internal MAC support"
+	depends on OF && HAS_IOMEM
 	select MII
 	select PHYLIB
 	select FIXED_PHY
 	select BCM7XXX_PHY
+	select MDIO_BCM_UNIMAC
 	help
 	  This driver supports the built-in Ethernet MACs found in the
 	  Broadcom BCM7xxx Set Top Box family chipset.
@@ -182,6 +184,7 @@ config BGMAC_PLATFORM
 config SYSTEMPORT
 	tristate "Broadcom SYSTEMPORT internal MAC support"
 	depends on OF
+	depends on NET_DSA || !NET_DSA
 	select MII
 	select PHYLIB
 	select FIXED_PHY
@@ -193,6 +196,7 @@ config SYSTEMPORT
 config BNXT
 	tristate "Broadcom NetXtreme-C/E support"
 	depends on PCI
+	depends on MAY_USE_DEVLINK
 	select FW_LOADER
 	select LIBCRC32C
 	---help---
@@ -209,6 +213,15 @@ config BNXT_SRIOV
 	  Virtualization support in the NetXtreme-C/E products. This
 	  allows for virtual function acceleration in virtual environments.
 
+config BNXT_FLOWER_OFFLOAD
+	bool "TC Flower offload support for NetXtreme-C/E"
+	depends on BNXT
+	default y
+	---help---
+	  This configuration parameter enables TC Flower packet classifier
+	  offload for eswitch.  This option enables SR-IOV switchdev eswitch
+	  offload.
+
 config BNXT_DCB
 	bool "Data Center Bridging (DCB) Support"
 	default n
diff --git a/drivers/net/ethernet/broadcom/Makefile b/drivers/net/ethernet/broadcom/Makefile
index 79f2372c66ec..7046ad6d3d0e 100644
--- a/drivers/net/ethernet/broadcom/Makefile
+++ b/drivers/net/ethernet/broadcom/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Makefile for the Broadcom network device drivers.
 #
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index f411936b744c..e445ab724827 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -599,9 +599,9 @@ static void b44_check_phy(struct b44 *bp)
 	}
 }
 
-static void b44_timer(unsigned long __opaque)
+static void b44_timer(struct timer_list *t)
 {
-	struct b44 *bp = (struct b44 *) __opaque;
+	struct b44 *bp = from_timer(bp, t, timer);
 
 	spin_lock_irq(&bp->lock);
 
@@ -1474,10 +1474,8 @@ static int b44_open(struct net_device *dev)
 		goto out;
 	}
 
-	init_timer(&bp->timer);
+	timer_setup(&bp->timer, b44_timer, 0);
 	bp->timer.expires = jiffies + HZ;
-	bp->timer.data = (unsigned long) bp;
-	bp->timer.function = b44_timer;
 	add_timer(&bp->timer);
 
 	b44_enable_ints(bp);
@@ -2368,6 +2366,7 @@ static int b44_init_one(struct ssb_device *sdev,
 	bp->msg_enable = netif_msg_init(b44_debug, B44_DEF_MSG_ENABLE);
 
 	spin_lock_init(&bp->lock);
+	u64_stats_init(&bp->hw_stats.syncp);
 
 	bp->rx_pending = B44_DEF_RX_RING_PENDING;
 	bp->tx_pending = B44_DEF_TX_RING_PENDING;
diff --git a/drivers/net/ethernet/broadcom/b44.h b/drivers/net/ethernet/broadcom/b44.h
index 89d2cf341163..b3e36ca0fd19 100644
--- a/drivers/net/ethernet/broadcom/b44.h
+++ b/drivers/net/ethernet/broadcom/b44.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _B44_H
 #define _B44_H
 
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 61a88b64bd39..d9346e2ac720 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -295,16 +295,13 @@ static int bcm_enet_refill_rx(struct net_device *dev)
 /*
  * timer callback to defer refill rx queue in case we're OOM
  */
-static void bcm_enet_refill_rx_timer(unsigned long data)
+static void bcm_enet_refill_rx_timer(struct timer_list *t)
 {
-	struct net_device *dev;
-	struct bcm_enet_priv *priv;
-
-	dev = (struct net_device *)data;
-	priv = netdev_priv(dev);
+	struct bcm_enet_priv *priv = from_timer(priv, t, rx_timeout);
+	struct net_device *dev = priv->net_dev;
 
 	spin_lock(&priv->rx_lock);
-	bcm_enet_refill_rx((struct net_device *)data);
+	bcm_enet_refill_rx(dev);
 	spin_unlock(&priv->rx_lock);
 }
 
@@ -1062,7 +1059,8 @@ static int bcm_enet_open(struct net_device *dev)
 	val = enet_readl(priv, ENET_CTL_REG);
 	val |= ENET_CTL_ENABLE_MASK;
 	enet_writel(priv, val, ENET_CTL_REG);
-	enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG);
+	if (priv->dma_has_sram)
+		enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG);
 	enet_dmac_writel(priv, priv->dma_chan_en_mask,
 			 ENETDMAC_CHANCFG, priv->rx_chan);
 
@@ -1721,10 +1719,8 @@ static int bcm_enet_probe(struct platform_device *pdev)
 	const char *clk_name;
 	int i, ret;
 
-	/* stop if shared driver failed, assume driver->probe will be
-	 * called in the same order we register devices (correct ?) */
 	if (!bcm_enet_shared_base[0])
-		return -ENODEV;
+		return -EPROBE_DEFER;
 
 	res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	res_irq_rx = platform_get_resource(pdev, IORESOURCE_IRQ, 1);
@@ -1768,12 +1764,14 @@ static int bcm_enet_probe(struct platform_device *pdev)
 		clk_name = "enet1";
 	}
 
-	priv->mac_clk = clk_get(&pdev->dev, clk_name);
+	priv->mac_clk = devm_clk_get(&pdev->dev, clk_name);
 	if (IS_ERR(priv->mac_clk)) {
 		ret = PTR_ERR(priv->mac_clk);
 		goto out;
 	}
-	clk_prepare_enable(priv->mac_clk);
+	ret = clk_prepare_enable(priv->mac_clk);
+	if (ret)
+		goto out;
 
 	/* initialize default and fetch platform data */
 	priv->rx_ring_size = BCMENET_DEF_RX_DESC;
@@ -1801,13 +1799,15 @@ static int bcm_enet_probe(struct platform_device *pdev)
 
 	if (priv->mac_id == 0 && priv->has_phy && !priv->use_external_mii) {
 		/* using internal PHY, enable clock */
-		priv->phy_clk = clk_get(&pdev->dev, "ephy");
+		priv->phy_clk = devm_clk_get(&pdev->dev, "ephy");
 		if (IS_ERR(priv->phy_clk)) {
 			ret = PTR_ERR(priv->phy_clk);
 			priv->phy_clk = NULL;
-			goto out_put_clk_mac;
+			goto out_disable_clk_mac;
 		}
-		clk_prepare_enable(priv->phy_clk);
+		ret = clk_prepare_enable(priv->phy_clk);
+		if (ret)
+			goto out_disable_clk_mac;
 	}
 
 	/* do minimal hardware init to be able to probe mii bus */
@@ -1857,9 +1857,7 @@ static int bcm_enet_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->rx_lock);
 
 	/* init rx timeout (used for oom) */
-	init_timer(&priv->rx_timeout);
-	priv->rx_timeout.function = bcm_enet_refill_rx_timer;
-	priv->rx_timeout.data = (unsigned long)dev;
+	timer_setup(&priv->rx_timeout, bcm_enet_refill_rx_timer, 0);
 
 	/* init the mib update lock&work */
 	mutex_init(&priv->mib_update_lock);
@@ -1901,14 +1899,10 @@ out_free_mdio:
 out_uninit_hw:
 	/* turn off mdc clock */
 	enet_writel(priv, 0, ENET_MIISC_REG);
-	if (priv->phy_clk) {
-		clk_disable_unprepare(priv->phy_clk);
-		clk_put(priv->phy_clk);
-	}
+	clk_disable_unprepare(priv->phy_clk);
 
-out_put_clk_mac:
+out_disable_clk_mac:
 	clk_disable_unprepare(priv->mac_clk);
-	clk_put(priv->mac_clk);
 out:
 	free_netdev(dev);
 	return ret;
@@ -1944,12 +1938,8 @@ static int bcm_enet_remove(struct platform_device *pdev)
 	}
 
 	/* disable hw block clocks */
-	if (priv->phy_clk) {
-		clk_disable_unprepare(priv->phy_clk);
-		clk_put(priv->phy_clk);
-	}
+	clk_disable_unprepare(priv->phy_clk);
 	clk_disable_unprepare(priv->mac_clk);
-	clk_put(priv->mac_clk);
 
 	free_netdev(dev);
 	return 0;
@@ -2021,9 +2011,9 @@ static inline int bcm_enet_port_is_rgmii(int portid)
 /*
  * enet sw PHY polling
  */
-static void swphy_poll_timer(unsigned long data)
+static void swphy_poll_timer(struct timer_list *t)
 {
-	struct bcm_enet_priv *priv = (struct bcm_enet_priv *)data;
+	struct bcm_enet_priv *priv = from_timer(priv, t, swphy_poll);
 	unsigned int i;
 
 	for (i = 0; i < priv->num_ports; i++) {
@@ -2332,11 +2322,8 @@ static int bcm_enetsw_open(struct net_device *dev)
 	}
 
 	/* start phy polling timer */
-	init_timer(&priv->swphy_poll);
-	priv->swphy_poll.function = swphy_poll_timer;
-	priv->swphy_poll.data = (unsigned long)priv;
-	priv->swphy_poll.expires = jiffies;
-	add_timer(&priv->swphy_poll);
+	timer_setup(&priv->swphy_poll, swphy_poll_timer, 0);
+	mod_timer(&priv->swphy_poll, jiffies);
 	return 0;
 
 out:
@@ -2674,7 +2661,7 @@ static int bcm_enetsw_set_ringparam(struct net_device *dev,
 	return 0;
 }
 
-static struct ethtool_ops bcm_enetsw_ethtool_ops = {
+static const struct ethtool_ops bcm_enetsw_ethtool_ops = {
 	.get_strings		= bcm_enetsw_get_strings,
 	.get_sset_count		= bcm_enetsw_get_sset_count,
 	.get_ethtool_stats      = bcm_enetsw_get_ethtool_stats,
@@ -2692,11 +2679,8 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 	struct resource *res_mem;
 	int ret, irq_rx, irq_tx;
 
-	/* stop if shared driver failed, assume driver->probe will be
-	 * called in the same order we register devices (correct ?)
-	 */
 	if (!bcm_enet_shared_base[0])
-		return -ENODEV;
+		return -EPROBE_DEFER;
 
 	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq_rx = platform_get_irq(pdev, 0);
@@ -2735,33 +2719,27 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 	if (ret)
 		goto out;
 
-	if (!request_mem_region(res_mem->start, resource_size(res_mem),
-				"bcm63xx_enetsw")) {
-		ret = -EBUSY;
+	priv->base = devm_ioremap_resource(&pdev->dev, res_mem);
+	if (IS_ERR(priv->base)) {
+		ret = PTR_ERR(priv->base);
 		goto out;
 	}
 
-	priv->base = ioremap(res_mem->start, resource_size(res_mem));
-	if (priv->base == NULL) {
-		ret = -ENOMEM;
-		goto out_release_mem;
-	}
-
-	priv->mac_clk = clk_get(&pdev->dev, "enetsw");
+	priv->mac_clk = devm_clk_get(&pdev->dev, "enetsw");
 	if (IS_ERR(priv->mac_clk)) {
 		ret = PTR_ERR(priv->mac_clk);
-		goto out_unmap;
+		goto out;
 	}
-	clk_enable(priv->mac_clk);
+	ret = clk_prepare_enable(priv->mac_clk);
+	if (ret)
+		goto out;
 
 	priv->rx_chan = 0;
 	priv->tx_chan = 1;
 	spin_lock_init(&priv->rx_lock);
 
 	/* init rx timeout (used for oom) */
-	init_timer(&priv->rx_timeout);
-	priv->rx_timeout.function = bcm_enet_refill_rx_timer;
-	priv->rx_timeout.data = (unsigned long)dev;
+	timer_setup(&priv->rx_timeout, bcm_enet_refill_rx_timer, 0);
 
 	/* register netdevice */
 	dev->netdev_ops = &bcm_enetsw_ops;
@@ -2773,7 +2751,7 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 
 	ret = register_netdev(dev);
 	if (ret)
-		goto out_put_clk;
+		goto out_disable_clk;
 
 	netif_carrier_off(dev);
 	platform_set_drvdata(pdev, dev);
@@ -2782,14 +2760,8 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 
 	return 0;
 
-out_put_clk:
-	clk_put(priv->mac_clk);
-
-out_unmap:
-	iounmap(priv->base);
-
-out_release_mem:
-	release_mem_region(res_mem->start, resource_size(res_mem));
+out_disable_clk:
+	clk_disable_unprepare(priv->mac_clk);
 out:
 	free_netdev(dev);
 	return ret;
@@ -2801,17 +2773,13 @@ static int bcm_enetsw_remove(struct platform_device *pdev)
 {
 	struct bcm_enet_priv *priv;
 	struct net_device *dev;
-	struct resource *res;
 
 	/* stop netdevice */
 	dev = platform_get_drvdata(pdev);
 	priv = netdev_priv(dev);
 	unregister_netdev(dev);
 
-	/* release device resources */
-	iounmap(priv->base);
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(res->start, resource_size(res));
+	clk_disable_unprepare(priv->mac_clk);
 
 	free_netdev(dev);
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.h b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
index 0a1b7b2e55bd..5a66728d4776 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.h
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BCM63XX_ENET_H_
 #define BCM63XX_ENET_H_
 
@@ -8,7 +9,6 @@
 #include <linux/platform_device.h>
 
 #include <bcm63xx_regs.h>
-#include <bcm63xx_irq.h>
 #include <bcm63xx_io.h>
 #include <bcm63xx_iudma.h>
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 5333601f855f..087f01b4dc3a 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -32,13 +32,13 @@
 #define BCM_SYSPORT_IO_MACRO(name, offset) \
 static inline u32 name##_readl(struct bcm_sysport_priv *priv, u32 off)	\
 {									\
-	u32 reg = __raw_readl(priv->base + offset + off);		\
+	u32 reg = readl_relaxed(priv->base + offset + off);		\
 	return reg;							\
 }									\
 static inline void name##_writel(struct bcm_sysport_priv *priv,		\
 				  u32 val, u32 off)			\
 {									\
-	__raw_writel(val, priv->base + offset + off);			\
+	writel_relaxed(val, priv->base + offset + off);			\
 }									\
 
 BCM_SYSPORT_IO_MACRO(intrl2_0, SYS_PORT_INTRL2_0_OFFSET);
@@ -59,14 +59,14 @@ static inline u32 rdma_readl(struct bcm_sysport_priv *priv, u32 off)
 {
 	if (priv->is_lite && off >= RDMA_STATUS)
 		off += 4;
-	return __raw_readl(priv->base + SYS_PORT_RDMA_OFFSET + off);
+	return readl_relaxed(priv->base + SYS_PORT_RDMA_OFFSET + off);
 }
 
 static inline void rdma_writel(struct bcm_sysport_priv *priv, u32 val, u32 off)
 {
 	if (priv->is_lite && off >= RDMA_STATUS)
 		off += 4;
-	__raw_writel(val, priv->base + SYS_PORT_RDMA_OFFSET + off);
+	writel_relaxed(val, priv->base + SYS_PORT_RDMA_OFFSET + off);
 }
 
 static inline u32 tdma_control_bit(struct bcm_sysport_priv *priv, u32 bit)
@@ -110,10 +110,10 @@ static inline void dma_desc_set_addr(struct bcm_sysport_priv *priv,
 				     dma_addr_t addr)
 {
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
-	__raw_writel(upper_32_bits(addr) & DESC_ADDR_HI_MASK,
+	writel_relaxed(upper_32_bits(addr) & DESC_ADDR_HI_MASK,
 		     d + DESC_ADDR_HI_STATUS_LEN);
 #endif
-	__raw_writel(lower_32_bits(addr), d + DESC_ADDR_LO);
+	writel_relaxed(lower_32_bits(addr), d + DESC_ADDR_LO);
 }
 
 static inline void tdma_port_write_desc_addr(struct bcm_sysport_priv *priv,
@@ -201,10 +201,10 @@ static int bcm_sysport_set_features(struct net_device *dev,
  */
 static const struct bcm_sysport_stats bcm_sysport_gstrings_stats[] = {
 	/* general stats */
-	STAT_NETDEV(rx_packets),
-	STAT_NETDEV(tx_packets),
-	STAT_NETDEV(rx_bytes),
-	STAT_NETDEV(tx_bytes),
+	STAT_NETDEV64(rx_packets),
+	STAT_NETDEV64(tx_packets),
+	STAT_NETDEV64(rx_bytes),
+	STAT_NETDEV64(tx_bytes),
 	STAT_NETDEV(rx_errors),
 	STAT_NETDEV(tx_errors),
 	STAT_NETDEV(rx_dropped),
@@ -316,6 +316,7 @@ static inline bool bcm_sysport_lite_stat_valid(enum bcm_sysport_stat_type type)
 {
 	switch (type) {
 	case BCM_SYSPORT_STAT_NETDEV:
+	case BCM_SYSPORT_STAT_NETDEV64:
 	case BCM_SYSPORT_STAT_RXCHK:
 	case BCM_SYSPORT_STAT_RBUF:
 	case BCM_SYSPORT_STAT_SOFT:
@@ -398,6 +399,7 @@ static void bcm_sysport_update_mib_counters(struct bcm_sysport_priv *priv)
 		s = &bcm_sysport_gstrings_stats[i];
 		switch (s->type) {
 		case BCM_SYSPORT_STAT_NETDEV:
+		case BCM_SYSPORT_STAT_NETDEV64:
 		case BCM_SYSPORT_STAT_SOFT:
 			continue;
 		case BCM_SYSPORT_STAT_MIB_RX:
@@ -430,15 +432,44 @@ static void bcm_sysport_update_mib_counters(struct bcm_sysport_priv *priv)
 	netif_dbg(priv, hw, priv->netdev, "updated MIB counters\n");
 }
 
+static void bcm_sysport_update_tx_stats(struct bcm_sysport_priv *priv,
+					u64 *tx_bytes, u64 *tx_packets)
+{
+	struct bcm_sysport_tx_ring *ring;
+	u64 bytes = 0, packets = 0;
+	unsigned int start;
+	unsigned int q;
+
+	for (q = 0; q < priv->netdev->num_tx_queues; q++) {
+		ring = &priv->tx_rings[q];
+		do {
+			start = u64_stats_fetch_begin_irq(&priv->syncp);
+			bytes = ring->bytes;
+			packets = ring->packets;
+		} while (u64_stats_fetch_retry_irq(&priv->syncp, start));
+
+		*tx_bytes += bytes;
+		*tx_packets += packets;
+	}
+}
+
 static void bcm_sysport_get_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct bcm_sysport_stats64 *stats64 = &priv->stats64;
+	struct u64_stats_sync *syncp = &priv->syncp;
 	struct bcm_sysport_tx_ring *ring;
+	u64 tx_bytes = 0, tx_packets = 0;
+	unsigned int start;
 	int i, j;
 
-	if (netif_running(dev))
+	if (netif_running(dev)) {
 		bcm_sysport_update_mib_counters(priv);
+		bcm_sysport_update_tx_stats(priv, &tx_bytes, &tx_packets);
+		stats64->tx_bytes = tx_bytes;
+		stats64->tx_packets = tx_packets;
+	}
 
 	for (i =  0, j = 0; i < BCM_SYSPORT_STATS_LEN; i++) {
 		const struct bcm_sysport_stats *s;
@@ -447,10 +478,23 @@ static void bcm_sysport_get_stats(struct net_device *dev,
 		s = &bcm_sysport_gstrings_stats[i];
 		if (s->type == BCM_SYSPORT_STAT_NETDEV)
 			p = (char *)&dev->stats;
+		else if (s->type == BCM_SYSPORT_STAT_NETDEV64)
+			p = (char *)stats64;
 		else
 			p = (char *)priv;
+
+		if (priv->is_lite && !bcm_sysport_lite_stat_valid(s->type))
+			continue;
 		p += s->stat_offset;
-		data[j] = *(unsigned long *)p;
+
+		if (s->stat_sizeof == sizeof(u64) &&
+		    s->type == BCM_SYSPORT_STAT_NETDEV64) {
+			do {
+				start = u64_stats_fetch_begin_irq(syncp);
+				data[i] = *(u64 *)p;
+			} while (u64_stats_fetch_retry_irq(syncp, start));
+		} else
+			data[i] = *(u32 *)p;
 		j++;
 	}
 
@@ -593,7 +637,7 @@ static int bcm_sysport_set_coalesce(struct net_device *dev,
 
 static void bcm_sysport_free_cb(struct bcm_sysport_cb *cb)
 {
-	dev_kfree_skb_any(cb->skb);
+	dev_consume_skb_any(cb->skb);
 	cb->skb = NULL;
 	dma_unmap_addr_set(cb, dma_addr, 0);
 }
@@ -662,6 +706,7 @@ static int bcm_sysport_alloc_rx_bufs(struct bcm_sysport_priv *priv)
 static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 					unsigned int budget)
 {
+	struct bcm_sysport_stats64 *stats64 = &priv->stats64;
 	struct net_device *ndev = priv->netdev;
 	unsigned int processed = 0, to_process;
 	struct bcm_sysport_cb *cb;
@@ -765,6 +810,10 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 		skb->protocol = eth_type_trans(skb, ndev);
 		ndev->stats.rx_packets++;
 		ndev->stats.rx_bytes += len;
+		u64_stats_update_begin(&priv->syncp);
+		stats64->rx_packets++;
+		stats64->rx_bytes += len;
+		u64_stats_update_end(&priv->syncp);
 
 		napi_gro_receive(&priv->napi, skb);
 next:
@@ -787,17 +836,15 @@ static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring,
 	struct device *kdev = &priv->pdev->dev;
 
 	if (cb->skb) {
-		ring->bytes += cb->skb->len;
 		*bytes_compl += cb->skb->len;
 		dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
 				 dma_unmap_len(cb, dma_len),
 				 DMA_TO_DEVICE);
-		ring->packets++;
 		(*pkts_compl)++;
 		bcm_sysport_free_cb(cb);
 	/* SKB fragment */
 	} else if (dma_unmap_addr(cb, dma_addr)) {
-		ring->bytes += dma_unmap_len(cb, dma_len);
+		*bytes_compl += dma_unmap_len(cb, dma_len);
 		dma_unmap_page(kdev, dma_unmap_addr(cb, dma_addr),
 			       dma_unmap_len(cb, dma_len), DMA_TO_DEVICE);
 		dma_unmap_addr_set(cb, dma_addr, 0);
@@ -808,9 +855,9 @@ static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring,
 static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 					     struct bcm_sysport_tx_ring *ring)
 {
-	struct net_device *ndev = priv->netdev;
 	unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
+	struct net_device *ndev = priv->netdev;
 	struct bcm_sysport_cb *cb;
 	u32 hw_ind;
 
@@ -849,6 +896,11 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 		last_c_index &= (num_tx_cbs - 1);
 	}
 
+	u64_stats_update_begin(&priv->syncp);
+	ring->packets += pkts_compl;
+	ring->bytes += bytes_compl;
+	u64_stats_update_end(&priv->syncp);
+
 	ring->c_index = c_index;
 
 	netif_dbg(priv, tx_done, ndev,
@@ -1342,6 +1394,8 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 
 	ring->cbs = kcalloc(size, sizeof(struct bcm_sysport_cb), GFP_KERNEL);
 	if (!ring->cbs) {
+		dma_free_coherent(kdev, sizeof(struct dma_desc),
+				  ring->desc_cpu, ring->desc_dma);
 		netif_err(priv, hw, priv->netdev, "CB allocation failed\n");
 		return -ENOMEM;
 	}
@@ -1362,9 +1416,37 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	tdma_writel(priv, 0, TDMA_DESC_RING_COUNT(index));
 	tdma_writel(priv, 1, TDMA_DESC_RING_INTR_CONTROL(index));
 	tdma_writel(priv, 0, TDMA_DESC_RING_PROD_CONS_INDEX(index));
-	tdma_writel(priv, RING_IGNORE_STATUS, TDMA_DESC_RING_MAPPING(index));
+
+	/* Configure QID and port mapping */
+	reg = tdma_readl(priv, TDMA_DESC_RING_MAPPING(index));
+	reg &= ~(RING_QID_MASK | RING_PORT_ID_MASK << RING_PORT_ID_SHIFT);
+	if (ring->inspect) {
+		reg |= ring->switch_queue & RING_QID_MASK;
+		reg |= ring->switch_port << RING_PORT_ID_SHIFT;
+	} else {
+		reg |= RING_IGNORE_STATUS;
+	}
+	tdma_writel(priv, reg, TDMA_DESC_RING_MAPPING(index));
 	tdma_writel(priv, 0, TDMA_DESC_RING_PCP_DEI_VID(index));
 
+	/* Enable ACB algorithm 2 */
+	reg = tdma_readl(priv, TDMA_CONTROL);
+	reg |= tdma_control_bit(priv, ACB_ALGO);
+	tdma_writel(priv, reg, TDMA_CONTROL);
+
+	/* Do not use tdma_control_bit() here because TSB_SWAP1 collides
+	 * with the original definition of ACB_ALGO
+	 */
+	reg = tdma_readl(priv, TDMA_CONTROL);
+	if (priv->is_lite)
+		reg &= ~BIT(TSB_SWAP1);
+	/* Set a correct TSB format based on host endian */
+	if (!IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		reg |= tdma_control_bit(priv, TSB_SWAP0);
+	else
+		reg &= ~tdma_control_bit(priv, TSB_SWAP0);
+	tdma_writel(priv, reg, TDMA_CONTROL);
+
 	/* Program the number of descriptors as MAX_THRESHOLD and half of
 	 * its size for the hysteresis trigger
 	 */
@@ -1380,8 +1462,9 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	napi_enable(&ring->napi);
 
 	netif_dbg(priv, hw, priv->netdev,
-		  "TDMA cfg, size=%d, desc_cpu=%p\n",
-		  ring->size, ring->desc_cpu);
+		  "TDMA cfg, size=%d, desc_cpu=%p switch q=%d,port=%d\n",
+		  ring->size, ring->desc_cpu, ring->switch_queue,
+		  ring->switch_port);
 
 	return 0;
 }
@@ -1671,22 +1754,23 @@ static int bcm_sysport_change_mac(struct net_device *dev, void *p)
 	return 0;
 }
 
-static struct net_device_stats *bcm_sysport_get_nstats(struct net_device *dev)
+static void bcm_sysport_get_stats64(struct net_device *dev,
+				    struct rtnl_link_stats64 *stats)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
-	unsigned long tx_bytes = 0, tx_packets = 0;
-	struct bcm_sysport_tx_ring *ring;
-	unsigned int q;
+	struct bcm_sysport_stats64 *stats64 = &priv->stats64;
+	unsigned int start;
 
-	for (q = 0; q < dev->num_tx_queues; q++) {
-		ring = &priv->tx_rings[q];
-		tx_bytes += ring->bytes;
-		tx_packets += ring->packets;
-	}
+	netdev_stats_to_stats64(stats, &dev->stats);
+
+	bcm_sysport_update_tx_stats(priv, &stats->tx_bytes,
+				    &stats->tx_packets);
 
-	dev->stats.tx_bytes = tx_bytes;
-	dev->stats.tx_packets = tx_packets;
-	return &dev->stats;
+	do {
+		start = u64_stats_fetch_begin_irq(&priv->syncp);
+		stats->rx_packets = stats64->rx_packets;
+		stats->rx_bytes = stats64->rx_bytes;
+	} while (u64_stats_fetch_retry_irq(&priv->syncp, start));
 }
 
 static void bcm_sysport_netif_start(struct net_device *dev)
@@ -1718,10 +1802,14 @@ static void rbuf_init(struct bcm_sysport_priv *priv)
 	reg = rbuf_readl(priv, RBUF_CONTROL);
 	reg |= RBUF_4B_ALGN | RBUF_RSB_EN;
 	/* Set a correct RSB format on SYSTEMPORT Lite */
-	if (priv->is_lite) {
+	if (priv->is_lite)
 		reg &= ~RBUF_RSB_SWAP1;
+
+	/* Set a correct RSB format based on host endian */
+	if (!IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
 		reg |= RBUF_RSB_SWAP0;
-	}
+	else
+		reg &= ~RBUF_RSB_SWAP0;
 	rbuf_writel(priv, reg, RBUF_CONTROL);
 }
 
@@ -1737,15 +1825,17 @@ static inline void bcm_sysport_mask_all_intrs(struct bcm_sysport_priv *priv)
 
 static inline void gib_set_pad_extension(struct bcm_sysport_priv *priv)
 {
-	u32 __maybe_unused reg;
+	u32 reg;
 
-	/* Include Broadcom tag in pad extension */
+	reg = gib_readl(priv, GIB_CONTROL);
+	/* Include Broadcom tag in pad extension and fix up IPG_LENGTH */
 	if (netdev_uses_dsa(priv->netdev)) {
-		reg = gib_readl(priv, GIB_CONTROL);
 		reg &= ~(GIB_PAD_EXTENSION_MASK << GIB_PAD_EXTENSION_SHIFT);
 		reg |= ENET_BRCM_TAG_LEN << GIB_PAD_EXTENSION_SHIFT;
-		gib_writel(priv, reg, GIB_CONTROL);
 	}
+	reg &= ~(GIB_IPG_LEN_MASK << GIB_IPG_LEN_SHIFT);
+	reg |= 12 << GIB_IPG_LEN_SHIFT;
+	gib_writel(priv, reg, GIB_CONTROL);
 }
 
 static int bcm_sysport_open(struct net_device *dev)
@@ -1939,6 +2029,29 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
+static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
+				    void *accel_priv,
+				    select_queue_fallback_t fallback)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	u16 queue = skb_get_queue_mapping(skb);
+	struct bcm_sysport_tx_ring *tx_ring;
+	unsigned int q, port;
+
+	if (!netdev_uses_dsa(dev))
+		return fallback(dev, skb);
+
+	/* DSA tagging layer will have configured the correct queue */
+	q = BRCM_TAG_GET_QUEUE(queue);
+	port = BRCM_TAG_GET_PORT(queue);
+	tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues];
+
+	if (unlikely(!tx_ring))
+		return fallback(dev, skb);
+
+	return tx_ring->index;
+}
+
 static const struct net_device_ops bcm_sysport_netdev_ops = {
 	.ndo_start_xmit		= bcm_sysport_xmit,
 	.ndo_tx_timeout		= bcm_sysport_tx_timeout,
@@ -1950,9 +2063,80 @@ static const struct net_device_ops bcm_sysport_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= bcm_sysport_poll_controller,
 #endif
-	.ndo_get_stats		= bcm_sysport_get_nstats,
+	.ndo_get_stats64	= bcm_sysport_get_stats64,
+	.ndo_select_queue	= bcm_sysport_select_queue,
 };
 
+static int bcm_sysport_map_queues(struct net_device *dev,
+				  struct dsa_notifier_register_info *info)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct bcm_sysport_tx_ring *ring;
+	struct net_device *slave_dev;
+	unsigned int num_tx_queues;
+	unsigned int q, start, port;
+
+	/* We can't be setting up queue inspection for non directly attached
+	 * switches
+	 */
+	if (info->switch_number)
+		return 0;
+
+	if (dev->netdev_ops != &bcm_sysport_netdev_ops)
+		return 0;
+
+	port = info->port_number;
+	slave_dev = info->info.dev;
+
+	/* On SYSTEMPORT Lite we have twice as less queues, so we cannot do a
+	 * 1:1 mapping, we can only do a 2:1 mapping. By reducing the number of
+	 * per-port (slave_dev) network devices queue, we achieve just that.
+	 * This need to happen now before any slave network device is used such
+	 * it accurately reflects the number of real TX queues.
+	 */
+	if (priv->is_lite)
+		netif_set_real_num_tx_queues(slave_dev,
+					     slave_dev->num_tx_queues / 2);
+	num_tx_queues = slave_dev->real_num_tx_queues;
+
+	if (priv->per_port_num_tx_queues &&
+	    priv->per_port_num_tx_queues != num_tx_queues)
+		netdev_warn(slave_dev, "asymetric number of per-port queues\n");
+
+	priv->per_port_num_tx_queues = num_tx_queues;
+
+	start = find_first_zero_bit(&priv->queue_bitmap, dev->num_tx_queues);
+	for (q = 0; q < num_tx_queues; q++) {
+		ring = &priv->tx_rings[q + start];
+
+		/* Just remember the mapping actual programming done
+		 * during bcm_sysport_init_tx_ring
+		 */
+		ring->switch_queue = q;
+		ring->switch_port = port;
+		ring->inspect = true;
+		priv->ring_map[q + port * num_tx_queues] = ring;
+
+		/* Set all queues as being used now */
+		set_bit(q + start, &priv->queue_bitmap);
+	}
+
+	return 0;
+}
+
+static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
+				    unsigned long event, void *ptr)
+{
+	struct dsa_notifier_register_info *info;
+
+	if (event != DSA_PORT_REGISTER)
+		return NOTIFY_DONE;
+
+	info = ptr;
+
+	return notifier_from_errno(bcm_sysport_map_queues(info->master, info));
+}
+
 #define REV_FMT	"v%2x.%02x"
 
 static const struct bcm_sysport_hw_params bcm_sysport_params[] = {
@@ -2098,10 +2282,20 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 	/* libphy will adjust the link state accordingly */
 	netif_carrier_off(dev);
 
+	u64_stats_init(&priv->syncp);
+
+	priv->dsa_notifier.notifier_call = bcm_sysport_dsa_notifier;
+
+	ret = register_dsa_notifier(&priv->dsa_notifier);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register DSA notifier\n");
+		goto err_deregister_fixed_link;
+	}
+
 	ret = register_netdev(dev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register net_device\n");
-		goto err_deregister_fixed_link;
+		goto err_deregister_notifier;
 	}
 
 	priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK;
@@ -2114,6 +2308,8 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_deregister_notifier:
+	unregister_dsa_notifier(&priv->dsa_notifier);
 err_deregister_fixed_link:
 	if (of_phy_is_fixed_link(dn))
 		of_phy_deregister_fixed_link(dn);
@@ -2125,11 +2321,13 @@ err_free_netdev:
 static int bcm_sysport_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = dev_get_drvdata(&pdev->dev);
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct device_node *dn = pdev->dev.of_node;
 
 	/* Not much to do, ndo_close has been called
 	 * and we use managed allocations
 	 */
+	unregister_dsa_notifier(&priv->dsa_notifier);
 	unregister_netdev(dev);
 	if (of_phy_is_fixed_link(dn))
 		of_phy_deregister_fixed_link(dn);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 77a51c167a69..f5a984c1c986 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -404,7 +404,7 @@ struct bcm_rsb {
 #define  RING_CONS_INDEX_MASK		0xffff
 
 #define RING_MAPPING			0x14
-#define  RING_QID_MASK			0x3
+#define  RING_QID_MASK			0x7
 #define  RING_PORT_ID_SHIFT		3
 #define  RING_PORT_ID_MASK		0x7
 #define  RING_IGNORE_STATUS		(1 << 6)
@@ -449,7 +449,8 @@ struct bcm_rsb {
 /* Uses 2 bits on SYSTEMPORT Lite and shifts everything by 1 bit, we
  * keep the SYSTEMPORT layout here and adjust with tdma_control_bit()
  */
-#define  TSB_SWAP			2
+#define  TSB_SWAP0			2
+#define  TSB_SWAP1			3
 #define  ACB_ALGO			3
 #define  BUF_DATA_OFFSET_SHIFT		4
 #define  BUF_DATA_OFFSET_MASK		0x3ff
@@ -603,6 +604,7 @@ struct bcm_sysport_mib {
 /* HW maintains a large list of counters */
 enum bcm_sysport_stat_type {
 	BCM_SYSPORT_STAT_NETDEV = -1,
+	BCM_SYSPORT_STAT_NETDEV64,
 	BCM_SYSPORT_STAT_MIB_RX,
 	BCM_SYSPORT_STAT_MIB_TX,
 	BCM_SYSPORT_STAT_RUNT,
@@ -619,6 +621,13 @@ enum bcm_sysport_stat_type {
 	.type = BCM_SYSPORT_STAT_NETDEV, \
 }
 
+#define STAT_NETDEV64(m) { \
+	.stat_string = __stringify(m), \
+	.stat_sizeof = sizeof(((struct bcm_sysport_stats64 *)0)->m), \
+	.stat_offset = offsetof(struct bcm_sysport_stats64, m), \
+	.type = BCM_SYSPORT_STAT_NETDEV64, \
+}
+
 #define STAT_MIB(str, m, _type) { \
 	.stat_string = str, \
 	.stat_sizeof = sizeof(((struct bcm_sysport_priv *)0)->m), \
@@ -659,6 +668,14 @@ struct bcm_sysport_stats {
 	u16 reg_offset;
 };
 
+struct bcm_sysport_stats64 {
+	/* 64bit stats on 32bit/64bit Machine */
+	u64	rx_packets;
+	u64	rx_bytes;
+	u64	tx_packets;
+	u64	tx_bytes;
+};
+
 /* Software house keeping helper structure */
 struct bcm_sysport_cb {
 	struct sk_buff	*skb;		/* SKB for RX packets */
@@ -695,6 +712,9 @@ struct bcm_sysport_tx_ring {
 	struct bcm_sysport_priv *priv;	/* private context backpointer */
 	unsigned long	packets;	/* packets statistics */
 	unsigned long	bytes;		/* bytes statistics */
+	unsigned int	switch_queue;	/* switch port queue number */
+	unsigned int	switch_port;	/* switch port queue number */
+	bool		inspect;	/* inspect switch port and queue */
 };
 
 /* Driver private structure */
@@ -743,5 +763,17 @@ struct bcm_sysport_priv {
 
 	/* Ethtool */
 	u32			msg_enable;
+
+	struct bcm_sysport_stats64	stats64;
+
+	/* For atomic update generic 64bit value on 32bit Machine */
+	struct u64_stats_sync	syncp;
+
+	/* map information between switch port queues and local queues */
+	struct notifier_block	dsa_notifier;
+	unsigned int		per_port_num_tx_queues;
+	unsigned long		queue_bitmap;
+	struct bcm_sysport_tx_ring *ring_map[DSA_MAX_PORTS * 8];
+
 };
 #endif /* __BCM_SYSPORT_H */
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 6322594ab260..6fe074c1588b 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -184,13 +184,19 @@ static int bgmac_probe(struct bcma_device *core)
 
 	if (!bgmac_is_bcm4707_family(core) &&
 	    !(ci->id == BCMA_CHIP_ID_BCM53573 && core->core_unit == 1)) {
+		struct phy_device *phydev;
+
 		mii_bus = bcma_mdio_mii_register(bgmac);
 		if (IS_ERR(mii_bus)) {
 			err = PTR_ERR(mii_bus);
 			goto err;
 		}
-
 		bgmac->mii_bus = mii_bus;
+
+		phydev = mdiobus_get_phy(bgmac->mii_bus, bgmac->phyaddr);
+		if (ci->id == BCMA_CHIP_ID_BCM53573 && phydev &&
+		    (phydev->drv->phy_id & phydev->drv->phy_id_mask) == PHY_ID_BCM54210E)
+			phydev->dev_flags |= PHY_BRCM_EN_MASTER_MODE;
 	}
 
 	if (core->bus->hosttype == BCMA_HOSTTYPE_PCI) {
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index d937083db9a4..894eda5b13cf 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -131,6 +131,7 @@ static void bgmac_nicpm_speed_set(struct net_device *net_dev)
 	switch (bgmac->net_dev->phydev->speed) {
 	default:
 		netdev_err(net_dev, "Unsupported speed. Defaulting to 1000Mb\n");
+		/* fall through */
 	case SPEED_1000:
 		val |= NICPM_IOMUX_CTRL_SPD_1000M << NICPM_IOMUX_CTRL_SPD_SHIFT;
 		break;
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 48d672b204a4..1d96cd594ade 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -15,6 +15,7 @@
 #include <linux/bcm47xx_nvram.h>
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
+#include <net/dsa.h>
 #include "bgmac.h"
 
 static bool bgmac_wait_value(struct bgmac *bgmac, u16 reg, u32 mask,
@@ -127,6 +128,8 @@ bgmac_dma_tx_add_buf(struct bgmac *bgmac, struct bgmac_dma_ring *ring,
 	dma_desc->ctl1 = cpu_to_le32(ctl1);
 }
 
+#define ENET_BRCM_TAG_LEN	4
+
 static netdev_tx_t bgmac_dma_tx_add(struct bgmac *bgmac,
 				    struct bgmac_dma_ring *ring,
 				    struct sk_buff *skb)
@@ -139,6 +142,18 @@ static netdev_tx_t bgmac_dma_tx_add(struct bgmac *bgmac,
 	u32 flags;
 	int i;
 
+	/* The Ethernet switch we are interfaced with needs packets to be at
+	 * least 64 bytes (including FCS) otherwise they will be discarded when
+	 * they enter the switch port logic. When Broadcom tags are enabled, we
+	 * need to make sure that packets are at least 68 bytes
+	 * (including FCS and tag) because the length verification is done after
+	 * the Broadcom tag is stripped off the ingress packet.
+	 */
+	if (netdev_uses_dsa(net_dev)) {
+		if (skb_put_padto(skb, ETH_ZLEN + ENET_BRCM_TAG_LEN))
+			goto err_stats;
+	}
+
 	if (skb->len > BGMAC_DESC_CTL1_LEN) {
 		netdev_err(bgmac->net_dev, "Too long skb (%d)\n", skb->len);
 		goto err_drop;
@@ -225,6 +240,7 @@ err_dma_head:
 
 err_drop:
 	dev_kfree_skb(skb);
+err_stats:
 	net_dev->stats.tx_dropped++;
 	net_dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index 443d57b10264..4040d846da8e 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _BGMAC_H
 #define _BGMAC_H
 
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index e3af1f3cb61f..7919f6112ecf 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -6183,9 +6183,9 @@ bnx2_5708_serdes_timer(struct bnx2 *bp)
 }
 
 static void
-bnx2_timer(unsigned long data)
+bnx2_timer(struct timer_list *t)
 {
-	struct bnx2 *bp = (struct bnx2 *) data;
+	struct bnx2 *bp = from_timer(bp, t, timer);
 
 	if (!netif_running(bp->dev))
 		return;
@@ -8462,10 +8462,8 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev)
 	bnx2_set_default_link(bp);
 	bp->req_flow_ctrl = FLOW_CTRL_RX | FLOW_CTRL_TX;
 
-	init_timer(&bp->timer);
+	timer_setup(&bp->timer, bnx2_timer, 0);
 	bp->timer.expires = RUN_AT(BNX2_TIMER_INTERVAL);
-	bp->timer.data = (unsigned long) bp;
-	bp->timer.function = bnx2_timer;
 
 #ifdef BCM_CNIC
 	if (bnx2_shmem_rd(bp, BNX2_ISCSI_INITIATOR) & BNX2_ISCSI_INITIATOR_EN)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 67fe3d826566..4c739d5355d2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4284,15 +4284,17 @@ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc)
 	return 0;
 }
 
-int __bnx2x_setup_tc(struct net_device *dev, u32 handle, u32 chain_index,
-		     __be16 proto, struct tc_to_netdev *tc)
+int __bnx2x_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		     void *type_data)
 {
-	if (tc->type != TC_SETUP_MQPRIO)
-		return -EINVAL;
+	struct tc_mqprio_qopt *mqprio = type_data;
+
+	if (type != TC_SETUP_QDISC_MQPRIO)
+		return -EOPNOTSUPP;
 
-	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
-	return bnx2x_setup_tc(dev, tc->mqprio->num_tc);
+	return bnx2x_setup_tc(dev, mqprio->num_tc);
 }
 
 /* called with rtnl_lock */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index c26688d2f326..a5265e1344f1 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -486,8 +486,8 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev);
 
 /* setup_tc callback */
 int bnx2x_setup_tc(struct net_device *dev, u8 num_tc);
-int __bnx2x_setup_tc(struct net_device *dev, u32 handle, u32 chain_index,
-		     __be16 proto, struct tc_to_netdev *tc);
+int __bnx2x_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		     void *type_data);
 
 int bnx2x_get_vf_config(struct net_device *dev, int vf,
 			struct ifla_vf_info *ivi);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c12b4d3e946e..91e2a7560b48 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -5761,9 +5761,9 @@ void bnx2x_drv_pulse(struct bnx2x *bp)
 		 bp->fw_drv_pulse_wr_seq);
 }
 
-static void bnx2x_timer(unsigned long data)
+static void bnx2x_timer(struct timer_list *t)
 {
-	struct bnx2x *bp = (struct bnx2x *) data;
+	struct bnx2x *bp = from_timer(bp, t, timer);
 
 	if (!netif_running(bp->dev))
 		return;
@@ -9332,7 +9332,7 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link)
 	/* Schedule the rx_mode command */
 	if (test_bit(BNX2X_FILTER_RX_MODE_PENDING, &bp->sp_state))
 		set_bit(BNX2X_FILTER_RX_MODE_SCHED, &bp->sp_state);
-	else
+	else if (bp->slowpath)
 		bnx2x_set_storm_rx_mode(bp);
 
 	/* Cleanup multicast configuration */
@@ -10271,8 +10271,15 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work)
 		smp_mb();
 
 		bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
-		bnx2x_nic_load(bp, LOAD_NORMAL);
-
+		/* When ret value shows failure of allocation failure,
+		 * the nic is rebooted again. If open still fails, a error
+		 * message to notify the user.
+		 */
+		if (bnx2x_nic_load(bp, LOAD_NORMAL) == -ENOMEM) {
+			bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
+			if (bnx2x_nic_load(bp, LOAD_NORMAL))
+				BNX2X_ERR("Open the NIC fails again!\n");
+		}
 		rtnl_unlock();
 		return;
 	}
@@ -12414,10 +12421,8 @@ static int bnx2x_init_bp(struct bnx2x *bp)
 
 	bp->current_interval = CHIP_REV_IS_SLOW(bp) ? 5*HZ : HZ;
 
-	init_timer(&bp->timer);
+	timer_setup(&bp->timer, bnx2x_timer, 0);
 	bp->timer.expires = jiffies + bp->current_interval;
-	bp->timer.data = (unsigned long) bp;
-	bp->timer.function = bnx2x_timer;
 
 	if (SHMEM2_HAS(bp, dcbx_lldp_params_offset) &&
 	    SHMEM2_HAS(bp, dcbx_lldp_dcbx_stat_offset) &&
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 9ca994d0bab6..3591077a5f6b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1074,11 +1074,6 @@ static void bnx2x_vf_set_bars(struct bnx2x *bp, struct bnx2x_virtf *vf)
 	}
 }
 
-static int bnx2x_ari_enabled(struct pci_dev *dev)
-{
-	return dev->bus->self && dev->bus->self->ari_enabled;
-}
-
 static int
 bnx2x_get_vf_igu_cam_info(struct bnx2x *bp)
 {
@@ -1212,7 +1207,7 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
 
 	err = -EIO;
 	/* verify ari is enabled */
-	if (!bnx2x_ari_enabled(bp->pdev)) {
+	if (!pci_ari_enabled(bp->pdev->bus)) {
 		BNX2X_ERR("ARI not supported (check pci bridge ARI forwarding), SRIOV can not be enabled\n");
 		return 0;
 	}
diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile
index a7ca45b251cb..59c8ec9c1cad 100644
--- a/drivers/net/ethernet/broadcom/bnxt/Makefile
+++ b/drivers/net/ethernet/broadcom/bnxt/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_BNXT) += bnxt_en.o
 
-bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o
+bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_devlink.o
+bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e7c8539cbddf..c5c38d4b7d1c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -33,6 +33,7 @@
 #include <linux/mii.h>
 #include <linux/if.h>
 #include <linux/if_vlan.h>
+#include <linux/if_bridge.h>
 #include <linux/rtc.h>
 #include <linux/bpf.h>
 #include <net/ip.h>
@@ -48,6 +49,8 @@
 #include <linux/aer.h>
 #include <linux/bitmap.h>
 #include <linux/cpu_rmap.h>
+#include <linux/cpumask.h>
+#include <net/pkt_cls.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -56,6 +59,9 @@
 #include "bnxt_ethtool.h"
 #include "bnxt_dcb.h"
 #include "bnxt_xdp.h"
+#include "bnxt_vfr.h"
+#include "bnxt_tc.h"
+#include "bnxt_devlink.h"
 
 #define BNXT_TX_TIMEOUT		(5 * HZ)
 
@@ -101,47 +107,56 @@ enum board_idx {
 	BCM57416_NPAR,
 	BCM57452,
 	BCM57454,
+	BCM58802,
+	BCM58804,
+	BCM58808,
 	NETXTREME_E_VF,
 	NETXTREME_C_VF,
+	NETXTREME_S_VF,
 };
 
 /* indexed by enum above */
 static const struct {
 	char *name;
 } board_info[] = {
-	{ "Broadcom BCM57301 NetXtreme-C 10Gb Ethernet" },
-	{ "Broadcom BCM57302 NetXtreme-C 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57304 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
-	{ "Broadcom BCM57417 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM58700 Nitro 1Gb/2.5Gb/10Gb Ethernet" },
-	{ "Broadcom BCM57311 NetXtreme-C 10Gb Ethernet" },
-	{ "Broadcom BCM57312 NetXtreme-C 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57402 NetXtreme-E 10Gb Ethernet" },
-	{ "Broadcom BCM57404 NetXtreme-E 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57406 NetXtreme-E 10GBase-T Ethernet" },
-	{ "Broadcom BCM57402 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57407 NetXtreme-E 10GBase-T Ethernet" },
-	{ "Broadcom BCM57412 NetXtreme-E 10Gb Ethernet" },
-	{ "Broadcom BCM57414 NetXtreme-E 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57416 NetXtreme-E 10GBase-T Ethernet" },
-	{ "Broadcom BCM57417 NetXtreme-E 10GBase-T Ethernet" },
-	{ "Broadcom BCM57412 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57314 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
-	{ "Broadcom BCM57417 NetXtreme-E 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57416 NetXtreme-E 10Gb Ethernet" },
-	{ "Broadcom BCM57404 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57406 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57407 NetXtreme-E 25Gb Ethernet" },
-	{ "Broadcom BCM57407 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57414 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57416 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb Ethernet" },
-	{ "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
-	{ "Broadcom NetXtreme-E Ethernet Virtual Function" },
-	{ "Broadcom NetXtreme-C Ethernet Virtual Function" },
+	[BCM57301] = { "Broadcom BCM57301 NetXtreme-C 10Gb Ethernet" },
+	[BCM57302] = { "Broadcom BCM57302 NetXtreme-C 10Gb/25Gb Ethernet" },
+	[BCM57304] = { "Broadcom BCM57304 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	[BCM57417_NPAR] = { "Broadcom BCM57417 NetXtreme-E Ethernet Partition" },
+	[BCM58700] = { "Broadcom BCM58700 Nitro 1Gb/2.5Gb/10Gb Ethernet" },
+	[BCM57311] = { "Broadcom BCM57311 NetXtreme-C 10Gb Ethernet" },
+	[BCM57312] = { "Broadcom BCM57312 NetXtreme-C 10Gb/25Gb Ethernet" },
+	[BCM57402] = { "Broadcom BCM57402 NetXtreme-E 10Gb Ethernet" },
+	[BCM57404] = { "Broadcom BCM57404 NetXtreme-E 10Gb/25Gb Ethernet" },
+	[BCM57406] = { "Broadcom BCM57406 NetXtreme-E 10GBase-T Ethernet" },
+	[BCM57402_NPAR] = { "Broadcom BCM57402 NetXtreme-E Ethernet Partition" },
+	[BCM57407] = { "Broadcom BCM57407 NetXtreme-E 10GBase-T Ethernet" },
+	[BCM57412] = { "Broadcom BCM57412 NetXtreme-E 10Gb Ethernet" },
+	[BCM57414] = { "Broadcom BCM57414 NetXtreme-E 10Gb/25Gb Ethernet" },
+	[BCM57416] = { "Broadcom BCM57416 NetXtreme-E 10GBase-T Ethernet" },
+	[BCM57417] = { "Broadcom BCM57417 NetXtreme-E 10GBase-T Ethernet" },
+	[BCM57412_NPAR] = { "Broadcom BCM57412 NetXtreme-E Ethernet Partition" },
+	[BCM57314] = { "Broadcom BCM57314 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	[BCM57417_SFP] = { "Broadcom BCM57417 NetXtreme-E 10Gb/25Gb Ethernet" },
+	[BCM57416_SFP] = { "Broadcom BCM57416 NetXtreme-E 10Gb Ethernet" },
+	[BCM57404_NPAR] = { "Broadcom BCM57404 NetXtreme-E Ethernet Partition" },
+	[BCM57406_NPAR] = { "Broadcom BCM57406 NetXtreme-E Ethernet Partition" },
+	[BCM57407_SFP] = { "Broadcom BCM57407 NetXtreme-E 25Gb Ethernet" },
+	[BCM57407_NPAR] = { "Broadcom BCM57407 NetXtreme-E Ethernet Partition" },
+	[BCM57414_NPAR] = { "Broadcom BCM57414 NetXtreme-E Ethernet Partition" },
+	[BCM57416_NPAR] = { "Broadcom BCM57416 NetXtreme-E Ethernet Partition" },
+	[BCM57452] = { "Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	[BCM57454] = { "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
+	[BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	[BCM58804] = { "Broadcom BCM58804 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
+	[BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
+	[NETXTREME_E_VF] = { "Broadcom NetXtreme-E Ethernet Virtual Function" },
+	[NETXTREME_C_VF] = { "Broadcom NetXtreme-C Ethernet Virtual Function" },
+	[NETXTREME_S_VF] = { "Broadcom NetXtreme-S Ethernet Virtual Function" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
+	{ PCI_VDEVICE(BROADCOM, 0x1614), .driver_data = BCM57454 },
 	{ PCI_VDEVICE(BROADCOM, 0x16c0), .driver_data = BCM57417_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x16c8), .driver_data = BCM57301 },
 	{ PCI_VDEVICE(BROADCOM, 0x16c9), .driver_data = BCM57302 },
@@ -172,8 +187,10 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16ed), .driver_data = BCM57414_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x16ee), .driver_data = BCM57416_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x16ef), .driver_data = BCM57416_NPAR },
+	{ PCI_VDEVICE(BROADCOM, 0x16f0), .driver_data = BCM58808 },
 	{ PCI_VDEVICE(BROADCOM, 0x16f1), .driver_data = BCM57452 },
-	{ PCI_VDEVICE(BROADCOM, 0x1614), .driver_data = BCM57454 },
+	{ PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 },
+	{ PCI_VDEVICE(BROADCOM, 0xd804), .driver_data = BCM58804 },
 #ifdef CONFIG_BNXT_SRIOV
 	{ PCI_VDEVICE(BROADCOM, 0x1606), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x1609), .driver_data = NETXTREME_E_VF },
@@ -183,6 +200,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16dc), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e1), .driver_data = NETXTREME_C_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e5), .driver_data = NETXTREME_C_VF },
+	{ PCI_VDEVICE(BROADCOM, 0xd800), .driver_data = NETXTREME_S_VF },
 #endif
 	{ 0 }
 };
@@ -203,9 +221,12 @@ static const u16 bnxt_async_events_arr[] = {
 	ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE,
 };
 
+static struct workqueue_struct *bnxt_pf_wq;
+
 static bool bnxt_vf_pciid(enum board_idx idx)
 {
-	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF);
+	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF ||
+		idx == NETXTREME_S_VF);
 }
 
 #define DB_CP_REARM_FLAGS	(DB_KEY_CP | DB_IDX_VALID)
@@ -243,6 +264,16 @@ const u16 bnxt_lhint_arr[] = {
 	TX_BD_FLAGS_LHINT_2048_AND_LARGER,
 };
 
+static u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb)
+{
+	struct metadata_dst *md_dst = skb_metadata_dst(skb);
+
+	if (!md_dst || md_dst->type != METADATA_HW_PORT_MUX)
+		return 0;
+
+	return md_dst->u.port_info.port_id;
+}
+
 static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -287,7 +318,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	tx_buf->nr_frags = last_frag;
 
 	vlan_tag_flags = 0;
-	cfa_action = 0;
+	cfa_action = bnxt_xmit_get_cfa_action(skb);
 	if (skb_vlan_tag_present(skb)) {
 		vlan_tag_flags = TX_BD_CFA_META_KEY_VLAN |
 				 skb_vlan_tag_get(skb);
@@ -322,7 +353,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			tx_push1->tx_bd_hsize_lflags = 0;
 
 		tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags);
-		tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action);
+		tx_push1->tx_bd_cfa_action =
+			cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT);
 
 		end = pdata + length;
 		end = PTR_ALIGN(end, 8) - 1;
@@ -427,7 +459,8 @@ normal_tx:
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
 
 	txbd1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags);
-	txbd1->tx_bd_cfa_action = cpu_to_le32(cfa_action);
+	txbd1->tx_bd_cfa_action =
+			cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT);
 	for (i = 0; i < last_frag; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
@@ -1001,12 +1034,28 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_napi *bnapi,
 	return 0;
 }
 
+static void bnxt_queue_sp_work(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		queue_work(bnxt_pf_wq, &bp->sp_task);
+	else
+		schedule_work(&bp->sp_task);
+}
+
+static void bnxt_cancel_sp_work(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		flush_workqueue(bnxt_pf_wq);
+	else
+		cancel_work_sync(&bp->sp_task);
+}
+
 static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
 	if (!rxr->bnapi->in_reset) {
 		rxr->bnapi->in_reset = true;
 		set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 	}
 	rxr->rx_next_cons = 0xffff;
 }
@@ -1032,7 +1081,10 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		bnxt_sched_reset(bp, rxr);
 		return;
 	}
-
+	/* Store cfa_code in tpa_info to use in tpa_end
+	 * completion processing.
+	 */
+	tpa_info->cfa_code = TPA_START_CFA_CODE(tpa_start1);
 	prod_rx_buf->data = tpa_info->data;
 	prod_rx_buf->data_ptr = tpa_info->data_ptr;
 
@@ -1267,6 +1319,17 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
 	return skb;
 }
 
+/* Given the cfa_code of a received packet determine which
+ * netdev (vf-rep or PF) the packet is destined to.
+ */
+static struct net_device *bnxt_get_pkt_dev(struct bnxt *bp, u16 cfa_code)
+{
+	struct net_device *dev = bnxt_get_vf_rep(bp, cfa_code);
+
+	/* if vf-rep dev is NULL, the must belongs to the PF */
+	return dev ? dev : bp->dev;
+}
+
 static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 					   struct bnxt_napi *bnapi,
 					   u32 *raw_cons,
@@ -1360,7 +1423,9 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 			return NULL;
 		}
 	}
-	skb->protocol = eth_type_trans(skb, bp->dev);
+
+	skb->protocol =
+		eth_type_trans(skb, bnxt_get_pkt_dev(bp, tpa_info->cfa_code));
 
 	if (tpa_info->hash_type != PKT_HASH_TYPE_NONE)
 		skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type);
@@ -1387,6 +1452,18 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 	return skb;
 }
 
+static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
+			     struct sk_buff *skb)
+{
+	if (skb->dev != bp->dev) {
+		/* this packet belongs to a vf-rep */
+		bnxt_vf_rep_rx(bp, skb);
+		return;
+	}
+	skb_record_rx_queue(skb, bnapi->index);
+	napi_gro_receive(&bnapi->napi, skb);
+}
+
 /* returns the following:
  * 1       - 1 packet successfully received
  * 0       - successful TPA_START, packet not completed yet
@@ -1403,7 +1480,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 	struct rx_cmp *rxcmp;
 	struct rx_cmp_ext *rxcmp1;
 	u32 tmp_raw_cons = *raw_cons;
-	u16 cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
+	u16 cfa_code, cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
 	struct bnxt_sw_rx_bd *rx_buf;
 	unsigned int len;
 	u8 *data_ptr, agg_bufs, cmp_type;
@@ -1440,13 +1517,12 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 				   (struct rx_tpa_end_cmp *)rxcmp,
 				   (struct rx_tpa_end_cmp_ext *)rxcmp1, event);
 
-		if (unlikely(IS_ERR(skb)))
+		if (IS_ERR(skb))
 			return -EBUSY;
 
 		rc = -ENOMEM;
 		if (likely(skb)) {
-			skb_record_rx_queue(skb, bnapi->index);
-			napi_gro_receive(&bnapi->napi, skb);
+			bnxt_deliver_skb(bp, bnapi, skb);
 			rc = 1;
 		}
 		*event |= BNXT_RX_EVENT;
@@ -1535,7 +1611,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 		skb_set_hash(skb, le32_to_cpu(rxcmp->rx_cmp_rss_hash), type);
 	}
 
-	skb->protocol = eth_type_trans(skb, dev);
+	cfa_code = RX_CMP_CFA_CODE(rxcmp1);
+	skb->protocol = eth_type_trans(skb, bnxt_get_pkt_dev(bp, cfa_code));
 
 	if ((rxcmp1->rx_cmp_flags2 &
 	     cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) &&
@@ -1560,8 +1637,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 		}
 	}
 
-	skb_record_rx_queue(skb, bnapi->index);
-	napi_gro_receive(&bnapi->napi, skb);
+	bnxt_deliver_skb(bp, bnapi, skb);
 	rc = 1;
 
 next_rx:
@@ -1667,7 +1743,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 	default:
 		goto async_event_process_exit;
 	}
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 async_event_process_exit:
 	bnxt_ulp_async_events(bp, cmpl);
 	return 0;
@@ -1701,7 +1777,7 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 
 		set_bit(vf_id - bp->pf.first_vf_id, bp->pf.vf_event_bmap);
 		set_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 		break;
 
 	case CMPL_BASE_TYPE_HWRM_ASYNC_EVENT:
@@ -1802,6 +1878,13 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 							   &event);
 			if (likely(rc >= 0))
 				rx_pkts += rc;
+			/* Increment rx_pkts when rc is -ENOMEM to count towards
+			 * the NAPI budget.  Otherwise, we may potentially loop
+			 * here forever if we consistently cannot allocate
+			 * buffers.
+			 */
+			else if (rc == -ENOMEM)
+				rx_pkts++;
 			else if (rc == -EBUSY)	/* partial completion */
 				break;
 		} else if (unlikely((TX_CMP_TYPE(txcmp) ==
@@ -2752,7 +2835,8 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 	if (page_mode) {
 		if (bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU)
 			return -EOPNOTSUPP;
-		bp->dev->max_mtu = BNXT_MAX_PAGE_MODE_MTU;
+		bp->dev->max_mtu =
+			min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU);
 		bp->flags &= ~BNXT_FLAG_AGG_RINGS;
 		bp->flags |= BNXT_FLAG_NO_AGG_RINGS | BNXT_FLAG_RX_PAGE_MODE;
 		bp->dev->hw_features &= ~NETIF_F_LRO;
@@ -2760,7 +2844,7 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 		bp->rx_dir = DMA_BIDIRECTIONAL;
 		bp->rx_skb_func = bnxt_rx_page_skb;
 	} else {
-		bp->dev->max_mtu = BNXT_MAX_MTU;
+		bp->dev->max_mtu = bp->max_mtu;
 		bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE;
 		bp->rx_dir = DMA_FROM_DEVICE;
 		bp->rx_skb_func = bnxt_rx_skb;
@@ -3391,6 +3475,12 @@ int _hwrm_send_message(struct bnxt *bp, void *msg, u32 msg_len, int timeout)
 	return bnxt_hwrm_do_send_msg(bp, msg, msg_len, timeout, false);
 }
 
+int _hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 msg_len,
+			      int timeout)
+{
+	return bnxt_hwrm_do_send_msg(bp, msg, msg_len, timeout, true);
+}
+
 int hwrm_send_message(struct bnxt *bp, void *msg, u32 msg_len, int timeout)
 {
 	int rc;
@@ -4420,22 +4510,73 @@ static int bnxt_hwrm_reserve_tx_rings(struct bnxt *bp, int *tx_rings)
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = __bnxt_hwrm_get_tx_rings(bp, 0xffff, tx_rings);
 	mutex_unlock(&bp->hwrm_cmd_lock);
+	if (!rc)
+		bp->tx_reserved_rings = *tx_rings;
 	return rc;
 }
 
-static void bnxt_hwrm_set_coal_params(struct bnxt *bp, u32 max_bufs,
-	u32 buf_tmrs, u16 flags,
+static int bnxt_hwrm_check_tx_rings(struct bnxt *bp, int tx_rings)
+{
+	struct hwrm_func_cfg_input req = {0};
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10801)
+		return 0;
+
+	if (BNXT_VF(bp))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
+	req.fid = cpu_to_le16(0xffff);
+	req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST);
+	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS);
+	req.num_tx_rings = cpu_to_le16(tx_rings);
+	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		return -ENOMEM;
+	return 0;
+}
+
+static void bnxt_hwrm_set_coal_params(struct bnxt_coal *hw_coal,
 	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req)
 {
+	u16 val, tmr, max, flags;
+
+	max = hw_coal->bufs_per_record * 128;
+	if (hw_coal->budget)
+		max = hw_coal->bufs_per_record * hw_coal->budget;
+
+	val = clamp_t(u16, hw_coal->coal_bufs, 1, max);
+	req->num_cmpl_aggr_int = cpu_to_le16(val);
+
+	/* This is a 6-bit value and must not be 0, or we'll get non stop IRQ */
+	val = min_t(u16, val, 63);
+	req->num_cmpl_dma_aggr = cpu_to_le16(val);
+
+	/* This is a 6-bit value and must not be 0, or we'll get non stop IRQ */
+	val = clamp_t(u16, hw_coal->coal_bufs_irq, 1, 63);
+	req->num_cmpl_dma_aggr_during_int = cpu_to_le16(val);
+
+	tmr = BNXT_USEC_TO_COAL_TIMER(hw_coal->coal_ticks);
+	tmr = max_t(u16, tmr, 1);
+	req->int_lat_tmr_max = cpu_to_le16(tmr);
+
+	/* min timer set to 1/2 of interrupt timer */
+	val = tmr / 2;
+	req->int_lat_tmr_min = cpu_to_le16(val);
+
+	/* buf timer set to 1/4 of interrupt timer */
+	val = max_t(u16, tmr / 4, 1);
+	req->cmpl_aggr_dma_tmr = cpu_to_le16(val);
+
+	tmr = BNXT_USEC_TO_COAL_TIMER(hw_coal->coal_ticks_irq);
+	tmr = max_t(u16, tmr, 1);
+	req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(tmr);
+
+	flags = RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET;
+	if (hw_coal->idle_thresh && hw_coal->coal_ticks < hw_coal->idle_thresh)
+		flags |= RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE;
 	req->flags = cpu_to_le16(flags);
-	req->num_cmpl_dma_aggr = cpu_to_le16((u16)max_bufs);
-	req->num_cmpl_dma_aggr_during_int = cpu_to_le16(max_bufs >> 16);
-	req->cmpl_aggr_dma_tmr = cpu_to_le16((u16)buf_tmrs);
-	req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(buf_tmrs >> 16);
-	/* Minimum time between 2 interrupts set to buf_tmr x 2 */
-	req->int_lat_tmr_min = cpu_to_le16((u16)buf_tmrs * 2);
-	req->int_lat_tmr_max = cpu_to_le16((u16)buf_tmrs * 4);
-	req->num_cmpl_aggr_int = cpu_to_le16((u16)max_bufs * 4);
 }
 
 int bnxt_hwrm_set_coal(struct bnxt *bp)
@@ -4443,51 +4584,14 @@ int bnxt_hwrm_set_coal(struct bnxt *bp)
 	int i, rc = 0;
 	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input req_rx = {0},
 							   req_tx = {0}, *req;
-	u16 max_buf, max_buf_irq;
-	u16 buf_tmr, buf_tmr_irq;
-	u32 flags;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req_rx,
 			       HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS, -1, -1);
 	bnxt_hwrm_cmd_hdr_init(bp, &req_tx,
 			       HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS, -1, -1);
 
-	/* Each rx completion (2 records) should be DMAed immediately.
-	 * DMA 1/4 of the completion buffers at a time.
-	 */
-	max_buf = min_t(u16, bp->rx_coal_bufs / 4, 2);
-	/* max_buf must not be zero */
-	max_buf = clamp_t(u16, max_buf, 1, 63);
-	max_buf_irq = clamp_t(u16, bp->rx_coal_bufs_irq, 1, 63);
-	buf_tmr = BNXT_USEC_TO_COAL_TIMER(bp->rx_coal_ticks);
-	/* buf timer set to 1/4 of interrupt timer */
-	buf_tmr = max_t(u16, buf_tmr / 4, 1);
-	buf_tmr_irq = BNXT_USEC_TO_COAL_TIMER(bp->rx_coal_ticks_irq);
-	buf_tmr_irq = max_t(u16, buf_tmr_irq, 1);
-
-	flags = RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET;
-
-	/* RING_IDLE generates more IRQs for lower latency.  Enable it only
-	 * if coal_ticks is less than 25 us.
-	 */
-	if (bp->rx_coal_ticks < 25)
-		flags |= RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE;
-
-	bnxt_hwrm_set_coal_params(bp, max_buf_irq << 16 | max_buf,
-				  buf_tmr_irq << 16 | buf_tmr, flags, &req_rx);
-
-	/* max_buf must not be zero */
-	max_buf = clamp_t(u16, bp->tx_coal_bufs, 1, 63);
-	max_buf_irq = clamp_t(u16, bp->tx_coal_bufs_irq, 1, 63);
-	buf_tmr = BNXT_USEC_TO_COAL_TIMER(bp->tx_coal_ticks);
-	/* buf timer set to 1/4 of interrupt timer */
-	buf_tmr = max_t(u16, buf_tmr / 4, 1);
-	buf_tmr_irq = BNXT_USEC_TO_COAL_TIMER(bp->tx_coal_ticks_irq);
-	buf_tmr_irq = max_t(u16, buf_tmr_irq, 1);
-
-	flags = RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET;
-	bnxt_hwrm_set_coal_params(bp, max_buf_irq << 16 | max_buf,
-				  buf_tmr_irq << 16 | buf_tmr, flags, &req_tx);
+	bnxt_hwrm_set_coal_params(&bp->rx_coal, &req_rx);
+	bnxt_hwrm_set_coal_params(&bp->tx_coal, &req_tx);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
@@ -4577,6 +4681,7 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 {
 	struct hwrm_func_qcfg_input req = {0};
 	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	u16 flags;
 	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
@@ -4593,15 +4698,15 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 		vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK;
 	}
 #endif
-	if (BNXT_PF(bp)) {
-		u16 flags = le16_to_cpu(resp->flags);
-
-		if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED |
-			     FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED))
-			bp->flags |= BNXT_FLAG_FW_LLDP_AGENT;
-		if (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST)
-			bp->flags |= BNXT_FLAG_MULTI_HOST;
+	flags = le16_to_cpu(resp->flags);
+	if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED |
+		     FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED)) {
+		bp->flags |= BNXT_FLAG_FW_LLDP_AGENT;
+		if (flags & FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED)
+			bp->flags |= BNXT_FLAG_FW_DCBX_AGENT;
 	}
+	if (BNXT_PF(bp) && (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST))
+		bp->flags |= BNXT_FLAG_MULTI_HOST;
 
 	switch (resp->port_partition_type) {
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:
@@ -4610,6 +4715,17 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 		bp->port_partition_type = resp->port_partition_type;
 		break;
 	}
+	if (bp->hwrm_spec_code < 0x10707 ||
+	    resp->evb_mode == FUNC_QCFG_RESP_EVB_MODE_VEB)
+		bp->br_mode = BRIDGE_MODE_VEB;
+	else if (resp->evb_mode == FUNC_QCFG_RESP_EVB_MODE_VEPA)
+		bp->br_mode = BRIDGE_MODE_VEPA;
+	else
+		bp->br_mode = BRIDGE_MODE_UNDEF;
+
+	bp->max_mtu = le16_to_cpu(resp->max_mtu_configured);
+	if (!bp->max_mtu)
+		bp->max_mtu = BNXT_MAX_MTU;
 
 func_qcfg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
@@ -4647,7 +4763,6 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		pf->port_id = le16_to_cpu(resp->port_id);
 		bp->dev->dev_port = pf->port_id;
 		memcpy(pf->mac_addr, resp->mac_address, ETH_ALEN);
-		memcpy(bp->dev->dev_addr, pf->mac_addr, ETH_ALEN);
 		pf->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
 		pf->max_cp_rings = le16_to_cpu(resp->max_cmpl_rings);
 		pf->max_tx_rings = le16_to_cpu(resp->max_tx_rings);
@@ -4687,16 +4802,6 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		vf->max_stat_ctxs = le16_to_cpu(resp->max_stat_ctx);
 
 		memcpy(vf->mac_addr, resp->mac_address, ETH_ALEN);
-		mutex_unlock(&bp->hwrm_cmd_lock);
-
-		if (is_valid_ether_addr(vf->mac_addr)) {
-			/* overwrite netdev dev_adr with admin VF MAC */
-			memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN);
-		} else {
-			eth_hw_addr_random(bp->dev);
-			rc = bnxt_approve_mac(bp, bp->dev->dev_addr);
-		}
-		return rc;
 #endif
 	}
 
@@ -4782,9 +4887,9 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 			    resp->hwrm_intf_upd);
 		netdev_warn(bp->dev, "Please update firmware with HWRM interface 1.0.0 or newer.\n");
 	}
-	snprintf(bp->fw_ver_str, BC_HWRM_STR_LEN, "%d.%d.%d/%d.%d.%d",
+	snprintf(bp->fw_ver_str, BC_HWRM_STR_LEN, "%d.%d.%d.%d",
 		 resp->hwrm_fw_maj, resp->hwrm_fw_min, resp->hwrm_fw_bld,
-		 resp->hwrm_intf_maj, resp->hwrm_intf_min, resp->hwrm_intf_upd);
+		 resp->hwrm_fw_rsvd);
 
 	bp->hwrm_cmd_timeout = le16_to_cpu(resp->def_req_timeout);
 	if (!bp->hwrm_cmd_timeout)
@@ -4810,16 +4915,14 @@ hwrm_ver_get_exit:
 
 int bnxt_hwrm_fw_set_time(struct bnxt *bp)
 {
-#if IS_ENABLED(CONFIG_RTC_LIB)
 	struct hwrm_fw_set_time_input req = {0};
-	struct rtc_time tm;
-	struct timeval tv;
+	struct tm tm;
+	time64_t now = ktime_get_real_seconds();
 
 	if (bp->hwrm_spec_code < 0x10400)
 		return -EOPNOTSUPP;
 
-	do_gettimeofday(&tv);
-	rtc_time_to_tm(tv.tv_sec, &tm);
+	time64_to_tm(now, 0, &tm);
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_SET_TIME, -1, -1);
 	req.year = cpu_to_le16(1900 + tm.tm_year);
 	req.month = 1 + tm.tm_mon;
@@ -4828,9 +4931,6 @@ int bnxt_hwrm_fw_set_time(struct bnxt *bp)
 	req.minute = tm.tm_min;
 	req.second = tm.tm_sec;
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
 static int bnxt_hwrm_port_qstats(struct bnxt *bp)
@@ -4911,6 +5011,26 @@ static void bnxt_hwrm_resource_free(struct bnxt *bp, bool close_path,
 	}
 }
 
+static int bnxt_hwrm_set_br_mode(struct bnxt *bp, u16 br_mode)
+{
+	struct hwrm_func_cfg_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
+	req.fid = cpu_to_le16(0xffff);
+	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_EVB_MODE);
+	if (br_mode == BRIDGE_MODE_VEB)
+		req.evb_mode = FUNC_CFG_REQ_EVB_MODE_VEB;
+	else if (br_mode == BRIDGE_MODE_VEPA)
+		req.evb_mode = FUNC_CFG_REQ_EVB_MODE_VEPA;
+	else
+		return -EINVAL;
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		rc = -EIO;
+	return rc;
+}
+
 static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 {
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
@@ -5046,6 +5166,15 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 				   rc);
 			goto err_out;
 		}
+		if (bp->tx_reserved_rings != bp->tx_nr_rings) {
+			int tx = bp->tx_nr_rings;
+
+			if (bnxt_hwrm_reserve_tx_rings(bp, &tx) ||
+			    tx < bp->tx_nr_rings) {
+				rc = -ENOMEM;
+				goto err_out;
+			}
+		}
 	}
 
 	rc = bnxt_hwrm_ring_alloc(bp);
@@ -5452,8 +5581,15 @@ static void bnxt_free_irq(struct bnxt *bp)
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		irq = &bp->irq_tbl[i];
-		if (irq->requested)
+		if (irq->requested) {
+			if (irq->have_cpumask) {
+				irq_set_affinity_hint(irq->vector, NULL);
+				free_cpumask_var(irq->cpu_mask);
+				irq->have_cpumask = 0;
+			}
 			free_irq(irq->vector, bp->bnapi[i]);
+		}
+
 		irq->requested = 0;
 	}
 }
@@ -5486,6 +5622,21 @@ static int bnxt_request_irq(struct bnxt *bp)
 			break;
 
 		irq->requested = 1;
+
+		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
+			int numa_node = dev_to_node(&bp->pdev->dev);
+
+			irq->have_cpumask = 1;
+			cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+					irq->cpu_mask);
+			rc = irq_set_affinity_hint(irq->vector, irq->cpu_mask);
+			if (rc) {
+				netdev_warn(bp->dev,
+					    "Set affinity failed, IRQ = %d\n",
+					    irq->vector);
+				break;
+			}
+		}
 	}
 	return rc;
 }
@@ -5559,12 +5710,10 @@ void bnxt_tx_disable(struct bnxt *bp)
 {
 	int i;
 	struct bnxt_tx_ring_info *txr;
-	struct netdev_queue *txq;
 
 	if (bp->tx_ring) {
 		for (i = 0; i < bp->tx_nr_rings; i++) {
 			txr = &bp->tx_ring[i];
-			txq = netdev_get_tx_queue(bp->dev, i);
 			txr->dev_state = BNXT_DEV_STATE_CLOSING;
 		}
 	}
@@ -5577,11 +5726,9 @@ void bnxt_tx_enable(struct bnxt *bp)
 {
 	int i;
 	struct bnxt_tx_ring_info *txr;
-	struct netdev_queue *txq;
 
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		txr = &bp->tx_ring[i];
-		txq = netdev_get_tx_queue(bp->dev, i);
 		txr->dev_state = 0;
 	}
 	netif_tx_wake_all_queues(bp->dev);
@@ -5646,7 +5793,7 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 	if (rc)
 		goto hwrm_phy_qcaps_exit;
 
-	if (resp->eee_supported & PORT_PHY_QCAPS_RESP_EEE_SUPPORTED) {
+	if (resp->flags & PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED) {
 		struct ethtool_eee *eee = &bp->eee;
 		u16 fw_speeds = le16_to_cpu(resp->supported_speeds_eee_mode);
 
@@ -5661,6 +5808,8 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 		link_info->support_auto_speeds =
 			le16_to_cpu(resp->supported_speeds_auto_mode);
 
+	bp->port_count = resp->port_cnt;
+
 hwrm_phy_qcaps_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -5686,13 +5835,15 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 
 	memcpy(&link_info->phy_qcfg_resp, resp, sizeof(*resp));
 	link_info->phy_link_status = resp->link;
-	link_info->duplex =  resp->duplex;
+	link_info->duplex = resp->duplex_cfg;
+	if (bp->hwrm_spec_code >= 0x10800)
+		link_info->duplex = resp->duplex_state;
 	link_info->pause = resp->pause;
 	link_info->auto_mode = resp->auto_mode;
 	link_info->auto_pause_setting = resp->auto_pause;
 	link_info->lp_pause = resp->link_partner_adv_pause;
 	link_info->force_pause_setting = resp->force_pause;
-	link_info->duplex_setting = resp->duplex;
+	link_info->duplex_setting = resp->duplex_cfg;
 	if (link_info->phy_link_status == BNXT_LINK_LINK)
 		link_info->link_speed = le16_to_cpu(resp->link_speed);
 	else
@@ -6198,7 +6349,9 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	}
 
 	if (link_re_init) {
+		mutex_lock(&bp->link_lock);
 		rc = bnxt_update_phy_setting(bp);
+		mutex_unlock(&bp->link_lock);
 		if (rc)
 			netdev_warn(bp->dev, "failed to update phy settings\n");
 	}
@@ -6214,6 +6367,9 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	/* Poll link status and check for SFP+ module status */
 	bnxt_get_port_module_status(bp);
 
+	/* VF-reps may need to be re-opened after the PF is re-opened */
+	if (BNXT_PF(bp))
+		bnxt_vf_reps_open(bp);
 	return 0;
 
 open_err:
@@ -6302,6 +6458,10 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		if (rc)
 			netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete!\n");
 	}
+
+	/* Close the VF-reps before closing PF */
+	if (BNXT_PF(bp))
+		bnxt_vf_reps_close(bp);
 #endif
 	/* Change device state to avoid TX queue wake up's */
 	bnxt_tx_disable(bp);
@@ -6511,7 +6671,7 @@ static void bnxt_set_rx_mode(struct net_device *dev)
 		vnic->rx_mask = mask;
 
 		set_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 	}
 }
 
@@ -6784,7 +6944,7 @@ static void bnxt_tx_timeout(struct net_device *dev)
 
 	netdev_err(bp->dev,  "TX timeout detected, starting reset task!\n");
 	set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -6802,9 +6962,9 @@ static void bnxt_poll_controller(struct net_device *dev)
 }
 #endif
 
-static void bnxt_timer(unsigned long data)
+static void bnxt_timer(struct timer_list *t)
 {
-	struct bnxt *bp = (struct bnxt *)data;
+	struct bnxt *bp = from_timer(bp, t, timer);
 	struct net_device *dev = bp->dev;
 
 	if (!netif_running(dev))
@@ -6813,9 +6973,15 @@ static void bnxt_timer(unsigned long data)
 	if (atomic_read(&bp->intr_sem) != 0)
 		goto bnxt_restart_timer;
 
-	if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS)) {
+	if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS) &&
+	    bp->stats_coal_ticks) {
 		set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
+	}
+
+	if (bnxt_tc_flower_enabled(bp)) {
+		set_bit(BNXT_FLOW_STATS_SP_EVENT, &bp->sp_event);
+		bnxt_queue_sp_work(bp);
 	}
 bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
@@ -6888,30 +7054,32 @@ static void bnxt_sp_task(struct work_struct *work)
 	if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
 		bnxt_hwrm_port_qstats(bp);
 
-	/* These functions below will clear BNXT_STATE_IN_SP_TASK.  They
-	 * must be the last functions to be called before exiting.
-	 */
 	if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
-		int rc = 0;
+		int rc;
 
+		mutex_lock(&bp->link_lock);
 		if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT,
 				       &bp->sp_event))
 			bnxt_hwrm_phy_qcaps(bp);
 
-		bnxt_rtnl_lock_sp(bp);
-		if (test_bit(BNXT_STATE_OPEN, &bp->state))
-			rc = bnxt_update_link(bp, true);
-		bnxt_rtnl_unlock_sp(bp);
+		rc = bnxt_update_link(bp, true);
+		mutex_unlock(&bp->link_lock);
 		if (rc)
 			netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
 				   rc);
 	}
 	if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) {
-		bnxt_rtnl_lock_sp(bp);
-		if (test_bit(BNXT_STATE_OPEN, &bp->state))
-			bnxt_get_port_module_status(bp);
-		bnxt_rtnl_unlock_sp(bp);
+		mutex_lock(&bp->link_lock);
+		bnxt_get_port_module_status(bp);
+		mutex_unlock(&bp->link_lock);
 	}
+
+	if (test_and_clear_bit(BNXT_FLOW_STATS_SP_EVENT, &bp->sp_event))
+		bnxt_tc_flow_stats_work(bp);
+
+	/* These functions below will clear BNXT_STATE_IN_SP_TASK.  They
+	 * must be the last functions to be called before exiting.
+	 */
 	if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event))
 		bnxt_reset(bp, false);
 
@@ -6923,8 +7091,8 @@ static void bnxt_sp_task(struct work_struct *work)
 }
 
 /* Under rtnl_lock */
-int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
-		       int tx_xdp)
+int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
+		     int tx_xdp)
 {
 	int max_rx, max_tx, tx_sets = 1;
 	int tx_rings_needed;
@@ -6944,10 +7112,7 @@ int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 	if (max_tx < tx_rings_needed)
 		return -ENOMEM;
 
-	if (bnxt_hwrm_reserve_tx_rings(bp, &tx_rings_needed) ||
-	    tx_rings_needed < (tx * tx_sets + tx_xdp))
-		return -ENOMEM;
-	return 0;
+	return bnxt_hwrm_check_tx_rings(bp, tx_rings_needed);
 }
 
 static void bnxt_unmap_bars(struct bnxt *bp, struct pci_dev *pdev)
@@ -6975,6 +7140,32 @@ static void bnxt_cleanup_pci(struct bnxt *bp)
 	pci_disable_device(bp->pdev);
 }
 
+static void bnxt_init_dflt_coal(struct bnxt *bp)
+{
+	struct bnxt_coal *coal;
+
+	/* Tick values in micro seconds.
+	 * 1 coal_buf x bufs_per_record = 1 completion record.
+	 */
+	coal = &bp->rx_coal;
+	coal->coal_ticks = 14;
+	coal->coal_bufs = 30;
+	coal->coal_ticks_irq = 1;
+	coal->coal_bufs_irq = 2;
+	coal->idle_thresh = 25;
+	coal->bufs_per_record = 2;
+	coal->budget = 64;		/* NAPI budget */
+
+	coal = &bp->tx_coal;
+	coal->coal_ticks = 28;
+	coal->coal_bufs = 30;
+	coal->coal_ticks_irq = 2;
+	coal->coal_bufs_irq = 2;
+	coal->bufs_per_record = 1;
+
+	bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS;
+}
+
 static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 {
 	int rc;
@@ -7043,22 +7234,9 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 	bp->rx_ring_size = BNXT_DEFAULT_RX_RING_SIZE;
 	bp->tx_ring_size = BNXT_DEFAULT_TX_RING_SIZE;
 
-	/* tick values in micro seconds */
-	bp->rx_coal_ticks = 12;
-	bp->rx_coal_bufs = 30;
-	bp->rx_coal_ticks_irq = 1;
-	bp->rx_coal_bufs_irq = 2;
+	bnxt_init_dflt_coal(bp);
 
-	bp->tx_coal_ticks = 25;
-	bp->tx_coal_bufs = 30;
-	bp->tx_coal_ticks_irq = 2;
-	bp->tx_coal_bufs_irq = 2;
-
-	bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS;
-
-	init_timer(&bp->timer);
-	bp->timer.data = (unsigned long)bp;
-	bp->timer.function = bnxt_timer;
+	timer_setup(&bp->timer, bnxt_timer, 0);
 	bp->current_interval = BNXT_TIMER_INTERVAL;
 
 	clear_bit(BNXT_STATE_OPEN, &bp->state);
@@ -7085,13 +7263,13 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
+	if (ether_addr_equal(addr->sa_data, dev->dev_addr))
+		return 0;
+
 	rc = bnxt_approve_mac(bp, addr->sa_data);
 	if (rc)
 		return rc;
 
-	if (ether_addr_equal(addr->sa_data, dev->dev_addr))
-		return 0;
-
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
 	if (netif_running(dev)) {
 		bnxt_close_nic(bp, false, false);
@@ -7136,8 +7314,8 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
 		sh = true;
 
-	rc = bnxt_reserve_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
-				sh, tc, bp->tx_nr_rings_xdp);
+	rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
+			      sh, tc, bp->tx_nr_rings_xdp);
 	if (rc)
 		return rc;
 
@@ -7152,6 +7330,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
 		netdev_reset_tc(dev);
 	}
+	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
 	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
 			       bp->tx_nr_rings + bp->rx_nr_rings;
 	bp->num_stat_ctxs = bp->cp_nr_rings;
@@ -7162,15 +7341,58 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	return 0;
 }
 
-static int bnxt_setup_tc(struct net_device *dev, u32 handle, u32 chain_index,
-			 __be16 proto, struct tc_to_netdev *ntc)
+static int bnxt_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				  void *cb_priv)
 {
-	if (ntc->type != TC_SETUP_MQPRIO)
-		return -EINVAL;
+	struct bnxt *bp = cb_priv;
+
+	if (!bnxt_tc_flower_enabled(bp) || !tc_can_offload(bp->dev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return bnxt_tc_setup_flower(bp, bp->pf.fw_fid, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int bnxt_setup_tc_block(struct net_device *dev,
+			       struct tc_block_offload *f)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb,
+					     bp, bp);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			 void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return bnxt_setup_tc_block(dev, type_data);
+	case TC_SETUP_QDISC_MQPRIO: {
+		struct tc_mqprio_qopt *mqprio = type_data;
 
-	ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+		mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
-	return bnxt_setup_mq_tc(dev, ntc->mqprio->num_tc);
+		return bnxt_setup_mq_tc(dev, mqprio->num_tc);
+	}
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 #ifdef CONFIG_RFS_ACCEL
@@ -7280,7 +7502,7 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	spin_unlock_bh(&bp->ntp_fltr_lock);
 
 	set_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event);
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 
 	return new_fltr->sw_id;
 
@@ -7363,7 +7585,7 @@ static void bnxt_udp_tunnel_add(struct net_device *dev,
 		if (bp->vxlan_port_cnt == 1) {
 			bp->vxlan_port = ti->port;
 			set_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event);
-			schedule_work(&bp->sp_task);
+			bnxt_queue_sp_work(bp);
 		}
 		break;
 	case UDP_TUNNEL_TYPE_GENEVE:
@@ -7380,7 +7602,7 @@ static void bnxt_udp_tunnel_add(struct net_device *dev,
 		return;
 	}
 
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 }
 
 static void bnxt_udp_tunnel_del(struct net_device *dev,
@@ -7419,9 +7641,105 @@ static void bnxt_udp_tunnel_del(struct net_device *dev,
 		return;
 	}
 
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
+}
+
+static int bnxt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+			       struct net_device *dev, u32 filter_mask,
+			       int nlflags)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, bp->br_mode, 0, 0,
+				       nlflags, filter_mask, NULL);
+}
+
+static int bnxt_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
+			       u16 flags)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	struct nlattr *attr, *br_spec;
+	int rem, rc = 0;
+
+	if (bp->hwrm_spec_code < 0x10708 || !BNXT_SINGLE_PF(bp))
+		return -EOPNOTSUPP;
+
+	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!br_spec)
+		return -EINVAL;
+
+	nla_for_each_nested(attr, br_spec, rem) {
+		u16 mode;
+
+		if (nla_type(attr) != IFLA_BRIDGE_MODE)
+			continue;
+
+		if (nla_len(attr) < sizeof(mode))
+			return -EINVAL;
+
+		mode = nla_get_u16(attr);
+		if (mode == bp->br_mode)
+			break;
+
+		rc = bnxt_hwrm_set_br_mode(bp, mode);
+		if (!rc)
+			bp->br_mode = mode;
+		break;
+	}
+	return rc;
+}
+
+static int bnxt_get_phys_port_name(struct net_device *dev, char *buf,
+				   size_t len)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
+	/* The PF and it's VF-reps only support the switchdev framework */
+	if (!BNXT_PF(bp))
+		return -EOPNOTSUPP;
+
+	rc = snprintf(buf, len, "p%d", bp->pf.port_id);
+
+	if (rc >= len)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr)
+{
+	if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		return -EOPNOTSUPP;
+
+	/* The PF and it's VF-reps only support the switchdev framework */
+	if (!BNXT_PF(bp))
+		return -EOPNOTSUPP;
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+		/* In SRIOV each PF-pool (PF + child VFs) serves as a
+		 * switching domain, the PF's perm mac-addr can be used
+		 * as the unique parent-id
+		 */
+		attr->u.ppid.id_len = ETH_ALEN;
+		ether_addr_copy(attr->u.ppid.id, bp->pf.mac_addr);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int bnxt_swdev_port_attr_get(struct net_device *dev,
+				    struct switchdev_attr *attr)
+{
+	return bnxt_port_attr_get(netdev_priv(dev), attr);
 }
 
+static const struct switchdev_ops bnxt_switchdev_ops = {
+	.switchdev_port_attr_get	= bnxt_swdev_port_attr_get
+};
+
 static const struct net_device_ops bnxt_netdev_ops = {
 	.ndo_open		= bnxt_open,
 	.ndo_start_xmit		= bnxt_start_xmit,
@@ -7452,7 +7770,10 @@ static const struct net_device_ops bnxt_netdev_ops = {
 #endif
 	.ndo_udp_tunnel_add	= bnxt_udp_tunnel_add,
 	.ndo_udp_tunnel_del	= bnxt_udp_tunnel_del,
-	.ndo_xdp		= bnxt_xdp,
+	.ndo_bpf		= bnxt_xdp,
+	.ndo_bridge_getlink	= bnxt_bridge_getlink,
+	.ndo_bridge_setlink	= bnxt_bridge_setlink,
+	.ndo_get_phys_port_name = bnxt_get_phys_port_name
 };
 
 static void bnxt_remove_one(struct pci_dev *pdev)
@@ -7460,12 +7781,15 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (BNXT_PF(bp))
+	if (BNXT_PF(bp)) {
 		bnxt_sriov_disable(bp);
+		bnxt_dl_unregister(bp);
+	}
 
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
-	cancel_work_sync(&bp->sp_task);
+	bnxt_shutdown_tc(bp);
+	bnxt_cancel_sp_work(bp);
 	bp->sp_event = 0;
 
 	bnxt_clear_int_mode(bp);
@@ -7493,6 +7817,7 @@ static int bnxt_probe_phy(struct bnxt *bp)
 			   rc);
 		return rc;
 	}
+	mutex_init(&bp->link_lock);
 
 	rc = bnxt_update_link(bp, false);
 	if (rc) {
@@ -7633,6 +7958,9 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 	if (sh)
 		bp->flags |= BNXT_FLAG_SHARED_RINGS;
 	dflt_rings = netif_get_num_default_rss_queues();
+	/* Reduce default rings to reduce memory usage on multi-port cards */
+	if (bp->port_count > 1)
+		dflt_rings = min_t(int, dflt_rings, 4);
 	rc = bnxt_get_dflt_rings(bp, &max_rx_rings, &max_tx_rings, sh);
 	if (rc)
 		return rc;
@@ -7661,12 +7989,34 @@ void bnxt_restore_pf_fw_resources(struct bnxt *bp)
 	bnxt_subtract_ulp_resources(bp, BNXT_ROCE_ULP);
 }
 
+static int bnxt_init_mac_addr(struct bnxt *bp)
+{
+	int rc = 0;
+
+	if (BNXT_PF(bp)) {
+		memcpy(bp->dev->dev_addr, bp->pf.mac_addr, ETH_ALEN);
+	} else {
+#ifdef CONFIG_BNXT_SRIOV
+		struct bnxt_vf_info *vf = &bp->vf;
+
+		if (is_valid_ether_addr(vf->mac_addr)) {
+			/* overwrite netdev dev_adr with admin VF MAC */
+			memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN);
+		} else {
+			eth_hw_addr_random(bp->dev);
+			rc = bnxt_approve_mac(bp, bp->dev->dev_addr);
+		}
+#endif
+	}
+	return rc;
+}
+
 static void bnxt_parse_log_pcie_link(struct bnxt *bp)
 {
 	enum pcie_link_width width = PCIE_LNK_WIDTH_UNKNOWN;
 	enum pci_bus_speed speed = PCI_SPEED_UNKNOWN;
 
-	if (pcie_get_minimum_link(bp->pdev, &speed, &width) ||
+	if (pcie_get_minimum_link(pci_physfn(bp->pdev), &speed, &width) ||
 	    speed == PCI_SPEED_UNKNOWN || width == PCIE_LNK_WIDTH_UNKNOWN)
 		netdev_info(bp->dev, "Failed to determine PCIe Link Info\n");
 	else
@@ -7710,6 +8060,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->netdev_ops = &bnxt_netdev_ops;
 	dev->watchdog_timeo = BNXT_TX_TIMEOUT;
 	dev->ethtool_ops = &bnxt_ethtool_ops;
+	SWITCHDEV_SET_OPS(dev, &bnxt_switchdev_ops);
 	pci_set_drvdata(pdev, dev);
 
 	rc = bnxt_alloc_hwrm_resources(bp);
@@ -7758,12 +8109,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->features |= dev->hw_features | NETIF_F_HIGHDMA;
 	dev->priv_flags |= IFF_UNICAST_FLT;
 
-	/* MTU range: 60 - 9500 */
-	dev->min_mtu = ETH_ZLEN;
-	dev->max_mtu = BNXT_MAX_MTU;
-
 #ifdef CONFIG_BNXT_SRIOV
 	init_waitqueue_head(&bp->sriov_cfg_wait);
+	mutex_init(&bp->sriov_lock);
 #endif
 	bp->gro_func = bnxt_gro_func_5730x;
 	if (BNXT_CHIP_P4_PLUS(bp))
@@ -7789,7 +8137,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		rc = -1;
 		goto init_err_pci_clean;
 	}
-
+	rc = bnxt_init_mac_addr(bp);
+	if (rc) {
+		dev_err(&pdev->dev, "Unable to initialize mac address.\n");
+		rc = -EADDRNOTAVAIL;
+		goto init_err_pci_clean;
+	}
 	rc = bnxt_hwrm_queue_qportcfg(bp);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm query qportcfg failure rc: %x\n",
@@ -7803,6 +8156,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_ethtool_init(bp);
 	bnxt_dcb_init(bp);
 
+	/* MTU range: 60 - FW defined max */
+	dev->min_mtu = ETH_ZLEN;
+	dev->max_mtu = bp->max_mtu;
+
+	rc = bnxt_probe_phy(bp);
+	if (rc)
+		goto init_err_pci_clean;
+
 	bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
@@ -7837,10 +8198,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (dev->hw_features & NETIF_F_HW_VLAN_CTAG_RX)
 		bp->flags |= BNXT_FLAG_STRIP_VLAN;
 
-	rc = bnxt_probe_phy(bp);
-	if (rc)
-		goto init_err_pci_clean;
-
 	rc = bnxt_init_int_mode(bp);
 	if (rc)
 		goto init_err_pci_clean;
@@ -7851,9 +8208,24 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	else
 		device_set_wakeup_capable(&pdev->dev, false);
 
+	if (BNXT_PF(bp)) {
+		if (!bnxt_pf_wq) {
+			bnxt_pf_wq =
+				create_singlethread_workqueue("bnxt_pf_wq");
+			if (!bnxt_pf_wq) {
+				dev_err(&pdev->dev, "Unable to create workqueue.\n");
+				goto init_err_pci_clean;
+			}
+		}
+		bnxt_init_tc(bp);
+	}
+
 	rc = register_netdev(dev);
 	if (rc)
-		goto init_err_clr_int;
+		goto init_err_cleanup_tc;
+
+	if (BNXT_PF(bp))
+		bnxt_dl_register(bp);
 
 	netdev_info(dev, "%s found at mem %lx, node addr %pM\n",
 		    board_info[ent->driver_data].name,
@@ -7863,7 +8235,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
-init_err_clr_int:
+init_err_cleanup_tc:
+	bnxt_shutdown_tc(bp);
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
@@ -8081,4 +8454,17 @@ static struct pci_driver bnxt_pci_driver = {
 #endif
 };
 
-module_pci_driver(bnxt_pci_driver);
+static int __init bnxt_init(void)
+{
+	return pci_register_driver(&bnxt_pci_driver);
+}
+
+static void __exit bnxt_exit(void)
+{
+	pci_unregister_driver(&bnxt_pci_driver);
+	if (bnxt_pf_wq)
+		destroy_workqueue(bnxt_pf_wq);
+}
+
+module_init(bnxt_init);
+module_exit(bnxt_exit);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index f34691f85602..5359a1f0045f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -12,13 +12,17 @@
 #define BNXT_H
 
 #define DRV_MODULE_NAME		"bnxt_en"
-#define DRV_MODULE_VERSION	"1.7.0"
+#define DRV_MODULE_VERSION	"1.8.0"
 
 #define DRV_VER_MAJ	1
-#define DRV_VER_MIN	7
+#define DRV_VER_MIN	8
 #define DRV_VER_UPD	0
 
 #include <linux/interrupt.h>
+#include <linux/rhashtable.h>
+#include <net/devlink.h>
+#include <net/dst_metadata.h>
+#include <net/switchdev.h>
 
 struct tx_bd {
 	__le32 tx_bd_len_flags_type;
@@ -242,6 +246,10 @@ struct rx_cmp_ext {
 	    ((le32_to_cpu((rxcmp1)->rx_cmp_flags2) &			\
 	     RX_CMP_FLAGS2_T_L4_CS_CALC) >> 3)
 
+#define RX_CMP_CFA_CODE(rxcmpl1)					\
+	((le32_to_cpu((rxcmpl1)->rx_cmp_cfa_code_errors_v2) &		\
+	  RX_CMPL_CFA_CODE_MASK) >> RX_CMPL_CFA_CODE_SFT)
+
 struct rx_agg_cmp {
 	__le32 rx_agg_cmp_len_flags_type;
 	#define RX_AGG_CMP_TYPE					(0x3f << 0)
@@ -311,6 +319,10 @@ struct rx_tpa_start_cmp_ext {
 	__le32 rx_tpa_start_cmp_hdr_info;
 };
 
+#define TPA_START_CFA_CODE(rx_tpa_start)				\
+	((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) &	\
+	 RX_TPA_START_CMP_CFA_CODE) >> RX_TPA_START_CMPL_CFA_CODE_SHIFT)
+
 struct rx_tpa_end_cmp {
 	__le32 rx_tpa_end_cmp_len_flags_type;
 	#define RX_TPA_END_CMP_TYPE				(0x3f << 0)
@@ -618,6 +630,8 @@ struct bnxt_tpa_info {
 
 #define BNXT_TPA_OUTER_L3_OFF(hdr_info)	\
 	((hdr_info) & 0x1ff)
+
+	u16			cfa_code; /* cfa_code in TPA start compl */
 };
 
 struct bnxt_rx_ring_info {
@@ -688,8 +702,10 @@ struct bnxt_napi {
 struct bnxt_irq {
 	irq_handler_t	handler;
 	unsigned int	vector;
-	u8		requested;
+	u8		requested:1;
+	u8		have_cpumask:1;
 	char		name[IFNAMSIZ + 2];
+	cpumask_var_t	cpu_mask;
 };
 
 #define HWRM_RING_ALLOC_TX	0x1
@@ -825,8 +841,8 @@ struct bnxt_link_info {
 	u8			loop_back;
 	u8			link_up;
 	u8			duplex;
-#define BNXT_LINK_DUPLEX_HALF	PORT_PHY_QCFG_RESP_DUPLEX_HALF
-#define BNXT_LINK_DUPLEX_FULL	PORT_PHY_QCFG_RESP_DUPLEX_FULL
+#define BNXT_LINK_DUPLEX_HALF	PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF
+#define BNXT_LINK_DUPLEX_FULL	PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL
 	u8			pause;
 #define BNXT_LINK_PAUSE_TX	PORT_PHY_QCFG_RESP_PAUSE_TX
 #define BNXT_LINK_PAUSE_RX	PORT_PHY_QCFG_RESP_PAUSE_RX
@@ -928,6 +944,78 @@ struct bnxt_test_info {
 #define BNXT_CAG_REG_LEGACY_INT_STATUS	0x4014
 #define BNXT_CAG_REG_BASE		0x300000
 
+struct bnxt_coal {
+	u16			coal_ticks;
+	u16			coal_ticks_irq;
+	u16			coal_bufs;
+	u16			coal_bufs_irq;
+			/* RING_IDLE enabled when coal ticks < idle_thresh  */
+	u16			idle_thresh;
+	u8			bufs_per_record;
+	u8			budget;
+};
+
+struct bnxt_tc_flow_stats {
+	u64		packets;
+	u64		bytes;
+};
+
+struct bnxt_tc_info {
+	bool				enabled;
+
+	/* hash table to store TC offloaded flows */
+	struct rhashtable		flow_table;
+	struct rhashtable_params	flow_ht_params;
+
+	/* hash table to store L2 keys of TC flows */
+	struct rhashtable		l2_table;
+	struct rhashtable_params	l2_ht_params;
+	/* hash table to store L2 keys for TC tunnel decap */
+	struct rhashtable		decap_l2_table;
+	struct rhashtable_params	decap_l2_ht_params;
+	/* hash table to store tunnel decap entries */
+	struct rhashtable		decap_table;
+	struct rhashtable_params	decap_ht_params;
+	/* hash table to store tunnel encap entries */
+	struct rhashtable		encap_table;
+	struct rhashtable_params	encap_ht_params;
+
+	/* lock to atomically add/del an l2 node when a flow is
+	 * added or deleted.
+	 */
+	struct mutex			lock;
+
+	/* Fields used for batching stats query */
+	struct rhashtable_iter		iter;
+#define BNXT_FLOW_STATS_BATCH_MAX	10
+	struct bnxt_tc_stats_batch {
+		void			  *flow_node;
+		struct bnxt_tc_flow_stats hw_stats;
+	} stats_batch[BNXT_FLOW_STATS_BATCH_MAX];
+
+	/* Stat counter mask (width) */
+	u64				bytes_mask;
+	u64				packets_mask;
+};
+
+struct bnxt_vf_rep_stats {
+	u64			packets;
+	u64			bytes;
+	u64			dropped;
+};
+
+struct bnxt_vf_rep {
+	struct bnxt			*bp;
+	struct net_device		*dev;
+	struct metadata_dst		*dst;
+	u16				vf_idx;
+	u16				tx_cfa_action;
+	u16				rx_cfa_code;
+
+	struct bnxt_vf_rep_stats	rx_stats;
+	struct bnxt_vf_rep_stats	tx_stats;
+};
+
 struct bnxt {
 	void __iomem		*bar0;
 	void __iomem		*bar1;
@@ -957,6 +1045,10 @@ struct bnxt {
 
 #define CHIP_NUM_5745X		0xd730
 
+#define CHIP_NUM_58802		0xd802
+#define CHIP_NUM_58804		0xd804
+#define CHIP_NUM_58808		0xd808
+
 #define BNXT_CHIP_NUM_5730X(chip_num)		\
 	((chip_num) >= CHIP_NUM_57301 &&	\
 	 (chip_num) <= CHIP_NUM_57304)
@@ -988,6 +1080,11 @@ struct bnxt {
 #define BNXT_CHIP_NUM_57X1X(chip_num)		\
 	(BNXT_CHIP_NUM_5731X(chip_num) || BNXT_CHIP_NUM_5741X(chip_num))
 
+#define BNXT_CHIP_NUM_588XX(chip_num)		\
+	((chip_num) == CHIP_NUM_58802 ||	\
+	 (chip_num) == CHIP_NUM_58804 ||        \
+	 (chip_num) == CHIP_NUM_58808)
+
 	struct net_device	*dev;
 	struct pci_dev		*pdev;
 
@@ -1027,6 +1124,7 @@ struct bnxt {
 	#define BNXT_FLAG_MULTI_HOST	0x100000
 	#define BNXT_FLAG_SHORT_CMD	0x200000
 	#define BNXT_FLAG_DOUBLE_DB	0x400000
+	#define BNXT_FLAG_FW_DCBX_AGENT	0x800000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
@@ -1045,6 +1143,7 @@ struct bnxt {
 #define BNXT_CHIP_P4_PLUS(bp)			\
 	(BNXT_CHIP_NUM_57X1X((bp)->chip_num) ||	\
 	 BNXT_CHIP_NUM_5745X((bp)->chip_num) ||	\
+	 BNXT_CHIP_NUM_588XX((bp)->chip_num) ||	\
 	 (BNXT_CHIP_NUM_58700((bp)->chip_num) &&	\
 	  !BNXT_CHIP_TYPE_NITRO_A0(bp)))
 
@@ -1086,6 +1185,7 @@ struct bnxt {
 	int			tx_nr_rings;
 	int			tx_nr_rings_per_tc;
 	int			tx_nr_rings_xdp;
+	int			tx_reserved_rings;
 
 	int			tx_wake_thresh;
 	int			tx_push_thresh;
@@ -1105,6 +1205,7 @@ struct bnxt {
 	int			nr_vnics;
 	u32			rss_hash_cfg;
 
+	u16			max_mtu;
 	u8			max_tc;
 	u8			max_lltc;	/* lossless TCs */
 	struct bnxt_queue_info	q_info[BNXT_MAX_QUEUE];
@@ -1164,15 +1265,11 @@ struct bnxt {
 	u8			nge_port_cnt;
 	__le16			nge_fw_dst_port_id;
 	u8			port_partition_type;
+	u8			port_count;
+	u16			br_mode;
 
-	u16			rx_coal_ticks;
-	u16			rx_coal_ticks_irq;
-	u16			rx_coal_bufs;
-	u16			rx_coal_bufs_irq;
-	u16			tx_coal_ticks;
-	u16			tx_coal_ticks_irq;
-	u16			tx_coal_bufs;
-	u16			tx_coal_bufs_irq;
+	struct bnxt_coal	rx_coal;
+	struct bnxt_coal	tx_coal;
 
 #define BNXT_USEC_TO_COAL_TIMER(x)	((x) * 25 / 2)
 
@@ -1198,6 +1295,7 @@ struct bnxt {
 #define BNXT_GENEVE_ADD_PORT_SP_EVENT	12
 #define BNXT_GENEVE_DEL_PORT_SP_EVENT	13
 #define BNXT_LINK_SPEED_CHNG_SP_EVENT	14
+#define BNXT_FLOW_STATS_SP_EVENT	15
 
 	struct bnxt_pf_info	pf;
 #ifdef CONFIG_BNXT_SRIOV
@@ -1206,6 +1304,12 @@ struct bnxt {
 	wait_queue_head_t	sriov_cfg_wait;
 	bool			sriov_cfg;
 #define BNXT_SRIOV_CFG_WAIT_TMO	msecs_to_jiffies(10000)
+
+	/* lock to protect VF-rep creation/cleanup via
+	 * multiple paths such as ->sriov_configure() and
+	 * devlink ->eswitch_mode_set()
+	 */
+	struct mutex		sriov_lock;
 #endif
 
 #define BNXT_NTP_FLTR_MAX_FLTR	4096
@@ -1217,6 +1321,10 @@ struct bnxt {
 	unsigned long		*ntp_fltr_bmap;
 	int			ntp_fltr_count;
 
+	/* To protect link related settings during link changes and
+	 * ethtool settings changes.
+	 */
+	struct mutex		link_lock;
 	struct bnxt_link_info	link_info;
 	struct ethtool_eee	eee;
 	u32			lpi_tmr_lo;
@@ -1232,6 +1340,13 @@ struct bnxt {
 	struct bnxt_led_info	leds[BNXT_MAX_LED];
 
 	struct bpf_prog		*xdp_prog;
+
+	/* devlink interface and vf-rep structs */
+	struct devlink		*dl;
+	enum devlink_eswitch_mode eswitch_mode;
+	struct bnxt_vf_rep	**vf_reps; /* array of vf-rep ptrs */
+	u16			*cfa_code_map; /* cfa_code -> vf_idx map */
+	struct bnxt_tc_info	*tc_info;
 };
 
 #define BNXT_RX_STATS_OFFSET(counter)			\
@@ -1278,6 +1393,7 @@ void bnxt_set_ring_params(struct bnxt *);
 int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 void bnxt_hwrm_cmd_hdr_init(struct bnxt *, void *, u16, u16, u16);
 int _hwrm_send_message(struct bnxt *, void *, u32, int);
+int _hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 len, int timeout);
 int hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
 int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
@@ -1301,9 +1417,10 @@ int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
 int bnxt_close_nic(struct bnxt *, bool, bool);
-int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
-		       int tx_xdp);
+int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
+		     int tx_xdp);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
 int bnxt_get_max_rings(struct bnxt *, int *, int *, bool);
 void bnxt_restore_pf_fw_resources(struct bnxt *bp);
+int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr);
 #endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 5c6dd0ce209f..fed37cd9ae1d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -50,7 +50,9 @@ static int bnxt_hwrm_queue_pri2cos_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PRI2COS_QCFG, -1, -1);
 	req.flags = cpu_to_le32(QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
 		u8 *pri2cos = &resp->pri0_cos_queue_id;
 		int i, j;
@@ -66,6 +68,7 @@ static int bnxt_hwrm_queue_pri2cos_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 			}
 		}
 	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
 
@@ -93,6 +96,12 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets,
 			cos2bw.tsa =
 				QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_ETS;
 			cos2bw.bw_weight = ets->tc_tx_bw[i];
+			/* older firmware requires min_bw to be set to the
+			 * same weight value in percent.
+			 */
+			cos2bw.min_bw =
+				cpu_to_le32((ets->tc_tx_bw[i] * 100) |
+					    BW_VALUE_UNIT_PERCENT1_100);
 		}
 		memcpy(data, &cos2bw.queue_id, sizeof(cos2bw) - 4);
 		if (i == 0) {
@@ -113,9 +122,13 @@ static int bnxt_hwrm_queue_cos2bw_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 	int rc, i;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_COS2BW_QCFG, -1, -1);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc) {
+		mutex_unlock(&bp->hwrm_cmd_lock);
 		return rc;
+	}
 
 	data = &resp->queue_id0 + offsetof(struct bnxt_cos2bw_cfg, queue_id);
 	for (i = 0; i < bp->max_tc; i++, data += sizeof(cos2bw) - 4) {
@@ -137,6 +150,7 @@ static int bnxt_hwrm_queue_cos2bw_qcfg(struct bnxt *bp, struct ieee_ets *ets)
 			}
 		}
 	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
 	return 0;
 }
 
@@ -234,12 +248,17 @@ static int bnxt_hwrm_queue_pfc_qcfg(struct bnxt *bp, struct ieee_pfc *pfc)
 	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PFCENABLE_QCFG, -1, -1);
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc) {
+		mutex_unlock(&bp->hwrm_cmd_lock);
 		return rc;
+	}
 
 	pri_mask = le32_to_cpu(resp->flags);
 	pfc->pfc_en = pri_mask;
+	mutex_unlock(&bp->hwrm_cmd_lock);
 	return 0;
 }
 
@@ -549,13 +568,18 @@ static u8 bnxt_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	/* only support IEEE */
-	if ((mode & DCB_CAP_DCBX_VER_CEE) || !(mode & DCB_CAP_DCBX_VER_IEEE))
+	/* All firmware DCBX settings are set in NVRAM */
+	if (bp->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED)
 		return 1;
 
 	if (mode & DCB_CAP_DCBX_HOST) {
 		if (BNXT_VF(bp) || (bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
 			return 1;
+
+		/* only support IEEE */
+		if ((mode & DCB_CAP_DCBX_VER_CEE) ||
+		    !(mode & DCB_CAP_DCBX_VER_IEEE))
+			return 1;
 	}
 
 	if (mode == bp->dcbx_cap)
@@ -584,7 +608,7 @@ void bnxt_dcb_init(struct bnxt *bp)
 	bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE;
 	if (BNXT_PF(bp) && !(bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
 		bp->dcbx_cap |= DCB_CAP_DCBX_HOST;
-	else
+	else if (bp->flags & BNXT_FLAG_FW_DCBX_AGENT)
 		bp->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED;
 	bp->dev->dcbnl_ops = &dcbnl_ops;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
index ecd0a5e46a49..d2e0af960bf5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
@@ -26,6 +26,7 @@ struct bnxt_cos2bw_cfg {
 	u8			queue_id;
 	__le32			min_bw;
 	__le32			max_bw;
+#define BW_VALUE_UNIT_PERCENT1_100		(0x1UL << 29)
 	u8			tsa;
 	u8			pri_lvl;
 	u8			bw_weight;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
new file mode 100644
index 000000000000..402fa32f7a88
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -0,0 +1,65 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+#include "bnxt_vfr.h"
+#include "bnxt_devlink.h"
+
+static const struct devlink_ops bnxt_dl_ops = {
+#ifdef CONFIG_BNXT_SRIOV
+	.eswitch_mode_set = bnxt_dl_eswitch_mode_set,
+	.eswitch_mode_get = bnxt_dl_eswitch_mode_get,
+#endif /* CONFIG_BNXT_SRIOV */
+};
+
+int bnxt_dl_register(struct bnxt *bp)
+{
+	struct devlink *dl;
+	int rc;
+
+	if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
+		return 0;
+
+	if (bp->hwrm_spec_code < 0x10803) {
+		netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n");
+		return -ENOTSUPP;
+	}
+
+	dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+	if (!dl) {
+		netdev_warn(bp->dev, "devlink_alloc failed");
+		return -ENOMEM;
+	}
+
+	bnxt_link_bp_to_dl(bp, dl);
+	bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+	rc = devlink_register(dl, &bp->pdev->dev);
+	if (rc) {
+		bnxt_link_bp_to_dl(bp, NULL);
+		devlink_free(dl);
+		netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+void bnxt_dl_unregister(struct bnxt *bp)
+{
+	struct devlink *dl = bp->dl;
+
+	if (!dl)
+		return;
+
+	devlink_unregister(dl);
+	devlink_free(dl);
+}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
new file mode 100644
index 000000000000..e92a35d8b642
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -0,0 +1,39 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_DEVLINK_H
+#define BNXT_DEVLINK_H
+
+/* Struct to hold housekeeping info needed by devlink interface */
+struct bnxt_dl {
+	struct bnxt *bp;	/* back ptr to the controlling dev */
+};
+
+static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl)
+{
+	return ((struct bnxt_dl *)devlink_priv(dl))->bp;
+}
+
+/* To clear devlink pointer from bp, pass NULL dl */
+static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
+{
+	bp->dl = dl;
+
+	/* add a back pointer in dl to bp */
+	if (dl) {
+		struct bnxt_dl *bp_dl = devlink_priv(dl);
+
+		bp_dl->bp = bp;
+	}
+}
+
+int bnxt_dl_register(struct bnxt *bp);
+void bnxt_dl_unregister(struct bnxt *bp);
+
+#endif /* BNXT_DEVLINK_H */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index be6acadcb202..7ce1d4b7e67d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -26,8 +26,6 @@
 #define FLASH_PACKAGE_TIMEOUT	((HWRM_CMD_TIMEOUT) * 200)
 #define INSTALL_PACKAGE_TIMEOUT	((HWRM_CMD_TIMEOUT) * 200)
 
-static char *bnxt_get_pkgver(struct net_device *dev, char *buf, size_t buflen);
-
 static u32 bnxt_get_msglevel(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -46,19 +44,24 @@ static int bnxt_get_coalesce(struct net_device *dev,
 			     struct ethtool_coalesce *coal)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_coal *hw_coal;
+	u16 mult;
 
 	memset(coal, 0, sizeof(*coal));
 
-	coal->rx_coalesce_usecs = bp->rx_coal_ticks;
-	/* 2 completion records per rx packet */
-	coal->rx_max_coalesced_frames = bp->rx_coal_bufs / 2;
-	coal->rx_coalesce_usecs_irq = bp->rx_coal_ticks_irq;
-	coal->rx_max_coalesced_frames_irq = bp->rx_coal_bufs_irq / 2;
+	hw_coal = &bp->rx_coal;
+	mult = hw_coal->bufs_per_record;
+	coal->rx_coalesce_usecs = hw_coal->coal_ticks;
+	coal->rx_max_coalesced_frames = hw_coal->coal_bufs / mult;
+	coal->rx_coalesce_usecs_irq = hw_coal->coal_ticks_irq;
+	coal->rx_max_coalesced_frames_irq = hw_coal->coal_bufs_irq / mult;
 
-	coal->tx_coalesce_usecs = bp->tx_coal_ticks;
-	coal->tx_max_coalesced_frames = bp->tx_coal_bufs;
-	coal->tx_coalesce_usecs_irq = bp->tx_coal_ticks_irq;
-	coal->tx_max_coalesced_frames_irq = bp->tx_coal_bufs_irq;
+	hw_coal = &bp->tx_coal;
+	mult = hw_coal->bufs_per_record;
+	coal->tx_coalesce_usecs = hw_coal->coal_ticks;
+	coal->tx_max_coalesced_frames = hw_coal->coal_bufs / mult;
+	coal->tx_coalesce_usecs_irq = hw_coal->coal_ticks_irq;
+	coal->tx_max_coalesced_frames_irq = hw_coal->coal_bufs_irq / mult;
 
 	coal->stats_block_coalesce_usecs = bp->stats_coal_ticks;
 
@@ -70,25 +73,32 @@ static int bnxt_set_coalesce(struct net_device *dev,
 {
 	struct bnxt *bp = netdev_priv(dev);
 	bool update_stats = false;
+	struct bnxt_coal *hw_coal;
 	int rc = 0;
-
-	bp->rx_coal_ticks = coal->rx_coalesce_usecs;
-	/* 2 completion records per rx packet */
-	bp->rx_coal_bufs = coal->rx_max_coalesced_frames * 2;
-	bp->rx_coal_ticks_irq = coal->rx_coalesce_usecs_irq;
-	bp->rx_coal_bufs_irq = coal->rx_max_coalesced_frames_irq * 2;
-
-	bp->tx_coal_ticks = coal->tx_coalesce_usecs;
-	bp->tx_coal_bufs = coal->tx_max_coalesced_frames;
-	bp->tx_coal_ticks_irq = coal->tx_coalesce_usecs_irq;
-	bp->tx_coal_bufs_irq = coal->tx_max_coalesced_frames_irq;
+	u16 mult;
+
+	hw_coal = &bp->rx_coal;
+	mult = hw_coal->bufs_per_record;
+	hw_coal->coal_ticks = coal->rx_coalesce_usecs;
+	hw_coal->coal_bufs = coal->rx_max_coalesced_frames * mult;
+	hw_coal->coal_ticks_irq = coal->rx_coalesce_usecs_irq;
+	hw_coal->coal_bufs_irq = coal->rx_max_coalesced_frames_irq * mult;
+
+	hw_coal = &bp->tx_coal;
+	mult = hw_coal->bufs_per_record;
+	hw_coal->coal_ticks = coal->tx_coalesce_usecs;
+	hw_coal->coal_bufs = coal->tx_max_coalesced_frames * mult;
+	hw_coal->coal_ticks_irq = coal->tx_coalesce_usecs_irq;
+	hw_coal->coal_bufs_irq = coal->tx_max_coalesced_frames_irq * mult;
 
 	if (bp->stats_coal_ticks != coal->stats_block_coalesce_usecs) {
 		u32 stats_ticks = coal->stats_block_coalesce_usecs;
 
-		stats_ticks = clamp_t(u32, stats_ticks,
-				      BNXT_MIN_STATS_COAL_TICKS,
-				      BNXT_MAX_STATS_COAL_TICKS);
+		/* Allow 0, which means disable. */
+		if (stats_ticks)
+			stats_ticks = clamp_t(u32, stats_ticks,
+					      BNXT_MIN_STATS_COAL_TICKS,
+					      BNXT_MAX_STATS_COAL_TICKS);
 		stats_ticks = rounddown(stats_ticks, BNXT_MIN_STATS_COAL_TICKS);
 		bp->stats_coal_ticks = stats_ticks;
 		update_stats = true;
@@ -198,19 +208,23 @@ static const struct {
 
 #define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr)
 
+static int bnxt_get_num_stats(struct bnxt *bp)
+{
+	int num_stats = BNXT_NUM_STATS * bp->cp_nr_rings;
+
+	if (bp->flags & BNXT_FLAG_PORT_STATS)
+		num_stats += BNXT_NUM_PORT_STATS;
+
+	return num_stats;
+}
+
 static int bnxt_get_sset_count(struct net_device *dev, int sset)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
 	switch (sset) {
-	case ETH_SS_STATS: {
-		int num_stats = BNXT_NUM_STATS * bp->cp_nr_rings;
-
-		if (bp->flags & BNXT_FLAG_PORT_STATS)
-			num_stats += BNXT_NUM_PORT_STATS;
-
-		return num_stats;
-	}
+	case ETH_SS_STATS:
+		return bnxt_get_num_stats(bp);
 	case ETH_SS_TEST:
 		if (!bp->num_tests)
 			return -EOPNOTSUPP;
@@ -225,11 +239,8 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 {
 	u32 i, j = 0;
 	struct bnxt *bp = netdev_priv(dev);
-	u32 buf_size = sizeof(struct ctx_hw_stats) * bp->cp_nr_rings;
 	u32 stat_fields = sizeof(struct ctx_hw_stats) / 8;
 
-	memset(buf, 0, buf_size);
-
 	if (!bp->bnapi)
 		return;
 
@@ -432,8 +443,7 @@ static int bnxt_set_channels(struct net_device *dev,
 		}
 		tx_xdp = req_rx_rings;
 	}
-	rc = bnxt_reserve_rings(bp, req_tx_rings, req_rx_rings, sh, tcs,
-				tx_xdp);
+	rc = bnxt_check_rings(bp, req_tx_rings, req_rx_rings, sh, tcs, tx_xdp);
 	if (rc) {
 		netdev_warn(dev, "Unable to allocate the requested rings\n");
 		return rc;
@@ -520,7 +530,7 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 	struct flow_keys *fkeys;
 	int i, rc = -EINVAL;
 
-	if (fs->location < 0 || fs->location >= BNXT_NTP_FLTR_MAX_FLTR)
+	if (fs->location >= BNXT_NTP_FLTR_MAX_FLTR)
 		return rc;
 
 	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
@@ -820,28 +830,17 @@ static void bnxt_get_drvinfo(struct net_device *dev,
 			     struct ethtool_drvinfo *info)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	char *pkglog;
-	char *pkgver = NULL;
 
-	pkglog = kmalloc(BNX_PKG_LOG_MAX_LENGTH, GFP_KERNEL);
-	if (pkglog)
-		pkgver = bnxt_get_pkgver(dev, pkglog, BNX_PKG_LOG_MAX_LENGTH);
 	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
 	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
-	if (pkgver && *pkgver != 0 && isdigit(*pkgver))
-		snprintf(info->fw_version, sizeof(info->fw_version) - 1,
-			 "%s pkg %s", bp->fw_ver_str, pkgver);
-	else
-		strlcpy(info->fw_version, bp->fw_ver_str,
-			sizeof(info->fw_version));
+	strlcpy(info->fw_version, bp->fw_ver_str, sizeof(info->fw_version));
 	strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
-	info->n_stats = BNXT_NUM_STATS * bp->cp_nr_rings;
+	info->n_stats = bnxt_get_num_stats(bp);
 	info->testinfo_len = bp->num_tests;
 	/* TODO CHIMP_FW: eeprom dump details */
 	info->eedump_len = 0;
 	/* TODO CHIMP FW: reg dump details */
 	info->regdump_len = 0;
-	kfree(pkglog);
 }
 
 static void bnxt_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
@@ -1050,6 +1049,7 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 	u32 ethtool_speed;
 
 	ethtool_link_ksettings_zero_link_mode(lk_ksettings, supported);
+	mutex_lock(&bp->link_lock);
 	bnxt_fw_to_ethtool_support_spds(link_info, lk_ksettings);
 
 	ethtool_link_ksettings_zero_link_mode(lk_ksettings, advertising);
@@ -1097,6 +1097,7 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 			base->port = PORT_FIBRE;
 	}
 	base->phy_address = link_info->phy_addr;
+	mutex_unlock(&bp->link_lock);
 
 	return 0;
 }
@@ -1188,6 +1189,7 @@ static int bnxt_set_link_ksettings(struct net_device *dev,
 	if (!BNXT_SINGLE_PF(bp))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
 	if (base->autoneg == AUTONEG_ENABLE) {
 		BNXT_ETHTOOL_TO_FW_SPDS(fw_advertising, lk_ksettings,
 					advertising);
@@ -1232,6 +1234,7 @@ static int bnxt_set_link_ksettings(struct net_device *dev,
 		rc = bnxt_hwrm_set_link_setting(bp, set_pause, false);
 
 set_setting_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
@@ -1344,7 +1347,6 @@ static int bnxt_firmware_reset(struct net_device *dev,
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1);
 
-	/* TODO: Support ASAP ChiMP self-reset (e.g. upon PF driver unload) */
 	/* TODO: Address self-reset of APE/KONG/BONO/TANG or ungraceful reset */
 	/*       (e.g. when firmware isn't already running) */
 	switch (dir_type) {
@@ -1370,6 +1372,10 @@ static int bnxt_firmware_reset(struct net_device *dev,
 	case BNX_DIR_TYPE_BONO_PATCH:
 		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE;
 		break;
+	case BNXT_FW_RESET_CHIP:
+		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP;
+		req.selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1767,6 +1773,9 @@ static int bnxt_get_nvram_item(struct net_device *dev, u32 index, u32 offset,
 	dma_addr_t dma_handle;
 	struct hwrm_nvm_read_input req = {0};
 
+	if (!length)
+		return -EINVAL;
+
 	buf = dma_alloc_coherent(&bp->pdev->dev, length, &dma_handle,
 				 GFP_KERNEL);
 	if (!buf) {
@@ -1803,7 +1812,8 @@ static int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal,
 	req.dir_ordinal = cpu_to_le16(ordinal);
 	req.dir_ext = cpu_to_le16(ext);
 	req.opt_ordinal = NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_EQ;
-	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc == 0) {
 		if (index)
 			*index = le16_to_cpu(output->dir_idx);
@@ -1812,6 +1822,7 @@ static int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal,
 		if (data_length)
 			*data_length = le32_to_cpu(output->dir_data_length);
 	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
 
@@ -2487,13 +2498,59 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 	}
 }
 
+static int bnxt_reset(struct net_device *dev, u32 *flags)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	int rc = 0;
+
+	if (!BNXT_PF(bp)) {
+		netdev_err(dev, "Reset is not supported from a VF\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (pci_vfs_assigned(bp->pdev)) {
+		netdev_err(dev,
+			   "Reset not allowed when VFs are assigned to VMs\n");
+		return -EBUSY;
+	}
+
+	if (*flags == ETH_RESET_ALL) {
+		/* This feature is not supported in older firmware versions */
+		if (bp->hwrm_spec_code < 0x10803)
+			return -EOPNOTSUPP;
+
+		rc = bnxt_firmware_reset(dev, BNXT_FW_RESET_CHIP);
+		if (!rc)
+			netdev_info(dev, "Reset request successful. Reload driver to complete reset\n");
+	} else {
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
 void bnxt_ethtool_init(struct bnxt *bp)
 {
 	struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_selftest_qlist_input req = {0};
 	struct bnxt_test_info *test_info;
+	struct net_device *dev = bp->dev;
+	char *pkglog;
 	int i, rc;
 
+	pkglog = kzalloc(BNX_PKG_LOG_MAX_LENGTH, GFP_KERNEL);
+	if (pkglog) {
+		char *pkgver;
+		int len;
+
+		pkgver = bnxt_get_pkgver(dev, pkglog, BNX_PKG_LOG_MAX_LENGTH);
+		if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
+			len = strlen(bp->fw_ver_str);
+			snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
+				 "/pkg %s", pkgver);
+		}
+		kfree(pkglog);
+	}
 	if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
 		return;
 
@@ -2584,4 +2641,5 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.nway_reset		= bnxt_nway_reset,
 	.set_phys_id		= bnxt_set_phys_id,
 	.self_test		= bnxt_self_test,
+	.reset			= bnxt_reset,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
index f1bc90b6fb5b..ff601b42fcc8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
@@ -34,6 +34,8 @@ struct bnxt_led_cfg {
 #define BNXT_LED_DFLT_ENABLES(x)			\
 	cpu_to_le32(BNXT_LED_DFLT_ENA << (BNXT_LED_DFLT_ENA_SHIFT * (x)))
 
+#define BNXT_FW_RESET_CHIP	0xffff
+
 extern const struct ethtool_ops bnxt_ethtool_ops;
 
 u32 _bnxt_fw_to_ethtool_adv_spds(u16, u8);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 7dc71bb95837..c99f4d0880e4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -11,21 +11,21 @@
 #ifndef BNXT_HSI_H
 #define BNXT_HSI_H
 
-/* HSI and HWRM Specification 1.7.6 */
+/* HSI and HWRM Specification 1.8.3 */
 #define HWRM_VERSION_MAJOR	1
-#define HWRM_VERSION_MINOR	7
-#define HWRM_VERSION_UPDATE	6
+#define HWRM_VERSION_MINOR	8
+#define HWRM_VERSION_UPDATE	3
 
-#define HWRM_VERSION_RSVD	2 /* non-zero means beta version */
+#define HWRM_VERSION_RSVD	1 /* non-zero means beta version */
 
-#define HWRM_VERSION_STR	"1.7.6.2"
+#define HWRM_VERSION_STR	"1.8.3.1"
 /*
  * Following is the signature for HWRM message field that indicates not
  * applicable (All F's). Need to cast it the size of the field if needed.
  */
 #define HWRM_NA_SIGNATURE	((__le32)(-1))
 #define HWRM_MAX_REQ_LEN    (128)  /* hwrm_func_buf_rgtr */
-#define HWRM_MAX_RESP_LEN    (248)  /* hwrm_selftest_qlist */
+#define HWRM_MAX_RESP_LEN    (280)  /* hwrm_selftest_qlist */
 #define HW_HASH_INDEX_SIZE      0x80    /* 7 bit indirection table index. */
 #define HW_HASH_KEY_SIZE	40
 #define HWRM_RESP_VALID_KEY      1 /* valid key for HWRM response */
@@ -111,6 +111,7 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_MAC_ADDR_CHANGE      0x31UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE 0x32UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE	   0x33UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE	   0x34UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR		   0xffUL
 	__le32 event_data2;
 	u8 opaque_v;
@@ -813,7 +814,7 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED	    0x4UL
 	#define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED      0x8UL
 	#define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED	    0x10UL
-	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST			    0x20UL
+	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST		    0x20UL
 	u8 mac_address[6];
 	__le16 pci_id;
 	__le16 alloc_rsscos_ctx;
@@ -835,9 +836,7 @@ struct hwrm_func_qcfg_output {
 	u8 port_pf_cnt;
 	#define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL		   0x0UL
 	__le16 dflt_vnic_id;
-	u8 host_cnt;
-	#define FUNC_QCFG_RESP_HOST_CNT_UNAVAIL		   0x0UL
-	u8 unused_0;
+	__le16 max_mtu_configured;
 	__le32 min_bw;
 	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK		    0xfffffffUL
 	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT		    0
@@ -874,12 +873,56 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB			   0x0UL
 	#define FUNC_QCFG_RESP_EVB_MODE_VEB			   0x1UL
 	#define FUNC_QCFG_RESP_EVB_MODE_VEPA			   0x2UL
-	u8 unused_1;
+	u8 unused_0;
 	__le16 alloc_vfs;
 	__le32 alloc_mcast_filters;
 	__le32 alloc_hw_ring_grps;
 	__le16 alloc_sp_tx_rings;
+	u8 unused_1;
+	u8 valid;
+};
+
+/* hwrm_func_vlan_cfg */
+/* Input (48 bytes) */
+struct hwrm_func_vlan_cfg_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 fid;
+	u8 unused_0;
+	u8 unused_1;
+	__le32 enables;
+	#define FUNC_VLAN_CFG_REQ_ENABLES_STAG_VID		    0x1UL
+	#define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_VID		    0x2UL
+	#define FUNC_VLAN_CFG_REQ_ENABLES_STAG_PCP		    0x4UL
+	#define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_PCP		    0x8UL
+	#define FUNC_VLAN_CFG_REQ_ENABLES_STAG_TPID		    0x10UL
+	#define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_TPID		    0x20UL
+	__le16 stag_vid;
+	u8 stag_pcp;
+	u8 unused_2;
+	__be16 stag_tpid;
+	__le16 ctag_vid;
+	u8 ctag_pcp;
+	u8 unused_3;
+	__be16 ctag_tpid;
+	__le32 rsvd1;
+	__le32 rsvd2;
+	__le32 unused_4;
+};
+
+/* Output (16 bytes) */
+struct hwrm_func_vlan_cfg_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
 	u8 unused_2;
+	u8 unused_3;
 	u8 valid;
 };
 
@@ -902,6 +945,8 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE	    0x200UL
 	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE	    0x400UL
 	#define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST		    0x800UL
+	#define FUNC_CFG_REQ_FLAGS_NO_AUTOCLEAR_STATISTIC	    0x1000UL
+	#define FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST		    0x2000UL
 	__le32 enables;
 	#define FUNC_CFG_REQ_ENABLES_MTU			    0x1UL
 	#define FUNC_CFG_REQ_ENABLES_MRU			    0x2UL
@@ -1456,9 +1501,9 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_50GB		   0x1f4UL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB		   0x3e8UL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB		   0xffffUL
-	u8 duplex;
-	#define PORT_PHY_QCFG_RESP_DUPLEX_HALF			   0x0UL
-	#define PORT_PHY_QCFG_RESP_DUPLEX_FULL			   0x1UL
+	u8 duplex_cfg;
+	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_HALF		   0x0UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL		   0x1UL
 	u8 pause;
 	#define PORT_PHY_QCFG_RESP_PAUSE_TX			    0x1UL
 	#define PORT_PHY_QCFG_RESP_PAUSE_RX			    0x2UL
@@ -1573,6 +1618,9 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASELR4	   0x16UL
 	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASEER4	   0x17UL
 	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_ACTIVE_CABLE      0x18UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASET		   0x19UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASESX		   0x1aUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASECX		   0x1bUL
 	u8 media_type;
 	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN		   0x0UL
 	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP		   0x1UL
@@ -1651,14 +1699,16 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED    0x10UL
 	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED  0x20UL
 	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED    0x40UL
+	u8 duplex_state;
+	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF		   0x0UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL		   0x1UL
 	u8 unused_1;
-	u8 unused_2;
 	char phy_vendor_name[16];
 	char phy_vendor_partnumber[16];
-	__le32 unused_3;
+	__le32 unused_2;
+	u8 unused_3;
 	u8 unused_4;
 	u8 unused_5;
-	u8 unused_6;
 	u8 valid;
 };
 
@@ -1744,6 +1794,51 @@ struct hwrm_port_mac_cfg_output {
 	u8 valid;
 };
 
+/* hwrm_port_mac_ptp_qcfg */
+/* Input (24 bytes) */
+struct hwrm_port_mac_ptp_qcfg_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 port_id;
+	__le16 unused_0[3];
+};
+
+/* Output (80 bytes) */
+struct hwrm_port_mac_ptp_qcfg_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 flags;
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS	    0x1UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS	    0x2UL
+	u8 unused_0;
+	__le16 unused_1;
+	__le32 rx_ts_reg_off_lower;
+	__le32 rx_ts_reg_off_upper;
+	__le32 rx_ts_reg_off_seq_id;
+	__le32 rx_ts_reg_off_src_id_0;
+	__le32 rx_ts_reg_off_src_id_1;
+	__le32 rx_ts_reg_off_src_id_2;
+	__le32 rx_ts_reg_off_domain_id;
+	__le32 rx_ts_reg_off_fifo;
+	__le32 rx_ts_reg_off_fifo_adv;
+	__le32 rx_ts_reg_off_granularity;
+	__le32 tx_ts_reg_off_lower;
+	__le32 tx_ts_reg_off_upper;
+	__le32 tx_ts_reg_off_seq_id;
+	__le32 tx_ts_reg_off_fifo;
+	__le32 tx_ts_reg_off_granularity;
+	__le32 unused_2;
+	u8 unused_3;
+	u8 unused_4;
+	u8 unused_5;
+	u8 valid;
+};
+
 /* hwrm_port_qstats */
 /* Input (40 bytes) */
 struct hwrm_port_qstats_input {
@@ -1874,11 +1969,16 @@ struct hwrm_port_phy_qcaps_output {
 	__le16 req_type;
 	__le16 seq_id;
 	__le16 resp_len;
-	u8 eee_supported;
-	#define PORT_PHY_QCAPS_RESP_EEE_SUPPORTED		    0x1UL
-	#define PORT_PHY_QCAPS_RESP_RSVD1_MASK			    0xfeUL
-	#define PORT_PHY_QCAPS_RESP_RSVD1_SFT			    1
-	u8 unused_0;
+	u8 flags;
+	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED	    0x1UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK		    0xfeUL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT		    1
+	u8 port_cnt;
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN		   0x0UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_1			   0x1UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_2			   0x2UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_3			   0x3UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_4			   0x4UL
 	__le16 supported_speeds_force_mode;
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD 0x1UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB 0x2UL
@@ -3152,6 +3252,95 @@ struct hwrm_queue_cos2bw_cfg_output {
 	u8 valid;
 };
 
+/* hwrm_queue_dscp_qcaps */
+/* Input (24 bytes) */
+struct hwrm_queue_dscp_qcaps_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	u8 port_id;
+	u8 unused_0[7];
+};
+
+/* Output (16 bytes) */
+struct hwrm_queue_dscp_qcaps_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 num_dscp_bits;
+	u8 unused_0;
+	__le16 max_entries;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_queue_dscp2pri_qcfg */
+/* Input (32 bytes) */
+struct hwrm_queue_dscp2pri_qcfg_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 dest_data_addr;
+	u8 port_id;
+	u8 unused_0;
+	__le16 dest_data_buffer_size;
+	__le32 unused_1;
+};
+
+/* Output (16 bytes) */
+struct hwrm_queue_dscp2pri_qcfg_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 entry_cnt;
+	u8 default_pri;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_queue_dscp2pri_cfg */
+/* Input (40 bytes) */
+struct hwrm_queue_dscp2pri_cfg_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 src_data_addr;
+	__le32 flags;
+	#define QUEUE_DSCP2PRI_CFG_REQ_FLAGS_USE_HW_DEFAULT_PRI    0x1UL
+	__le32 enables;
+	#define QUEUE_DSCP2PRI_CFG_REQ_ENABLES_DEFAULT_PRI	    0x1UL
+	u8 port_id;
+	u8 default_pri;
+	__le16 entry_cnt;
+	__le32 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_queue_dscp2pri_cfg_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
 /* hwrm_vnic_alloc */
 /* Input (24 bytes) */
 struct hwrm_vnic_alloc_input {
@@ -3218,6 +3407,7 @@ struct hwrm_vnic_cfg_input {
 	#define VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE		    0x8UL
 	#define VNIC_CFG_REQ_FLAGS_ROCE_ONLY_VNIC_MODE		    0x10UL
 	#define VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE		    0x20UL
+	#define VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE 0x40UL
 	__le32 enables;
 	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP		    0x1UL
 	#define VNIC_CFG_REQ_ENABLES_RSS_RULE			    0x2UL
@@ -3274,6 +3464,7 @@ struct hwrm_vnic_qcaps_output {
 	#define VNIC_QCAPS_RESP_FLAGS_ROCE_DUAL_VNIC_CAP	    0x8UL
 	#define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP	    0x10UL
 	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP		    0x20UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRROING_CAPABLE_VNIC_CAP 0x40UL
 	__le32 unused_2;
 	u8 unused_3;
 	u8 unused_4;
@@ -3805,6 +3996,7 @@ struct hwrm_cfa_l2_filter_alloc_input {
 	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS	   0x6UL
 	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT	   0x7UL
 	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE	   0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4      0x9UL
 	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL     0xffUL
 	u8 unused_7;
 	__le16 dst_id;
@@ -3933,6 +4125,14 @@ struct hwrm_cfa_l2_set_rx_mask_output {
 	u8 valid;
 };
 
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_cfa_l2_set_rx_mask_cmd_err {
+	u8 code;
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_UNKNOWN	   0x0UL
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR 0x1UL
+	u8 unused_0[7];
+};
+
 /* hwrm_cfa_tunnel_filter_alloc */
 /* Input (88 bytes) */
 struct hwrm_cfa_tunnel_filter_alloc_input {
@@ -3972,6 +4172,7 @@ struct hwrm_cfa_tunnel_filter_alloc_input {
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
 	u8 unused_0;
 	__le32 vni;
@@ -4038,7 +4239,7 @@ struct hwrm_cfa_encap_record_alloc_input {
 	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE       0x8UL
 	u8 unused_0;
 	__le16 unused_1;
-	__le32 encap_data[16];
+	__le32 encap_data[20];
 };
 
 /* Output (16 bytes) */
@@ -4120,8 +4321,8 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6     0x6UL
 	u8 ip_protocol;
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN   0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP       0x6UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP       0x11UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP       0x6UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP       0x11UL
 	__le16 dst_id;
 	__le16 mirror_vnic_id;
 	u8 tunnel_type;
@@ -4134,6 +4335,7 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
 	u8 pri_hint;
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER    0x0UL
@@ -4166,6 +4368,14 @@ struct hwrm_cfa_ntuple_filter_alloc_output {
 	u8 valid;
 };
 
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_cfa_ntuple_filter_alloc_cmd_err {
+	u8 code;
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_UNKNOWN      0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR 0x1UL
+	u8 unused_0[7];
+};
+
 /* hwrm_cfa_ntuple_filter_free */
 /* Input (24 bytes) */
 struct hwrm_cfa_ntuple_filter_free_input {
@@ -4224,6 +4434,326 @@ struct hwrm_cfa_ntuple_filter_cfg_output {
 	u8 valid;
 };
 
+/* hwrm_cfa_decap_filter_alloc */
+/* Input (104 bytes) */
+struct hwrm_cfa_decap_filter_alloc_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le32 flags;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL	    0x1UL
+	__le32 enables;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE     0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_ID       0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR     0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR     0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_OVLAN_VID       0x10UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IVLAN_VID       0x20UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_OVLAN_VID     0x40UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID     0x80UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE       0x100UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR      0x200UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR      0x400UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE     0x800UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL     0x1000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_PORT	    0x2000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_PORT	    0x4000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_ID	    0x8000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID  0x10000UL
+	__be32 tunnel_id;
+	u8 tunnel_type;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL  0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN      0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE      0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE      0x3UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP       0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE     0x5UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS       0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT	   0x7UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE      0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4   0x9UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL  0xffUL
+	u8 unused_0;
+	__le16 unused_1;
+	u8 src_macaddr[6];
+	u8 unused_2;
+	u8 unused_3;
+	u8 dst_macaddr[6];
+	__be16 ovlan_vid;
+	__be16 ivlan_vid;
+	__be16 t_ovlan_vid;
+	__be16 t_ivlan_vid;
+	__be16 ethertype;
+	u8 ip_addr_type;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN   0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4      0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6      0x6UL
+	u8 ip_protocol;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN    0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP	   0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP	   0x11UL
+	u8 unused_4;
+	u8 unused_5;
+	u8 unused_6[3];
+	u8 unused_7;
+	__be32 src_ipaddr[4];
+	__be32 dst_ipaddr[4];
+	__be16 src_port;
+	__be16 dst_port;
+	__le16 dst_id;
+	__le16 l2_ctxt_ref_id;
+};
+
+/* Output (16 bytes) */
+struct hwrm_cfa_decap_filter_alloc_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 decap_filter_id;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 valid;
+};
+
+/* hwrm_cfa_decap_filter_free */
+/* Input (24 bytes) */
+struct hwrm_cfa_decap_filter_free_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le32 decap_filter_id;
+	__le32 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_cfa_decap_filter_free_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_cfa_flow_alloc */
+/* Input (128 bytes) */
+struct hwrm_cfa_flow_alloc_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 flags;
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL		    0x1UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_MASK		    0x6UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_SFT		    1
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_NONE		   (0x0UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE		   (0x1UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO		   (0x2UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_LAST    CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_MASK		    0x38UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_SFT		    3
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2		   (0x0UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4		   (0x1UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6		   (0x2UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_LAST    CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6
+	__le16 src_fid;
+	__le32 tunnel_handle;
+	__le16 action_flags;
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD		    0x1UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE	    0x2UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP		    0x4UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER		    0x8UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL		    0x10UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC	    0x20UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST	    0x40UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS   0x80UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE  0x100UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT      0x200UL
+	__le16 dst_fid;
+	__be16 l2_rewrite_vlan_tpid;
+	__be16 l2_rewrite_vlan_tci;
+	__le16 act_meter_id;
+	__le16 ref_flow_handle;
+	__be16 ethertype;
+	__be16 outer_vlan_tci;
+	__be16 dmac[3];
+	__be16 inner_vlan_tci;
+	__be16 smac[3];
+	u8 ip_dst_mask_len;
+	u8 ip_src_mask_len;
+	__be32 ip_dst[4];
+	__be32 ip_src[4];
+	__be16 l4_src_port;
+	__be16 l4_src_port_mask;
+	__be16 l4_dst_port;
+	__be16 l4_dst_port_mask;
+	__be32 nat_ip_address[4];
+	__be16 l2_rewrite_dmac[3];
+	__be16 nat_port;
+	__be16 l2_rewrite_smac[3];
+	u8 ip_proto;
+	u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_cfa_flow_alloc_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 flow_handle;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 unused_4;
+	u8 valid;
+};
+
+/* hwrm_cfa_flow_free */
+/* Input (24 bytes) */
+struct hwrm_cfa_flow_free_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 flow_handle;
+	__le16 unused_0[3];
+};
+
+/* Output (32 bytes) */
+struct hwrm_cfa_flow_free_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le64 packet;
+	__le64 byte;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_cfa_flow_stats */
+/* Input (40 bytes) */
+struct hwrm_cfa_flow_stats_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 num_flows;
+	__le16 flow_handle_0;
+	__le16 flow_handle_1;
+	__le16 flow_handle_2;
+	__le16 flow_handle_3;
+	__le16 flow_handle_4;
+	__le16 flow_handle_5;
+	__le16 flow_handle_6;
+	__le16 flow_handle_7;
+	__le16 flow_handle_8;
+	__le16 flow_handle_9;
+	__le16 unused_0;
+};
+
+/* Output (176 bytes) */
+struct hwrm_cfa_flow_stats_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le64 packet_0;
+	__le64 packet_1;
+	__le64 packet_2;
+	__le64 packet_3;
+	__le64 packet_4;
+	__le64 packet_5;
+	__le64 packet_6;
+	__le64 packet_7;
+	__le64 packet_8;
+	__le64 packet_9;
+	__le64 byte_0;
+	__le64 byte_1;
+	__le64 byte_2;
+	__le64 byte_3;
+	__le64 byte_4;
+	__le64 byte_5;
+	__le64 byte_6;
+	__le64 byte_7;
+	__le64 byte_8;
+	__le64 byte_9;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_cfa_vfr_alloc */
+/* Input (32 bytes) */
+struct hwrm_cfa_vfr_alloc_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 vf_id;
+	__le16 reserved;
+	__le32 unused_0;
+	char vfr_name[32];
+};
+
+/* Output (16 bytes) */
+struct hwrm_cfa_vfr_alloc_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 rx_cfa_code;
+	__le16 tx_cfa_action;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 valid;
+};
+
+/* hwrm_cfa_vfr_free */
+/* Input (24 bytes) */
+struct hwrm_cfa_vfr_free_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	char vfr_name[32];
+};
+
+/* Output (16 bytes) */
+struct hwrm_cfa_vfr_free_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
 /* hwrm_tunnel_dst_port_query */
 /* Input (24 bytes) */
 struct hwrm_tunnel_dst_port_query_input {
@@ -4235,6 +4765,7 @@ struct hwrm_tunnel_dst_port_query_input {
 	u8 tunnel_type;
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN       0x1UL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE      0x5UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4    0x9UL
 	u8 unused_0[7];
 };
 
@@ -4263,9 +4794,10 @@ struct hwrm_tunnel_dst_port_alloc_input {
 	u8 tunnel_type;
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN       0x1UL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE      0x5UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4    0x9UL
 	u8 unused_0;
 	__be16 tunnel_dst_port_val;
-	__le32 unused_1;
+	__be32 unused_1;
 };
 
 /* Output (16 bytes) */
@@ -4294,6 +4826,7 @@ struct hwrm_tunnel_dst_port_free_input {
 	u8 tunnel_type;
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN	   0x1UL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
 	u8 unused_0;
 	__le16 tunnel_dst_port_id;
 	__le32 unused_1;
@@ -4448,12 +4981,15 @@ struct hwrm_fw_reset_input {
 	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT		   0x1UL
 	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL	   0x2UL
 	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE		   0x3UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_RSVD		   0x4UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST		   0x4UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP		   0x5UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP		   0x6UL
 	u8 selfrst_status;
 	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE	   0x0UL
 	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP	   0x1UL
 	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST	   0x2UL
-	__le16 unused_0[3];
+	u8 host_idx;
+	u8 unused_0[5];
 };
 
 /* Output (16 bytes) */
@@ -4487,7 +5023,9 @@ struct hwrm_fw_qstatus_input {
 	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_MGMT		   0x1UL
 	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_NETCTRL	   0x2UL
 	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_ROCE		   0x3UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_RSVD		   0x4UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_HOST		   0x4UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_AP		   0x5UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP		   0x6UL
 	u8 unused_0[7];
 };
 
@@ -4572,6 +5110,16 @@ struct hwrm_fw_set_structured_data_output {
 	u8 valid;
 };
 
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_fw_set_structured_data_cmd_err {
+	u8 code;
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN       0x0UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_HDR_CNT   0x1UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_FMT       0x2UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID	   0x3UL
+	u8 unused_0[7];
+};
+
 /* hwrm_fw_get_structured_data */
 /* Input (32 bytes) */
 struct hwrm_fw_get_structured_data_input {
@@ -4611,6 +5159,14 @@ struct hwrm_fw_get_structured_data_output {
 	u8 valid;
 };
 
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_fw_get_structured_data_cmd_err {
+	u8 code;
+	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN       0x0UL
+	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID	   0x3UL
+	u8 unused_0[7];
+};
+
 /* hwrm_exec_fwd_resp */
 /* Input (128 bytes) */
 struct hwrm_exec_fwd_resp_input {
@@ -4906,6 +5462,32 @@ struct hwrm_wol_reason_qcfg_output {
 	u8 valid;
 };
 
+/* hwrm_dbg_read_direct */
+/* Input (32 bytes) */
+struct hwrm_dbg_read_direct_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 host_dest_addr;
+	__le32 read_addr;
+	__le32 read_len32;
+};
+
+/* Output (16 bytes) */
+struct hwrm_dbg_read_direct_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
 /* hwrm_nvm_read */
 /* Input (40 bytes) */
 struct hwrm_nvm_read_input {
@@ -5258,6 +5840,105 @@ struct hwrm_nvm_install_update_cmd_err {
 	u8 unused_0[7];
 };
 
+/* hwrm_nvm_get_variable */
+/* Input (40 bytes) */
+struct hwrm_nvm_get_variable_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 dest_data_addr;
+	__le16 data_len;
+	__le16 option_num;
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_0		   0x0UL
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF	   0xffffUL
+	__le16 dimensions;
+	__le16 index_0;
+	__le16 index_1;
+	__le16 index_2;
+	__le16 index_3;
+	u8 flags;
+	#define NVM_GET_VARIABLE_REQ_FLAGS_FACTORY_DFLT	    0x1UL
+	u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_nvm_get_variable_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 data_len;
+	__le16 option_num;
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_0	   0x0UL
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF	   0xffffUL
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 valid;
+};
+
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_nvm_get_variable_cmd_err {
+	u8 code;
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_UNKNOWN		   0x0UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST       0x1UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR	   0x2UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT       0x3UL
+	u8 unused_0[7];
+};
+
+/* hwrm_nvm_set_variable */
+/* Input (40 bytes) */
+struct hwrm_nvm_set_variable_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 src_data_addr;
+	__le16 data_len;
+	__le16 option_num;
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_0		   0x0UL
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF	   0xffffUL
+	__le16 dimensions;
+	__le16 index_0;
+	__le16 index_1;
+	__le16 index_2;
+	__le16 index_3;
+	u8 flags;
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH		    0x1UL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK       0xeUL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT	    1
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE      (0x0UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1 (0x1UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST    NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1
+	u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_nvm_set_variable_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_nvm_set_variable_cmd_err {
+	u8 code;
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_UNKNOWN		   0x0UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST       0x1UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR	   0x2UL
+	u8 unused_0[7];
+};
+
 /* hwrm_selftest_qlist */
 /* Input (16 bytes) */
 struct hwrm_selftest_qlist_input {
@@ -5268,7 +5949,7 @@ struct hwrm_selftest_qlist_input {
 	__le64 resp_addr;
 };
 
-/* Output (248 bytes) */
+/* Output (280 bytes) */
 struct hwrm_selftest_qlist_output {
 	__le16 error_code;
 	__le16 req_type;
@@ -5280,11 +5961,15 @@ struct hwrm_selftest_qlist_output {
 	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST      0x2UL
 	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST  0x4UL
 	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST    0x8UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_PCIE_SERDES_TEST 0x10UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_ETHERNET_SERDES_TEST 0x20UL
 	u8 offline_tests;
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST	    0x1UL
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST	    0x2UL
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST    0x4UL
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST      0x8UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_PCIE_SERDES_TEST 0x10UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_ETHERNET_SERDES_TEST 0x20UL
 	u8 unused_0;
 	__le16 test_timeout;
 	u8 unused_1;
@@ -5297,6 +5982,11 @@ struct hwrm_selftest_qlist_output {
 	char test5_name[32];
 	char test6_name[32];
 	char test7_name[32];
+	__le32 unused_3;
+	u8 unused_4;
+	u8 unused_5;
+	u8 unused_6;
+	u8 valid;
 };
 
 /* hwrm_selftest_exec */
@@ -5312,6 +6002,8 @@ struct hwrm_selftest_exec_input {
 	#define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST		    0x2UL
 	#define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST		    0x4UL
 	#define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST		    0x8UL
+	#define SELFTEST_EXEC_REQ_FLAGS_PCIE_SERDES_TEST	    0x10UL
+	#define SELFTEST_EXEC_REQ_FLAGS_ETHERNET_SERDES_TEST       0x20UL
 	u8 unused_0[7];
 };
 
@@ -5326,12 +6018,21 @@ struct hwrm_selftest_exec_output {
 	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST       0x2UL
 	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST   0x4UL
 	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST     0x8UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_PCIE_SERDES_TEST 0x10UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_ETHERNET_SERDES_TEST 0x20UL
 	u8 test_success;
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST	    0x1UL
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST	    0x2UL
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST      0x4UL
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST	    0x8UL
-	__le16 unused_0[3];
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_PCIE_SERDES_TEST   0x10UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_ETHERNET_SERDES_TEST 0x20UL
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 unused_4;
+	u8 valid;
 };
 
 /* hwrm_selftest_irq */
@@ -5344,12 +6045,50 @@ struct hwrm_selftest_irq_input {
 	__le64 resp_addr;
 };
 
-/* Output (8 bytes) */
+/* Output (16 bytes) */
 struct hwrm_selftest_irq_output {
 	__le16 error_code;
 	__le16 req_type;
 	__le16 seq_id;
 	__le16 resp_len;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_selftest_retrieve_serdes_data */
+/* Input (32 bytes) */
+struct hwrm_selftest_retrieve_serdes_data_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 resp_data_addr;
+	__le32 resp_data_offset;
+	__le16 data_len;
+	u8 flags;
+	#define SELFTEST_RETRIEVE_SERDES_DATA_REQ_FLAGS_UNUSED_TEST_MASK 0xfUL
+	#define SELFTEST_RETRIEVE_SERDES_DATA_REQ_FLAGS_UNUSED_TEST_SFT 0
+	#define SELFTEST_RETRIEVE_SERDES_DATA_REQ_FLAGS_PCIE_SERDES_TEST 0x10UL
+	#define SELFTEST_RETRIEVE_SERDES_DATA_REQ_FLAGS_ETHERNET_SERDES_TEST 0x20UL
+	u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_selftest_retrieve_serdes_data_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 total_data_len;
+	__le16 copied_data_len;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 valid;
 };
 
 /* Hardware Resource Manager Specification */
@@ -5411,7 +6150,7 @@ struct cmd_nums {
 	#define HWRM_PORT_LPBK_CLR_STATS			   (0x26UL)
 	#define HWRM_PORT_PHY_QCFG				   (0x27UL)
 	#define HWRM_PORT_MAC_QCFG				   (0x28UL)
-	#define RESERVED7					   (0x29UL)
+	#define HWRM_PORT_MAC_PTP_QCFG				   (0x29UL)
 	#define HWRM_PORT_PHY_QCAPS				   (0x2aUL)
 	#define HWRM_PORT_PHY_I2C_WRITE			   (0x2bUL)
 	#define HWRM_PORT_PHY_I2C_READ				   (0x2cUL)
@@ -5421,14 +6160,17 @@ struct cmd_nums {
 	#define HWRM_QUEUE_QPORTCFG				   (0x30UL)
 	#define HWRM_QUEUE_QCFG				   (0x31UL)
 	#define HWRM_QUEUE_CFG					   (0x32UL)
-	#define RESERVED2					   (0x33UL)
-	#define RESERVED3					   (0x34UL)
+	#define HWRM_FUNC_VLAN_CFG				   (0x33UL)
+	#define HWRM_FUNC_VLAN_QCFG				   (0x34UL)
 	#define HWRM_QUEUE_PFCENABLE_QCFG			   (0x35UL)
 	#define HWRM_QUEUE_PFCENABLE_CFG			   (0x36UL)
 	#define HWRM_QUEUE_PRI2COS_QCFG			   (0x37UL)
 	#define HWRM_QUEUE_PRI2COS_CFG				   (0x38UL)
 	#define HWRM_QUEUE_COS2BW_QCFG				   (0x39UL)
 	#define HWRM_QUEUE_COS2BW_CFG				   (0x3aUL)
+	#define HWRM_QUEUE_DSCP_QCAPS				   (0x3bUL)
+	#define HWRM_QUEUE_DSCP2PRI_QCFG			   (0x3cUL)
+	#define HWRM_QUEUE_DSCP2PRI_CFG			   (0x3dUL)
 	#define HWRM_VNIC_ALLOC				   (0x40UL)
 	#define HWRM_VNIC_FREE					   (0x41UL)
 	#define HWRM_VNIC_CFG					   (0x42UL)
@@ -5455,7 +6197,7 @@ struct cmd_nums {
 	#define HWRM_CFA_L2_FILTER_FREE			   (0x91UL)
 	#define HWRM_CFA_L2_FILTER_CFG				   (0x92UL)
 	#define HWRM_CFA_L2_SET_RX_MASK			   (0x93UL)
-	#define RESERVED4					   (0x94UL)
+	#define HWRM_CFA_VLAN_ANTISPOOF_CFG			   (0x94UL)
 	#define HWRM_CFA_TUNNEL_FILTER_ALLOC			   (0x95UL)
 	#define HWRM_CFA_TUNNEL_FILTER_FREE			   (0x96UL)
 	#define HWRM_CFA_ENCAP_RECORD_ALLOC			   (0x97UL)
@@ -5494,6 +6236,8 @@ struct cmd_nums {
 	#define HWRM_CFA_METER_PROFILE_CFG			   (0xf7UL)
 	#define HWRM_CFA_METER_INSTANCE_ALLOC			   (0xf8UL)
 	#define HWRM_CFA_METER_INSTANCE_FREE			   (0xf9UL)
+	#define HWRM_CFA_VFR_ALLOC				   (0xfdUL)
+	#define HWRM_CFA_VFR_FREE				   (0xfeUL)
 	#define HWRM_CFA_VF_PAIR_ALLOC				   (0x100UL)
 	#define HWRM_CFA_VF_PAIR_FREE				   (0x101UL)
 	#define HWRM_CFA_VF_PAIR_INFO				   (0x102UL)
@@ -5502,14 +6246,29 @@ struct cmd_nums {
 	#define HWRM_CFA_FLOW_FLUSH				   (0x105UL)
 	#define HWRM_CFA_FLOW_STATS				   (0x106UL)
 	#define HWRM_CFA_FLOW_INFO				   (0x107UL)
+	#define HWRM_CFA_DECAP_FILTER_ALLOC			   (0x108UL)
+	#define HWRM_CFA_DECAP_FILTER_FREE			   (0x109UL)
+	#define HWRM_CFA_VLAN_ANTISPOOF_QCFG			   (0x10aUL)
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_ALLOC		   (0x10bUL)
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_FREE		   (0x10cUL)
+	#define HWRM_CFA_PAIR_ALLOC				   (0x10dUL)
+	#define HWRM_CFA_PAIR_FREE				   (0x10eUL)
+	#define HWRM_CFA_PAIR_INFO				   (0x10fUL)
+	#define HWRM_FW_IPC_MSG				   (0x110UL)
 	#define HWRM_SELFTEST_QLIST				   (0x200UL)
 	#define HWRM_SELFTEST_EXEC				   (0x201UL)
 	#define HWRM_SELFTEST_IRQ				   (0x202UL)
+	#define HWRM_SELFTEST_RETRIEVE_SERDES_DATA		   (0x203UL)
 	#define HWRM_DBG_READ_DIRECT				   (0xff10UL)
 	#define HWRM_DBG_READ_INDIRECT				   (0xff11UL)
 	#define HWRM_DBG_WRITE_DIRECT				   (0xff12UL)
 	#define HWRM_DBG_WRITE_INDIRECT			   (0xff13UL)
 	#define HWRM_DBG_DUMP					   (0xff14UL)
+	#define HWRM_DBG_ERASE_NVM				   (0xff15UL)
+	#define HWRM_DBG_CFG					   (0xff16UL)
+	#define HWRM_DBG_COREDUMP_LIST				   (0xff17UL)
+	#define HWRM_DBG_COREDUMP_INITIATE			   (0xff18UL)
+	#define HWRM_DBG_COREDUMP_RETRIEVE			   (0xff19UL)
 	#define HWRM_NVM_FACTORY_DEFAULTS			   (0xffeeUL)
 	#define HWRM_NVM_VALIDATE_OPTION			   (0xffefUL)
 	#define HWRM_NVM_FLUSH					   (0xfff0UL)
@@ -5684,6 +6443,58 @@ struct rx_port_stats {
 	__le64 rx_stat_err;
 };
 
+/* VXLAN IPv4 encapsulation structure (16 bytes) */
+struct hwrm_vxlan_ipv4_hdr {
+	u8 ver_hlen;
+	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_MASK	    0xfUL
+	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_SFT	    0
+	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_MASK		    0xf0UL
+	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_SFT		    4
+	u8 tos;
+	__be16 ip_id;
+	__be16 flags_frag_offset;
+	u8 ttl;
+	u8 protocol;
+	__be32 src_ip_addr;
+	__be32 dest_ip_addr;
+};
+
+/* VXLAN IPv6 encapsulation structure (32 bytes) */
+struct hwrm_vxlan_ipv6_hdr {
+	__be32 ver_tc_flow_label;
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_SFT	   0x1cUL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_MASK	   0xf0000000UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_SFT	   0x14UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_MASK	   0xff00000UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_SFT   0x0UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK  0xfffffUL
+	__be16 payload_len;
+	u8 next_hdr;
+	u8 ttl;
+	__be32 src_ip_addr[4];
+	__be32 dest_ip_addr[4];
+};
+
+/* VXLAN encapsulation structure (72 bytes) */
+struct hwrm_cfa_encap_data_vxlan {
+	u8 src_mac_addr[6];
+	__le16 unused_0;
+	u8 dst_mac_addr[6];
+	u8 num_vlan_tags;
+	u8 unused_1;
+	__be16 ovlan_tpid;
+	__be16 ovlan_tci;
+	__be16 ivlan_tpid;
+	__be16 ivlan_tci;
+	__le32 l3[10];
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_MASK		   0xfUL
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV4		   0x4UL
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6		   0x6UL
+	__be16 src_port;
+	__be16 dst_port;
+	__be32 vni;
+};
+
 /* Periodic Statistics Context DMA to host (160 bytes) */
 struct ctx_hw_stats {
 	__le64 rx_ucast_pkts;
@@ -5720,6 +6531,7 @@ struct hwrm_struct_hdr {
 	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE		   0x426UL
 	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE		   0x1UL
 	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION		   0xaUL
+	#define STRUCT_HDR_STRUCT_ID_RSS_V2			   0x64UL
 	__le16 len;
 	u8 version;
 	u8 count;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index b8e7248294d9..5ee18660bc33 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -18,6 +18,7 @@
 #include "bnxt.h"
 #include "bnxt_ulp.h"
 #include "bnxt_sriov.h"
+#include "bnxt_vfr.h"
 #include "bnxt_ethtool.h"
 
 #ifdef CONFIG_BNXT_SRIOV
@@ -501,6 +502,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 	int rc = 0, vfs_supported;
 	int min_rx_rings, min_tx_rings, min_rss_ctxs;
 	int tx_ok = 0, rx_ok = 0, rss_ok = 0;
+	int avail_cp, avail_stat;
 
 	/* Check if we can enable requested num of vf's. At a mininum
 	 * we require 1 RX 1 TX rings for each VF. In this minimum conf
@@ -508,6 +510,10 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 	 */
 	vfs_supported = *num_vfs;
 
+	avail_cp = bp->pf.max_cp_rings - bp->cp_nr_rings;
+	avail_stat = bp->pf.max_stat_ctxs - bp->num_stat_ctxs;
+	avail_cp = min_t(int, avail_cp, avail_stat);
+
 	while (vfs_supported) {
 		min_rx_rings = vfs_supported;
 		min_tx_rings = vfs_supported;
@@ -522,10 +528,12 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 			    min_rx_rings)
 				rx_ok = 1;
 		}
-		if (bp->pf.max_vnics - bp->nr_vnics < min_rx_rings)
+		if (bp->pf.max_vnics - bp->nr_vnics < min_rx_rings ||
+		    avail_cp < min_rx_rings)
 			rx_ok = 0;
 
-		if (bp->pf.max_tx_rings - bp->tx_nr_rings >= min_tx_rings)
+		if (bp->pf.max_tx_rings - bp->tx_nr_rings >= min_tx_rings &&
+		    avail_cp >= min_tx_rings)
 			tx_ok = 1;
 
 		if (bp->pf.max_rsscos_ctxs - bp->rsscos_nr_ctxs >= min_rss_ctxs)
@@ -587,6 +595,10 @@ void bnxt_sriov_disable(struct bnxt *bp)
 	if (!num_vfs)
 		return;
 
+	/* synchronize VF and VF-rep create and destroy */
+	mutex_lock(&bp->sriov_lock);
+	bnxt_vf_reps_destroy(bp);
+
 	if (pci_vfs_assigned(bp->pdev)) {
 		bnxt_hwrm_fwd_async_event_cmpl(
 			bp, NULL, ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD);
@@ -597,6 +609,7 @@ void bnxt_sriov_disable(struct bnxt *bp)
 		/* Free the HW resources reserved for various VF's */
 		bnxt_hwrm_func_vf_resource_free(bp, num_vfs);
 	}
+	mutex_unlock(&bp->sriov_lock);
 
 	bnxt_free_vf_resources(bp);
 
@@ -794,8 +807,10 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf)
 					PORT_PHY_QCFG_RESP_LINK_LINK;
 				phy_qcfg_resp.link_speed = cpu_to_le16(
 					PORT_PHY_QCFG_RESP_LINK_SPEED_10GB);
-				phy_qcfg_resp.duplex =
-					PORT_PHY_QCFG_RESP_DUPLEX_FULL;
+				phy_qcfg_resp.duplex_cfg =
+					PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL;
+				phy_qcfg_resp.duplex_state =
+					PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL;
 				phy_qcfg_resp.pause =
 					(PORT_PHY_QCFG_RESP_PAUSE_TX |
 					 PORT_PHY_QCFG_RESP_PAUSE_RX);
@@ -804,7 +819,8 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf)
 			/* force link down */
 			phy_qcfg_resp.link = PORT_PHY_QCFG_RESP_LINK_NO_LINK;
 			phy_qcfg_resp.link_speed = 0;
-			phy_qcfg_resp.duplex = PORT_PHY_QCFG_RESP_DUPLEX_HALF;
+			phy_qcfg_resp.duplex_state =
+				PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF;
 			phy_qcfg_resp.pause = 0;
 		}
 		rc = bnxt_hwrm_fwd_resp(bp, vf, &phy_qcfg_resp,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
new file mode 100644
index 000000000000..d5031f436f83
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -0,0 +1,1616 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/if_vlan.h>
+#include <net/flow_dissector.h>
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_skbedit.h>
+#include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_vlan.h>
+#include <net/tc_act/tc_tunnel_key.h>
+
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+#include "bnxt_sriov.h"
+#include "bnxt_tc.h"
+#include "bnxt_vfr.h"
+
+#define BNXT_FID_INVALID			0xffff
+#define VLAN_TCI(vid, prio)	((vid) | ((prio) << VLAN_PRIO_SHIFT))
+
+/* Return the dst fid of the func for flow forwarding
+ * For PFs: src_fid is the fid of the PF
+ * For VF-reps: src_fid the fid of the VF
+ */
+static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev)
+{
+	struct bnxt *bp;
+
+	/* check if dev belongs to the same switch */
+	if (!switchdev_port_same_parent_id(pf_bp->dev, dev)) {
+		netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch",
+			    dev->ifindex);
+		return BNXT_FID_INVALID;
+	}
+
+	/* Is dev a VF-rep? */
+	if (dev != pf_bp->dev)
+		return bnxt_vf_rep_get_fid(dev);
+
+	bp = netdev_priv(dev);
+	return bp->pf.fw_fid;
+}
+
+static int bnxt_tc_parse_redir(struct bnxt *bp,
+			       struct bnxt_tc_actions *actions,
+			       const struct tc_action *tc_act)
+{
+	int ifindex = tcf_mirred_ifindex(tc_act);
+	struct net_device *dev;
+	u16 dst_fid;
+
+	dev = __dev_get_by_index(dev_net(bp->dev), ifindex);
+	if (!dev) {
+		netdev_info(bp->dev, "no dev for ifindex=%d", ifindex);
+		return -EINVAL;
+	}
+
+	/* find the FID from dev */
+	dst_fid = bnxt_flow_get_dst_fid(bp, dev);
+	if (dst_fid == BNXT_FID_INVALID) {
+		netdev_info(bp->dev, "can't get fid for ifindex=%d", ifindex);
+		return -EINVAL;
+	}
+
+	actions->flags |= BNXT_TC_ACTION_FLAG_FWD;
+	actions->dst_fid = dst_fid;
+	actions->dst_dev = dev;
+	return 0;
+}
+
+static void bnxt_tc_parse_vlan(struct bnxt *bp,
+			       struct bnxt_tc_actions *actions,
+			       const struct tc_action *tc_act)
+{
+	if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_POP) {
+		actions->flags |= BNXT_TC_ACTION_FLAG_POP_VLAN;
+	} else if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_PUSH) {
+		actions->flags |= BNXT_TC_ACTION_FLAG_PUSH_VLAN;
+		actions->push_vlan_tci = htons(tcf_vlan_push_vid(tc_act));
+		actions->push_vlan_tpid = tcf_vlan_push_proto(tc_act);
+	}
+}
+
+static int bnxt_tc_parse_tunnel_set(struct bnxt *bp,
+				    struct bnxt_tc_actions *actions,
+				    const struct tc_action *tc_act)
+{
+	struct ip_tunnel_info *tun_info = tcf_tunnel_info(tc_act);
+	struct ip_tunnel_key *tun_key = &tun_info->key;
+
+	if (ip_tunnel_info_af(tun_info) != AF_INET) {
+		netdev_info(bp->dev, "only IPv4 tunnel-encap is supported");
+		return -EOPNOTSUPP;
+	}
+
+	actions->tun_encap_key = *tun_key;
+	actions->flags |= BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP;
+	return 0;
+}
+
+static int bnxt_tc_parse_actions(struct bnxt *bp,
+				 struct bnxt_tc_actions *actions,
+				 struct tcf_exts *tc_exts)
+{
+	const struct tc_action *tc_act;
+	LIST_HEAD(tc_actions);
+	int rc;
+
+	if (!tcf_exts_has_actions(tc_exts)) {
+		netdev_info(bp->dev, "no actions");
+		return -EINVAL;
+	}
+
+	tcf_exts_to_list(tc_exts, &tc_actions);
+	list_for_each_entry(tc_act, &tc_actions, list) {
+		/* Drop action */
+		if (is_tcf_gact_shot(tc_act)) {
+			actions->flags |= BNXT_TC_ACTION_FLAG_DROP;
+			return 0; /* don't bother with other actions */
+		}
+
+		/* Redirect action */
+		if (is_tcf_mirred_egress_redirect(tc_act)) {
+			rc = bnxt_tc_parse_redir(bp, actions, tc_act);
+			if (rc)
+				return rc;
+			continue;
+		}
+
+		/* Push/pop VLAN */
+		if (is_tcf_vlan(tc_act)) {
+			bnxt_tc_parse_vlan(bp, actions, tc_act);
+			continue;
+		}
+
+		/* Tunnel encap */
+		if (is_tcf_tunnel_set(tc_act)) {
+			rc = bnxt_tc_parse_tunnel_set(bp, actions, tc_act);
+			if (rc)
+				return rc;
+			continue;
+		}
+
+		/* Tunnel decap */
+		if (is_tcf_tunnel_release(tc_act)) {
+			actions->flags |= BNXT_TC_ACTION_FLAG_TUNNEL_DECAP;
+			continue;
+		}
+	}
+
+	if (rc)
+		return rc;
+
+	/* Tunnel encap/decap action must be accompanied by a redirect action */
+	if ((actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP ||
+	     actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP) &&
+	    !(actions->flags & BNXT_TC_ACTION_FLAG_FWD)) {
+		netdev_info(bp->dev,
+			    "error: no redir action along with encap/decap");
+		return -EINVAL;
+	}
+
+	return rc;
+}
+
+#define GET_KEY(flow_cmd, key_type)					\
+		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
+					  (flow_cmd)->key)
+#define GET_MASK(flow_cmd, key_type)					\
+		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
+					  (flow_cmd)->mask)
+
+static int bnxt_tc_parse_flow(struct bnxt *bp,
+			      struct tc_cls_flower_offload *tc_flow_cmd,
+			      struct bnxt_tc_flow *flow)
+{
+	struct flow_dissector *dissector = tc_flow_cmd->dissector;
+	u16 addr_type = 0;
+
+	/* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */
+	if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 ||
+	    (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) {
+		netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x",
+			    dissector->used_keys);
+		return -EOPNOTSUPP;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_dissector_key_control *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_CONTROL);
+
+		addr_type = key->addr_type;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
+		struct flow_dissector_key_basic *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
+
+		flow->l2_key.ether_type = key->n_proto;
+		flow->l2_mask.ether_type = mask->n_proto;
+
+		if (key->n_proto == htons(ETH_P_IP) ||
+		    key->n_proto == htons(ETH_P_IPV6)) {
+			flow->l4_key.ip_proto = key->ip_proto;
+			flow->l4_mask.ip_proto = mask->ip_proto;
+		}
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_dissector_key_eth_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
+		struct flow_dissector_key_eth_addrs *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_ETH_ADDRS;
+		ether_addr_copy(flow->l2_key.dmac, key->dst);
+		ether_addr_copy(flow->l2_mask.dmac, mask->dst);
+		ether_addr_copy(flow->l2_key.smac, key->src);
+		ether_addr_copy(flow->l2_mask.smac, mask->src);
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_dissector_key_vlan *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
+		struct flow_dissector_key_vlan *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
+
+		flow->l2_key.inner_vlan_tci =
+		   cpu_to_be16(VLAN_TCI(key->vlan_id, key->vlan_priority));
+		flow->l2_mask.inner_vlan_tci =
+		   cpu_to_be16((VLAN_TCI(mask->vlan_id, mask->vlan_priority)));
+		flow->l2_key.inner_vlan_tpid = htons(ETH_P_8021Q);
+		flow->l2_mask.inner_vlan_tpid = htons(0xffff);
+		flow->l2_key.num_vlans = 1;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_dissector_key_ipv4_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+		struct flow_dissector_key_ipv4_addrs *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV4_ADDRS;
+		flow->l3_key.ipv4.daddr.s_addr = key->dst;
+		flow->l3_mask.ipv4.daddr.s_addr = mask->dst;
+		flow->l3_key.ipv4.saddr.s_addr = key->src;
+		flow->l3_mask.ipv4.saddr.s_addr = mask->src;
+	} else if (dissector_uses_key(dissector,
+				      FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_dissector_key_ipv6_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
+		struct flow_dissector_key_ipv6_addrs *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV6_ADDRS;
+		flow->l3_key.ipv6.daddr = key->dst;
+		flow->l3_mask.ipv6.daddr = mask->dst;
+		flow->l3_key.ipv6.saddr = key->src;
+		flow->l3_mask.ipv6.saddr = mask->src;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_dissector_key_ports *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
+		struct flow_dissector_key_ports *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_PORTS;
+		flow->l4_key.ports.dport = key->dst;
+		flow->l4_mask.ports.dport = mask->dst;
+		flow->l4_key.ports.sport = key->src;
+		flow->l4_mask.ports.sport = mask->src;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ICMP)) {
+		struct flow_dissector_key_icmp *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
+		struct flow_dissector_key_icmp *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_ICMP;
+		flow->l4_key.icmp.type = key->type;
+		flow->l4_key.icmp.code = key->code;
+		flow->l4_mask.icmp.type = mask->type;
+		flow->l4_mask.icmp.code = mask->code;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+		struct flow_dissector_key_control *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_CONTROL);
+
+		addr_type = key->addr_type;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+		struct flow_dissector_key_ipv4_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
+		struct flow_dissector_key_ipv4_addrs *mask =
+				GET_MASK(tc_flow_cmd,
+					 FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS;
+		flow->tun_key.u.ipv4.dst = key->dst;
+		flow->tun_mask.u.ipv4.dst = mask->dst;
+		flow->tun_key.u.ipv4.src = key->src;
+		flow->tun_mask.u.ipv4.src = mask->src;
+	} else if (dissector_uses_key(dissector,
+				      FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
+		return -EOPNOTSUPP;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_dissector_key_keyid *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID);
+		struct flow_dissector_key_keyid *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_ID;
+		flow->tun_key.tun_id = key32_to_tunnel_id(key->keyid);
+		flow->tun_mask.tun_id = key32_to_tunnel_id(mask->keyid);
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+		struct flow_dissector_key_ports *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS);
+		struct flow_dissector_key_ports *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_PORTS;
+		flow->tun_key.tp_dst = key->dst;
+		flow->tun_mask.tp_dst = mask->dst;
+		flow->tun_key.tp_src = key->src;
+		flow->tun_mask.tp_src = mask->src;
+	}
+
+	return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts);
+}
+
+static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, __le16 flow_handle)
+{
+	struct hwrm_cfa_flow_free_input req = { 0 };
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_FREE, -1, -1);
+	req.flow_handle = flow_handle;
+
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		netdev_info(bp->dev, "Error: %s: flow_handle=0x%x rc=%d",
+			    __func__, flow_handle, rc);
+	return rc;
+}
+
+static int ipv6_mask_len(struct in6_addr *mask)
+{
+	int mask_len = 0, i;
+
+	for (i = 0; i < 4; i++)
+		mask_len += inet_mask_len(mask->s6_addr32[i]);
+
+	return mask_len;
+}
+
+static bool is_wildcard(void *mask, int len)
+{
+	const u8 *p = mask;
+	int i;
+
+	for (i = 0; i < len; i++) {
+		if (p[i] != 0)
+			return false;
+	}
+	return true;
+}
+
+static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				    __le16 ref_flow_handle,
+				    __le32 tunnel_handle, __le16 *flow_handle)
+{
+	struct hwrm_cfa_flow_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct bnxt_tc_actions *actions = &flow->actions;
+	struct bnxt_tc_l3_key *l3_mask = &flow->l3_mask;
+	struct bnxt_tc_l3_key *l3_key = &flow->l3_key;
+	struct hwrm_cfa_flow_alloc_input req = { 0 };
+	u16 flow_flags = 0, action_flags = 0;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_ALLOC, -1, -1);
+
+	req.src_fid = cpu_to_le16(flow->src_fid);
+	req.ref_flow_handle = ref_flow_handle;
+
+	if (actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP ||
+	    actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP) {
+		req.tunnel_handle = tunnel_handle;
+		flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL;
+		action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL;
+	}
+
+	req.ethertype = flow->l2_key.ether_type;
+	req.ip_proto = flow->l4_key.ip_proto;
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_ETH_ADDRS) {
+		memcpy(req.dmac, flow->l2_key.dmac, ETH_ALEN);
+		memcpy(req.smac, flow->l2_key.smac, ETH_ALEN);
+	}
+
+	if (flow->l2_key.num_vlans > 0) {
+		flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE;
+		/* FW expects the inner_vlan_tci value to be set
+		 * in outer_vlan_tci when num_vlans is 1 (which is
+		 * always the case in TC.)
+		 */
+		req.outer_vlan_tci = flow->l2_key.inner_vlan_tci;
+	}
+
+	/* If all IP and L4 fields are wildcarded then this is an L2 flow */
+	if (is_wildcard(&l3_mask, sizeof(l3_mask)) &&
+	    is_wildcard(&flow->l4_mask, sizeof(flow->l4_mask))) {
+		flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2;
+	} else {
+		flow_flags |= flow->l2_key.ether_type == htons(ETH_P_IP) ?
+				CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4 :
+				CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6;
+
+		if (flow->flags & BNXT_TC_FLOW_FLAGS_IPV4_ADDRS) {
+			req.ip_dst[0] = l3_key->ipv4.daddr.s_addr;
+			req.ip_dst_mask_len =
+				inet_mask_len(l3_mask->ipv4.daddr.s_addr);
+			req.ip_src[0] = l3_key->ipv4.saddr.s_addr;
+			req.ip_src_mask_len =
+				inet_mask_len(l3_mask->ipv4.saddr.s_addr);
+		} else if (flow->flags & BNXT_TC_FLOW_FLAGS_IPV6_ADDRS) {
+			memcpy(req.ip_dst, l3_key->ipv6.daddr.s6_addr32,
+			       sizeof(req.ip_dst));
+			req.ip_dst_mask_len =
+					ipv6_mask_len(&l3_mask->ipv6.daddr);
+			memcpy(req.ip_src, l3_key->ipv6.saddr.s6_addr32,
+			       sizeof(req.ip_src));
+			req.ip_src_mask_len =
+					ipv6_mask_len(&l3_mask->ipv6.saddr);
+		}
+	}
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) {
+		req.l4_src_port = flow->l4_key.ports.sport;
+		req.l4_src_port_mask = flow->l4_mask.ports.sport;
+		req.l4_dst_port = flow->l4_key.ports.dport;
+		req.l4_dst_port_mask = flow->l4_mask.ports.dport;
+	} else if (flow->flags & BNXT_TC_FLOW_FLAGS_ICMP) {
+		/* l4 ports serve as type/code when ip_proto is ICMP */
+		req.l4_src_port = htons(flow->l4_key.icmp.type);
+		req.l4_src_port_mask = htons(flow->l4_mask.icmp.type);
+		req.l4_dst_port = htons(flow->l4_key.icmp.code);
+		req.l4_dst_port_mask = htons(flow->l4_mask.icmp.code);
+	}
+	req.flags = cpu_to_le16(flow_flags);
+
+	if (actions->flags & BNXT_TC_ACTION_FLAG_DROP) {
+		action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP;
+	} else {
+		if (actions->flags & BNXT_TC_ACTION_FLAG_FWD) {
+			action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD;
+			req.dst_fid = cpu_to_le16(actions->dst_fid);
+		}
+		if (actions->flags & BNXT_TC_ACTION_FLAG_PUSH_VLAN) {
+			action_flags |=
+			    CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE;
+			req.l2_rewrite_vlan_tpid = actions->push_vlan_tpid;
+			req.l2_rewrite_vlan_tci = actions->push_vlan_tci;
+			memcpy(&req.l2_rewrite_dmac, &req.dmac, ETH_ALEN);
+			memcpy(&req.l2_rewrite_smac, &req.smac, ETH_ALEN);
+		}
+		if (actions->flags & BNXT_TC_ACTION_FLAG_POP_VLAN) {
+			action_flags |=
+			    CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE;
+			/* Rewrite config with tpid = 0 implies vlan pop */
+			req.l2_rewrite_vlan_tpid = 0;
+			memcpy(&req.l2_rewrite_dmac, &req.dmac, ETH_ALEN);
+			memcpy(&req.l2_rewrite_smac, &req.smac, ETH_ALEN);
+		}
+	}
+	req.action_flags = cpu_to_le16(action_flags);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*flow_handle = resp->flow_handle;
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	return rc;
+}
+
+static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
+				       struct bnxt_tc_flow *flow,
+				       struct bnxt_tc_l2_key *l2_info,
+				       __le32 ref_decap_handle,
+				       __le32 *decap_filter_handle)
+{
+	struct hwrm_cfa_decap_filter_alloc_output *resp =
+						bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_decap_filter_alloc_input req = { 0 };
+	struct ip_tunnel_key *tun_key = &flow->tun_key;
+	u32 enables = 0;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_DECAP_FILTER_ALLOC, -1, -1);
+
+	req.flags = cpu_to_le32(CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL);
+	enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE |
+		   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL;
+	req.tunnel_type = CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN;
+	req.ip_protocol = CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP;
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_ID) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_ID;
+		/* tunnel_id is wrongly defined in hsi defn. as __le32 */
+		req.tunnel_id = tunnel_id_to_key32(tun_key->tun_id);
+	}
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR |
+			   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR;
+		ether_addr_copy(req.dst_macaddr, l2_info->dmac);
+		ether_addr_copy(req.src_macaddr, l2_info->smac);
+	}
+	if (l2_info->num_vlans) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID;
+		req.t_ivlan_vid = l2_info->inner_vlan_tci;
+	}
+
+	enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE;
+	req.ethertype = htons(ETH_P_IP);
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR |
+			   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR |
+			   CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE;
+		req.ip_addr_type = CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
+		req.dst_ipaddr[0] = tun_key->u.ipv4.dst;
+		req.src_ipaddr[0] = tun_key->u.ipv4.src;
+	}
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_TUNL_PORTS) {
+		enables |= CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_PORT;
+		req.dst_port = tun_key->tp_dst;
+	}
+
+	/* Eventhough the decap_handle returned by hwrm_cfa_decap_filter_alloc
+	 * is defined as __le32, l2_ctxt_ref_id is defined in HSI as __le16.
+	 */
+	req.l2_ctxt_ref_id = (__force __le16)ref_decap_handle;
+	req.enables = cpu_to_le32(enables);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*decap_filter_handle = resp->decap_filter_id;
+	else
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	return rc;
+}
+
+static int hwrm_cfa_decap_filter_free(struct bnxt *bp,
+				      __le32 decap_filter_handle)
+{
+	struct hwrm_cfa_decap_filter_free_input req = { 0 };
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_DECAP_FILTER_FREE, -1, -1);
+	req.decap_filter_id = decap_filter_handle;
+
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	return rc;
+}
+
+static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
+				       struct ip_tunnel_key *encap_key,
+				       struct bnxt_tc_l2_key *l2_info,
+				       __le32 *encap_record_handle)
+{
+	struct hwrm_cfa_encap_record_alloc_output *resp =
+						bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_encap_record_alloc_input req = { 0 };
+	struct hwrm_cfa_encap_data_vxlan *encap =
+			(struct hwrm_cfa_encap_data_vxlan *)&req.encap_data;
+	struct hwrm_vxlan_ipv4_hdr *encap_ipv4 =
+				(struct hwrm_vxlan_ipv4_hdr *)encap->l3;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_ENCAP_RECORD_ALLOC, -1, -1);
+
+	req.encap_type = CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN;
+
+	ether_addr_copy(encap->dst_mac_addr, l2_info->dmac);
+	ether_addr_copy(encap->src_mac_addr, l2_info->smac);
+	if (l2_info->num_vlans) {
+		encap->num_vlan_tags = l2_info->num_vlans;
+		encap->ovlan_tci = l2_info->inner_vlan_tci;
+		encap->ovlan_tpid = l2_info->inner_vlan_tpid;
+	}
+
+	encap_ipv4->ver_hlen = 4 << VXLAN_IPV4_HDR_VER_HLEN_VERSION_SFT;
+	encap_ipv4->ver_hlen |= 5 << VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_SFT;
+	encap_ipv4->ttl = encap_key->ttl;
+
+	encap_ipv4->dest_ip_addr = encap_key->u.ipv4.dst;
+	encap_ipv4->src_ip_addr = encap_key->u.ipv4.src;
+	encap_ipv4->protocol = IPPROTO_UDP;
+
+	encap->dst_port = encap_key->tp_dst;
+	encap->vni = tunnel_id_to_key32(encap_key->tun_id);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*encap_record_handle = resp->encap_record_id;
+	else
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	return rc;
+}
+
+static int hwrm_cfa_encap_record_free(struct bnxt *bp,
+				      __le32 encap_record_handle)
+{
+	struct hwrm_cfa_encap_record_free_input req = { 0 };
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_ENCAP_RECORD_FREE, -1, -1);
+	req.encap_record_id = encap_record_handle;
+
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	return rc;
+}
+
+static int bnxt_tc_put_l2_node(struct bnxt *bp,
+			       struct bnxt_tc_flow_node *flow_node)
+{
+	struct bnxt_tc_l2_node *l2_node = flow_node->l2_node;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc;
+
+	/* remove flow_node from the L2 shared flow list */
+	list_del(&flow_node->l2_list_node);
+	if (--l2_node->refcount == 0) {
+		rc =  rhashtable_remove_fast(&tc_info->l2_table, &l2_node->node,
+					     tc_info->l2_ht_params);
+		if (rc)
+			netdev_err(bp->dev,
+				   "Error: %s: rhashtable_remove_fast: %d",
+				   __func__, rc);
+		kfree_rcu(l2_node, rcu);
+	}
+	return 0;
+}
+
+static struct bnxt_tc_l2_node *
+bnxt_tc_get_l2_node(struct bnxt *bp, struct rhashtable *l2_table,
+		    struct rhashtable_params ht_params,
+		    struct bnxt_tc_l2_key *l2_key)
+{
+	struct bnxt_tc_l2_node *l2_node;
+	int rc;
+
+	l2_node = rhashtable_lookup_fast(l2_table, l2_key, ht_params);
+	if (!l2_node) {
+		l2_node = kzalloc(sizeof(*l2_node), GFP_KERNEL);
+		if (!l2_node) {
+			rc = -ENOMEM;
+			return NULL;
+		}
+
+		l2_node->key = *l2_key;
+		rc = rhashtable_insert_fast(l2_table, &l2_node->node,
+					    ht_params);
+		if (rc) {
+			kfree_rcu(l2_node, rcu);
+			netdev_err(bp->dev,
+				   "Error: %s: rhashtable_insert_fast: %d",
+				   __func__, rc);
+			return NULL;
+		}
+		INIT_LIST_HEAD(&l2_node->common_l2_flows);
+	}
+	return l2_node;
+}
+
+/* Get the ref_flow_handle for a flow by checking if there are any other
+ * flows that share the same L2 key as this flow.
+ */
+static int
+bnxt_tc_get_ref_flow_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
+			    struct bnxt_tc_flow_node *flow_node,
+			    __le16 *ref_flow_handle)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_flow_node *ref_flow_node;
+	struct bnxt_tc_l2_node *l2_node;
+
+	l2_node = bnxt_tc_get_l2_node(bp, &tc_info->l2_table,
+				      tc_info->l2_ht_params,
+				      &flow->l2_key);
+	if (!l2_node)
+		return -1;
+
+	/* If any other flow is using this l2_node, use it's flow_handle
+	 * as the ref_flow_handle
+	 */
+	if (l2_node->refcount > 0) {
+		ref_flow_node = list_first_entry(&l2_node->common_l2_flows,
+						 struct bnxt_tc_flow_node,
+						 l2_list_node);
+		*ref_flow_handle = ref_flow_node->flow_handle;
+	} else {
+		*ref_flow_handle = cpu_to_le16(0xffff);
+	}
+
+	/* Insert the l2_node into the flow_node so that subsequent flows
+	 * with a matching l2 key can use the flow_handle of this flow
+	 * as their ref_flow_handle
+	 */
+	flow_node->l2_node = l2_node;
+	list_add(&flow_node->l2_list_node, &l2_node->common_l2_flows);
+	l2_node->refcount++;
+	return 0;
+}
+
+/* After the flow parsing is done, this routine is used for checking
+ * if there are any aspects of the flow that prevent it from being
+ * offloaded.
+ */
+static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow)
+{
+	/* If L4 ports are specified then ip_proto must be TCP or UDP */
+	if ((flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) &&
+	    (flow->l4_key.ip_proto != IPPROTO_TCP &&
+	     flow->l4_key.ip_proto != IPPROTO_UDP)) {
+		netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports",
+			    flow->l4_key.ip_proto);
+		return false;
+	}
+
+	return true;
+}
+
+/* Returns the final refcount of the node on success
+ * or a -ve error code on failure
+ */
+static int bnxt_tc_put_tunnel_node(struct bnxt *bp,
+				   struct rhashtable *tunnel_table,
+				   struct rhashtable_params *ht_params,
+				   struct bnxt_tc_tunnel_node *tunnel_node)
+{
+	int rc;
+
+	if (--tunnel_node->refcount == 0) {
+		rc =  rhashtable_remove_fast(tunnel_table, &tunnel_node->node,
+					     *ht_params);
+		if (rc) {
+			netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc);
+			rc = -1;
+		}
+		kfree_rcu(tunnel_node, rcu);
+		return rc;
+	} else {
+		return tunnel_node->refcount;
+	}
+}
+
+/* Get (or add) either encap or decap tunnel node from/to the supplied
+ * hash table.
+ */
+static struct bnxt_tc_tunnel_node *
+bnxt_tc_get_tunnel_node(struct bnxt *bp, struct rhashtable *tunnel_table,
+			struct rhashtable_params *ht_params,
+			struct ip_tunnel_key *tun_key)
+{
+	struct bnxt_tc_tunnel_node *tunnel_node;
+	int rc;
+
+	tunnel_node = rhashtable_lookup_fast(tunnel_table, tun_key, *ht_params);
+	if (!tunnel_node) {
+		tunnel_node = kzalloc(sizeof(*tunnel_node), GFP_KERNEL);
+		if (!tunnel_node) {
+			rc = -ENOMEM;
+			goto err;
+		}
+
+		tunnel_node->key = *tun_key;
+		tunnel_node->tunnel_handle = INVALID_TUNNEL_HANDLE;
+		rc = rhashtable_insert_fast(tunnel_table, &tunnel_node->node,
+					    *ht_params);
+		if (rc) {
+			kfree_rcu(tunnel_node, rcu);
+			goto err;
+		}
+	}
+	tunnel_node->refcount++;
+	return tunnel_node;
+err:
+	netdev_info(bp->dev, "error rc=%d", rc);
+	return NULL;
+}
+
+static int bnxt_tc_get_ref_decap_handle(struct bnxt *bp,
+					struct bnxt_tc_flow *flow,
+					struct bnxt_tc_l2_key *l2_key,
+					struct bnxt_tc_flow_node *flow_node,
+					__le32 *ref_decap_handle)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_flow_node *ref_flow_node;
+	struct bnxt_tc_l2_node *decap_l2_node;
+
+	decap_l2_node = bnxt_tc_get_l2_node(bp, &tc_info->decap_l2_table,
+					    tc_info->decap_l2_ht_params,
+					    l2_key);
+	if (!decap_l2_node)
+		return -1;
+
+	/* If any other flow is using this decap_l2_node, use it's decap_handle
+	 * as the ref_decap_handle
+	 */
+	if (decap_l2_node->refcount > 0) {
+		ref_flow_node =
+			list_first_entry(&decap_l2_node->common_l2_flows,
+					 struct bnxt_tc_flow_node,
+					 decap_l2_list_node);
+		*ref_decap_handle = ref_flow_node->decap_node->tunnel_handle;
+	} else {
+		*ref_decap_handle = INVALID_TUNNEL_HANDLE;
+	}
+
+	/* Insert the l2_node into the flow_node so that subsequent flows
+	 * with a matching decap l2 key can use the decap_filter_handle of
+	 * this flow as their ref_decap_handle
+	 */
+	flow_node->decap_l2_node = decap_l2_node;
+	list_add(&flow_node->decap_l2_list_node,
+		 &decap_l2_node->common_l2_flows);
+	decap_l2_node->refcount++;
+	return 0;
+}
+
+static void bnxt_tc_put_decap_l2_node(struct bnxt *bp,
+				      struct bnxt_tc_flow_node *flow_node)
+{
+	struct bnxt_tc_l2_node *decap_l2_node = flow_node->decap_l2_node;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc;
+
+	/* remove flow_node from the decap L2 sharing flow list */
+	list_del(&flow_node->decap_l2_list_node);
+	if (--decap_l2_node->refcount == 0) {
+		rc =  rhashtable_remove_fast(&tc_info->decap_l2_table,
+					     &decap_l2_node->node,
+					     tc_info->decap_l2_ht_params);
+		if (rc)
+			netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc);
+		kfree_rcu(decap_l2_node, rcu);
+	}
+}
+
+static void bnxt_tc_put_decap_handle(struct bnxt *bp,
+				     struct bnxt_tc_flow_node *flow_node)
+{
+	__le32 decap_handle = flow_node->decap_node->tunnel_handle;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc;
+
+	if (flow_node->decap_l2_node)
+		bnxt_tc_put_decap_l2_node(bp, flow_node);
+
+	rc = bnxt_tc_put_tunnel_node(bp, &tc_info->decap_table,
+				     &tc_info->decap_ht_params,
+				     flow_node->decap_node);
+	if (!rc && decap_handle != INVALID_TUNNEL_HANDLE)
+		hwrm_cfa_decap_filter_free(bp, decap_handle);
+}
+
+static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp,
+				       struct ip_tunnel_key *tun_key,
+				       struct bnxt_tc_l2_key *l2_info,
+				       struct net_device *real_dst_dev)
+{
+#ifdef CONFIG_INET
+	struct flowi4 flow = { {0} };
+	struct net_device *dst_dev;
+	struct neighbour *nbr;
+	struct rtable *rt;
+	int rc;
+
+	flow.flowi4_proto = IPPROTO_UDP;
+	flow.fl4_dport = tun_key->tp_dst;
+	flow.daddr = tun_key->u.ipv4.dst;
+
+	rt = ip_route_output_key(dev_net(real_dst_dev), &flow);
+	if (IS_ERR(rt)) {
+		netdev_info(bp->dev, "no route to %pI4b", &flow.daddr);
+		return -EOPNOTSUPP;
+	}
+
+	/* The route must either point to the real_dst_dev or a dst_dev that
+	 * uses the real_dst_dev.
+	 */
+	dst_dev = rt->dst.dev;
+	if (is_vlan_dev(dst_dev)) {
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
+		struct vlan_dev_priv *vlan = vlan_dev_priv(dst_dev);
+
+		if (vlan->real_dev != real_dst_dev) {
+			netdev_info(bp->dev,
+				    "dst_dev(%s) doesn't use PF-if(%s)",
+				    netdev_name(dst_dev),
+				    netdev_name(real_dst_dev));
+			rc = -EOPNOTSUPP;
+			goto put_rt;
+		}
+		l2_info->inner_vlan_tci = htons(vlan->vlan_id);
+		l2_info->inner_vlan_tpid = vlan->vlan_proto;
+		l2_info->num_vlans = 1;
+#endif
+	} else if (dst_dev != real_dst_dev) {
+		netdev_info(bp->dev,
+			    "dst_dev(%s) for %pI4b is not PF-if(%s)",
+			    netdev_name(dst_dev), &flow.daddr,
+			    netdev_name(real_dst_dev));
+		rc = -EOPNOTSUPP;
+		goto put_rt;
+	}
+
+	nbr = dst_neigh_lookup(&rt->dst, &flow.daddr);
+	if (!nbr) {
+		netdev_info(bp->dev, "can't lookup neighbor for %pI4b",
+			    &flow.daddr);
+		rc = -EOPNOTSUPP;
+		goto put_rt;
+	}
+
+	tun_key->u.ipv4.src = flow.saddr;
+	tun_key->ttl = ip4_dst_hoplimit(&rt->dst);
+	neigh_ha_snapshot(l2_info->dmac, nbr, dst_dev);
+	ether_addr_copy(l2_info->smac, dst_dev->dev_addr);
+	neigh_release(nbr);
+	ip_rt_put(rt);
+
+	return 0;
+put_rt:
+	ip_rt_put(rt);
+	return rc;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int bnxt_tc_get_decap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				    struct bnxt_tc_flow_node *flow_node,
+				    __le32 *decap_filter_handle)
+{
+	struct ip_tunnel_key *decap_key = &flow->tun_key;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_l2_key l2_info = { {0} };
+	struct bnxt_tc_tunnel_node *decap_node;
+	struct ip_tunnel_key tun_key = { 0 };
+	struct bnxt_tc_l2_key *decap_l2_info;
+	__le32 ref_decap_handle;
+	int rc;
+
+	/* Check if there's another flow using the same tunnel decap.
+	 * If not, add this tunnel to the table and resolve the other
+	 * tunnel header fileds
+	 */
+	decap_node = bnxt_tc_get_tunnel_node(bp, &tc_info->decap_table,
+					     &tc_info->decap_ht_params,
+					     decap_key);
+	if (!decap_node)
+		return -ENOMEM;
+
+	flow_node->decap_node = decap_node;
+
+	if (decap_node->tunnel_handle != INVALID_TUNNEL_HANDLE)
+		goto done;
+
+	/* Resolve the L2 fields for tunnel decap
+	 * Resolve the route for remote vtep (saddr) of the decap key
+	 * Find it's next-hop mac addrs
+	 */
+	tun_key.u.ipv4.dst = flow->tun_key.u.ipv4.src;
+	tun_key.tp_dst = flow->tun_key.tp_dst;
+	rc = bnxt_tc_resolve_tunnel_hdrs(bp, &tun_key, &l2_info, bp->dev);
+	if (rc)
+		goto put_decap;
+
+	decap_key->ttl = tun_key.ttl;
+	decap_l2_info = &decap_node->l2_info;
+	ether_addr_copy(decap_l2_info->dmac, l2_info.smac);
+	ether_addr_copy(decap_l2_info->smac, l2_info.dmac);
+	if (l2_info.num_vlans) {
+		decap_l2_info->num_vlans = l2_info.num_vlans;
+		decap_l2_info->inner_vlan_tpid = l2_info.inner_vlan_tpid;
+		decap_l2_info->inner_vlan_tci = l2_info.inner_vlan_tci;
+	}
+	flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS;
+
+	/* For getting a decap_filter_handle we first need to check if
+	 * there are any other decap flows that share the same tunnel L2
+	 * key and if so, pass that flow's decap_filter_handle as the
+	 * ref_decap_handle for this flow.
+	 */
+	rc = bnxt_tc_get_ref_decap_handle(bp, flow, decap_l2_info, flow_node,
+					  &ref_decap_handle);
+	if (rc)
+		goto put_decap;
+
+	/* Issue the hwrm cmd to allocate a decap filter handle */
+	rc = hwrm_cfa_decap_filter_alloc(bp, flow, decap_l2_info,
+					 ref_decap_handle,
+					 &decap_node->tunnel_handle);
+	if (rc)
+		goto put_decap_l2;
+
+done:
+	*decap_filter_handle = decap_node->tunnel_handle;
+	return 0;
+
+put_decap_l2:
+	bnxt_tc_put_decap_l2_node(bp, flow_node);
+put_decap:
+	bnxt_tc_put_tunnel_node(bp, &tc_info->decap_table,
+				&tc_info->decap_ht_params,
+				flow_node->decap_node);
+	return rc;
+}
+
+static void bnxt_tc_put_encap_handle(struct bnxt *bp,
+				     struct bnxt_tc_tunnel_node *encap_node)
+{
+	__le32 encap_handle = encap_node->tunnel_handle;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc;
+
+	rc = bnxt_tc_put_tunnel_node(bp, &tc_info->encap_table,
+				     &tc_info->encap_ht_params, encap_node);
+	if (!rc && encap_handle != INVALID_TUNNEL_HANDLE)
+		hwrm_cfa_encap_record_free(bp, encap_handle);
+}
+
+/* Lookup the tunnel encap table and check if there's an encap_handle
+ * alloc'd already.
+ * If not, query L2 info via a route lookup and issue an encap_record_alloc
+ * cmd to FW.
+ */
+static int bnxt_tc_get_encap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				    struct bnxt_tc_flow_node *flow_node,
+				    __le32 *encap_handle)
+{
+	struct ip_tunnel_key *encap_key = &flow->actions.tun_encap_key;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_tunnel_node *encap_node;
+	int rc;
+
+	/* Check if there's another flow using the same tunnel encap.
+	 * If not, add this tunnel to the table and resolve the other
+	 * tunnel header fileds
+	 */
+	encap_node = bnxt_tc_get_tunnel_node(bp, &tc_info->encap_table,
+					     &tc_info->encap_ht_params,
+					     encap_key);
+	if (!encap_node)
+		return -ENOMEM;
+
+	flow_node->encap_node = encap_node;
+
+	if (encap_node->tunnel_handle != INVALID_TUNNEL_HANDLE)
+		goto done;
+
+	rc = bnxt_tc_resolve_tunnel_hdrs(bp, encap_key, &encap_node->l2_info,
+					 flow->actions.dst_dev);
+	if (rc)
+		goto put_encap;
+
+	/* Allocate a new tunnel encap record */
+	rc = hwrm_cfa_encap_record_alloc(bp, encap_key, &encap_node->l2_info,
+					 &encap_node->tunnel_handle);
+	if (rc)
+		goto put_encap;
+
+done:
+	*encap_handle = encap_node->tunnel_handle;
+	return 0;
+
+put_encap:
+	bnxt_tc_put_tunnel_node(bp, &tc_info->encap_table,
+				&tc_info->encap_ht_params, encap_node);
+	return rc;
+}
+
+static void bnxt_tc_put_tunnel_handle(struct bnxt *bp,
+				      struct bnxt_tc_flow *flow,
+				      struct bnxt_tc_flow_node *flow_node)
+{
+	if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP)
+		bnxt_tc_put_decap_handle(bp, flow_node);
+	else if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP)
+		bnxt_tc_put_encap_handle(bp, flow_node->encap_node);
+}
+
+static int bnxt_tc_get_tunnel_handle(struct bnxt *bp,
+				     struct bnxt_tc_flow *flow,
+				     struct bnxt_tc_flow_node *flow_node,
+				     __le32 *tunnel_handle)
+{
+	if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_DECAP)
+		return bnxt_tc_get_decap_handle(bp, flow, flow_node,
+						tunnel_handle);
+	else if (flow->actions.flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP)
+		return bnxt_tc_get_encap_handle(bp, flow, flow_node,
+						tunnel_handle);
+	else
+		return 0;
+}
+static int __bnxt_tc_del_flow(struct bnxt *bp,
+			      struct bnxt_tc_flow_node *flow_node)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc;
+
+	/* send HWRM cmd to free the flow-id */
+	bnxt_hwrm_cfa_flow_free(bp, flow_node->flow_handle);
+
+	mutex_lock(&tc_info->lock);
+
+	/* release references to any tunnel encap/decap nodes */
+	bnxt_tc_put_tunnel_handle(bp, &flow_node->flow, flow_node);
+
+	/* release reference to l2 node */
+	bnxt_tc_put_l2_node(bp, flow_node);
+
+	mutex_unlock(&tc_info->lock);
+
+	rc = rhashtable_remove_fast(&tc_info->flow_table, &flow_node->node,
+				    tc_info->flow_ht_params);
+	if (rc)
+		netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d",
+			   __func__, rc);
+
+	kfree_rcu(flow_node, rcu);
+	return 0;
+}
+
+/* Add a new flow or replace an existing flow.
+ * Notes on locking:
+ * There are essentially two critical sections here.
+ * 1. while adding a new flow
+ *    a) lookup l2-key
+ *    b) issue HWRM cmd and get flow_handle
+ *    c) link l2-key with flow
+ * 2. while deleting a flow
+ *    a) unlinking l2-key from flow
+ * A lock is needed to protect these two critical sections.
+ *
+ * The hash-tables are already protected by the rhashtable API.
+ */
+static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
+			    struct tc_cls_flower_offload *tc_flow_cmd)
+{
+	struct bnxt_tc_flow_node *new_node, *old_node;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_flow *flow;
+	__le32 tunnel_handle = 0;
+	__le16 ref_flow_handle;
+	int rc;
+
+	/* allocate memory for the new flow and it's node */
+	new_node = kzalloc(sizeof(*new_node), GFP_KERNEL);
+	if (!new_node) {
+		rc = -ENOMEM;
+		goto done;
+	}
+	new_node->cookie = tc_flow_cmd->cookie;
+	flow = &new_node->flow;
+
+	rc = bnxt_tc_parse_flow(bp, tc_flow_cmd, flow);
+	if (rc)
+		goto free_node;
+	flow->src_fid = src_fid;
+
+	if (!bnxt_tc_can_offload(bp, flow)) {
+		rc = -ENOSPC;
+		goto free_node;
+	}
+
+	/* If a flow exists with the same cookie, delete it */
+	old_node = rhashtable_lookup_fast(&tc_info->flow_table,
+					  &tc_flow_cmd->cookie,
+					  tc_info->flow_ht_params);
+	if (old_node)
+		__bnxt_tc_del_flow(bp, old_node);
+
+	/* Check if the L2 part of the flow has been offloaded already.
+	 * If so, bump up it's refcnt and get it's reference handle.
+	 */
+	mutex_lock(&tc_info->lock);
+	rc = bnxt_tc_get_ref_flow_handle(bp, flow, new_node, &ref_flow_handle);
+	if (rc)
+		goto unlock;
+
+	/* If the flow involves tunnel encap/decap, get tunnel_handle */
+	rc = bnxt_tc_get_tunnel_handle(bp, flow, new_node, &tunnel_handle);
+	if (rc)
+		goto put_l2;
+
+	/* send HWRM cmd to alloc the flow */
+	rc = bnxt_hwrm_cfa_flow_alloc(bp, flow, ref_flow_handle,
+				      tunnel_handle, &new_node->flow_handle);
+	if (rc)
+		goto put_tunnel;
+
+	flow->lastused = jiffies;
+	spin_lock_init(&flow->stats_lock);
+	/* add new flow to flow-table */
+	rc = rhashtable_insert_fast(&tc_info->flow_table, &new_node->node,
+				    tc_info->flow_ht_params);
+	if (rc)
+		goto hwrm_flow_free;
+
+	mutex_unlock(&tc_info->lock);
+	return 0;
+
+hwrm_flow_free:
+	bnxt_hwrm_cfa_flow_free(bp, new_node->flow_handle);
+put_tunnel:
+	bnxt_tc_put_tunnel_handle(bp, flow, new_node);
+put_l2:
+	bnxt_tc_put_l2_node(bp, new_node);
+unlock:
+	mutex_unlock(&tc_info->lock);
+free_node:
+	kfree_rcu(new_node, rcu);
+done:
+	netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d",
+		   __func__, tc_flow_cmd->cookie, rc);
+	return rc;
+}
+
+static int bnxt_tc_del_flow(struct bnxt *bp,
+			    struct tc_cls_flower_offload *tc_flow_cmd)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_flow_node *flow_node;
+
+	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
+					   &tc_flow_cmd->cookie,
+					   tc_info->flow_ht_params);
+	if (!flow_node) {
+		netdev_info(bp->dev, "ERROR: no flow_node for cookie %lx",
+			    tc_flow_cmd->cookie);
+		return -EINVAL;
+	}
+
+	return __bnxt_tc_del_flow(bp, flow_node);
+}
+
+static int bnxt_tc_get_flow_stats(struct bnxt *bp,
+				  struct tc_cls_flower_offload *tc_flow_cmd)
+{
+	struct bnxt_tc_flow_stats stats, *curr_stats, *prev_stats;
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct bnxt_tc_flow_node *flow_node;
+	struct bnxt_tc_flow *flow;
+	unsigned long lastused;
+
+	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
+					   &tc_flow_cmd->cookie,
+					   tc_info->flow_ht_params);
+	if (!flow_node) {
+		netdev_info(bp->dev, "Error: no flow_node for cookie %lx",
+			    tc_flow_cmd->cookie);
+		return -1;
+	}
+
+	flow = &flow_node->flow;
+	curr_stats = &flow->stats;
+	prev_stats = &flow->prev_stats;
+
+	spin_lock(&flow->stats_lock);
+	stats.packets = curr_stats->packets - prev_stats->packets;
+	stats.bytes = curr_stats->bytes - prev_stats->bytes;
+	*prev_stats = *curr_stats;
+	lastused = flow->lastused;
+	spin_unlock(&flow->stats_lock);
+
+	tcf_exts_stats_update(tc_flow_cmd->exts, stats.bytes, stats.packets,
+			      lastused);
+	return 0;
+}
+
+static int
+bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
+			     struct bnxt_tc_stats_batch stats_batch[])
+{
+	struct hwrm_cfa_flow_stats_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_flow_stats_input req = { 0 };
+	__le16 *req_flow_handles = &req.flow_handle_0;
+	int rc, i;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_STATS, -1, -1);
+	req.num_flows = cpu_to_le16(num_flows);
+	for (i = 0; i < num_flows; i++) {
+		struct bnxt_tc_flow_node *flow_node = stats_batch[i].flow_node;
+
+		req_flow_handles[i] = flow_node->flow_handle;
+	}
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		__le64 *resp_packets = &resp->packet_0;
+		__le64 *resp_bytes = &resp->byte_0;
+
+		for (i = 0; i < num_flows; i++) {
+			stats_batch[i].hw_stats.packets =
+						le64_to_cpu(resp_packets[i]);
+			stats_batch[i].hw_stats.bytes =
+						le64_to_cpu(resp_bytes[i]);
+		}
+	} else {
+		netdev_info(bp->dev, "error rc=%d", rc);
+	}
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+/* Add val to accum while handling a possible wraparound
+ * of val. Eventhough val is of type u64, its actual width
+ * is denoted by mask and will wrap-around beyond that width.
+ */
+static void accumulate_val(u64 *accum, u64 val, u64 mask)
+{
+#define low_bits(x, mask)		((x) & (mask))
+#define high_bits(x, mask)		((x) & ~(mask))
+	bool wrapped = val < low_bits(*accum, mask);
+
+	*accum = high_bits(*accum, mask) + val;
+	if (wrapped)
+		*accum += (mask + 1);
+}
+
+/* The HW counters' width is much less than 64bits.
+ * Handle possible wrap-around while updating the stat counters
+ */
+static void bnxt_flow_stats_accum(struct bnxt_tc_info *tc_info,
+				  struct bnxt_tc_flow_stats *acc_stats,
+				  struct bnxt_tc_flow_stats *hw_stats)
+{
+	accumulate_val(&acc_stats->bytes, hw_stats->bytes, tc_info->bytes_mask);
+	accumulate_val(&acc_stats->packets, hw_stats->packets,
+		       tc_info->packets_mask);
+}
+
+static int
+bnxt_tc_flow_stats_batch_update(struct bnxt *bp, int num_flows,
+				struct bnxt_tc_stats_batch stats_batch[])
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int rc, i;
+
+	rc = bnxt_hwrm_cfa_flow_stats_get(bp, num_flows, stats_batch);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < num_flows; i++) {
+		struct bnxt_tc_flow_node *flow_node = stats_batch[i].flow_node;
+		struct bnxt_tc_flow *flow = &flow_node->flow;
+
+		spin_lock(&flow->stats_lock);
+		bnxt_flow_stats_accum(tc_info, &flow->stats,
+				      &stats_batch[i].hw_stats);
+		if (flow->stats.packets != flow->prev_stats.packets)
+			flow->lastused = jiffies;
+		spin_unlock(&flow->stats_lock);
+	}
+
+	return 0;
+}
+
+static int
+bnxt_tc_flow_stats_batch_prep(struct bnxt *bp,
+			      struct bnxt_tc_stats_batch stats_batch[],
+			      int *num_flows)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	struct rhashtable_iter *iter = &tc_info->iter;
+	void *flow_node;
+	int rc, i;
+
+	rc = rhashtable_walk_start(iter);
+	if (rc && rc != -EAGAIN) {
+		i = 0;
+		goto done;
+	}
+
+	rc = 0;
+	for (i = 0; i < BNXT_FLOW_STATS_BATCH_MAX; i++) {
+		flow_node = rhashtable_walk_next(iter);
+		if (IS_ERR(flow_node)) {
+			i = 0;
+			if (PTR_ERR(flow_node) == -EAGAIN) {
+				continue;
+			} else {
+				rc = PTR_ERR(flow_node);
+				goto done;
+			}
+		}
+
+		/* No more flows */
+		if (!flow_node)
+			goto done;
+
+		stats_batch[i].flow_node = flow_node;
+	}
+done:
+	rhashtable_walk_stop(iter);
+	*num_flows = i;
+	return rc;
+}
+
+void bnxt_tc_flow_stats_work(struct bnxt *bp)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+	int num_flows, rc;
+
+	num_flows = atomic_read(&tc_info->flow_table.nelems);
+	if (!num_flows)
+		return;
+
+	rhashtable_walk_enter(&tc_info->flow_table, &tc_info->iter);
+
+	for (;;) {
+		rc = bnxt_tc_flow_stats_batch_prep(bp, tc_info->stats_batch,
+						   &num_flows);
+		if (rc) {
+			if (rc == -EAGAIN)
+				continue;
+			break;
+		}
+
+		if (!num_flows)
+			break;
+
+		bnxt_tc_flow_stats_batch_update(bp, num_flows,
+						tc_info->stats_batch);
+	}
+
+	rhashtable_walk_exit(&tc_info->iter);
+}
+
+int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
+			 struct tc_cls_flower_offload *cls_flower)
+{
+	int rc = 0;
+
+	if (cls_flower->common.chain_index)
+		return -EOPNOTSUPP;
+
+	switch (cls_flower->command) {
+	case TC_CLSFLOWER_REPLACE:
+		rc = bnxt_tc_add_flow(bp, src_fid, cls_flower);
+		break;
+
+	case TC_CLSFLOWER_DESTROY:
+		rc = bnxt_tc_del_flow(bp, cls_flower);
+		break;
+
+	case TC_CLSFLOWER_STATS:
+		rc = bnxt_tc_get_flow_stats(bp, cls_flower);
+		break;
+	}
+	return rc;
+}
+
+static const struct rhashtable_params bnxt_tc_flow_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_flow_node, node),
+	.key_offset = offsetof(struct bnxt_tc_flow_node, cookie),
+	.key_len = sizeof(((struct bnxt_tc_flow_node *)0)->cookie),
+	.automatic_shrinking = true
+};
+
+static const struct rhashtable_params bnxt_tc_l2_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_l2_node, node),
+	.key_offset = offsetof(struct bnxt_tc_l2_node, key),
+	.key_len = BNXT_TC_L2_KEY_LEN,
+	.automatic_shrinking = true
+};
+
+static const struct rhashtable_params bnxt_tc_decap_l2_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_l2_node, node),
+	.key_offset = offsetof(struct bnxt_tc_l2_node, key),
+	.key_len = BNXT_TC_L2_KEY_LEN,
+	.automatic_shrinking = true
+};
+
+static const struct rhashtable_params bnxt_tc_tunnel_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_tunnel_node, node),
+	.key_offset = offsetof(struct bnxt_tc_tunnel_node, key),
+	.key_len = sizeof(struct ip_tunnel_key),
+	.automatic_shrinking = true
+};
+
+/* convert counter width in bits to a mask */
+#define mask(width)		((u64)~0 >> (64 - (width)))
+
+int bnxt_init_tc(struct bnxt *bp)
+{
+	struct bnxt_tc_info *tc_info;
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10803) {
+		netdev_warn(bp->dev,
+			    "Firmware does not support TC flower offload.\n");
+		return -ENOTSUPP;
+	}
+
+	tc_info = kzalloc(sizeof(*tc_info), GFP_KERNEL);
+	if (!tc_info)
+		return -ENOMEM;
+	mutex_init(&tc_info->lock);
+
+	/* Counter widths are programmed by FW */
+	tc_info->bytes_mask = mask(36);
+	tc_info->packets_mask = mask(28);
+
+	tc_info->flow_ht_params = bnxt_tc_flow_ht_params;
+	rc = rhashtable_init(&tc_info->flow_table, &tc_info->flow_ht_params);
+	if (rc)
+		goto free_tc_info;
+
+	tc_info->l2_ht_params = bnxt_tc_l2_ht_params;
+	rc = rhashtable_init(&tc_info->l2_table, &tc_info->l2_ht_params);
+	if (rc)
+		goto destroy_flow_table;
+
+	tc_info->decap_l2_ht_params = bnxt_tc_decap_l2_ht_params;
+	rc = rhashtable_init(&tc_info->decap_l2_table,
+			     &tc_info->decap_l2_ht_params);
+	if (rc)
+		goto destroy_l2_table;
+
+	tc_info->decap_ht_params = bnxt_tc_tunnel_ht_params;
+	rc = rhashtable_init(&tc_info->decap_table,
+			     &tc_info->decap_ht_params);
+	if (rc)
+		goto destroy_decap_l2_table;
+
+	tc_info->encap_ht_params = bnxt_tc_tunnel_ht_params;
+	rc = rhashtable_init(&tc_info->encap_table,
+			     &tc_info->encap_ht_params);
+	if (rc)
+		goto destroy_decap_table;
+
+	tc_info->enabled = true;
+	bp->dev->hw_features |= NETIF_F_HW_TC;
+	bp->dev->features |= NETIF_F_HW_TC;
+	bp->tc_info = tc_info;
+	return 0;
+
+destroy_decap_table:
+	rhashtable_destroy(&tc_info->decap_table);
+destroy_decap_l2_table:
+	rhashtable_destroy(&tc_info->decap_l2_table);
+destroy_l2_table:
+	rhashtable_destroy(&tc_info->l2_table);
+destroy_flow_table:
+	rhashtable_destroy(&tc_info->flow_table);
+free_tc_info:
+	kfree(tc_info);
+	return rc;
+}
+
+void bnxt_shutdown_tc(struct bnxt *bp)
+{
+	struct bnxt_tc_info *tc_info = bp->tc_info;
+
+	if (!bnxt_tc_flower_enabled(bp))
+		return;
+
+	rhashtable_destroy(&tc_info->flow_table);
+	rhashtable_destroy(&tc_info->l2_table);
+	rhashtable_destroy(&tc_info->decap_l2_table);
+	rhashtable_destroy(&tc_info->decap_table);
+	rhashtable_destroy(&tc_info->encap_table);
+	kfree(tc_info);
+	bp->tc_info = NULL;
+}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
new file mode 100644
index 000000000000..97e09a880693
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
@@ -0,0 +1,230 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_TC_H
+#define BNXT_TC_H
+
+#ifdef CONFIG_BNXT_FLOWER_OFFLOAD
+
+#include <net/ip_tunnels.h>
+
+/* Structs used for storing the filter/actions of the TC cmd.
+ */
+struct bnxt_tc_l2_key {
+	u8		dmac[ETH_ALEN];
+	u8		smac[ETH_ALEN];
+	__be16		inner_vlan_tpid;
+	__be16		inner_vlan_tci;
+	__be16		ether_type;
+	u8		num_vlans;
+};
+
+struct bnxt_tc_l3_key {
+	union {
+		struct {
+			struct in_addr daddr;
+			struct in_addr saddr;
+		} ipv4;
+		struct {
+			struct in6_addr daddr;
+			struct in6_addr saddr;
+		} ipv6;
+	};
+};
+
+struct bnxt_tc_l4_key {
+	u8  ip_proto;
+	union {
+		struct {
+			__be16 sport;
+			__be16 dport;
+		} ports;
+		struct {
+			u8 type;
+			u8 code;
+		} icmp;
+	};
+};
+
+struct bnxt_tc_tunnel_key {
+	struct bnxt_tc_l2_key	l2;
+	struct bnxt_tc_l3_key	l3;
+	struct bnxt_tc_l4_key	l4;
+	__be32			id;
+};
+
+struct bnxt_tc_actions {
+	u32				flags;
+#define BNXT_TC_ACTION_FLAG_FWD			BIT(0)
+#define BNXT_TC_ACTION_FLAG_FWD_VXLAN		BIT(1)
+#define BNXT_TC_ACTION_FLAG_PUSH_VLAN		BIT(3)
+#define BNXT_TC_ACTION_FLAG_POP_VLAN		BIT(4)
+#define BNXT_TC_ACTION_FLAG_DROP		BIT(5)
+#define BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP	BIT(6)
+#define BNXT_TC_ACTION_FLAG_TUNNEL_DECAP	BIT(7)
+
+	u16				dst_fid;
+	struct net_device		*dst_dev;
+	__be16				push_vlan_tpid;
+	__be16				push_vlan_tci;
+
+	/* tunnel encap */
+	struct ip_tunnel_key		tun_encap_key;
+};
+
+struct bnxt_tc_flow {
+	u32				flags;
+#define BNXT_TC_FLOW_FLAGS_ETH_ADDRS		BIT(1)
+#define BNXT_TC_FLOW_FLAGS_IPV4_ADDRS		BIT(2)
+#define BNXT_TC_FLOW_FLAGS_IPV6_ADDRS		BIT(3)
+#define BNXT_TC_FLOW_FLAGS_PORTS		BIT(4)
+#define BNXT_TC_FLOW_FLAGS_ICMP			BIT(5)
+#define BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS	BIT(6)
+#define BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS	BIT(7)
+#define BNXT_TC_FLOW_FLAGS_TUNL_IPV6_ADDRS	BIT(8)
+#define BNXT_TC_FLOW_FLAGS_TUNL_PORTS		BIT(9)
+#define BNXT_TC_FLOW_FLAGS_TUNL_ID		BIT(10)
+#define BNXT_TC_FLOW_FLAGS_TUNNEL	(BNXT_TC_FLOW_FLAGS_TUNL_ETH_ADDRS | \
+					 BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS | \
+					 BNXT_TC_FLOW_FLAGS_TUNL_IPV6_ADDRS |\
+					 BNXT_TC_FLOW_FLAGS_TUNL_PORTS |\
+					 BNXT_TC_FLOW_FLAGS_TUNL_ID)
+
+	/* flow applicable to pkts ingressing on this fid */
+	u16				src_fid;
+	struct bnxt_tc_l2_key		l2_key;
+	struct bnxt_tc_l2_key		l2_mask;
+	struct bnxt_tc_l3_key		l3_key;
+	struct bnxt_tc_l3_key		l3_mask;
+	struct bnxt_tc_l4_key		l4_key;
+	struct bnxt_tc_l4_key		l4_mask;
+	struct ip_tunnel_key		tun_key;
+	struct ip_tunnel_key		tun_mask;
+
+	struct bnxt_tc_actions		actions;
+
+	/* updated stats accounting for hw-counter wrap-around */
+	struct bnxt_tc_flow_stats	stats;
+	/* previous snap-shot of stats */
+	struct bnxt_tc_flow_stats	prev_stats;
+	unsigned long			lastused; /* jiffies */
+	/* for calculating delta from prev_stats and
+	 * updating prev_stats atomically.
+	 */
+	spinlock_t			stats_lock;
+};
+
+/* Tunnel encap/decap hash table
+ * This table is used to maintain a list of flows that use
+ * the same tunnel encap/decap params (ip_daddrs, vni, udp_dport)
+ * and the FW returned handle.
+ * A separate table is maintained for encap and decap
+ */
+struct bnxt_tc_tunnel_node {
+	struct ip_tunnel_key		key;
+	struct rhash_head		node;
+
+	/* tunnel l2 info */
+	struct bnxt_tc_l2_key		l2_info;
+
+#define	INVALID_TUNNEL_HANDLE		cpu_to_le32(0xffffffff)
+	/* tunnel handle returned by FW */
+	__le32				tunnel_handle;
+
+	u32				refcount;
+	struct rcu_head			rcu;
+};
+
+/* L2 hash table
+ * The same data-struct is used for L2-flow table and L2-tunnel table.
+ * The L2 part of a flow or tunnel is stored in a hash table.
+ * A flow that shares the same L2 key/mask with an
+ * already existing flow/tunnel must refer to it's flow handle or
+ * decap_filter_id respectively.
+ */
+struct bnxt_tc_l2_node {
+	/* hash key: first 16b of key */
+#define BNXT_TC_L2_KEY_LEN			16
+	struct bnxt_tc_l2_key	key;
+	struct rhash_head	node;
+
+	/* a linked list of flows that share the same l2 key */
+	struct list_head	common_l2_flows;
+
+	/* number of flows/tunnels sharing the l2 key */
+	u16			refcount;
+
+	struct rcu_head		rcu;
+};
+
+struct bnxt_tc_flow_node {
+	/* hash key: provided by TC */
+	unsigned long			cookie;
+	struct rhash_head		node;
+
+	struct bnxt_tc_flow		flow;
+
+	__le16				flow_handle;
+
+	/* L2 node in l2 hashtable that shares flow's l2 key */
+	struct bnxt_tc_l2_node		*l2_node;
+	/* for the shared_flows list maintained in l2_node */
+	struct list_head		l2_list_node;
+
+	/* tunnel encap related */
+	struct bnxt_tc_tunnel_node	*encap_node;
+
+	/* tunnel decap related */
+	struct bnxt_tc_tunnel_node	*decap_node;
+	/* L2 node in tunnel-l2 hashtable that shares flow's tunnel l2 key */
+	struct bnxt_tc_l2_node		*decap_l2_node;
+	/* for the shared_flows list maintained in tunnel decap l2_node */
+	struct list_head		decap_l2_list_node;
+
+	struct rcu_head			rcu;
+};
+
+int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
+			 struct tc_cls_flower_offload *cls_flower);
+int bnxt_init_tc(struct bnxt *bp);
+void bnxt_shutdown_tc(struct bnxt *bp);
+void bnxt_tc_flow_stats_work(struct bnxt *bp);
+
+static inline bool bnxt_tc_flower_enabled(struct bnxt *bp)
+{
+	return bp->tc_info && bp->tc_info->enabled;
+}
+
+#else /* CONFIG_BNXT_FLOWER_OFFLOAD */
+
+static inline int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
+				       struct tc_cls_flower_offload *cls_flower)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int bnxt_init_tc(struct bnxt *bp)
+{
+	return 0;
+}
+
+static inline void bnxt_shutdown_tc(struct bnxt *bp)
+{
+}
+
+static inline void bnxt_tc_flow_stats_work(struct bnxt *bp)
+{
+}
+
+static inline bool bnxt_tc_flower_enabled(struct bnxt *bp)
+{
+	return false;
+}
+#endif /* CONFIG_BNXT_FLOWER_OFFLOAD */
+#endif /* BNXT_TC_H */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 77da75a55c02..997e10e8b863 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -84,6 +84,8 @@ static int bnxt_unregister_dev(struct bnxt_en_dev *edev, int ulp_id)
 
 		max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp);
 		bnxt_set_max_func_stat_ctxs(bp, max_stat_ctxs + 1);
+		if (ulp->msix_requested)
+			edev->en_ops->bnxt_free_msix(edev, ulp_id);
 	}
 	if (ulp->max_async_event_id)
 		bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
new file mode 100644
index 000000000000..69186d188c43
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -0,0 +1,503 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2016-2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/jhash.h>
+#include <net/pkt_cls.h>
+
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+#include "bnxt_vfr.h"
+#include "bnxt_devlink.h"
+#include "bnxt_tc.h"
+
+#ifdef CONFIG_BNXT_SRIOV
+
+#define CFA_HANDLE_INVALID		0xffff
+#define VF_IDX_INVALID			0xffff
+
+static int hwrm_cfa_vfr_alloc(struct bnxt *bp, u16 vf_idx,
+			      u16 *tx_cfa_action, u16 *rx_cfa_code)
+{
+	struct hwrm_cfa_vfr_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_vfr_alloc_input req = { 0 };
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_VFR_ALLOC, -1, -1);
+	req.vf_id = cpu_to_le16(vf_idx);
+	sprintf(req.vfr_name, "vfr%d", vf_idx);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		*tx_cfa_action = le16_to_cpu(resp->tx_cfa_action);
+		*rx_cfa_code = le16_to_cpu(resp->rx_cfa_code);
+		netdev_dbg(bp->dev, "tx_cfa_action=0x%x, rx_cfa_code=0x%x",
+			   *tx_cfa_action, *rx_cfa_code);
+	} else {
+		netdev_info(bp->dev, "%s error rc=%d", __func__, rc);
+	}
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+static int hwrm_cfa_vfr_free(struct bnxt *bp, u16 vf_idx)
+{
+	struct hwrm_cfa_vfr_free_input req = { 0 };
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_VFR_FREE, -1, -1);
+	sprintf(req.vfr_name, "vfr%d", vf_idx);
+
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		netdev_info(bp->dev, "%s error rc=%d", __func__, rc);
+	return rc;
+}
+
+static int bnxt_vf_rep_open(struct net_device *dev)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+	struct bnxt *bp = vf_rep->bp;
+
+	/* Enable link and TX only if the parent PF is open. */
+	if (netif_running(bp->dev)) {
+		netif_carrier_on(dev);
+		netif_tx_start_all_queues(dev);
+	}
+	return 0;
+}
+
+static int bnxt_vf_rep_close(struct net_device *dev)
+{
+	netif_carrier_off(dev);
+	netif_tx_disable(dev);
+
+	return 0;
+}
+
+static netdev_tx_t bnxt_vf_rep_xmit(struct sk_buff *skb,
+				    struct net_device *dev)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+	int rc, len = skb->len;
+
+	skb_dst_drop(skb);
+	dst_hold((struct dst_entry *)vf_rep->dst);
+	skb_dst_set(skb, (struct dst_entry *)vf_rep->dst);
+	skb->dev = vf_rep->dst->u.port_info.lower_dev;
+
+	rc = dev_queue_xmit(skb);
+	if (!rc) {
+		vf_rep->tx_stats.packets++;
+		vf_rep->tx_stats.bytes += len;
+	}
+	return rc;
+}
+
+static void
+bnxt_vf_rep_get_stats64(struct net_device *dev,
+			struct rtnl_link_stats64 *stats)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+
+	stats->rx_packets = vf_rep->rx_stats.packets;
+	stats->rx_bytes = vf_rep->rx_stats.bytes;
+	stats->tx_packets = vf_rep->tx_stats.packets;
+	stats->tx_bytes = vf_rep->tx_stats.bytes;
+}
+
+static int bnxt_vf_rep_setup_tc_block_cb(enum tc_setup_type type,
+					 void *type_data,
+					 void *cb_priv)
+{
+	struct bnxt_vf_rep *vf_rep = cb_priv;
+	struct bnxt *bp = vf_rep->bp;
+	int vf_fid = bp->pf.vf[vf_rep->vf_idx].fw_fid;
+
+	if (!bnxt_tc_flower_enabled(vf_rep->bp) || !tc_can_offload(bp->dev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return bnxt_tc_setup_flower(bp, vf_fid, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int bnxt_vf_rep_setup_tc_block(struct net_device *dev,
+				      struct tc_block_offload *f)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block,
+					     bnxt_vf_rep_setup_tc_block_cb,
+					     vf_rep, vf_rep);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block,
+					bnxt_vf_rep_setup_tc_block_cb, vf_rep);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
+				void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return bnxt_vf_rep_setup_tc_block(dev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code)
+{
+	u16 vf_idx;
+
+	if (cfa_code && bp->cfa_code_map && BNXT_PF(bp)) {
+		vf_idx = bp->cfa_code_map[cfa_code];
+		if (vf_idx != VF_IDX_INVALID)
+			return bp->vf_reps[vf_idx]->dev;
+	}
+	return NULL;
+}
+
+void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(skb->dev);
+	struct bnxt_vf_rep_stats *rx_stats;
+
+	rx_stats = &vf_rep->rx_stats;
+	vf_rep->rx_stats.bytes += skb->len;
+	vf_rep->rx_stats.packets++;
+
+	netif_receive_skb(skb);
+}
+
+static int bnxt_vf_rep_get_phys_port_name(struct net_device *dev, char *buf,
+					  size_t len)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+	struct pci_dev *pf_pdev = vf_rep->bp->pdev;
+	int rc;
+
+	rc = snprintf(buf, len, "pf%dvf%d", PCI_FUNC(pf_pdev->devfn),
+		      vf_rep->vf_idx);
+	if (rc >= len)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static void bnxt_vf_rep_get_drvinfo(struct net_device *dev,
+				    struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+}
+
+static int bnxt_vf_rep_port_attr_get(struct net_device *dev,
+				     struct switchdev_attr *attr)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+
+	/* as only PORT_PARENT_ID is supported currently use common code
+	 * between PF and VF-rep for now.
+	 */
+	return bnxt_port_attr_get(vf_rep->bp, attr);
+}
+
+static const struct switchdev_ops bnxt_vf_rep_switchdev_ops = {
+	.switchdev_port_attr_get	= bnxt_vf_rep_port_attr_get
+};
+
+static const struct ethtool_ops bnxt_vf_rep_ethtool_ops = {
+	.get_drvinfo		= bnxt_vf_rep_get_drvinfo
+};
+
+static const struct net_device_ops bnxt_vf_rep_netdev_ops = {
+	.ndo_open		= bnxt_vf_rep_open,
+	.ndo_stop		= bnxt_vf_rep_close,
+	.ndo_start_xmit		= bnxt_vf_rep_xmit,
+	.ndo_get_stats64	= bnxt_vf_rep_get_stats64,
+	.ndo_setup_tc		= bnxt_vf_rep_setup_tc,
+	.ndo_get_phys_port_name = bnxt_vf_rep_get_phys_port_name
+};
+
+/* Called when the parent PF interface is closed:
+ * As the mode transition from SWITCHDEV to LEGACY
+ * happens under the rtnl_lock() this routine is safe
+ * under the rtnl_lock()
+ */
+void bnxt_vf_reps_close(struct bnxt *bp)
+{
+	struct bnxt_vf_rep *vf_rep;
+	u16 num_vfs, i;
+
+	if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		return;
+
+	num_vfs = pci_num_vf(bp->pdev);
+	for (i = 0; i < num_vfs; i++) {
+		vf_rep = bp->vf_reps[i];
+		if (netif_running(vf_rep->dev))
+			bnxt_vf_rep_close(vf_rep->dev);
+	}
+}
+
+/* Called when the parent PF interface is opened (re-opened):
+ * As the mode transition from SWITCHDEV to LEGACY
+ * happen under the rtnl_lock() this routine is safe
+ * under the rtnl_lock()
+ */
+void bnxt_vf_reps_open(struct bnxt *bp)
+{
+	int i;
+
+	if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		return;
+
+	for (i = 0; i < pci_num_vf(bp->pdev); i++)
+		bnxt_vf_rep_open(bp->vf_reps[i]->dev);
+}
+
+static void __bnxt_vf_reps_destroy(struct bnxt *bp)
+{
+	u16 num_vfs = pci_num_vf(bp->pdev);
+	struct bnxt_vf_rep *vf_rep;
+	int i;
+
+	for (i = 0; i < num_vfs; i++) {
+		vf_rep = bp->vf_reps[i];
+		if (vf_rep) {
+			dst_release((struct dst_entry *)vf_rep->dst);
+
+			if (vf_rep->tx_cfa_action != CFA_HANDLE_INVALID)
+				hwrm_cfa_vfr_free(bp, vf_rep->vf_idx);
+
+			if (vf_rep->dev) {
+				/* if register_netdev failed, then netdev_ops
+				 * would have been set to NULL
+				 */
+				if (vf_rep->dev->netdev_ops)
+					unregister_netdev(vf_rep->dev);
+				free_netdev(vf_rep->dev);
+			}
+		}
+	}
+
+	kfree(bp->vf_reps);
+	bp->vf_reps = NULL;
+}
+
+void bnxt_vf_reps_destroy(struct bnxt *bp)
+{
+	bool closed = false;
+
+	if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		return;
+
+	if (!bp->vf_reps)
+		return;
+
+	/* Ensure that parent PF's and VF-reps' RX/TX has been quiesced
+	 * before proceeding with VF-rep cleanup.
+	 */
+	rtnl_lock();
+	if (netif_running(bp->dev)) {
+		bnxt_close_nic(bp, false, false);
+		closed = true;
+	}
+	/* un-publish cfa_code_map so that RX path can't see it anymore */
+	kfree(bp->cfa_code_map);
+	bp->cfa_code_map = NULL;
+	bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+
+	if (closed)
+		bnxt_open_nic(bp, false, false);
+	rtnl_unlock();
+
+	/* Need to call vf_reps_destroy() outside of rntl_lock
+	 * as unregister_netdev takes rtnl_lock
+	 */
+	__bnxt_vf_reps_destroy(bp);
+}
+
+/* Use the OUI of the PF's perm addr and report the same mac addr
+ * for the same VF-rep each time
+ */
+static void bnxt_vf_rep_eth_addr_gen(u8 *src_mac, u16 vf_idx, u8 *mac)
+{
+	u32 addr;
+
+	ether_addr_copy(mac, src_mac);
+
+	addr = jhash(src_mac, ETH_ALEN, 0) + vf_idx;
+	mac[3] = (u8)(addr & 0xFF);
+	mac[4] = (u8)((addr >> 8) & 0xFF);
+	mac[5] = (u8)((addr >> 16) & 0xFF);
+}
+
+static void bnxt_vf_rep_netdev_init(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
+				    struct net_device *dev)
+{
+	struct net_device *pf_dev = bp->dev;
+
+	dev->netdev_ops = &bnxt_vf_rep_netdev_ops;
+	dev->ethtool_ops = &bnxt_vf_rep_ethtool_ops;
+	SWITCHDEV_SET_OPS(dev, &bnxt_vf_rep_switchdev_ops);
+	/* Just inherit all the featues of the parent PF as the VF-R
+	 * uses the RX/TX rings of the parent PF
+	 */
+	dev->hw_features = pf_dev->hw_features;
+	dev->gso_partial_features = pf_dev->gso_partial_features;
+	dev->vlan_features = pf_dev->vlan_features;
+	dev->hw_enc_features = pf_dev->hw_enc_features;
+	dev->features |= pf_dev->features;
+	bnxt_vf_rep_eth_addr_gen(bp->pf.mac_addr, vf_rep->vf_idx,
+				 dev->perm_addr);
+	ether_addr_copy(dev->dev_addr, dev->perm_addr);
+}
+
+static int bnxt_vf_reps_create(struct bnxt *bp)
+{
+	u16 *cfa_code_map = NULL, num_vfs = pci_num_vf(bp->pdev);
+	struct bnxt_vf_rep *vf_rep;
+	struct net_device *dev;
+	int rc, i;
+
+	bp->vf_reps = kcalloc(num_vfs, sizeof(vf_rep), GFP_KERNEL);
+	if (!bp->vf_reps)
+		return -ENOMEM;
+
+	/* storage for cfa_code to vf-idx mapping */
+	cfa_code_map = kmalloc(sizeof(*bp->cfa_code_map) * MAX_CFA_CODE,
+			       GFP_KERNEL);
+	if (!cfa_code_map) {
+		rc = -ENOMEM;
+		goto err;
+	}
+	for (i = 0; i < MAX_CFA_CODE; i++)
+		cfa_code_map[i] = VF_IDX_INVALID;
+
+	for (i = 0; i < num_vfs; i++) {
+		dev = alloc_etherdev(sizeof(*vf_rep));
+		if (!dev) {
+			rc = -ENOMEM;
+			goto err;
+		}
+
+		vf_rep = netdev_priv(dev);
+		bp->vf_reps[i] = vf_rep;
+		vf_rep->dev = dev;
+		vf_rep->bp = bp;
+		vf_rep->vf_idx = i;
+		vf_rep->tx_cfa_action = CFA_HANDLE_INVALID;
+
+		/* get cfa handles from FW */
+		rc = hwrm_cfa_vfr_alloc(bp, vf_rep->vf_idx,
+					&vf_rep->tx_cfa_action,
+					&vf_rep->rx_cfa_code);
+		if (rc) {
+			rc = -ENOLINK;
+			goto err;
+		}
+		cfa_code_map[vf_rep->rx_cfa_code] = vf_rep->vf_idx;
+
+		vf_rep->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+						 GFP_KERNEL);
+		if (!vf_rep->dst) {
+			rc = -ENOMEM;
+			goto err;
+		}
+		/* only cfa_action is needed to mux a packet while TXing */
+		vf_rep->dst->u.port_info.port_id = vf_rep->tx_cfa_action;
+		vf_rep->dst->u.port_info.lower_dev = bp->dev;
+
+		bnxt_vf_rep_netdev_init(bp, vf_rep, dev);
+		rc = register_netdev(dev);
+		if (rc) {
+			/* no need for unregister_netdev in cleanup */
+			dev->netdev_ops = NULL;
+			goto err;
+		}
+	}
+
+	/* publish cfa_code_map only after all VF-reps have been initialized */
+	bp->cfa_code_map = cfa_code_map;
+	bp->eswitch_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
+	netif_keep_dst(bp->dev);
+	return 0;
+
+err:
+	netdev_info(bp->dev, "%s error=%d", __func__, rc);
+	kfree(cfa_code_map);
+	__bnxt_vf_reps_destroy(bp);
+	return rc;
+}
+
+/* Devlink related routines */
+int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+	struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
+
+	*mode = bp->eswitch_mode;
+	return 0;
+}
+
+int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode)
+{
+	struct bnxt *bp = bnxt_get_bp_from_dl(devlink);
+	int rc = 0;
+
+	mutex_lock(&bp->sriov_lock);
+	if (bp->eswitch_mode == mode) {
+		netdev_info(bp->dev, "already in %s eswitch mode",
+			    mode == DEVLINK_ESWITCH_MODE_LEGACY ?
+			    "legacy" : "switchdev");
+		rc = -EINVAL;
+		goto done;
+	}
+
+	switch (mode) {
+	case DEVLINK_ESWITCH_MODE_LEGACY:
+		bnxt_vf_reps_destroy(bp);
+		break;
+
+	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+		if (pci_num_vf(bp->pdev) == 0) {
+			netdev_info(bp->dev,
+				    "Enable VFs before setting switchdev mode");
+			rc = -EPERM;
+			goto done;
+		}
+		rc = bnxt_vf_reps_create(bp);
+		break;
+
+	default:
+		rc = -EINVAL;
+		goto done;
+	}
+done:
+	mutex_unlock(&bp->sriov_lock);
+	return rc;
+}
+
+#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
new file mode 100644
index 000000000000..fb06bbe70e42
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
@@ -0,0 +1,58 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2016-2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_VFR_H
+#define BNXT_VFR_H
+
+#ifdef CONFIG_BNXT_SRIOV
+
+#define	MAX_CFA_CODE			65536
+
+void bnxt_vf_reps_destroy(struct bnxt *bp);
+void bnxt_vf_reps_close(struct bnxt *bp);
+void bnxt_vf_reps_open(struct bnxt *bp);
+void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb);
+struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code);
+
+static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+	struct bnxt *bp = vf_rep->bp;
+
+	return bp->pf.vf[vf_rep->vf_idx].fw_fid;
+}
+
+int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode);
+int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode);
+
+#else
+
+static inline void bnxt_vf_reps_close(struct bnxt *bp)
+{
+}
+
+static inline void bnxt_vf_reps_open(struct bnxt *bp)
+{
+}
+
+static inline void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb)
+{
+}
+
+static inline struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code)
+{
+	return NULL;
+}
+
+static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev)
+{
+	return 0;
+}
+#endif /* CONFIG_BNXT_SRIOV */
+#endif /* BNXT_VFR_H */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 3961a6807454..261e5847557a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -94,6 +94,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 
 	xdp.data_hard_start = *data_ptr - offset;
 	xdp.data = *data_ptr;
+	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = *data_ptr + *len;
 	orig_data = xdp.data;
 	mapping = rx_buf->mapping - bp->rx_dma_offset;
@@ -169,8 +170,8 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	tc = netdev_get_num_tc(dev);
 	if (!tc)
 		tc = 1;
-	rc = bnxt_reserve_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
-				true, tc, tx_xdp);
+	rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
+			      true, tc, tx_xdp);
 	if (rc) {
 		netdev_warn(dev, "Unable to reserve enough TX rings to support XDP.\n");
 		return rc;
@@ -207,7 +208,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	return 0;
 }
 
-int bnxt_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	int rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 12a5ad66b564..414b748038ca 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -16,6 +16,6 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		 struct page *page, u8 **data_ptr, unsigned int *len,
 		 u8 *event);
-int bnxt_xdp(struct net_device *dev, struct netdev_xdp *xdp);
+int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp);
 
 #endif
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index cec94bbb2ea5..8bc126a156e8 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -1278,7 +1278,7 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev)
 
 	ret = cnic_alloc_dma(dev, kwq_16_dma, pages, 0);
 	if (ret)
-		return -ENOMEM;
+		goto error;
 
 	n = CNIC_PAGE_SIZE / CNIC_KWQ16_DATA_SIZE;
 	for (i = 0, j = 0; i < cp->max_cid_space; i++) {
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 7b0b399aaedd..24b4f4ceceef 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -72,23 +72,42 @@
 #define GENET_RDMA_REG_OFF	(priv->hw_params->rdma_offset + \
 				TOTAL_DESC * DMA_DESC_SIZE)
 
+static inline void bcmgenet_writel(u32 value, void __iomem *offset)
+{
+	/* MIPS chips strapped for BE will automagically configure the
+	 * peripheral registers for CPU-native byte order.
+	 */
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		__raw_writel(value, offset);
+	else
+		writel_relaxed(value, offset);
+}
+
+static inline u32 bcmgenet_readl(void __iomem *offset)
+{
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		return __raw_readl(offset);
+	else
+		return readl_relaxed(offset);
+}
+
 static inline void dmadesc_set_length_status(struct bcmgenet_priv *priv,
 					     void __iomem *d, u32 value)
 {
-	__raw_writel(value, d + DMA_DESC_LENGTH_STATUS);
+	bcmgenet_writel(value, d + DMA_DESC_LENGTH_STATUS);
 }
 
 static inline u32 dmadesc_get_length_status(struct bcmgenet_priv *priv,
 					    void __iomem *d)
 {
-	return __raw_readl(d + DMA_DESC_LENGTH_STATUS);
+	return bcmgenet_readl(d + DMA_DESC_LENGTH_STATUS);
 }
 
 static inline void dmadesc_set_addr(struct bcmgenet_priv *priv,
 				    void __iomem *d,
 				    dma_addr_t addr)
 {
-	__raw_writel(lower_32_bits(addr), d + DMA_DESC_ADDRESS_LO);
+	bcmgenet_writel(lower_32_bits(addr), d + DMA_DESC_ADDRESS_LO);
 
 	/* Register writes to GISB bus can take couple hundred nanoseconds
 	 * and are done for each packet, save these expensive writes unless
@@ -96,7 +115,7 @@ static inline void dmadesc_set_addr(struct bcmgenet_priv *priv,
 	 */
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 	if (priv->hw_params->flags & GENET_HAS_40BITS)
-		__raw_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI);
+		bcmgenet_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI);
 #endif
 }
 
@@ -113,7 +132,7 @@ static inline dma_addr_t dmadesc_get_addr(struct bcmgenet_priv *priv,
 {
 	dma_addr_t addr;
 
-	addr = __raw_readl(d + DMA_DESC_ADDRESS_LO);
+	addr = bcmgenet_readl(d + DMA_DESC_ADDRESS_LO);
 
 	/* Register writes to GISB bus can take couple hundred nanoseconds
 	 * and are done for each packet, save these expensive writes unless
@@ -121,7 +140,7 @@ static inline dma_addr_t dmadesc_get_addr(struct bcmgenet_priv *priv,
 	 */
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 	if (priv->hw_params->flags & GENET_HAS_40BITS)
-		addr |= (u64)__raw_readl(d + DMA_DESC_ADDRESS_HI) << 32;
+		addr |= (u64)bcmgenet_readl(d + DMA_DESC_ADDRESS_HI) << 32;
 #endif
 	return addr;
 }
@@ -156,8 +175,8 @@ static inline u32 bcmgenet_tbuf_ctrl_get(struct bcmgenet_priv *priv)
 	if (GENET_IS_V1(priv))
 		return bcmgenet_rbuf_readl(priv, TBUF_CTRL_V1);
 	else
-		return __raw_readl(priv->base +
-				priv->hw_params->tbuf_offset + TBUF_CTRL);
+		return bcmgenet_readl(priv->base +
+				      priv->hw_params->tbuf_offset + TBUF_CTRL);
 }
 
 static inline void bcmgenet_tbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val)
@@ -165,7 +184,7 @@ static inline void bcmgenet_tbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val)
 	if (GENET_IS_V1(priv))
 		bcmgenet_rbuf_writel(priv, val, TBUF_CTRL_V1);
 	else
-		__raw_writel(val, priv->base +
+		bcmgenet_writel(val, priv->base +
 				priv->hw_params->tbuf_offset + TBUF_CTRL);
 }
 
@@ -174,8 +193,8 @@ static inline u32 bcmgenet_bp_mc_get(struct bcmgenet_priv *priv)
 	if (GENET_IS_V1(priv))
 		return bcmgenet_rbuf_readl(priv, TBUF_BP_MC_V1);
 	else
-		return __raw_readl(priv->base +
-				priv->hw_params->tbuf_offset + TBUF_BP_MC);
+		return bcmgenet_readl(priv->base +
+				      priv->hw_params->tbuf_offset + TBUF_BP_MC);
 }
 
 static inline void bcmgenet_bp_mc_set(struct bcmgenet_priv *priv, u32 val)
@@ -183,7 +202,7 @@ static inline void bcmgenet_bp_mc_set(struct bcmgenet_priv *priv, u32 val)
 	if (GENET_IS_V1(priv))
 		bcmgenet_rbuf_writel(priv, val, TBUF_BP_MC_V1);
 	else
-		__raw_writel(val, priv->base +
+		bcmgenet_writel(val, priv->base +
 				priv->hw_params->tbuf_offset + TBUF_BP_MC);
 }
 
@@ -326,28 +345,28 @@ static inline struct bcmgenet_priv *dev_to_priv(struct device *dev)
 static inline u32 bcmgenet_tdma_readl(struct bcmgenet_priv *priv,
 				      enum dma_reg r)
 {
-	return __raw_readl(priv->base + GENET_TDMA_REG_OFF +
-			DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
+	return bcmgenet_readl(priv->base + GENET_TDMA_REG_OFF +
+			      DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
 }
 
 static inline void bcmgenet_tdma_writel(struct bcmgenet_priv *priv,
 					u32 val, enum dma_reg r)
 {
-	__raw_writel(val, priv->base + GENET_TDMA_REG_OFF +
+	bcmgenet_writel(val, priv->base + GENET_TDMA_REG_OFF +
 			DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
 }
 
 static inline u32 bcmgenet_rdma_readl(struct bcmgenet_priv *priv,
 				      enum dma_reg r)
 {
-	return __raw_readl(priv->base + GENET_RDMA_REG_OFF +
-			DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
+	return bcmgenet_readl(priv->base + GENET_RDMA_REG_OFF +
+			      DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
 }
 
 static inline void bcmgenet_rdma_writel(struct bcmgenet_priv *priv,
 					u32 val, enum dma_reg r)
 {
-	__raw_writel(val, priv->base + GENET_RDMA_REG_OFF +
+	bcmgenet_writel(val, priv->base + GENET_RDMA_REG_OFF +
 			DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
 }
 
@@ -418,16 +437,16 @@ static inline u32 bcmgenet_tdma_ring_readl(struct bcmgenet_priv *priv,
 					   unsigned int ring,
 					   enum dma_ring_reg r)
 {
-	return __raw_readl(priv->base + GENET_TDMA_REG_OFF +
-			(DMA_RING_SIZE * ring) +
-			genet_dma_ring_regs[r]);
+	return bcmgenet_readl(priv->base + GENET_TDMA_REG_OFF +
+			      (DMA_RING_SIZE * ring) +
+			      genet_dma_ring_regs[r]);
 }
 
 static inline void bcmgenet_tdma_ring_writel(struct bcmgenet_priv *priv,
 					     unsigned int ring, u32 val,
 					     enum dma_ring_reg r)
 {
-	__raw_writel(val, priv->base + GENET_TDMA_REG_OFF +
+	bcmgenet_writel(val, priv->base + GENET_TDMA_REG_OFF +
 			(DMA_RING_SIZE * ring) +
 			genet_dma_ring_regs[r]);
 }
@@ -436,16 +455,16 @@ static inline u32 bcmgenet_rdma_ring_readl(struct bcmgenet_priv *priv,
 					   unsigned int ring,
 					   enum dma_ring_reg r)
 {
-	return __raw_readl(priv->base + GENET_RDMA_REG_OFF +
-			(DMA_RING_SIZE * ring) +
-			genet_dma_ring_regs[r]);
+	return bcmgenet_readl(priv->base + GENET_RDMA_REG_OFF +
+			      (DMA_RING_SIZE * ring) +
+			      genet_dma_ring_regs[r]);
 }
 
 static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv,
 					     unsigned int ring, u32 val,
 					     enum dma_ring_reg r)
 {
-	__raw_writel(val, priv->base + GENET_RDMA_REG_OFF +
+	bcmgenet_writel(val, priv->base + GENET_RDMA_REG_OFF +
 			(DMA_RING_SIZE * ring) +
 			genet_dma_ring_regs[r]);
 }
@@ -469,15 +488,13 @@ static void bcmgenet_complete(struct net_device *dev)
 static int bcmgenet_get_link_ksettings(struct net_device *dev,
 				       struct ethtool_link_ksettings *cmd)
 {
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	if (!priv->phydev)
+	if (!dev->phydev)
 		return -ENODEV;
 
-	phy_ethtool_ksettings_get(priv->phydev, cmd);
+	phy_ethtool_ksettings_get(dev->phydev, cmd);
 
 	return 0;
 }
@@ -485,15 +502,13 @@ static int bcmgenet_get_link_ksettings(struct net_device *dev,
 static int bcmgenet_set_link_ksettings(struct net_device *dev,
 				       const struct ethtool_link_ksettings *cmd)
 {
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	if (!priv->phydev)
+	if (!dev->phydev)
 		return -ENODEV;
 
-	return phy_ethtool_ksettings_set(priv->phydev, cmd);
+	return phy_ethtool_ksettings_set(dev->phydev, cmd);
 }
 
 static int bcmgenet_set_rx_csum(struct net_device *dev,
@@ -991,12 +1006,12 @@ static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable)
 	bcmgenet_umac_writel(priv, reg, UMAC_EEE_CTRL);
 
 	/* Enable EEE and switch to a 27Mhz clock automatically */
-	reg = __raw_readl(priv->base + off);
+	reg = bcmgenet_readl(priv->base + off);
 	if (enable)
 		reg |= TBUF_EEE_EN | TBUF_PM_EN;
 	else
 		reg &= ~(TBUF_EEE_EN | TBUF_PM_EN);
-	__raw_writel(reg, priv->base + off);
+	bcmgenet_writel(reg, priv->base + off);
 
 	/* Do the same for thing for RBUF */
 	reg = bcmgenet_rbuf_readl(priv, RBUF_ENERGY_CTRL);
@@ -1023,11 +1038,14 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e)
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
 
+	if (!dev->phydev)
+		return -ENODEV;
+
 	e->eee_enabled = p->eee_enabled;
 	e->eee_active = p->eee_active;
 	e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER);
 
-	return phy_ethtool_get_eee(priv->phydev, e);
+	return phy_ethtool_get_eee(dev->phydev, e);
 }
 
 static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
@@ -1039,12 +1057,15 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
 
+	if (!dev->phydev)
+		return -ENODEV;
+
 	p->eee_enabled = e->eee_enabled;
 
 	if (!p->eee_enabled) {
 		bcmgenet_eee_enable_set(dev, false);
 	} else {
-		ret = phy_init_eee(priv->phydev, 0);
+		ret = phy_init_eee(dev->phydev, 0);
 		if (ret) {
 			netif_err(priv, hw, dev, "EEE initialization failed\n");
 			return ret;
@@ -1054,7 +1075,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
 		bcmgenet_eee_enable_set(dev, true);
 	}
 
-	return phy_ethtool_set_eee(priv->phydev, e);
+	return phy_ethtool_set_eee(dev->phydev, e);
 }
 
 /* standard ethtool support functions. */
@@ -1088,7 +1109,7 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 
 	switch (mode) {
 	case GENET_POWER_CABLE_SENSE:
-		phy_detach(priv->phydev);
+		phy_detach(priv->dev->phydev);
 		break;
 
 	case GENET_POWER_WOL_MAGIC:
@@ -1153,7 +1174,6 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 		}
 		bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
 		bcmgenet_phy_power_set(priv->dev, true);
-		bcmgenet_mii_reset(priv->dev);
 		break;
 
 	case GENET_POWER_CABLE_SENSE:
@@ -1174,15 +1194,13 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 /* ioctl handle special commands that are not present in ethtool. */
 static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	if (!priv->phydev)
+	if (!dev->phydev)
 		return -ENODEV;
 
-	return phy_mii_ioctl(priv->phydev, rq, cmd);
+	return phy_mii_ioctl(dev->phydev, rq, cmd);
 }
 
 static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
@@ -1360,7 +1378,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 		if (skb) {
 			pkts_compl++;
 			bytes_compl += GENET_CB(skb)->bytes_sent;
-			dev_kfree_skb_any(skb);
+			dev_consume_skb_any(skb);
 		}
 
 		txbds_processed++;
@@ -1386,11 +1404,10 @@ static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
 				struct bcmgenet_tx_ring *ring)
 {
 	unsigned int released;
-	unsigned long flags;
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock_bh(&ring->lock);
 	released = __bcmgenet_tx_reclaim(dev, ring);
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock_bh(&ring->lock);
 
 	return released;
 }
@@ -1401,15 +1418,14 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 		container_of(napi, struct bcmgenet_tx_ring, napi);
 	unsigned int work_done = 0;
 	struct netdev_queue *txq;
-	unsigned long flags;
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock(&ring->lock);
 	work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
 	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
 		txq = netdev_get_tx_queue(ring->priv->dev, ring->queue);
 		netif_tx_wake_queue(txq);
 	}
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock(&ring->lock);
 
 	if (work_done == 0) {
 		napi_complete(napi);
@@ -1504,7 +1520,6 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct bcmgenet_tx_ring *ring = NULL;
 	struct enet_cb *tx_cb_ptr;
 	struct netdev_queue *txq;
-	unsigned long flags = 0;
 	int nr_frags, index;
 	dma_addr_t mapping;
 	unsigned int size;
@@ -1531,7 +1546,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock(&ring->lock);
 	if (ring->free_bds <= (nr_frags + 1)) {
 		if (!netif_tx_queue_stopped(txq)) {
 			netif_tx_stop_queue(txq);
@@ -1565,8 +1580,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	for (i = 0; i <= nr_frags; i++) {
 		tx_cb_ptr = bcmgenet_get_txcb(priv, ring);
 
-		if (unlikely(!tx_cb_ptr))
-			BUG();
+		BUG_ON(!tx_cb_ptr);
 
 		if (!i) {
 			/* Transmit single SKB or head of fragment list */
@@ -1626,7 +1640,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		bcmgenet_tdma_ring_writel(priv, ring->index,
 					  ring->prod_index, TDMA_PROD_INDEX);
 out:
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock(&ring->lock);
 
 	return ret;
 
@@ -1875,7 +1889,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv,
 		cb = ring->cbs + i;
 		skb = bcmgenet_rx_refill(priv, cb);
 		if (skb)
-			dev_kfree_skb_any(skb);
+			dev_consume_skb_any(skb);
 		if (!cb->skb)
 			return -ENOMEM;
 	}
@@ -1894,7 +1908,7 @@ static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
 
 		skb = bcmgenet_free_rx_cb(&priv->pdev->dev, cb);
 		if (skb)
-			dev_kfree_skb_any(skb);
+			dev_consume_skb_any(skb);
 	}
 }
 
@@ -1916,12 +1930,8 @@ static void umac_enable_set(struct bcmgenet_priv *priv, u32 mask, bool enable)
 		usleep_range(1000, 2000);
 }
 
-static int reset_umac(struct bcmgenet_priv *priv)
+static void reset_umac(struct bcmgenet_priv *priv)
 {
-	struct device *kdev = &priv->pdev->dev;
-	unsigned int timeout = 0;
-	u32 reg;
-
 	/* 7358a0/7552a0: bad default in RBUF_FLUSH_CTRL.umac_sw_rst */
 	bcmgenet_rbuf_ctrl_set(priv, 0);
 	udelay(10);
@@ -1929,23 +1939,10 @@ static int reset_umac(struct bcmgenet_priv *priv)
 	/* disable MAC while updating its registers */
 	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 
-	/* issue soft reset, wait for it to complete */
-	bcmgenet_umac_writel(priv, CMD_SW_RESET, UMAC_CMD);
-	while (timeout++ < 1000) {
-		reg = bcmgenet_umac_readl(priv, UMAC_CMD);
-		if (!(reg & CMD_SW_RESET))
-			return 0;
-
-		udelay(1);
-	}
-
-	if (timeout == 1000) {
-		dev_err(kdev,
-			"timeout waiting for MAC to come out of reset\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
+	/* issue soft reset with (rg)mii loopback to ensure a stable rxclk */
+	bcmgenet_umac_writel(priv, CMD_SW_RESET | CMD_LCL_LOOP_EN, UMAC_CMD);
+	udelay(2);
+	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 }
 
 static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
@@ -1975,20 +1972,16 @@ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 }
 
-static int init_umac(struct bcmgenet_priv *priv)
+static void init_umac(struct bcmgenet_priv *priv)
 {
 	struct device *kdev = &priv->pdev->dev;
-	int ret;
 	u32 reg;
 	u32 int0_enable = 0;
 
 	dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n");
 
-	ret = reset_umac(priv);
-	if (ret)
-		return ret;
+	reset_umac(priv);
 
-	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 	/* clear tx/rx counter */
 	bcmgenet_umac_writel(priv,
 			     MIB_RESET_RX | MIB_RESET_TX | MIB_RESET_RUNT,
@@ -2027,8 +2020,6 @@ static int init_umac(struct bcmgenet_priv *priv)
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 
 	dev_dbg(kdev, "done init umac\n");
-
-	return 0;
 }
 
 /* Initialize a Tx ring along with corresponding hardware registers */
@@ -2085,6 +2076,10 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 				  TDMA_WRITE_PTR);
 	bcmgenet_tdma_ring_writel(priv, index, end_ptr * words_per_bd - 1,
 				  DMA_END_ADDR);
+
+	/* Initialize Tx NAPI */
+	netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
+		       NAPI_POLL_WEIGHT);
 }
 
 /* Initialize a RDMA ring */
@@ -2116,6 +2111,10 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 	if (ret)
 		return ret;
 
+	/* Initialize Rx NAPI */
+	netif_napi_add(priv->dev, &ring->napi, bcmgenet_rx_poll,
+		       NAPI_POLL_WEIGHT);
+
 	bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_PROD_INDEX);
 	bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_CONS_INDEX);
 	bcmgenet_rdma_ring_writel(priv, index, 1, DMA_MBUF_DONE_THRESH);
@@ -2140,50 +2139,27 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 	return ret;
 }
 
-static void bcmgenet_init_tx_napi(struct bcmgenet_priv *priv)
-{
-	unsigned int i;
-	struct bcmgenet_tx_ring *ring;
-
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
-		ring = &priv->tx_rings[i];
-		netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, 64);
-	}
-
-	ring = &priv->tx_rings[DESC_INDEX];
-	netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, 64);
-}
-
 static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
-	u32 int0_enable = UMAC_IRQ_TXDMA_DONE;
-	u32 int1_enable = 0;
 	struct bcmgenet_tx_ring *ring;
 
 	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_enable(&ring->napi);
-		int1_enable |= (1 << i);
+		ring->int_enable(ring);
 	}
 
 	ring = &priv->tx_rings[DESC_INDEX];
 	napi_enable(&ring->napi);
-
-	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
-	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
+	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
-	u32 int0_disable = UMAC_IRQ_TXDMA_DONE;
-	u32 int1_disable = 0xffff;
 	struct bcmgenet_tx_ring *ring;
 
-	bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
-	bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
-
 	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_disable(&ring->napi);
@@ -2267,9 +2243,6 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 	bcmgenet_tdma_writel(priv, dma_priority[1], DMA_PRIORITY_1);
 	bcmgenet_tdma_writel(priv, dma_priority[2], DMA_PRIORITY_2);
 
-	/* Initialize Tx NAPI */
-	bcmgenet_init_tx_napi(priv);
-
 	/* Enable Tx queues */
 	bcmgenet_tdma_writel(priv, ring_cfg, DMA_RING_CFG);
 
@@ -2279,50 +2252,27 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 	bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
 }
 
-static void bcmgenet_init_rx_napi(struct bcmgenet_priv *priv)
-{
-	unsigned int i;
-	struct bcmgenet_rx_ring *ring;
-
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
-		ring = &priv->rx_rings[i];
-		netif_napi_add(priv->dev, &ring->napi, bcmgenet_rx_poll, 64);
-	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	netif_napi_add(priv->dev, &ring->napi, bcmgenet_rx_poll, 64);
-}
-
 static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
-	u32 int0_enable = UMAC_IRQ_RXDMA_DONE;
-	u32 int1_enable = 0;
 	struct bcmgenet_rx_ring *ring;
 
 	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_enable(&ring->napi);
-		int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i));
+		ring->int_enable(ring);
 	}
 
 	ring = &priv->rx_rings[DESC_INDEX];
 	napi_enable(&ring->napi);
-
-	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
-	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
+	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
-	u32 int0_disable = UMAC_IRQ_RXDMA_DONE;
-	u32 int1_disable = 0xffff << UMAC_IRQ1_RX_INTR_SHIFT;
 	struct bcmgenet_rx_ring *ring;
 
-	bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
-	bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
-
 	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_disable(&ring->napi);
@@ -2395,9 +2345,6 @@ static int bcmgenet_init_rx_queues(struct net_device *dev)
 	ring_cfg |= (1 << DESC_INDEX);
 	dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));
 
-	/* Initialize Rx NAPI */
-	bcmgenet_init_rx_napi(priv);
-
 	/* Enable rings */
 	bcmgenet_rdma_writel(priv, ring_cfg, DMA_RING_CFG);
 
@@ -2486,9 +2433,6 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 	bcmgenet_fini_rx_napi(priv);
 	bcmgenet_fini_tx_napi(priv);
 
-	/* disable DMA */
-	bcmgenet_dma_teardown(priv);
-
 	for (i = 0; i < priv->num_tx_bds; i++) {
 		cb = priv->tx_cbs + i;
 		skb = bcmgenet_free_tx_cb(&priv->pdev->dev, cb);
@@ -2571,27 +2515,20 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
 /* Interrupt bottom half */
 static void bcmgenet_irq_task(struct work_struct *work)
 {
-	unsigned long flags;
 	unsigned int status;
 	struct bcmgenet_priv *priv = container_of(
 			work, struct bcmgenet_priv, bcmgenet_irq_work);
 
 	netif_dbg(priv, intr, priv->dev, "%s\n", __func__);
 
-	spin_lock_irqsave(&priv->lock, flags);
+	spin_lock_irq(&priv->lock);
 	status = priv->irq0_stat;
 	priv->irq0_stat = 0;
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	if (status & UMAC_IRQ_MPD_R) {
-		netif_dbg(priv, wol, priv->dev,
-			  "magic packet detected, waking up\n");
-		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
-	}
+	spin_unlock_irq(&priv->lock);
 
 	/* Link UP/DOWN event */
 	if (status & UMAC_IRQ_LINK_EVENT)
-		phy_mac_interrupt(priv->phydev,
+		phy_mac_interrupt(priv->dev->phydev,
 				  !!(status & UMAC_IRQ_LINK_UP));
 }
 
@@ -2679,23 +2616,13 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 		}
 	}
 
-	if (priv->irq0_stat & (UMAC_IRQ_PHY_DET_R |
-				UMAC_IRQ_PHY_DET_F |
-				UMAC_IRQ_LINK_EVENT |
-				UMAC_IRQ_HFB_SM |
-				UMAC_IRQ_HFB_MM)) {
-		/* all other interested interrupts handled in bottom half */
-		schedule_work(&priv->bcmgenet_irq_work);
-	}
-
 	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
 		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
 		wake_up(&priv->wq);
 	}
 
 	/* all other interested interrupts handled in bottom half */
-	status &= (UMAC_IRQ_LINK_EVENT |
-		   UMAC_IRQ_MPD_R);
+	status &= UMAC_IRQ_LINK_EVENT;
 	if (status) {
 		/* Save irq status for bottom-half processing. */
 		spin_lock_irqsave(&priv->lock, flags);
@@ -2830,16 +2757,16 @@ static void bcmgenet_netif_start(struct net_device *dev)
 
 	/* Start the network engine */
 	bcmgenet_enable_rx_napi(priv);
-	bcmgenet_enable_tx_napi(priv);
 
 	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true);
 
 	netif_tx_start_all_queues(dev);
+	bcmgenet_enable_tx_napi(priv);
 
 	/* Monitor link interrupts now */
 	bcmgenet_link_intr_enable(priv);
 
-	phy_start(priv->phydev);
+	phy_start(dev->phydev);
 }
 
 static int bcmgenet_open(struct net_device *dev)
@@ -2863,12 +2790,7 @@ static int bcmgenet_open(struct net_device *dev)
 	/* take MAC out of reset */
 	bcmgenet_umac_reset(priv);
 
-	ret = init_umac(priv);
-	if (ret)
-		goto err_clk_disable;
-
-	/* disable ethernet MAC while updating its registers */
-	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, false);
+	init_umac(priv);
 
 	/* Make sure we reflect the value of CRC_CMD_FWD */
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
@@ -2927,6 +2849,7 @@ err_irq1:
 err_irq0:
 	free_irq(priv->irq0, priv);
 err_fini_dma:
+	bcmgenet_dma_teardown(priv);
 	bcmgenet_fini_dma(priv);
 err_clk_disable:
 	if (priv->internal_phy)
@@ -2939,11 +2862,20 @@ static void bcmgenet_netif_stop(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
+	bcmgenet_disable_tx_napi(priv);
 	netif_tx_stop_all_queues(dev);
-	phy_stop(priv->phydev);
-	bcmgenet_intr_disable(priv);
+
+	/* Disable MAC receive */
+	umac_enable_set(priv, CMD_RX_EN, false);
+
+	bcmgenet_dma_teardown(priv);
+
+	/* Disable MAC transmit. TX DMA disabled must be done before this */
+	umac_enable_set(priv, CMD_TX_EN, false);
+
+	phy_stop(dev->phydev);
 	bcmgenet_disable_rx_napi(priv);
-	bcmgenet_disable_tx_napi(priv);
+	bcmgenet_intr_disable(priv);
 
 	/* Wait for pending work items to complete. Since interrupts are
 	 * disabled no new work will be scheduled.
@@ -2954,33 +2886,23 @@ static void bcmgenet_netif_stop(struct net_device *dev)
 	priv->old_speed = -1;
 	priv->old_duplex = -1;
 	priv->old_pause = -1;
+
+	/* tx reclaim */
+	bcmgenet_tx_reclaim_all(dev);
+	bcmgenet_fini_dma(priv);
 }
 
 static int bcmgenet_close(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int ret;
+	int ret = 0;
 
 	netif_dbg(priv, ifdown, dev, "bcmgenet_close\n");
 
 	bcmgenet_netif_stop(dev);
 
 	/* Really kill the PHY state machine and disconnect from it */
-	phy_disconnect(priv->phydev);
-
-	/* Disable MAC receive */
-	umac_enable_set(priv, CMD_RX_EN, false);
-
-	ret = bcmgenet_dma_teardown(priv);
-	if (ret)
-		return ret;
-
-	/* Disable MAC transmit. TX DMA disabled must be done before this */
-	umac_enable_set(priv, CMD_TX_EN, false);
-
-	/* tx reclaim */
-	bcmgenet_tx_reclaim_all(dev);
-	bcmgenet_fini_dma(priv);
+	phy_disconnect(dev->phydev);
 
 	free_irq(priv->irq0, priv);
 	free_irq(priv->irq1, priv);
@@ -2999,7 +2921,6 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 	u32 p_index, c_index, intsts, intmsk;
 	struct netdev_queue *txq;
 	unsigned int free_bds;
-	unsigned long flags;
 	bool txq_stopped;
 
 	if (!netif_msg_tx_err(priv))
@@ -3007,7 +2928,7 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 
 	txq = netdev_get_tx_queue(priv->dev, ring->queue);
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock(&ring->lock);
 	if (ring->index == DESC_INDEX) {
 		intsts = ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
 		intmsk = UMAC_IRQ_TXDMA_DONE | UMAC_IRQ_TXDMA_MBDONE;
@@ -3019,7 +2940,7 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 	p_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_PROD_INDEX);
 	txq_stopped = netif_tx_queue_stopped(txq);
 	free_bds = ring->free_bds;
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock(&ring->lock);
 
 	netif_err(priv, tx_err, priv->dev, "Ring %d queue %d status summary\n"
 		  "TX queue status: %s, interrupts: %s\n"
@@ -3545,9 +3466,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	    !strcasecmp(phy_mode_str, "internal"))
 		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
 
-	err = reset_umac(priv);
-	if (err)
-		goto err_clk_disable;
+	reset_umac(priv);
 
 	err = bcmgenet_mii_init(dev);
 	if (err)
@@ -3595,7 +3514,7 @@ static int bcmgenet_suspend(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int ret;
+	int ret = 0;
 
 	if (!netif_running(dev))
 		return 0;
@@ -3603,24 +3522,10 @@ static int bcmgenet_suspend(struct device *d)
 	bcmgenet_netif_stop(dev);
 
 	if (!device_may_wakeup(d))
-		phy_suspend(priv->phydev);
+		phy_suspend(dev->phydev);
 
 	netif_device_detach(dev);
 
-	/* Disable MAC receive */
-	umac_enable_set(priv, CMD_RX_EN, false);
-
-	ret = bcmgenet_dma_teardown(priv);
-	if (ret)
-		return ret;
-
-	/* Disable MAC transmit. TX DMA disabled must be done before this */
-	umac_enable_set(priv, CMD_TX_EN, false);
-
-	/* tx reclaim */
-	bcmgenet_tx_reclaim_all(dev);
-	bcmgenet_fini_dma(priv);
-
 	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
 	if (device_may_wakeup(d) && priv->wolopts) {
 		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
@@ -3659,20 +3564,16 @@ static int bcmgenet_resume(struct device *d)
 
 	bcmgenet_umac_reset(priv);
 
-	ret = init_umac(priv);
-	if (ret)
-		goto out_clk_disable;
+	init_umac(priv);
 
 	/* From WOL-enabled suspend, switch to regular clock */
 	if (priv->wolopts)
 		clk_disable_unprepare(priv->clk_wol);
 
-	phy_init_hw(priv->phydev);
-	/* Speed settings must be restored */
-	bcmgenet_mii_config(priv->dev);
+	phy_init_hw(dev->phydev);
 
-	/* disable ethernet MAC while updating its registers */
-	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, false);
+	/* Speed settings must be restored */
+	bcmgenet_mii_config(priv->dev, false);
 
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
 
@@ -3701,7 +3602,7 @@ static int bcmgenet_resume(struct device *d)
 	netif_device_attach(dev);
 
 	if (!device_may_wakeup(d))
-		phy_resume(priv->phydev);
+		phy_resume(dev->phydev);
 
 	if (priv->eee.eee_enabled)
 		bcmgenet_eee_enable_set(dev, true);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index b9344de669f8..3c50431ccd2a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -617,7 +617,6 @@ struct bcmgenet_priv {
 
 	/* MDIO bus variables */
 	wait_queue_head_t wq;
-	struct phy_device *phydev;
 	bool internal_phy;
 	struct device_node *phy_dn;
 	struct device_node *mdio_dn;
@@ -657,6 +656,7 @@ struct bcmgenet_priv {
 
 	struct clk *clk;
 	struct platform_device *pdev;
+	struct platform_device *mii_pdev;
 
 	/* WOL */
 	struct clk *clk_wol;
@@ -671,12 +671,21 @@ struct bcmgenet_priv {
 static inline u32 bcmgenet_##name##_readl(struct bcmgenet_priv *priv,	\
 					u32 off)			\
 {									\
-	return __raw_readl(priv->base + offset + off);			\
+	/* MIPS chips strapped for BE will automagically configure the	\
+	 * peripheral registers for CPU-native byte order.		\
+	 */								\
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) \
+		return __raw_readl(priv->base + offset + off);		\
+	else								\
+		return readl_relaxed(priv->base + offset + off);	\
 }									\
 static inline void bcmgenet_##name##_writel(struct bcmgenet_priv *priv,	\
 					u32 val, u32 off)		\
 {									\
-	__raw_writel(val, priv->base + offset + off);			\
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) \
+		__raw_writel(val, priv->base + offset + off);		\
+	else								\
+		writel_relaxed(val, priv->base + offset + off);		\
 }
 
 GENET_IO_MACRO(ext, GENET_EXT_OFF);
@@ -698,10 +707,9 @@ GENET_IO_MACRO(rbuf, GENET_RBUF_OFF);
 
 /* MDIO routines */
 int bcmgenet_mii_init(struct net_device *dev);
-int bcmgenet_mii_config(struct net_device *dev);
+int bcmgenet_mii_config(struct net_device *dev, bool init);
 int bcmgenet_mii_probe(struct net_device *dev);
 void bcmgenet_mii_exit(struct net_device *dev);
-void bcmgenet_mii_reset(struct net_device *dev);
 void bcmgenet_phy_power_set(struct net_device *dev, bool enable);
 void bcmgenet_mii_setup(struct net_device *dev);
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 071fcbd14e6a..5333274a283c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -24,69 +24,17 @@
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
 #include <linux/platform_data/bcmgenet.h>
+#include <linux/platform_data/mdio-bcm-unimac.h>
 
 #include "bcmgenet.h"
 
-/* read a value from the MII */
-static int bcmgenet_mii_read(struct mii_bus *bus, int phy_id, int location)
-{
-	int ret;
-	struct net_device *dev = bus->priv;
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 reg;
-
-	bcmgenet_umac_writel(priv, (MDIO_RD | (phy_id << MDIO_PMD_SHIFT) |
-			     (location << MDIO_REG_SHIFT)), UMAC_MDIO_CMD);
-	/* Start MDIO transaction*/
-	reg = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD);
-	reg |= MDIO_START_BUSY;
-	bcmgenet_umac_writel(priv, reg, UMAC_MDIO_CMD);
-	wait_event_timeout(priv->wq,
-			   !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD)
-			   & MDIO_START_BUSY),
-			   HZ / 100);
-	ret = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD);
-
-	/* Some broken devices are known not to release the line during
-	 * turn-around, e.g: Broadcom BCM53125 external switches, so check for
-	 * that condition here and ignore the MDIO controller read failure
-	 * indication.
-	 */
-	if (!(bus->phy_ignore_ta_mask & 1 << phy_id) && (ret & MDIO_READ_FAIL))
-		return -EIO;
-
-	return ret & 0xffff;
-}
-
-/* write a value to the MII */
-static int bcmgenet_mii_write(struct mii_bus *bus, int phy_id,
-			      int location, u16 val)
-{
-	struct net_device *dev = bus->priv;
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 reg;
-
-	bcmgenet_umac_writel(priv, (MDIO_WR | (phy_id << MDIO_PMD_SHIFT) |
-			     (location << MDIO_REG_SHIFT) | (0xffff & val)),
-			     UMAC_MDIO_CMD);
-	reg = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD);
-	reg |= MDIO_START_BUSY;
-	bcmgenet_umac_writel(priv, reg, UMAC_MDIO_CMD);
-	wait_event_timeout(priv->wq,
-			   !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD) &
-			   MDIO_START_BUSY),
-			   HZ / 100);
-
-	return 0;
-}
-
 /* setup netdev link state when PHY link status change and
  * update UMAC and RGMII block when link up
  */
 void bcmgenet_mii_setup(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	u32 reg, cmd_bits = 0;
 	bool status_changed = false;
 
@@ -173,22 +121,6 @@ static int bcmgenet_fixed_phy_link_update(struct net_device *dev,
 	return 0;
 }
 
-/* Perform a voluntary PHY software reset, since the EPHY is very finicky about
- * not doing it and will start corrupting packets
- */
-void bcmgenet_mii_reset(struct net_device *dev)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
-	if (GENET_IS_V4(priv))
-		return;
-
-	if (priv->phydev) {
-		phy_init_hw(priv->phydev);
-		phy_start_aneg(priv->phydev);
-	}
-}
-
 void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -234,14 +166,14 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 	}
 
 	if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
-		fixed_phy_set_link_update(priv->phydev,
+		fixed_phy_set_link_update(priv->dev->phydev,
 					  bcmgenet_fixed_phy_link_update);
 }
 
-int bcmgenet_mii_config(struct net_device *dev)
+int bcmgenet_mii_config(struct net_device *dev, bool init)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	struct device *kdev = &priv->pdev->dev;
 	const char *phy_name = NULL;
 	u32 id_mode_dis = 0;
@@ -288,7 +220,7 @@ int bcmgenet_mii_config(struct net_device *dev)
 		 * capabilities, use that knowledge to also configure the
 		 * Reverse MII interface correctly.
 		 */
-		if ((priv->phydev->supported & PHY_BASIC_FEATURES) ==
+		if ((dev->phydev->supported & PHY_BASIC_FEATURES) ==
 				PHY_BASIC_FEATURES)
 			port_ctrl = PORT_MODE_EXT_RVMII_25;
 		else
@@ -327,7 +259,8 @@ int bcmgenet_mii_config(struct net_device *dev)
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
-	dev_info_once(kdev, "configuring instance for %s\n", phy_name);
+	if (init)
+		dev_info(kdev, "configuring instance for %s\n", phy_name);
 
 	return 0;
 }
@@ -357,7 +290,7 @@ int bcmgenet_mii_probe(struct net_device *dev)
 			return -ENODEV;
 		}
 	} else {
-		phydev = priv->phydev;
+		phydev = dev->phydev;
 		phydev->dev_flags = phy_flags;
 
 		ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup,
@@ -368,16 +301,14 @@ int bcmgenet_mii_probe(struct net_device *dev)
 		}
 	}
 
-	priv->phydev = phydev;
-
 	/* Configure port multiplexer based on what the probed PHY device since
 	 * reading the 'max-speed' property determines the maximum supported
 	 * PHY speed which is needed for bcmgenet_mii_config() to configure
 	 * things appropriately.
 	 */
-	ret = bcmgenet_mii_config(dev);
+	ret = bcmgenet_mii_config(dev, true);
 	if (ret) {
-		phy_disconnect(priv->phydev);
+		phy_disconnect(dev->phydev);
 		return ret;
 	}
 
@@ -387,109 +318,126 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	 * Ethernet MAC ISRs
 	 */
 	if (priv->internal_phy)
-		priv->phydev->irq = PHY_IGNORE_INTERRUPT;
+		dev->phydev->irq = PHY_IGNORE_INTERRUPT;
 
 	return 0;
 }
 
-/* Workaround for integrated BCM7xxx Gigabit PHYs which have a problem with
- * their internal MDIO management controller making them fail to successfully
- * be read from or written to for the first transaction.  We insert a dummy
- * BMSR read here to make sure that phy_get_device() and get_phy_id() can
- * correctly read the PHY MII_PHYSID1/2 registers and successfully register a
- * PHY device for this peripheral.
- *
- * Once the PHY driver is registered, we can workaround subsequent reads from
- * there (e.g: during system-wide power management).
- *
- * bus->reset is invoked before mdiobus_scan during mdiobus_register and is
- * therefore the right location to stick that workaround. Since we do not want
- * to read from non-existing PHYs, we either use bus->phy_mask or do a manual
- * Device Tree scan to limit the search area.
- */
-static int bcmgenet_mii_bus_reset(struct mii_bus *bus)
+static struct device_node *bcmgenet_mii_of_find_mdio(struct bcmgenet_priv *priv)
 {
-	struct net_device *dev = bus->priv;
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct device_node *np = priv->mdio_dn;
-	struct device_node *child = NULL;
-	u32 read_mask = 0;
-	int addr = 0;
+	struct device_node *dn = priv->pdev->dev.of_node;
+	struct device *kdev = &priv->pdev->dev;
+	char *compat;
 
-	if (!np) {
-		read_mask = 1 << priv->phy_addr;
-	} else {
-		for_each_available_child_of_node(np, child) {
-			addr = of_mdio_parse_addr(&dev->dev, child);
-			if (addr < 0)
-				continue;
+	compat = kasprintf(GFP_KERNEL, "brcm,genet-mdio-v%d", priv->version);
+	if (!compat)
+		return NULL;
 
-			read_mask |= 1 << addr;
-		}
+	priv->mdio_dn = of_find_compatible_node(dn, NULL, compat);
+	kfree(compat);
+	if (!priv->mdio_dn) {
+		dev_err(kdev, "unable to find MDIO bus node\n");
+		return NULL;
 	}
 
-	for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
-		if (read_mask & 1 << addr) {
-			dev_dbg(&dev->dev, "Workaround for PHY @ %d\n", addr);
-			mdiobus_read(bus, addr, MII_BMSR);
-		}
+	return priv->mdio_dn;
+}
+
+static void bcmgenet_mii_pdata_init(struct bcmgenet_priv *priv,
+				    struct unimac_mdio_pdata *ppd)
+{
+	struct device *kdev = &priv->pdev->dev;
+	struct bcmgenet_platform_data *pd = kdev->platform_data;
+
+	if (pd->phy_interface != PHY_INTERFACE_MODE_MOCA && pd->mdio_enabled) {
+		/*
+		 * Internal or external PHY with MDIO access
+		 */
+		if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR)
+			ppd->phy_mask = 1 << pd->phy_address;
+		else
+			ppd->phy_mask = 0;
 	}
+}
 
+static int bcmgenet_mii_wait(void *wait_func_data)
+{
+	struct bcmgenet_priv *priv = wait_func_data;
+
+	wait_event_timeout(priv->wq,
+			   !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD)
+			   & MDIO_START_BUSY),
+			   HZ / 100);
 	return 0;
 }
 
-static int bcmgenet_mii_alloc(struct bcmgenet_priv *priv)
+static int bcmgenet_mii_register(struct bcmgenet_priv *priv)
 {
-	struct mii_bus *bus;
+	struct platform_device *pdev = priv->pdev;
+	struct bcmgenet_platform_data *pdata = pdev->dev.platform_data;
+	struct device_node *dn = pdev->dev.of_node;
+	struct unimac_mdio_pdata ppd;
+	struct platform_device *ppdev;
+	struct resource *pres, res;
+	int id, ret;
+
+	pres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	memset(&res, 0, sizeof(res));
+	memset(&ppd, 0, sizeof(ppd));
+
+	ppd.wait_func = bcmgenet_mii_wait;
+	ppd.wait_func_data = priv;
+	ppd.bus_name = "bcmgenet MII bus";
+
+	/* Unimac MDIO bus controller starts at UniMAC offset + MDIO_CMD
+	 * and is 2 * 32-bits word long, 8 bytes total.
+	 */
+	res.start = pres->start + GENET_UMAC_OFF + UMAC_MDIO_CMD;
+	res.end = res.start + 8;
+	res.flags = IORESOURCE_MEM;
 
-	if (priv->mii_bus)
-		return 0;
+	if (dn)
+		id = of_alias_get_id(dn, "eth");
+	else
+		id = pdev->id;
 
-	priv->mii_bus = mdiobus_alloc();
-	if (!priv->mii_bus) {
-		pr_err("failed to allocate\n");
+	ppdev = platform_device_alloc(UNIMAC_MDIO_DRV_NAME, id);
+	if (!ppdev)
 		return -ENOMEM;
-	}
 
-	bus = priv->mii_bus;
-	bus->priv = priv->dev;
-	bus->name = "bcmgenet MII bus";
-	bus->parent = &priv->pdev->dev;
-	bus->read = bcmgenet_mii_read;
-	bus->write = bcmgenet_mii_write;
-	bus->reset = bcmgenet_mii_bus_reset;
-	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d",
-		 priv->pdev->name, priv->pdev->id);
+	/* Retain this platform_device pointer for later cleanup */
+	priv->mii_pdev = ppdev;
+	ppdev->dev.parent = &pdev->dev;
+	ppdev->dev.of_node = bcmgenet_mii_of_find_mdio(priv);
+	if (pdata)
+		bcmgenet_mii_pdata_init(priv, &ppd);
+
+	ret = platform_device_add_resources(ppdev, &res, 1);
+	if (ret)
+		goto out;
+
+	ret = platform_device_add_data(ppdev, &ppd, sizeof(ppd));
+	if (ret)
+		goto out;
+
+	ret = platform_device_add(ppdev);
+	if (ret)
+		goto out;
 
 	return 0;
+out:
+	platform_device_put(ppdev);
+	return ret;
 }
 
 static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv)
 {
 	struct device_node *dn = priv->pdev->dev.of_node;
 	struct device *kdev = &priv->pdev->dev;
-	struct phy_device *phydev = NULL;
-	char *compat;
+	struct phy_device *phydev;
 	int phy_mode;
 	int ret;
 
-	compat = kasprintf(GFP_KERNEL, "brcm,genet-mdio-v%d", priv->version);
-	if (!compat)
-		return -ENOMEM;
-
-	priv->mdio_dn = of_find_compatible_node(dn, NULL, compat);
-	kfree(compat);
-	if (!priv->mdio_dn) {
-		dev_err(kdev, "unable to find MDIO bus node\n");
-		return -ENODEV;
-	}
-
-	ret = of_mdiobus_register(priv->mii_bus, priv->mdio_dn);
-	if (ret) {
-		dev_err(kdev, "failed to register MDIO bus\n");
-		return ret;
-	}
-
 	/* Fetch the PHY phandle */
 	priv->phy_dn = of_parse_phandle(dn, "phy-handle", 0);
 
@@ -536,33 +484,23 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 {
 	struct device *kdev = &priv->pdev->dev;
 	struct bcmgenet_platform_data *pd = kdev->platform_data;
-	struct mii_bus *mdio = priv->mii_bus;
+	char phy_name[MII_BUS_ID_SIZE + 3];
+	char mdio_bus_id[MII_BUS_ID_SIZE];
 	struct phy_device *phydev;
-	int ret;
+
+	snprintf(mdio_bus_id, MII_BUS_ID_SIZE, "%s-%d",
+		 UNIMAC_MDIO_DRV_NAME, priv->pdev->id);
 
 	if (pd->phy_interface != PHY_INTERFACE_MODE_MOCA && pd->mdio_enabled) {
+		snprintf(phy_name, MII_BUS_ID_SIZE, PHY_ID_FMT,
+			 mdio_bus_id, pd->phy_address);
+
 		/*
 		 * Internal or external PHY with MDIO access
 		 */
-		if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR)
-			mdio->phy_mask = ~(1 << pd->phy_address);
-		else
-			mdio->phy_mask = 0;
-
-		ret = mdiobus_register(mdio);
-		if (ret) {
-			dev_err(kdev, "failed to register MDIO bus\n");
-			return ret;
-		}
-
-		if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR)
-			phydev = mdiobus_get_phy(mdio, pd->phy_address);
-		else
-			phydev = phy_find_first(mdio);
-
+		phydev = phy_attach(priv->dev, phy_name, pd->phy_interface);
 		if (!phydev) {
 			dev_err(kdev, "failed to register PHY device\n");
-			mdiobus_unregister(mdio);
 			return -ENODEV;
 		}
 	} else {
@@ -589,7 +527,6 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 
 	}
 
-	priv->phydev = phydev;
 	priv->phy_interface = pd->phy_interface;
 
 	return 0;
@@ -608,10 +545,9 @@ static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv)
 int bcmgenet_mii_init(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct device_node *dn = priv->pdev->dev.of_node;
 	int ret;
 
-	ret = bcmgenet_mii_alloc(priv);
+	ret = bcmgenet_mii_register(priv);
 	if (ret)
 		return ret;
 
@@ -622,11 +558,7 @@ int bcmgenet_mii_init(struct net_device *dev)
 	return 0;
 
 out:
-	if (of_phy_is_fixed_link(dn))
-		of_phy_deregister_fixed_link(dn);
-	of_node_put(priv->phy_dn);
-	mdiobus_unregister(priv->mii_bus);
-	mdiobus_free(priv->mii_bus);
+	bcmgenet_mii_exit(dev);
 	return ret;
 }
 
@@ -638,6 +570,5 @@ void bcmgenet_mii_exit(struct net_device *dev)
 	if (of_phy_is_fixed_link(dn))
 		of_phy_deregister_fixed_link(dn);
 	of_node_put(priv->phy_dn);
-	mdiobus_unregister(priv->mii_bus);
-	mdiobus_free(priv->mii_bus);
+	platform_device_unregister(priv->mii_pdev);
 }
diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c
index 16a0f192daec..ecdef42f0ae6 100644
--- a/drivers/net/ethernet/broadcom/sb1250-mac.c
+++ b/drivers/net/ethernet/broadcom/sb1250-mac.c
@@ -1367,15 +1367,11 @@ static int sbmac_initctx(struct sbmac_softc *s)
 
 static void sbdma_uninitctx(struct sbmacdma *d)
 {
-	if (d->sbdma_dscrtable_unaligned) {
-		kfree(d->sbdma_dscrtable_unaligned);
-		d->sbdma_dscrtable_unaligned = d->sbdma_dscrtable = NULL;
-	}
+	kfree(d->sbdma_dscrtable_unaligned);
+	d->sbdma_dscrtable_unaligned = d->sbdma_dscrtable = NULL;
 
-	if (d->sbdma_ctxtable) {
-		kfree(d->sbdma_ctxtable);
-		d->sbdma_ctxtable = NULL;
-	}
+	kfree(d->sbdma_ctxtable);
+	d->sbdma_ctxtable = NULL;
 }
 
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index d600c41fb1dc..de51c2177d03 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6587,7 +6587,7 @@ static void tg3_tx(struct tg3_napi *tnapi)
 		pkts_compl++;
 		bytes_compl += skb->len;
 
-		dev_kfree_skb_any(skb);
+		dev_consume_skb_any(skb);
 
 		if (unlikely(tx_bug)) {
 			tg3_tx_recover(tp);
@@ -7829,7 +7829,7 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 		}
 	}
 
-	dev_kfree_skb_any(skb);
+	dev_consume_skb_any(skb);
 	*pskb = new_skb;
 	return ret;
 }
@@ -7882,7 +7882,7 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
 	} while (segs);
 
 tg3_tso_bug_end:
-	dev_kfree_skb_any(skb);
+	dev_consume_skb_any(skb);
 
 	return NETDEV_TX_OK;
 }
@@ -8543,7 +8543,7 @@ static void tg3_free_rings(struct tg3 *tp)
 			tg3_tx_skb_unmap(tnapi, i,
 					 skb_shinfo(skb)->nr_frags - 1);
 
-			dev_kfree_skb_any(skb);
+			dev_consume_skb_any(skb);
 		}
 		netdev_tx_reset_queue(netdev_get_tx_queue(tp->dev, j));
 	}
@@ -10931,9 +10931,9 @@ static void tg3_chk_missed_msi(struct tg3 *tp)
 	}
 }
 
-static void tg3_timer(unsigned long __opaque)
+static void tg3_timer(struct timer_list *t)
 {
-	struct tg3 *tp = (struct tg3 *) __opaque;
+	struct tg3 *tp = from_timer(tp, t, timer);
 
 	spin_lock(&tp->lock);
 
@@ -11087,9 +11087,7 @@ static void tg3_timer_init(struct tg3 *tp)
 	tp->asf_multiplier = (HZ / tp->timer_offset) *
 			     TG3_FW_UPDATE_FREQ_SEC;
 
-	init_timer(&tp->timer);
-	tp->timer.data = (unsigned long) tp;
-	tp->timer.function = tg3_timer;
+	timer_setup(&tp->timer, tg3_timer, 0);
 }
 
 static void tg3_timer_start(struct tg3 *tp)
@@ -11536,11 +11534,11 @@ static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq,
 	tg3_napi_enable(tp);
 
 	for (i = 0; i < tp->irq_cnt; i++) {
-		struct tg3_napi *tnapi = &tp->napi[i];
 		err = tg3_request_irq(tp, i);
 		if (err) {
 			for (i--; i >= 0; i--) {
-				tnapi = &tp->napi[i];
+				struct tg3_napi *tnapi = &tp->napi[i];
+
 				free_irq(tnapi->irq_vec, tnapi);
 			}
 			goto out_napi_fini;
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index 3b5e98ecba00..c2d02d02d1e6 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* $Id: tg3.h,v 1.37.2.32 2002/03/11 12:18:18 davem Exp $
  * tg3.h: Definitions for Broadcom Tigon3 ethernet driver.
  *